Made code review changes
X-SVN-Rev: 3936
This commit is contained in:
Syn Wee Quek
parent
02d076091f
commit
71d1d249d7
@ -5,8 +5,8 @@
|
||||
*******************************************************************************
|
||||
*
|
||||
* $Source: /xsrl/Nsvn/icu/icu4j/src/com/ibm/icu/lang/UCharacter.java,v $
|
||||
* $Date: 2001/02/28 20:59:44 $
|
||||
* $Revision: 1.1 $
|
||||
* $Date: 2001/03/07 02:52:05 $
|
||||
* $Revision: 1.2 $
|
||||
*
|
||||
*******************************************************************************
|
||||
*/
|
||||
@ -354,36 +354,40 @@ public final class UCharacter
|
||||
int props = getProps(ch);
|
||||
int result = -1;
|
||||
// if props == 0, it will just fall through and return -1
|
||||
if (!UCharacterPropertyDB.isExceptionIndicator(props))
|
||||
{
|
||||
if (!UCharacterPropertyDB.isExceptionIndicator(props)) {
|
||||
// not contained in exception data
|
||||
if (UCharacterPropertyDB.getPropType(props) ==
|
||||
UCharacterCategory.DECIMAL_DIGIT_NUMBER)
|
||||
UCharacterCategory.DECIMAL_DIGIT_NUMBER) {
|
||||
result = UCharacterPropertyDB.getSignedValue(props);
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
else {
|
||||
// contained in exception data
|
||||
int index = UCharacterPropertyDB.getExceptionIndex(props);
|
||||
if (PROPERTY_DB_.hasExceptionValue(index,
|
||||
UCharacterPropertyDB.EXC_DIGIT_VALUE_))
|
||||
UCharacterPropertyDB.EXC_DIGIT_VALUE_)) {
|
||||
result = PROPERTY_DB_.getException(index,
|
||||
UCharacterPropertyDB.EXC_DIGIT_VALUE_) &
|
||||
LAST_CHAR_MASK_;
|
||||
else
|
||||
}
|
||||
else {
|
||||
if (!PROPERTY_DB_.hasExceptionValue(index,
|
||||
UCharacterPropertyDB.EXC_DENOMINATOR_VALUE_)
|
||||
UCharacterPropertyDB.EXC_DENOMINATOR_VALUE_)
|
||||
&& PROPERTY_DB_.hasExceptionValue(index,
|
||||
UCharacterPropertyDB.EXC_NUMERIC_VALUE_))
|
||||
result = PROPERTY_DB_.getException(index,
|
||||
UCharacterPropertyDB.EXC_NUMERIC_VALUE_);
|
||||
UCharacterPropertyDB.EXC_NUMERIC_VALUE_)) {
|
||||
result = PROPERTY_DB_.getException(index,
|
||||
UCharacterPropertyDB.EXC_NUMERIC_VALUE_);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if (result < 0)
|
||||
if (result < 0) {
|
||||
result = getHanDigit(ch);
|
||||
}
|
||||
|
||||
if (result < 0 || result >= radix)
|
||||
if (result < 0 || result >= radix) {
|
||||
return -1;
|
||||
}
|
||||
return result;
|
||||
}
|
||||
|
||||
@ -420,35 +424,41 @@ public final class UCharacter
|
||||
// if props == 0, it will just fall through and return -1
|
||||
if (type != UCharacterCategory.DECIMAL_DIGIT_NUMBER &&
|
||||
type != UCharacterCategory.LETTER_NUMBER &&
|
||||
type != UCharacterCategory.OTHER_NUMBER)
|
||||
type != UCharacterCategory.OTHER_NUMBER) {
|
||||
return -1;
|
||||
}
|
||||
|
||||
int result = -1;
|
||||
if (!UCharacterPropertyDB.isExceptionIndicator(props))
|
||||
if (!UCharacterPropertyDB.isExceptionIndicator(props)) {
|
||||
// not contained in exception data
|
||||
result = UCharacterPropertyDB.getSignedValue(props);
|
||||
else
|
||||
{
|
||||
}
|
||||
else {
|
||||
// contained in exception data
|
||||
int index = UCharacterPropertyDB.getExceptionIndex(props);
|
||||
if (PROPERTY_DB_.hasExceptionValue(index,
|
||||
UCharacterPropertyDB.EXC_DIGIT_VALUE_))
|
||||
UCharacterPropertyDB.EXC_DIGIT_VALUE_)) {
|
||||
result = PROPERTY_DB_.getException(index,
|
||||
UCharacterPropertyDB.EXC_DIGIT_VALUE_);
|
||||
else
|
||||
}
|
||||
else {
|
||||
if (!PROPERTY_DB_.hasExceptionValue(index,
|
||||
UCharacterPropertyDB.EXC_DENOMINATOR_VALUE_)
|
||||
UCharacterPropertyDB.EXC_DENOMINATOR_VALUE_)
|
||||
&& PROPERTY_DB_.hasExceptionValue(index,
|
||||
UCharacterPropertyDB.EXC_NUMERIC_VALUE_))
|
||||
result = PROPERTY_DB_.getException(index,
|
||||
UCharacterPropertyDB.EXC_NUMERIC_VALUE_)) {
|
||||
result = PROPERTY_DB_.getException(index,
|
||||
UCharacterPropertyDB.EXC_NUMERIC_VALUE_);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if (result < 0)
|
||||
if (result < 0) {
|
||||
result = getHanDigit(ch);
|
||||
}
|
||||
|
||||
if (result < 0)
|
||||
if (result < 0) {
|
||||
return -2;
|
||||
}
|
||||
return result;
|
||||
}
|
||||
|
||||
@ -755,20 +765,21 @@ public final class UCharacter
|
||||
{
|
||||
int props = getProps(ch);
|
||||
// if props == 0, it will just fall through and return itself
|
||||
if(!UCharacterPropertyDB.isExceptionIndicator(props))
|
||||
{
|
||||
if(!UCharacterPropertyDB.isExceptionIndicator(props)) {
|
||||
int cat = UCharacterPropertyDB.getPropType(props);
|
||||
if (cat == UCharacterCategory.UPPERCASE_LETTER ||
|
||||
cat == UCharacterCategory.TITLECASE_LETTER)
|
||||
cat == UCharacterCategory.TITLECASE_LETTER) {
|
||||
return ch + UCharacterPropertyDB.getSignedValue(props);
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
int index = UCharacterPropertyDB.getExceptionIndex(props);
|
||||
if (PROPERTY_DB_.hasExceptionValue(index,
|
||||
UCharacterPropertyDB.EXC_LOWERCASE_))
|
||||
UCharacterPropertyDB.EXC_LOWERCASE_)) {
|
||||
return PROPERTY_DB_.getException(index,
|
||||
UCharacterPropertyDB.EXC_LOWERCASE_);
|
||||
}
|
||||
}
|
||||
return ch;
|
||||
}
|
||||
@ -787,11 +798,13 @@ public final class UCharacter
|
||||
*/
|
||||
public static String toString(int ch)
|
||||
{
|
||||
if (ch < MIN_VALUE || ch > MAX_VALUE)
|
||||
if (ch < MIN_VALUE || ch > MAX_VALUE) {
|
||||
return null;
|
||||
}
|
||||
|
||||
if (ch < UCharacter.SUPPLEMENTARY_MIN_VALUE)
|
||||
if (ch < UCharacter.SUPPLEMENTARY_MIN_VALUE) {
|
||||
return String.valueOf((char)ch);
|
||||
}
|
||||
|
||||
char result[] = new char[2];
|
||||
result[0] = (char)UTF16.getLeadSurrogate(ch);
|
||||
@ -819,26 +832,28 @@ public final class UCharacter
|
||||
{
|
||||
int props = getProps(ch);
|
||||
// if props == 0, it will just fall through and return itself
|
||||
if (!UCharacterPropertyDB.isExceptionIndicator(props))
|
||||
{
|
||||
if (!UCharacterPropertyDB.isExceptionIndicator(props)) {
|
||||
if (UCharacterPropertyDB.getPropType(props) ==
|
||||
UCharacterCategory.LOWERCASE_LETTER)
|
||||
UCharacterCategory.LOWERCASE_LETTER) {
|
||||
// here, titlecase is same as uppercase
|
||||
return ch - UCharacterPropertyDB.getSignedValue(props);
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
else {
|
||||
int index = UCharacterPropertyDB.getExceptionIndex(props);
|
||||
if (PROPERTY_DB_.hasExceptionValue(index,
|
||||
UCharacterPropertyDB.EXC_TITLECASE_))
|
||||
UCharacterPropertyDB.EXC_TITLECASE_)) {
|
||||
return PROPERTY_DB_.getException(index,
|
||||
UCharacterPropertyDB.EXC_TITLECASE_);
|
||||
else
|
||||
}
|
||||
else {
|
||||
// here, titlecase is same as uppercase
|
||||
if (PROPERTY_DB_.hasExceptionValue(index,
|
||||
UCharacterPropertyDB.EXC_UPPERCASE_))
|
||||
UCharacterPropertyDB.EXC_UPPERCASE_)) {
|
||||
return PROPERTY_DB_.getException(index,
|
||||
UCharacterPropertyDB.EXC_UPPERCASE_);
|
||||
}
|
||||
}
|
||||
}
|
||||
return ch; // no mapping - return c itself
|
||||
}
|
||||
@ -860,20 +875,21 @@ public final class UCharacter
|
||||
{
|
||||
int props = getProps(ch);
|
||||
// if props == 0, it will just fall through and return itself
|
||||
if (!UCharacterPropertyDB.isExceptionIndicator(props))
|
||||
{
|
||||
if (!UCharacterPropertyDB.isExceptionIndicator(props)) {
|
||||
if (UCharacterPropertyDB.getPropType(props) ==
|
||||
UCharacterCategory.LOWERCASE_LETTER)
|
||||
UCharacterCategory.LOWERCASE_LETTER) {
|
||||
// here, titlecase is same as uppercase */
|
||||
return ch - UCharacterPropertyDB.getSignedValue(props);
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
int index = UCharacterPropertyDB.getExceptionIndex(props);
|
||||
if (PROPERTY_DB_.hasExceptionValue(index,
|
||||
UCharacterPropertyDB.EXC_UPPERCASE_))
|
||||
UCharacterPropertyDB.EXC_UPPERCASE_)) {
|
||||
return PROPERTY_DB_.getException(index,
|
||||
UCharacterPropertyDB.EXC_UPPERCASE_);
|
||||
}
|
||||
}
|
||||
return ch; // no mapping - return c itself
|
||||
}
|
||||
@ -1000,8 +1016,9 @@ public final class UCharacter
|
||||
public static int getDirection(int ch)
|
||||
{
|
||||
int props = getProps(ch);
|
||||
if (props != 0)
|
||||
if (props != 0) {
|
||||
return UCharacterPropertyDB.getDirection(props);
|
||||
}
|
||||
return UCharacterDirection.LEFT_TO_RIGHT;
|
||||
}
|
||||
|
||||
@ -1038,9 +1055,10 @@ public final class UCharacter
|
||||
int props = getProps(ch);
|
||||
// mirrored - the value is a mirror offset
|
||||
// if props == 0, it will just fall through and return false
|
||||
if (UCharacterPropertyDB.isMirrored(props))
|
||||
if(!UCharacterPropertyDB.isExceptionIndicator(props))
|
||||
if (UCharacterPropertyDB.isMirrored(props)) {
|
||||
if(!UCharacterPropertyDB.isExceptionIndicator(props)) {
|
||||
return ch + UCharacterPropertyDB.getSignedValue(props);
|
||||
}
|
||||
else
|
||||
{
|
||||
int index = UCharacterPropertyDB.getExceptionIndex(props);
|
||||
@ -1049,6 +1067,7 @@ public final class UCharacter
|
||||
return PROPERTY_DB_.getException(index,
|
||||
UCharacterPropertyDB.EXC_MIRROR_MAPPING_);
|
||||
}
|
||||
}
|
||||
return ch;
|
||||
}
|
||||
|
||||
@ -1060,17 +1079,21 @@ public final class UCharacter
|
||||
public static byte getCombiningClass(int ch)
|
||||
{
|
||||
int props = getProps(ch);
|
||||
if(!UCharacterPropertyDB.isExceptionIndicator(props))
|
||||
if(!UCharacterPropertyDB.isExceptionIndicator(props)) {
|
||||
if (UCharacterPropertyDB.getPropType(props) ==
|
||||
UCharacterCategory.NON_SPACING_MARK)
|
||||
UCharacterCategory.NON_SPACING_MARK) {
|
||||
return (byte)(PROPERTY_DB_.getUnsignedValue(props));
|
||||
else
|
||||
}
|
||||
else {
|
||||
return 0;
|
||||
else
|
||||
}
|
||||
}
|
||||
else {
|
||||
// the combining class is in bits 23..16 of the first exception value
|
||||
return (byte)((PROPERTY_DB_.getException(PROPERTY_DB_.getExceptionIndex(
|
||||
props), UCharacterPropertyDB.EXC_COMBINING_CLASS_)
|
||||
>> SHIFT_16_) & LAST_BYTE_MASK_);
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
@ -1086,12 +1109,18 @@ public final class UCharacter
|
||||
*/
|
||||
public static boolean isLegal(int ch)
|
||||
{
|
||||
if (ch < MIN_VALUE) return false;
|
||||
if (ch < SURROGATE_MIN_VALUE_) return true;
|
||||
if (ch <= SURROGATE_MAX_VALUE_) return false;
|
||||
|
||||
if ((ch & LAST_CHAR_MASK_) >= NOT_A_CHAR_SUFFIX_MIN_)
|
||||
if (ch < MIN_VALUE) {
|
||||
return false;
|
||||
}
|
||||
if (ch < SURROGATE_MIN_VALUE_) {
|
||||
return true;
|
||||
}
|
||||
if (ch <= SURROGATE_MAX_VALUE_) {
|
||||
return false;
|
||||
}
|
||||
if ((ch & LAST_CHAR_MASK_) >= NOT_A_CHAR_SUFFIX_MIN_) {
|
||||
return false;
|
||||
}
|
||||
return (ch <= MAX_VALUE);
|
||||
}
|
||||
|
||||
@ -1116,10 +1145,12 @@ public final class UCharacter
|
||||
for (int i = 0; i < size; i ++)
|
||||
{
|
||||
codepoint = UTF16.charAt(str, i);
|
||||
if (!isLegal(codepoint))
|
||||
if (!isLegal(codepoint)) {
|
||||
return false;
|
||||
if (isSupplementary(codepoint))
|
||||
}
|
||||
if (isSupplementary(codepoint)) {
|
||||
i ++;
|
||||
}
|
||||
}
|
||||
return true;
|
||||
}
|
||||
@ -1201,8 +1232,9 @@ public final class UCharacter
|
||||
*/
|
||||
public static int getCodePoint(char lead, char trail)
|
||||
{
|
||||
if (UTF16.isLeadSurrogate(lead) && UTF16.isTrailSurrogate(trail))
|
||||
if (UTF16.isLeadSurrogate(lead) && UTF16.isTrailSurrogate(trail)) {
|
||||
return getRawSupplementary(lead, trail);
|
||||
}
|
||||
return UCharacter.REPLACEMENT_CHAR;
|
||||
}
|
||||
|
||||
@ -1218,8 +1250,9 @@ public final class UCharacter
|
||||
*/
|
||||
public static int getCodePoint(char char16)
|
||||
{
|
||||
if (UCharacter.isLegal(char16))
|
||||
if (UCharacter.isLegal(char16)) {
|
||||
return char16;
|
||||
}
|
||||
throw new IllegalArgumentException("Illegal codepoint");
|
||||
}
|
||||
|
||||
@ -1254,7 +1287,7 @@ public final class UCharacter
|
||||
*/
|
||||
public static String toUpperCase(Locale locale, String str)
|
||||
{
|
||||
int size = UTF16.countCP(str);
|
||||
int size = UTF16.countCodePoint(str);
|
||||
StringBuffer result = new StringBuffer(size << 1); // initial buffer
|
||||
int props;
|
||||
int exception;
|
||||
@ -1266,26 +1299,30 @@ public final class UCharacter
|
||||
|
||||
for (int i = 0; i < size; i ++)
|
||||
{
|
||||
ch = UTF16.charAtCPOffset(str, i);
|
||||
ch = UTF16.charAtCodePointOffset(str, i);
|
||||
props = PROPERTY_DB_.getProperty(ch);
|
||||
if (!UCharacterPropertyDB.isExceptionIndicator(props))
|
||||
{
|
||||
if (UCharacterPropertyDB.getPropType(props) ==
|
||||
UCharacterCategory.LOWERCASE_LETTER)
|
||||
UCharacterCategory.LOWERCASE_LETTER) {
|
||||
ch -= UCharacterPropertyDB.getSignedValue(props);
|
||||
}
|
||||
UTF16.append(result, ch);
|
||||
}
|
||||
else
|
||||
{
|
||||
index = UCharacterPropertyDB.getExceptionIndex(props);
|
||||
if (PROPERTY_DB_.hasExceptionValue(index,
|
||||
UCharacterPropertyDB.EXC_SPECIAL_CASING_))
|
||||
getSpecialUpperCase(ch, index, result, str, i, tr_az, lt);
|
||||
else
|
||||
UCharacterPropertyDB.EXC_SPECIAL_CASING_)) {
|
||||
getSpecialUpperCase(ch, index, result, str, i, tr_az, lt);
|
||||
}
|
||||
else {
|
||||
if (PROPERTY_DB_.hasExceptionValue(index,
|
||||
UCharacterPropertyDB.EXC_UPPERCASE_))
|
||||
UCharacterPropertyDB.EXC_UPPERCASE_)) {
|
||||
UTF16.append(result, PROPERTY_DB_.getException(index,
|
||||
UCharacterPropertyDB.EXC_UPPERCASE_));
|
||||
UCharacterPropertyDB.EXC_UPPERCASE_));
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
return result.toString();
|
||||
@ -1300,7 +1337,7 @@ public final class UCharacter
|
||||
*/
|
||||
public static String toLowerCase(Locale locale, String str)
|
||||
{
|
||||
int size = UTF16.countCP(str);
|
||||
int size = UTF16.countCodePoint(str);
|
||||
StringBuffer result = new StringBuffer(size << 1); // initial buffer
|
||||
int props;
|
||||
int exception;
|
||||
@ -1313,27 +1350,29 @@ public final class UCharacter
|
||||
|
||||
for (int i = 0; i < size; i ++)
|
||||
{
|
||||
ch = UTF16.charAtCPOffset(str, i);
|
||||
ch = UTF16.charAtCodePointOffset(str, i);
|
||||
props = PROPERTY_DB_.getProperty(ch);
|
||||
if (!UCharacterPropertyDB.isExceptionIndicator(props))
|
||||
{
|
||||
if (!UCharacterPropertyDB.isExceptionIndicator(props)) {
|
||||
type = UCharacterPropertyDB.getPropType(props);
|
||||
if (type == UCharacterCategory.UPPERCASE_LETTER ||
|
||||
type == UCharacterCategory.TITLECASE_LETTER)
|
||||
type == UCharacterCategory.TITLECASE_LETTER) {
|
||||
ch += UCharacterPropertyDB.getSignedValue(props);
|
||||
}
|
||||
UTF16.append(result, ch);
|
||||
}
|
||||
else
|
||||
{
|
||||
else {
|
||||
index = UCharacterPropertyDB.getExceptionIndex(props);
|
||||
if (PROPERTY_DB_.hasExceptionValue(index,
|
||||
UCharacterPropertyDB.EXC_SPECIAL_CASING_))
|
||||
getSpecialLowerCase(ch, index, result, str, i, tr_az, lt);
|
||||
else
|
||||
UCharacterPropertyDB.EXC_SPECIAL_CASING_)) {
|
||||
getSpecialLowerCase(ch, index, result, str, i, tr_az, lt);
|
||||
}
|
||||
else {
|
||||
if (PROPERTY_DB_.hasExceptionValue(index,
|
||||
UCharacterPropertyDB.EXC_LOWERCASE_))
|
||||
UCharacterPropertyDB.EXC_LOWERCASE_)) {
|
||||
UTF16.append(result, PROPERTY_DB_.getException(index,
|
||||
UCharacterPropertyDB.EXC_LOWERCASE_));
|
||||
UCharacterPropertyDB.EXC_LOWERCASE_));
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
return result.toString();
|
||||
@ -1363,8 +1402,9 @@ public final class UCharacter
|
||||
*/
|
||||
private static int getProps(int ch)
|
||||
{
|
||||
if (ch >= UCharacter.MIN_VALUE & ch <= UCharacter.MAX_VALUE)
|
||||
if (ch >= UCharacter.MIN_VALUE & ch <= UCharacter.MAX_VALUE) {
|
||||
return PROPERTY_DB_.getProperty(ch);
|
||||
}
|
||||
return 0;
|
||||
}
|
||||
|
||||
@ -1419,41 +1459,42 @@ public final class UCharacter
|
||||
{
|
||||
int exception = PROPERTY_DB_.getException(index,
|
||||
UCharacterPropertyDB.EXC_SPECIAL_CASING_);
|
||||
if (exception < 0)
|
||||
{
|
||||
if (exception < 0) {
|
||||
// use hardcoded conditions and mappings
|
||||
if (ch == LATIN_SMALL_LETTER_I_)
|
||||
{
|
||||
if (tr_az)
|
||||
if (ch == LATIN_SMALL_LETTER_I_) {
|
||||
if (tr_az) {
|
||||
// turkish and azerbaijani : i maps to dotted I
|
||||
buffer.append(LATIN_CAPITAL_LETTER_I_WITH_DOT_ABOVE_);
|
||||
else
|
||||
}
|
||||
else {
|
||||
// other languages: i maps to I
|
||||
buffer.append(LATIN_CAPITAL_LETTER_I_);
|
||||
}
|
||||
}
|
||||
else
|
||||
if (ch == COMBINING_DOT_ABOVE_ && lt)
|
||||
{
|
||||
else {
|
||||
if (ch == COMBINING_DOT_ABOVE_ && lt) {
|
||||
// lithuanian: remove DOT ABOVE after U+0069 "i" with upper
|
||||
// or titlecase
|
||||
for (int j = chindex; j > 0; j ++)
|
||||
{
|
||||
ch = UTF16.charAtCPOffset(str, j);
|
||||
if (getType(ch) != UCharacterCategory.NON_SPACING_MARK)
|
||||
for (int j = chindex; j > 0; j ++) {
|
||||
ch = UTF16.charAtCodePointOffset(str, j);
|
||||
if (getType(ch) != UCharacterCategory.NON_SPACING_MARK) {
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
// if the base letter is not an 'i' (U+0069)? keep the dot
|
||||
if (ch != LATIN_SMALL_LETTER_I_)
|
||||
if (ch != LATIN_SMALL_LETTER_I_) {
|
||||
buffer.append(COMBINING_DOT_ABOVE_);
|
||||
}
|
||||
else
|
||||
// no known conditional special case mapping, output the code
|
||||
// point itself
|
||||
UTF16.append(buffer, ch);
|
||||
}
|
||||
}
|
||||
else {
|
||||
// no known conditional special case mapping, output the code
|
||||
// point itself
|
||||
UTF16.append(buffer, ch);
|
||||
}
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
else {
|
||||
// get the special case mapping string from the data file
|
||||
index = exception & LAST_CHAR_MASK_;
|
||||
PROPERTY_DB_.getUpperCase(index, buffer);
|
||||
@ -1478,34 +1519,37 @@ public final class UCharacter
|
||||
{
|
||||
int exception = PROPERTY_DB_.getException(index,
|
||||
UCharacterPropertyDB.EXC_SPECIAL_CASING_);
|
||||
if (exception < 0)
|
||||
{
|
||||
if (exception < 0) {
|
||||
// use hardcoded conditions and mappings
|
||||
if (ch == LATIN_CAPITAL_LETTER_I_)
|
||||
{
|
||||
if (tr_az)
|
||||
if (ch == LATIN_CAPITAL_LETTER_I_) {
|
||||
if (tr_az) {
|
||||
// turkish and azerbaijani : I maps to dotless i
|
||||
buffer.append(LATIN_SMALL_LETTER_DOTLESS_I_);
|
||||
else
|
||||
}
|
||||
else {
|
||||
// other languages: I maps to i
|
||||
buffer.append(LATIN_SMALL_LETTER_I_);
|
||||
}
|
||||
}
|
||||
else
|
||||
if (ch == GREEK_CAPITAL_LETTER_SIGMA_)
|
||||
{
|
||||
else {
|
||||
if (ch == GREEK_CAPITAL_LETTER_SIGMA_) {
|
||||
// greek capital sigma maps depending on whether the following
|
||||
// character is a letter
|
||||
chindex ++;
|
||||
if (chindex != str.length() &&
|
||||
isLetter(UTF16.charAtCPOffset(str, chindex)))
|
||||
isLetter(UTF16.charAtCodePointOffset(str, chindex))) {
|
||||
buffer.append(GREEK_SMALL_LETTER_SIGMA_);
|
||||
else
|
||||
}
|
||||
else {
|
||||
buffer.append(GREEK_SMALL_LETTER_RHO_);
|
||||
}
|
||||
}
|
||||
else
|
||||
else {
|
||||
// no known conditional special case mapping, output the code
|
||||
// point itself
|
||||
UTF16.append(buffer, ch);
|
||||
}
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
|
||||
@ -6,8 +6,8 @@
|
||||
*
|
||||
* $Source:
|
||||
* /usr/cvs/icu4j/icu4j/src/com/ibm/icu/text/UCharacterName.java $
|
||||
* $Date: 2001/02/28 20:59:44 $
|
||||
* $Revision: 1.1 $
|
||||
* $Date: 2001/03/07 02:52:05 $
|
||||
* $Revision: 1.2 $
|
||||
*
|
||||
*******************************************************************************
|
||||
*/
|
||||
@ -75,8 +75,9 @@ final class UCharacterName
|
||||
protected static String getName(int ch, int choice)
|
||||
{
|
||||
if (ch < 0 || ch > 0x1ffff ||
|
||||
choice >= UCharacterNameChoice.U_CHAR_NAME_CHOICE_COUNT)
|
||||
choice >= UCharacterNameChoice.U_CHAR_NAME_CHOICE_COUNT) {
|
||||
return null;
|
||||
}
|
||||
|
||||
String result = "";
|
||||
|
||||
@ -84,13 +85,15 @@ final class UCharacterName
|
||||
// the same as the modern ones, extension A was only introduced with
|
||||
// Unicode 3.0, and the Hangul syllable block was moved and changed around
|
||||
// Unicode 1.1.5.
|
||||
if (choice == UCharacterNameChoice.U_UNICODE_CHAR_NAME)
|
||||
if (choice == UCharacterNameChoice.U_UNICODE_CHAR_NAME) {
|
||||
// try getting algorithmic name first
|
||||
result = getAlgName(ch);
|
||||
}
|
||||
|
||||
// getting normal character name
|
||||
if (result == null || result.length() == 0)
|
||||
if (result == null || result.length() == 0) {
|
||||
result = NAME_DB_.getGroupName(ch, choice);
|
||||
}
|
||||
|
||||
return result;
|
||||
}
|
||||
@ -106,13 +109,15 @@ final class UCharacterName
|
||||
{
|
||||
// checks for illegal arguments
|
||||
if (choice >= UCharacterNameChoice.U_CHAR_NAME_CHOICE_COUNT ||
|
||||
name == null || name.length() == 0)
|
||||
name == null || name.length() == 0) {
|
||||
return -1;
|
||||
}
|
||||
|
||||
// try algorithmic names first, if fails then try group names
|
||||
int result = getAlgorithmChar(choice, name);
|
||||
if (result >= 0)
|
||||
if (result >= 0) {
|
||||
return result;
|
||||
}
|
||||
return getGroupChar(name, choice);
|
||||
}
|
||||
|
||||
@ -129,8 +134,7 @@ final class UCharacterName
|
||||
StringBuffer s = new StringBuffer();
|
||||
|
||||
int index = NAME_DB_.getAlgorithmIndex(ch);
|
||||
if (index >= 0)
|
||||
{
|
||||
if (index >= 0) {
|
||||
NAME_DB_.appendAlgorithmName(index, ch, s);
|
||||
return s.toString();
|
||||
}
|
||||
@ -145,14 +149,15 @@ final class UCharacterName
|
||||
private static int getAlgorithmChar(int choice, String name)
|
||||
{
|
||||
// 1.0 has no algorithmic names
|
||||
if (choice != UCharacterNameChoice.U_UNICODE_CHAR_NAME)
|
||||
if (choice != UCharacterNameChoice.U_UNICODE_CHAR_NAME) {
|
||||
return -1;
|
||||
}
|
||||
int result;
|
||||
for (int count = NAME_DB_.countAlgorithm() - 1; count >= 0; count --)
|
||||
{
|
||||
for (int count = NAME_DB_.countAlgorithm() - 1; count >= 0; count --) {
|
||||
result = NAME_DB_.getAlgorithmChar(count, name);
|
||||
if (result >= 0)
|
||||
if (result >= 0) {
|
||||
return result;
|
||||
}
|
||||
}
|
||||
return -1;
|
||||
}
|
||||
@ -168,11 +173,11 @@ final class UCharacterName
|
||||
int groupcount = NAME_DB_.countGroup();
|
||||
int result = 0;
|
||||
|
||||
for (int i = 0; i < groupcount; i ++)
|
||||
{
|
||||
for (int i = 0; i < groupcount; i ++) {
|
||||
result = NAME_DB_.getGroupChar(i, name, choice);
|
||||
if (result != -1)
|
||||
if (result != -1) {
|
||||
return result;
|
||||
}
|
||||
}
|
||||
return -1;
|
||||
}
|
||||
|
||||
@ -5,8 +5,8 @@
|
||||
*******************************************************************************
|
||||
*
|
||||
* $Source: /xsrl/Nsvn/icu/icu4j/src/com/ibm/icu/lang/Attic/UCharacterUtil.java,v $
|
||||
* $Date: 2001/02/28 20:59:44 $
|
||||
* $Revision: 1.1 $
|
||||
* $Date: 2001/03/07 02:52:05 $
|
||||
* $Revision: 1.2 $
|
||||
*
|
||||
*******************************************************************************
|
||||
*/
|
||||
@ -51,10 +51,12 @@ final class UCharacterUtil
|
||||
*/
|
||||
protected static char toChar(byte bytes[])
|
||||
{
|
||||
if (bytes == null || bytes.length == 0)
|
||||
if (bytes == null || bytes.length == 0) {
|
||||
return 0;
|
||||
if (bytes.length == 1)
|
||||
}
|
||||
if (bytes.length == 1) {
|
||||
return toChar(bytes[0]);
|
||||
}
|
||||
|
||||
char firstbyte = (char)(toChar(bytes[0]) << 8);
|
||||
char secondbyte = toChar(bytes[1]);
|
||||
@ -141,8 +143,9 @@ final class UCharacterUtil
|
||||
while (b != 0)
|
||||
{
|
||||
b = array[index];
|
||||
if (b != 0)
|
||||
if (b != 0) {
|
||||
str.append((char)(b & 0x00FF));
|
||||
}
|
||||
index ++;
|
||||
}
|
||||
return index;
|
||||
@ -170,12 +173,14 @@ final class UCharacterUtil
|
||||
{
|
||||
b = array[aindex];
|
||||
aindex ++;
|
||||
if (b == 0)
|
||||
if (b == 0) {
|
||||
break;
|
||||
}
|
||||
// if we have reached the end of the string and yet the array has not
|
||||
// reached the end of their substring yet, abort
|
||||
if (strindex == length || (str.charAt(strindex) != (char)(b & 0xFF)))
|
||||
if (strindex == length || (str.charAt(strindex) != (char)(b & 0xFF))) {
|
||||
return -1;
|
||||
}
|
||||
strindex ++;
|
||||
}
|
||||
return strindex;
|
||||
@ -255,8 +260,9 @@ final class UCharacterUtil
|
||||
{
|
||||
b = array[index + result];
|
||||
result ++;
|
||||
if (b == skipend)
|
||||
if (b == skipend) {
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
return result;
|
||||
|
||||
@ -5,8 +5,8 @@
|
||||
*******************************************************************************
|
||||
*
|
||||
* $Source: /xsrl/Nsvn/icu/icu4j/src/com/ibm/icu/text/UTF16.java,v $
|
||||
* $Date: 2001/02/28 20:59:44 $
|
||||
* $Revision: 1.1 $
|
||||
* $Date: 2001/03/07 02:52:05 $
|
||||
* $Revision: 1.2 $
|
||||
*
|
||||
*******************************************************************************
|
||||
*/
|
||||
@ -149,7 +149,7 @@ public final class UTF16
|
||||
* <code>UTF16.getCharCount()</code>, as well as random access. If a validity
|
||||
* check is required, use <code><a href="../UCharacter.html#isLegal(char)">
|
||||
* UCharacter.isLegal()</a></code> on the return value.
|
||||
* If tbe char retrieved is part of a surrogate pair, its supplementary
|
||||
* If the char retrieved is part of a surrogate pair, its supplementary
|
||||
* character will be returned. If a complete supplementary character is not
|
||||
* found the incomplete character will be returned
|
||||
* @param source array of UTF-16 chars
|
||||
@ -161,7 +161,7 @@ public final class UTF16
|
||||
*/
|
||||
public static int charAt(String source, int offset16)
|
||||
{
|
||||
if (offset16 >= source.length())
|
||||
if (offset16 < 0 || offset16 >= source.length())
|
||||
return -1;
|
||||
|
||||
char single = source.charAt(offset16);
|
||||
@ -211,9 +211,9 @@ public final class UTF16
|
||||
* @param offset32 UTF-32 offset to the start of the character.
|
||||
* @return a single UTF32 value, otherwise -1 if there's an error
|
||||
*/
|
||||
public static int charAtCPOffset(String source, int offset32)
|
||||
public static int charAtCodePointOffset(String source, int offset32)
|
||||
{
|
||||
int offset16 = findOffsetFromCP(source, offset32);
|
||||
int offset16 = findOffsetFromCodePoint(source, offset32);
|
||||
return charAt(source, offset16);
|
||||
}
|
||||
|
||||
@ -227,8 +227,9 @@ public final class UTF16
|
||||
*/
|
||||
public static int getCharCount(int char32)
|
||||
{
|
||||
if (char32 < UCharacter.SUPPLEMENTARY_MIN_VALUE)
|
||||
if (char32 < UCharacter.SUPPLEMENTARY_MIN_VALUE) {
|
||||
return 1;
|
||||
}
|
||||
return 2;
|
||||
}
|
||||
|
||||
@ -260,13 +261,15 @@ public final class UTF16
|
||||
if (isLeadSurrogate(ch))
|
||||
{
|
||||
if (++ offset16 < source.length() &&
|
||||
isTrailSurrogate(source.charAt(offset16)))
|
||||
isTrailSurrogate(source.charAt(offset16))) {
|
||||
return LEAD_SURROGATE_BOUNDARY;
|
||||
}
|
||||
}
|
||||
else
|
||||
// isTrailSurrogate(ch), so
|
||||
if (-- offset16 >= 0 && isLeadSurrogate(source.charAt(offset16)))
|
||||
if (-- offset16 >= 0 && isLeadSurrogate(source.charAt(offset16))) {
|
||||
return TRAIL_SURROGATE_BOUNDARY;
|
||||
}
|
||||
|
||||
return SINGLE_CHAR_BOUNDARY;
|
||||
}
|
||||
@ -292,9 +295,9 @@ public final class UTF16
|
||||
* [offset32 - (value >> 2), offset32 + (value & 3)].
|
||||
* @exception StringIndexOutOfBoundsException if offset32 is out of bounds.
|
||||
*/
|
||||
public static int boundsAtCPOffset(String source, int offset32)
|
||||
public static int boundsAtCodePointOffset(String source, int offset32)
|
||||
{
|
||||
int offset16 = findOffsetFromCP(source, offset32);
|
||||
int offset16 = findOffsetFromCodePoint(source, offset32);
|
||||
return bounds(source, offset16);
|
||||
}
|
||||
|
||||
@ -342,9 +345,10 @@ public final class UTF16
|
||||
*/
|
||||
public static int getLeadSurrogate(int char32)
|
||||
{
|
||||
if (char32 >= UCharacter.SUPPLEMENTARY_MIN_VALUE)
|
||||
if (char32 >= UCharacter.SUPPLEMENTARY_MIN_VALUE) {
|
||||
return LEAD_SURROGATE_OFFSET_ +
|
||||
(char32 >> UCharacter.LEAD_SURROGATE_SHIFT_);
|
||||
}
|
||||
|
||||
return 0;
|
||||
}
|
||||
@ -360,9 +364,10 @@ public final class UTF16
|
||||
*/
|
||||
public static int getTrailSurrogate(int char32)
|
||||
{
|
||||
if (char32 >= UCharacter.SUPPLEMENTARY_MIN_VALUE)
|
||||
if (char32 >= UCharacter.SUPPLEMENTARY_MIN_VALUE) {
|
||||
return TRAIL_SURROGATE_MIN_VALUE_ + (char32 &
|
||||
UCharacter.TRAIL_SURROGATE_MASK_);
|
||||
}
|
||||
|
||||
return (char)char32;
|
||||
}
|
||||
@ -379,10 +384,12 @@ public final class UTF16
|
||||
*/
|
||||
public static String valueOf(int char32)
|
||||
{
|
||||
if (char32 < UCharacter.MIN_VALUE || char32 > UCharacter.MAX_VALUE)
|
||||
if (char32 < UCharacter.MIN_VALUE || char32 > UCharacter.MAX_VALUE) {
|
||||
throw new IllegalArgumentException("Illegal codepoint");
|
||||
if (char32 < UCharacter.SUPPLEMENTARY_MIN_VALUE)
|
||||
}
|
||||
if (char32 < UCharacter.SUPPLEMENTARY_MIN_VALUE) {
|
||||
return String.valueOf((char)char32);
|
||||
}
|
||||
char str[] = new char[2];
|
||||
str[0] = (char)(LEAD_SURROGATE_OFFSET_ +
|
||||
(char32 >> UCharacter.LEAD_SURROGATE_SHIFT_));
|
||||
@ -400,7 +407,7 @@ public final class UTF16
|
||||
* @return UTF-16 offset
|
||||
* @exception StringIndexOutOfBoundsException if offset32 is out of bounds.
|
||||
*/
|
||||
public static int findOffsetFromCP(String source, int offset32)
|
||||
public static int findOffsetFromCodePoint(String source, int offset32)
|
||||
{
|
||||
char ch;
|
||||
int size = source.length(),
|
||||
@ -410,14 +417,16 @@ public final class UTF16
|
||||
{
|
||||
ch = source.charAt(result);
|
||||
if (isLeadSurrogate(ch) && ((result + 1) < size) &&
|
||||
isTrailSurrogate(source.charAt(result + 1)))
|
||||
isTrailSurrogate(source.charAt(result + 1))) {
|
||||
result ++;
|
||||
}
|
||||
|
||||
count --;
|
||||
result ++;
|
||||
}
|
||||
if (result >= size)
|
||||
if (result >= size) {
|
||||
throw new StringIndexOutOfBoundsException(offset32);
|
||||
}
|
||||
return result;
|
||||
}
|
||||
|
||||
@ -440,10 +449,11 @@ public final class UTF16
|
||||
* @return UTF-32 offset
|
||||
* @exception StringIndexOutOfBoundsException if offset16 is out of bounds.
|
||||
*/
|
||||
public static int findCPOffset(String source, int offset16)
|
||||
public static int findCodePointOffset(String source, int offset16)
|
||||
{
|
||||
if (offset16 >= source.length())
|
||||
throw new StringIndexOutOfBoundsException(offset16);
|
||||
if (offset16 >= source.length()) {
|
||||
throw new StringIndexOutOfBoundsException(offset16);
|
||||
}
|
||||
|
||||
int result = 0;
|
||||
char ch;
|
||||
@ -452,8 +462,9 @@ public final class UTF16
|
||||
for (int i = 0; i < offset16; ++ i)
|
||||
{
|
||||
ch = source.charAt(i);
|
||||
if (hadLeadSurrogate && isTrailSurrogate(ch))
|
||||
if (hadLeadSurrogate && isTrailSurrogate(ch)) {
|
||||
hadLeadSurrogate = false; // count valid trail as zero
|
||||
}
|
||||
else
|
||||
{
|
||||
hadLeadSurrogate = isLeadSurrogate(ch);
|
||||
@ -462,8 +473,9 @@ public final class UTF16
|
||||
}
|
||||
// end of source being a supplementary character
|
||||
// shift result back to the start of the supplementary character
|
||||
if (hadLeadSurrogate && isTrailSurrogate(source.charAt(offset16)))
|
||||
if (hadLeadSurrogate && isTrailSurrogate(source.charAt(offset16))) {
|
||||
result --;
|
||||
}
|
||||
|
||||
return result;
|
||||
}
|
||||
@ -480,8 +492,9 @@ public final class UTF16
|
||||
public static StringBuffer append(StringBuffer target, int char32)
|
||||
{
|
||||
// Check for irregular values
|
||||
if (char32 < UCharacter.MIN_VALUE || char32 > UCharacter.MAX_VALUE)
|
||||
if (char32 < UCharacter.MIN_VALUE || char32 > UCharacter.MAX_VALUE) {
|
||||
throw new IllegalArgumentException("Illegal codepoint");
|
||||
}
|
||||
|
||||
// Write the UTF-16 values
|
||||
if (char32 >= UCharacter.SUPPLEMENTARY_MIN_VALUE)
|
||||
@ -491,8 +504,9 @@ public final class UTF16
|
||||
target.append((char)(TRAIL_SURROGATE_MIN_VALUE_ +
|
||||
(char32 & UCharacter.TRAIL_SURROGATE_MASK_)));
|
||||
}
|
||||
else
|
||||
else {
|
||||
target.append((char)char32);
|
||||
}
|
||||
return target;
|
||||
}
|
||||
|
||||
@ -508,49 +522,59 @@ public final class UTF16
|
||||
*/
|
||||
public int compare(Object a, Object b)
|
||||
{
|
||||
if (a == b)
|
||||
if (a == b) {
|
||||
return 0;
|
||||
if (a == null)
|
||||
}
|
||||
if (a == null) {
|
||||
return -1;
|
||||
if (b == null)
|
||||
}
|
||||
if (b == null) {
|
||||
return 1;
|
||||
}
|
||||
|
||||
String sa = (String) a;
|
||||
String sb = (String) b;
|
||||
int lena = sa.length();
|
||||
int lenb = sb.length();
|
||||
int len = lena;
|
||||
if (len > lenb)
|
||||
if (len > lenb) {
|
||||
len = lenb;
|
||||
}
|
||||
|
||||
for (int i = 0; i < len; ++i)
|
||||
{
|
||||
char ca = sa.charAt(i);
|
||||
char cb = sb.charAt(i);
|
||||
if (ca == cb)
|
||||
if (ca == cb) {
|
||||
continue; // skip remap if equal
|
||||
}
|
||||
|
||||
// start of only different section
|
||||
// what this part does is to rearrange the characters 0xE000 to 0xFFFF
|
||||
// to the region starting from 0xD800
|
||||
// and shift the surrogate characters to above this region
|
||||
if (ca >= LEAD_SURROGATE_MIN_VALUE_)
|
||||
if (ca >= LEAD_SURROGATE_MIN_VALUE_) {
|
||||
ca += (ca <= TRAIL_SURROGATE_MAX_VALUE_) ? 0x2000 : -0x800;
|
||||
if (cb >= LEAD_SURROGATE_MIN_VALUE_)
|
||||
}
|
||||
if (cb >= LEAD_SURROGATE_MIN_VALUE_) {
|
||||
cb += (cb <= TRAIL_SURROGATE_MAX_VALUE_) ? 0x2000 : -0x800;
|
||||
}
|
||||
// end of only different section
|
||||
|
||||
if (ca < cb)
|
||||
if (ca < cb) {
|
||||
return -1;
|
||||
}
|
||||
|
||||
return 1; // wasn't equal, so return 1
|
||||
}
|
||||
|
||||
if (lena < lenb)
|
||||
if (lena < lenb) {
|
||||
return -1;
|
||||
}
|
||||
|
||||
if (lena > lenb)
|
||||
if (lena > lenb) {
|
||||
return 1;
|
||||
}
|
||||
|
||||
return 0;
|
||||
}
|
||||
@ -561,9 +585,9 @@ public final class UTF16
|
||||
* @param s UTF16 string
|
||||
* @return number of codepoint in string
|
||||
*/
|
||||
public static int countCP(String s)
|
||||
public static int countCodePoint(String s)
|
||||
{
|
||||
return findCPOffset(s, s.length() - 1) + 1;
|
||||
return findCodePointOffset(s, s.length() - 1) + 1;
|
||||
}
|
||||
|
||||
/**
|
||||
@ -572,10 +596,10 @@ public final class UTF16
|
||||
* @param offset32 UTF32 position to insert into
|
||||
* @param char32 code point
|
||||
*/
|
||||
public static void setCharAtCPOffset(StringBuffer str, int offset32,
|
||||
public static void setCharAtCodePointOffset(StringBuffer str, int offset32,
|
||||
int char32)
|
||||
{
|
||||
int offset16 = findOffsetFromCP(str.toString(), offset32);
|
||||
int offset16 = findOffsetFromCodePoint(str.toString(), offset32);
|
||||
setCharAt(str, offset16, char32);
|
||||
}
|
||||
|
||||
@ -587,9 +611,6 @@ public final class UTF16
|
||||
*/
|
||||
public static void setCharAt(StringBuffer source, int offset16, int char32)
|
||||
{
|
||||
if (offset16 >= source.length())
|
||||
throw new StringIndexOutOfBoundsException(offset16);
|
||||
|
||||
int count = 1;
|
||||
|
||||
char single = source.charAt(offset16);
|
||||
@ -598,9 +619,10 @@ public final class UTF16
|
||||
{
|
||||
// pairs of the surrogate with offset16 at the lead char found
|
||||
if (isLeadSurrogate(single) && (source.length() > offset16 + 1) &&
|
||||
isTrailSurrogate(source.charAt(offset16 + 1)))
|
||||
isTrailSurrogate(source.charAt(offset16 + 1))) {
|
||||
count ++;
|
||||
else
|
||||
}
|
||||
else {
|
||||
// pairs of the surrogate with offset16 at the trail char found
|
||||
if (isTrailSurrogate(single) && (offset16 > 0) &&
|
||||
isLeadSurrogate(source.charAt(offset16 -1)))
|
||||
@ -608,6 +630,7 @@ public final class UTF16
|
||||
offset16 --;
|
||||
count ++;
|
||||
}
|
||||
}
|
||||
}
|
||||
source.replace(offset16, offset16 + count, valueOf(char32));
|
||||
}
|
||||
|
||||
@ -5,8 +5,8 @@
|
||||
*******************************************************************************
|
||||
*
|
||||
* $Source: /xsrl/Nsvn/icu/icu4j/src/com/ibm/text/Attic/UCharacter.java,v $
|
||||
* $Date: 2001/02/28 20:59:44 $
|
||||
* $Revision: 1.1 $
|
||||
* $Date: 2001/03/07 02:52:05 $
|
||||
* $Revision: 1.2 $
|
||||
*
|
||||
*******************************************************************************
|
||||
*/
|
||||
@ -354,36 +354,40 @@ public final class UCharacter
|
||||
int props = getProps(ch);
|
||||
int result = -1;
|
||||
// if props == 0, it will just fall through and return -1
|
||||
if (!UCharacterPropertyDB.isExceptionIndicator(props))
|
||||
{
|
||||
if (!UCharacterPropertyDB.isExceptionIndicator(props)) {
|
||||
// not contained in exception data
|
||||
if (UCharacterPropertyDB.getPropType(props) ==
|
||||
UCharacterCategory.DECIMAL_DIGIT_NUMBER)
|
||||
UCharacterCategory.DECIMAL_DIGIT_NUMBER) {
|
||||
result = UCharacterPropertyDB.getSignedValue(props);
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
else {
|
||||
// contained in exception data
|
||||
int index = UCharacterPropertyDB.getExceptionIndex(props);
|
||||
if (PROPERTY_DB_.hasExceptionValue(index,
|
||||
UCharacterPropertyDB.EXC_DIGIT_VALUE_))
|
||||
UCharacterPropertyDB.EXC_DIGIT_VALUE_)) {
|
||||
result = PROPERTY_DB_.getException(index,
|
||||
UCharacterPropertyDB.EXC_DIGIT_VALUE_) &
|
||||
LAST_CHAR_MASK_;
|
||||
else
|
||||
}
|
||||
else {
|
||||
if (!PROPERTY_DB_.hasExceptionValue(index,
|
||||
UCharacterPropertyDB.EXC_DENOMINATOR_VALUE_)
|
||||
UCharacterPropertyDB.EXC_DENOMINATOR_VALUE_)
|
||||
&& PROPERTY_DB_.hasExceptionValue(index,
|
||||
UCharacterPropertyDB.EXC_NUMERIC_VALUE_))
|
||||
result = PROPERTY_DB_.getException(index,
|
||||
UCharacterPropertyDB.EXC_NUMERIC_VALUE_);
|
||||
UCharacterPropertyDB.EXC_NUMERIC_VALUE_)) {
|
||||
result = PROPERTY_DB_.getException(index,
|
||||
UCharacterPropertyDB.EXC_NUMERIC_VALUE_);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if (result < 0)
|
||||
if (result < 0) {
|
||||
result = getHanDigit(ch);
|
||||
}
|
||||
|
||||
if (result < 0 || result >= radix)
|
||||
if (result < 0 || result >= radix) {
|
||||
return -1;
|
||||
}
|
||||
return result;
|
||||
}
|
||||
|
||||
@ -420,35 +424,41 @@ public final class UCharacter
|
||||
// if props == 0, it will just fall through and return -1
|
||||
if (type != UCharacterCategory.DECIMAL_DIGIT_NUMBER &&
|
||||
type != UCharacterCategory.LETTER_NUMBER &&
|
||||
type != UCharacterCategory.OTHER_NUMBER)
|
||||
type != UCharacterCategory.OTHER_NUMBER) {
|
||||
return -1;
|
||||
}
|
||||
|
||||
int result = -1;
|
||||
if (!UCharacterPropertyDB.isExceptionIndicator(props))
|
||||
if (!UCharacterPropertyDB.isExceptionIndicator(props)) {
|
||||
// not contained in exception data
|
||||
result = UCharacterPropertyDB.getSignedValue(props);
|
||||
else
|
||||
{
|
||||
}
|
||||
else {
|
||||
// contained in exception data
|
||||
int index = UCharacterPropertyDB.getExceptionIndex(props);
|
||||
if (PROPERTY_DB_.hasExceptionValue(index,
|
||||
UCharacterPropertyDB.EXC_DIGIT_VALUE_))
|
||||
UCharacterPropertyDB.EXC_DIGIT_VALUE_)) {
|
||||
result = PROPERTY_DB_.getException(index,
|
||||
UCharacterPropertyDB.EXC_DIGIT_VALUE_);
|
||||
else
|
||||
}
|
||||
else {
|
||||
if (!PROPERTY_DB_.hasExceptionValue(index,
|
||||
UCharacterPropertyDB.EXC_DENOMINATOR_VALUE_)
|
||||
UCharacterPropertyDB.EXC_DENOMINATOR_VALUE_)
|
||||
&& PROPERTY_DB_.hasExceptionValue(index,
|
||||
UCharacterPropertyDB.EXC_NUMERIC_VALUE_))
|
||||
result = PROPERTY_DB_.getException(index,
|
||||
UCharacterPropertyDB.EXC_NUMERIC_VALUE_)) {
|
||||
result = PROPERTY_DB_.getException(index,
|
||||
UCharacterPropertyDB.EXC_NUMERIC_VALUE_);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if (result < 0)
|
||||
if (result < 0) {
|
||||
result = getHanDigit(ch);
|
||||
}
|
||||
|
||||
if (result < 0)
|
||||
if (result < 0) {
|
||||
return -2;
|
||||
}
|
||||
return result;
|
||||
}
|
||||
|
||||
@ -755,20 +765,21 @@ public final class UCharacter
|
||||
{
|
||||
int props = getProps(ch);
|
||||
// if props == 0, it will just fall through and return itself
|
||||
if(!UCharacterPropertyDB.isExceptionIndicator(props))
|
||||
{
|
||||
if(!UCharacterPropertyDB.isExceptionIndicator(props)) {
|
||||
int cat = UCharacterPropertyDB.getPropType(props);
|
||||
if (cat == UCharacterCategory.UPPERCASE_LETTER ||
|
||||
cat == UCharacterCategory.TITLECASE_LETTER)
|
||||
cat == UCharacterCategory.TITLECASE_LETTER) {
|
||||
return ch + UCharacterPropertyDB.getSignedValue(props);
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
int index = UCharacterPropertyDB.getExceptionIndex(props);
|
||||
if (PROPERTY_DB_.hasExceptionValue(index,
|
||||
UCharacterPropertyDB.EXC_LOWERCASE_))
|
||||
UCharacterPropertyDB.EXC_LOWERCASE_)) {
|
||||
return PROPERTY_DB_.getException(index,
|
||||
UCharacterPropertyDB.EXC_LOWERCASE_);
|
||||
}
|
||||
}
|
||||
return ch;
|
||||
}
|
||||
@ -787,11 +798,13 @@ public final class UCharacter
|
||||
*/
|
||||
public static String toString(int ch)
|
||||
{
|
||||
if (ch < MIN_VALUE || ch > MAX_VALUE)
|
||||
if (ch < MIN_VALUE || ch > MAX_VALUE) {
|
||||
return null;
|
||||
}
|
||||
|
||||
if (ch < UCharacter.SUPPLEMENTARY_MIN_VALUE)
|
||||
if (ch < UCharacter.SUPPLEMENTARY_MIN_VALUE) {
|
||||
return String.valueOf((char)ch);
|
||||
}
|
||||
|
||||
char result[] = new char[2];
|
||||
result[0] = (char)UTF16.getLeadSurrogate(ch);
|
||||
@ -819,26 +832,28 @@ public final class UCharacter
|
||||
{
|
||||
int props = getProps(ch);
|
||||
// if props == 0, it will just fall through and return itself
|
||||
if (!UCharacterPropertyDB.isExceptionIndicator(props))
|
||||
{
|
||||
if (!UCharacterPropertyDB.isExceptionIndicator(props)) {
|
||||
if (UCharacterPropertyDB.getPropType(props) ==
|
||||
UCharacterCategory.LOWERCASE_LETTER)
|
||||
UCharacterCategory.LOWERCASE_LETTER) {
|
||||
// here, titlecase is same as uppercase
|
||||
return ch - UCharacterPropertyDB.getSignedValue(props);
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
else {
|
||||
int index = UCharacterPropertyDB.getExceptionIndex(props);
|
||||
if (PROPERTY_DB_.hasExceptionValue(index,
|
||||
UCharacterPropertyDB.EXC_TITLECASE_))
|
||||
UCharacterPropertyDB.EXC_TITLECASE_)) {
|
||||
return PROPERTY_DB_.getException(index,
|
||||
UCharacterPropertyDB.EXC_TITLECASE_);
|
||||
else
|
||||
}
|
||||
else {
|
||||
// here, titlecase is same as uppercase
|
||||
if (PROPERTY_DB_.hasExceptionValue(index,
|
||||
UCharacterPropertyDB.EXC_UPPERCASE_))
|
||||
UCharacterPropertyDB.EXC_UPPERCASE_)) {
|
||||
return PROPERTY_DB_.getException(index,
|
||||
UCharacterPropertyDB.EXC_UPPERCASE_);
|
||||
}
|
||||
}
|
||||
}
|
||||
return ch; // no mapping - return c itself
|
||||
}
|
||||
@ -860,20 +875,21 @@ public final class UCharacter
|
||||
{
|
||||
int props = getProps(ch);
|
||||
// if props == 0, it will just fall through and return itself
|
||||
if (!UCharacterPropertyDB.isExceptionIndicator(props))
|
||||
{
|
||||
if (!UCharacterPropertyDB.isExceptionIndicator(props)) {
|
||||
if (UCharacterPropertyDB.getPropType(props) ==
|
||||
UCharacterCategory.LOWERCASE_LETTER)
|
||||
UCharacterCategory.LOWERCASE_LETTER) {
|
||||
// here, titlecase is same as uppercase */
|
||||
return ch - UCharacterPropertyDB.getSignedValue(props);
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
int index = UCharacterPropertyDB.getExceptionIndex(props);
|
||||
if (PROPERTY_DB_.hasExceptionValue(index,
|
||||
UCharacterPropertyDB.EXC_UPPERCASE_))
|
||||
UCharacterPropertyDB.EXC_UPPERCASE_)) {
|
||||
return PROPERTY_DB_.getException(index,
|
||||
UCharacterPropertyDB.EXC_UPPERCASE_);
|
||||
}
|
||||
}
|
||||
return ch; // no mapping - return c itself
|
||||
}
|
||||
@ -1000,8 +1016,9 @@ public final class UCharacter
|
||||
public static int getDirection(int ch)
|
||||
{
|
||||
int props = getProps(ch);
|
||||
if (props != 0)
|
||||
if (props != 0) {
|
||||
return UCharacterPropertyDB.getDirection(props);
|
||||
}
|
||||
return UCharacterDirection.LEFT_TO_RIGHT;
|
||||
}
|
||||
|
||||
@ -1038,9 +1055,10 @@ public final class UCharacter
|
||||
int props = getProps(ch);
|
||||
// mirrored - the value is a mirror offset
|
||||
// if props == 0, it will just fall through and return false
|
||||
if (UCharacterPropertyDB.isMirrored(props))
|
||||
if(!UCharacterPropertyDB.isExceptionIndicator(props))
|
||||
if (UCharacterPropertyDB.isMirrored(props)) {
|
||||
if(!UCharacterPropertyDB.isExceptionIndicator(props)) {
|
||||
return ch + UCharacterPropertyDB.getSignedValue(props);
|
||||
}
|
||||
else
|
||||
{
|
||||
int index = UCharacterPropertyDB.getExceptionIndex(props);
|
||||
@ -1049,6 +1067,7 @@ public final class UCharacter
|
||||
return PROPERTY_DB_.getException(index,
|
||||
UCharacterPropertyDB.EXC_MIRROR_MAPPING_);
|
||||
}
|
||||
}
|
||||
return ch;
|
||||
}
|
||||
|
||||
@ -1060,17 +1079,21 @@ public final class UCharacter
|
||||
public static byte getCombiningClass(int ch)
|
||||
{
|
||||
int props = getProps(ch);
|
||||
if(!UCharacterPropertyDB.isExceptionIndicator(props))
|
||||
if(!UCharacterPropertyDB.isExceptionIndicator(props)) {
|
||||
if (UCharacterPropertyDB.getPropType(props) ==
|
||||
UCharacterCategory.NON_SPACING_MARK)
|
||||
UCharacterCategory.NON_SPACING_MARK) {
|
||||
return (byte)(PROPERTY_DB_.getUnsignedValue(props));
|
||||
else
|
||||
}
|
||||
else {
|
||||
return 0;
|
||||
else
|
||||
}
|
||||
}
|
||||
else {
|
||||
// the combining class is in bits 23..16 of the first exception value
|
||||
return (byte)((PROPERTY_DB_.getException(PROPERTY_DB_.getExceptionIndex(
|
||||
props), UCharacterPropertyDB.EXC_COMBINING_CLASS_)
|
||||
>> SHIFT_16_) & LAST_BYTE_MASK_);
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
@ -1086,12 +1109,18 @@ public final class UCharacter
|
||||
*/
|
||||
public static boolean isLegal(int ch)
|
||||
{
|
||||
if (ch < MIN_VALUE) return false;
|
||||
if (ch < SURROGATE_MIN_VALUE_) return true;
|
||||
if (ch <= SURROGATE_MAX_VALUE_) return false;
|
||||
|
||||
if ((ch & LAST_CHAR_MASK_) >= NOT_A_CHAR_SUFFIX_MIN_)
|
||||
if (ch < MIN_VALUE) {
|
||||
return false;
|
||||
}
|
||||
if (ch < SURROGATE_MIN_VALUE_) {
|
||||
return true;
|
||||
}
|
||||
if (ch <= SURROGATE_MAX_VALUE_) {
|
||||
return false;
|
||||
}
|
||||
if ((ch & LAST_CHAR_MASK_) >= NOT_A_CHAR_SUFFIX_MIN_) {
|
||||
return false;
|
||||
}
|
||||
return (ch <= MAX_VALUE);
|
||||
}
|
||||
|
||||
@ -1116,10 +1145,12 @@ public final class UCharacter
|
||||
for (int i = 0; i < size; i ++)
|
||||
{
|
||||
codepoint = UTF16.charAt(str, i);
|
||||
if (!isLegal(codepoint))
|
||||
if (!isLegal(codepoint)) {
|
||||
return false;
|
||||
if (isSupplementary(codepoint))
|
||||
}
|
||||
if (isSupplementary(codepoint)) {
|
||||
i ++;
|
||||
}
|
||||
}
|
||||
return true;
|
||||
}
|
||||
@ -1201,8 +1232,9 @@ public final class UCharacter
|
||||
*/
|
||||
public static int getCodePoint(char lead, char trail)
|
||||
{
|
||||
if (UTF16.isLeadSurrogate(lead) && UTF16.isTrailSurrogate(trail))
|
||||
if (UTF16.isLeadSurrogate(lead) && UTF16.isTrailSurrogate(trail)) {
|
||||
return getRawSupplementary(lead, trail);
|
||||
}
|
||||
return UCharacter.REPLACEMENT_CHAR;
|
||||
}
|
||||
|
||||
@ -1218,8 +1250,9 @@ public final class UCharacter
|
||||
*/
|
||||
public static int getCodePoint(char char16)
|
||||
{
|
||||
if (UCharacter.isLegal(char16))
|
||||
if (UCharacter.isLegal(char16)) {
|
||||
return char16;
|
||||
}
|
||||
throw new IllegalArgumentException("Illegal codepoint");
|
||||
}
|
||||
|
||||
@ -1254,7 +1287,7 @@ public final class UCharacter
|
||||
*/
|
||||
public static String toUpperCase(Locale locale, String str)
|
||||
{
|
||||
int size = UTF16.countCP(str);
|
||||
int size = UTF16.countCodePoint(str);
|
||||
StringBuffer result = new StringBuffer(size << 1); // initial buffer
|
||||
int props;
|
||||
int exception;
|
||||
@ -1266,26 +1299,30 @@ public final class UCharacter
|
||||
|
||||
for (int i = 0; i < size; i ++)
|
||||
{
|
||||
ch = UTF16.charAtCPOffset(str, i);
|
||||
ch = UTF16.charAtCodePointOffset(str, i);
|
||||
props = PROPERTY_DB_.getProperty(ch);
|
||||
if (!UCharacterPropertyDB.isExceptionIndicator(props))
|
||||
{
|
||||
if (UCharacterPropertyDB.getPropType(props) ==
|
||||
UCharacterCategory.LOWERCASE_LETTER)
|
||||
UCharacterCategory.LOWERCASE_LETTER) {
|
||||
ch -= UCharacterPropertyDB.getSignedValue(props);
|
||||
}
|
||||
UTF16.append(result, ch);
|
||||
}
|
||||
else
|
||||
{
|
||||
index = UCharacterPropertyDB.getExceptionIndex(props);
|
||||
if (PROPERTY_DB_.hasExceptionValue(index,
|
||||
UCharacterPropertyDB.EXC_SPECIAL_CASING_))
|
||||
getSpecialUpperCase(ch, index, result, str, i, tr_az, lt);
|
||||
else
|
||||
UCharacterPropertyDB.EXC_SPECIAL_CASING_)) {
|
||||
getSpecialUpperCase(ch, index, result, str, i, tr_az, lt);
|
||||
}
|
||||
else {
|
||||
if (PROPERTY_DB_.hasExceptionValue(index,
|
||||
UCharacterPropertyDB.EXC_UPPERCASE_))
|
||||
UCharacterPropertyDB.EXC_UPPERCASE_)) {
|
||||
UTF16.append(result, PROPERTY_DB_.getException(index,
|
||||
UCharacterPropertyDB.EXC_UPPERCASE_));
|
||||
UCharacterPropertyDB.EXC_UPPERCASE_));
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
return result.toString();
|
||||
@ -1300,7 +1337,7 @@ public final class UCharacter
|
||||
*/
|
||||
public static String toLowerCase(Locale locale, String str)
|
||||
{
|
||||
int size = UTF16.countCP(str);
|
||||
int size = UTF16.countCodePoint(str);
|
||||
StringBuffer result = new StringBuffer(size << 1); // initial buffer
|
||||
int props;
|
||||
int exception;
|
||||
@ -1313,27 +1350,29 @@ public final class UCharacter
|
||||
|
||||
for (int i = 0; i < size; i ++)
|
||||
{
|
||||
ch = UTF16.charAtCPOffset(str, i);
|
||||
ch = UTF16.charAtCodePointOffset(str, i);
|
||||
props = PROPERTY_DB_.getProperty(ch);
|
||||
if (!UCharacterPropertyDB.isExceptionIndicator(props))
|
||||
{
|
||||
if (!UCharacterPropertyDB.isExceptionIndicator(props)) {
|
||||
type = UCharacterPropertyDB.getPropType(props);
|
||||
if (type == UCharacterCategory.UPPERCASE_LETTER ||
|
||||
type == UCharacterCategory.TITLECASE_LETTER)
|
||||
type == UCharacterCategory.TITLECASE_LETTER) {
|
||||
ch += UCharacterPropertyDB.getSignedValue(props);
|
||||
}
|
||||
UTF16.append(result, ch);
|
||||
}
|
||||
else
|
||||
{
|
||||
else {
|
||||
index = UCharacterPropertyDB.getExceptionIndex(props);
|
||||
if (PROPERTY_DB_.hasExceptionValue(index,
|
||||
UCharacterPropertyDB.EXC_SPECIAL_CASING_))
|
||||
getSpecialLowerCase(ch, index, result, str, i, tr_az, lt);
|
||||
else
|
||||
UCharacterPropertyDB.EXC_SPECIAL_CASING_)) {
|
||||
getSpecialLowerCase(ch, index, result, str, i, tr_az, lt);
|
||||
}
|
||||
else {
|
||||
if (PROPERTY_DB_.hasExceptionValue(index,
|
||||
UCharacterPropertyDB.EXC_LOWERCASE_))
|
||||
UCharacterPropertyDB.EXC_LOWERCASE_)) {
|
||||
UTF16.append(result, PROPERTY_DB_.getException(index,
|
||||
UCharacterPropertyDB.EXC_LOWERCASE_));
|
||||
UCharacterPropertyDB.EXC_LOWERCASE_));
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
return result.toString();
|
||||
@ -1363,8 +1402,9 @@ public final class UCharacter
|
||||
*/
|
||||
private static int getProps(int ch)
|
||||
{
|
||||
if (ch >= UCharacter.MIN_VALUE & ch <= UCharacter.MAX_VALUE)
|
||||
if (ch >= UCharacter.MIN_VALUE & ch <= UCharacter.MAX_VALUE) {
|
||||
return PROPERTY_DB_.getProperty(ch);
|
||||
}
|
||||
return 0;
|
||||
}
|
||||
|
||||
@ -1419,41 +1459,42 @@ public final class UCharacter
|
||||
{
|
||||
int exception = PROPERTY_DB_.getException(index,
|
||||
UCharacterPropertyDB.EXC_SPECIAL_CASING_);
|
||||
if (exception < 0)
|
||||
{
|
||||
if (exception < 0) {
|
||||
// use hardcoded conditions and mappings
|
||||
if (ch == LATIN_SMALL_LETTER_I_)
|
||||
{
|
||||
if (tr_az)
|
||||
if (ch == LATIN_SMALL_LETTER_I_) {
|
||||
if (tr_az) {
|
||||
// turkish and azerbaijani : i maps to dotted I
|
||||
buffer.append(LATIN_CAPITAL_LETTER_I_WITH_DOT_ABOVE_);
|
||||
else
|
||||
}
|
||||
else {
|
||||
// other languages: i maps to I
|
||||
buffer.append(LATIN_CAPITAL_LETTER_I_);
|
||||
}
|
||||
}
|
||||
else
|
||||
if (ch == COMBINING_DOT_ABOVE_ && lt)
|
||||
{
|
||||
else {
|
||||
if (ch == COMBINING_DOT_ABOVE_ && lt) {
|
||||
// lithuanian: remove DOT ABOVE after U+0069 "i" with upper
|
||||
// or titlecase
|
||||
for (int j = chindex; j > 0; j ++)
|
||||
{
|
||||
ch = UTF16.charAtCPOffset(str, j);
|
||||
if (getType(ch) != UCharacterCategory.NON_SPACING_MARK)
|
||||
for (int j = chindex; j > 0; j ++) {
|
||||
ch = UTF16.charAtCodePointOffset(str, j);
|
||||
if (getType(ch) != UCharacterCategory.NON_SPACING_MARK) {
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
// if the base letter is not an 'i' (U+0069)? keep the dot
|
||||
if (ch != LATIN_SMALL_LETTER_I_)
|
||||
if (ch != LATIN_SMALL_LETTER_I_) {
|
||||
buffer.append(COMBINING_DOT_ABOVE_);
|
||||
}
|
||||
else
|
||||
// no known conditional special case mapping, output the code
|
||||
// point itself
|
||||
UTF16.append(buffer, ch);
|
||||
}
|
||||
}
|
||||
else {
|
||||
// no known conditional special case mapping, output the code
|
||||
// point itself
|
||||
UTF16.append(buffer, ch);
|
||||
}
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
else {
|
||||
// get the special case mapping string from the data file
|
||||
index = exception & LAST_CHAR_MASK_;
|
||||
PROPERTY_DB_.getUpperCase(index, buffer);
|
||||
@ -1478,34 +1519,37 @@ public final class UCharacter
|
||||
{
|
||||
int exception = PROPERTY_DB_.getException(index,
|
||||
UCharacterPropertyDB.EXC_SPECIAL_CASING_);
|
||||
if (exception < 0)
|
||||
{
|
||||
if (exception < 0) {
|
||||
// use hardcoded conditions and mappings
|
||||
if (ch == LATIN_CAPITAL_LETTER_I_)
|
||||
{
|
||||
if (tr_az)
|
||||
if (ch == LATIN_CAPITAL_LETTER_I_) {
|
||||
if (tr_az) {
|
||||
// turkish and azerbaijani : I maps to dotless i
|
||||
buffer.append(LATIN_SMALL_LETTER_DOTLESS_I_);
|
||||
else
|
||||
}
|
||||
else {
|
||||
// other languages: I maps to i
|
||||
buffer.append(LATIN_SMALL_LETTER_I_);
|
||||
}
|
||||
}
|
||||
else
|
||||
if (ch == GREEK_CAPITAL_LETTER_SIGMA_)
|
||||
{
|
||||
else {
|
||||
if (ch == GREEK_CAPITAL_LETTER_SIGMA_) {
|
||||
// greek capital sigma maps depending on whether the following
|
||||
// character is a letter
|
||||
chindex ++;
|
||||
if (chindex != str.length() &&
|
||||
isLetter(UTF16.charAtCPOffset(str, chindex)))
|
||||
isLetter(UTF16.charAtCodePointOffset(str, chindex))) {
|
||||
buffer.append(GREEK_SMALL_LETTER_SIGMA_);
|
||||
else
|
||||
}
|
||||
else {
|
||||
buffer.append(GREEK_SMALL_LETTER_RHO_);
|
||||
}
|
||||
}
|
||||
else
|
||||
else {
|
||||
// no known conditional special case mapping, output the code
|
||||
// point itself
|
||||
UTF16.append(buffer, ch);
|
||||
}
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
|
||||
@ -5,8 +5,8 @@
|
||||
*******************************************************************************
|
||||
*
|
||||
* $Source: /xsrl/Nsvn/icu/icu4j/src/com/ibm/text/Attic/UCharacterDB.java,v $
|
||||
* $Date: 2001/02/28 20:59:44 $
|
||||
* $Revision: 1.1 $
|
||||
* $Date: 2001/03/07 02:52:05 $
|
||||
* $Revision: 1.2 $
|
||||
*
|
||||
*******************************************************************************
|
||||
*/
|
||||
@ -55,14 +55,6 @@ class UCharacterDB
|
||||
public String toString()
|
||||
{
|
||||
StringBuffer result = new StringBuffer();
|
||||
/*for (int i = 0; i < size; i ++)
|
||||
{
|
||||
result.append(" ");
|
||||
result.append(0x0000FFFF & m_db_[i]);
|
||||
}
|
||||
|
||||
result.append('\n');
|
||||
*/
|
||||
result.append("\nunicode version number ");
|
||||
result.append(m_unicodeversion_);
|
||||
|
||||
@ -79,21 +71,24 @@ class UCharacterDB
|
||||
protected boolean setUnicodeVersion(byte[] version)
|
||||
{
|
||||
int size = 0;
|
||||
if (version != null)
|
||||
if (version != null) {
|
||||
size = version.length;
|
||||
}
|
||||
boolean result = false;
|
||||
StringBuffer s = new StringBuffer(size);
|
||||
for (int i = 0; i < size; i++)
|
||||
{
|
||||
for (int i = 0; i < size; i++) {
|
||||
s.append((int)version[i]);
|
||||
s.append('.');
|
||||
if (version[i] < 0 || version[i] > 9)
|
||||
if (version[i] < 0 || version[i] > 9) {
|
||||
return false;
|
||||
if (version[i] != 0)
|
||||
}
|
||||
if (version[i] != 0) {
|
||||
result = true;
|
||||
}
|
||||
}
|
||||
if (result)
|
||||
if (result) {
|
||||
m_unicodeversion_ = s.substring(0, (size << 1) - 1);
|
||||
}
|
||||
return true;
|
||||
}
|
||||
}
|
||||
|
||||
@ -6,8 +6,8 @@
|
||||
*
|
||||
* $Source:
|
||||
* /usr/cvs/icu4j/icu4j/src/com/ibm/icu/text/UCharacterName.java $
|
||||
* $Date: 2001/02/28 20:59:44 $
|
||||
* $Revision: 1.1 $
|
||||
* $Date: 2001/03/07 02:52:05 $
|
||||
* $Revision: 1.2 $
|
||||
*
|
||||
*******************************************************************************
|
||||
*/
|
||||
@ -75,8 +75,9 @@ final class UCharacterName
|
||||
protected static String getName(int ch, int choice)
|
||||
{
|
||||
if (ch < 0 || ch > 0x1ffff ||
|
||||
choice >= UCharacterNameChoice.U_CHAR_NAME_CHOICE_COUNT)
|
||||
choice >= UCharacterNameChoice.U_CHAR_NAME_CHOICE_COUNT) {
|
||||
return null;
|
||||
}
|
||||
|
||||
String result = "";
|
||||
|
||||
@ -84,13 +85,15 @@ final class UCharacterName
|
||||
// the same as the modern ones, extension A was only introduced with
|
||||
// Unicode 3.0, and the Hangul syllable block was moved and changed around
|
||||
// Unicode 1.1.5.
|
||||
if (choice == UCharacterNameChoice.U_UNICODE_CHAR_NAME)
|
||||
if (choice == UCharacterNameChoice.U_UNICODE_CHAR_NAME) {
|
||||
// try getting algorithmic name first
|
||||
result = getAlgName(ch);
|
||||
}
|
||||
|
||||
// getting normal character name
|
||||
if (result == null || result.length() == 0)
|
||||
if (result == null || result.length() == 0) {
|
||||
result = NAME_DB_.getGroupName(ch, choice);
|
||||
}
|
||||
|
||||
return result;
|
||||
}
|
||||
@ -106,13 +109,15 @@ final class UCharacterName
|
||||
{
|
||||
// checks for illegal arguments
|
||||
if (choice >= UCharacterNameChoice.U_CHAR_NAME_CHOICE_COUNT ||
|
||||
name == null || name.length() == 0)
|
||||
name == null || name.length() == 0) {
|
||||
return -1;
|
||||
}
|
||||
|
||||
// try algorithmic names first, if fails then try group names
|
||||
int result = getAlgorithmChar(choice, name);
|
||||
if (result >= 0)
|
||||
if (result >= 0) {
|
||||
return result;
|
||||
}
|
||||
return getGroupChar(name, choice);
|
||||
}
|
||||
|
||||
@ -129,8 +134,7 @@ final class UCharacterName
|
||||
StringBuffer s = new StringBuffer();
|
||||
|
||||
int index = NAME_DB_.getAlgorithmIndex(ch);
|
||||
if (index >= 0)
|
||||
{
|
||||
if (index >= 0) {
|
||||
NAME_DB_.appendAlgorithmName(index, ch, s);
|
||||
return s.toString();
|
||||
}
|
||||
@ -145,14 +149,15 @@ final class UCharacterName
|
||||
private static int getAlgorithmChar(int choice, String name)
|
||||
{
|
||||
// 1.0 has no algorithmic names
|
||||
if (choice != UCharacterNameChoice.U_UNICODE_CHAR_NAME)
|
||||
if (choice != UCharacterNameChoice.U_UNICODE_CHAR_NAME) {
|
||||
return -1;
|
||||
}
|
||||
int result;
|
||||
for (int count = NAME_DB_.countAlgorithm() - 1; count >= 0; count --)
|
||||
{
|
||||
for (int count = NAME_DB_.countAlgorithm() - 1; count >= 0; count --) {
|
||||
result = NAME_DB_.getAlgorithmChar(count, name);
|
||||
if (result >= 0)
|
||||
if (result >= 0) {
|
||||
return result;
|
||||
}
|
||||
}
|
||||
return -1;
|
||||
}
|
||||
@ -168,11 +173,11 @@ final class UCharacterName
|
||||
int groupcount = NAME_DB_.countGroup();
|
||||
int result = 0;
|
||||
|
||||
for (int i = 0; i < groupcount; i ++)
|
||||
{
|
||||
for (int i = 0; i < groupcount; i ++) {
|
||||
result = NAME_DB_.getGroupChar(i, name, choice);
|
||||
if (result != -1)
|
||||
if (result != -1) {
|
||||
return result;
|
||||
}
|
||||
}
|
||||
return -1;
|
||||
}
|
||||
|
||||
@ -5,8 +5,8 @@
|
||||
*******************************************************************************
|
||||
*
|
||||
* $Source: /xsrl/Nsvn/icu/icu4j/src/com/ibm/text/Attic/UCharacterNameDB.java,v $
|
||||
* $Date: 2001/02/28 20:59:44 $
|
||||
* $Revision: 1.1 $
|
||||
* $Date: 2001/03/07 02:52:05 $
|
||||
* $Revision: 1.2 $
|
||||
*
|
||||
*******************************************************************************
|
||||
*/
|
||||
@ -16,6 +16,7 @@ package com.ibm.text;
|
||||
import java.io.InputStream;
|
||||
import java.io.DataInputStream;
|
||||
import java.io.BufferedInputStream;
|
||||
import java.io.IOException;
|
||||
|
||||
/**
|
||||
* Internal class used for Unicode character name database.
|
||||
@ -106,14 +107,13 @@ final class UCharacterNameDB extends UCharacterDB
|
||||
* protected constructor
|
||||
* @exception thrown when data reading fails or when data has been corrupted
|
||||
*/
|
||||
protected UCharacterNameDB() throws Exception
|
||||
protected UCharacterNameDB() throws IOException
|
||||
{
|
||||
UGenNameReader reader = new UGenNameReader();
|
||||
InputStream i = getClass().getResourceAsStream(NAME_FILE_NAME_);
|
||||
BufferedInputStream b = new BufferedInputStream(i, NAME_BUFFER_SIZE_);
|
||||
DataInputStream d = new DataInputStream(b);
|
||||
if (!reader.read(d, this))
|
||||
throw new Exception("Data corrupted in " + NAME_FILE_NAME_);
|
||||
reader.read(d, this);
|
||||
d.close();
|
||||
UNICODE_1_ = (';' >= m_tokentable_.length) ||
|
||||
(m_tokentable_[(int)';'] == 0xFFFF);
|
||||
@ -156,8 +156,7 @@ final class UCharacterNameDB extends UCharacterDB
|
||||
protected boolean setToken(char token[], byte tokenstring[])
|
||||
{
|
||||
if (token != null && tokenstring != null && token.length > 0 &&
|
||||
tokenstring.length > 0)
|
||||
{
|
||||
tokenstring.length > 0) {
|
||||
m_tokentable_ = token;
|
||||
m_tokenstring_ = tokenstring;
|
||||
return true;
|
||||
@ -173,8 +172,9 @@ final class UCharacterNameDB extends UCharacterDB
|
||||
*/
|
||||
protected boolean setGroupCountSize(int count, int size)
|
||||
{
|
||||
if (count <= 0 || size <= 0)
|
||||
if (count <= 0 || size <= 0) {
|
||||
return false;
|
||||
}
|
||||
m_groupcount_ = count;
|
||||
m_groupsize_ = size;
|
||||
return true;
|
||||
@ -189,8 +189,7 @@ final class UCharacterNameDB extends UCharacterDB
|
||||
protected boolean setGroup(char group[], byte groupstring[])
|
||||
{
|
||||
if (group != null && groupstring != null && group.length > 0 &&
|
||||
groupstring.length > 0)
|
||||
{
|
||||
groupstring.length > 0) {
|
||||
m_groupinfo_ = group;
|
||||
m_groupstring_ = groupstring;
|
||||
return true;
|
||||
@ -216,18 +215,18 @@ final class UCharacterNameDB extends UCharacterDB
|
||||
gindex = 0;
|
||||
|
||||
// binary search for the group of names that contains the one for code
|
||||
for (start = 0; start < end - 1;)
|
||||
{
|
||||
for (start = 0; start < end - 1;) {
|
||||
gindex = (start + end) >> 1;
|
||||
if (msb < getGroupMSB(gindex))
|
||||
if (msb < getGroupMSB(gindex)) {
|
||||
end = gindex;
|
||||
else
|
||||
}
|
||||
else {
|
||||
start = gindex;
|
||||
}
|
||||
}
|
||||
|
||||
// return this if it is an exact match
|
||||
if (msb == getGroupMSB(start))
|
||||
{
|
||||
if (msb == getGroupMSB(start)) {
|
||||
start = start * m_groupsize_;
|
||||
return UCharacterUtil.toInt(m_groupinfo_[start + OFFSET_HIGH_OFFSET_],
|
||||
m_groupinfo_[start + OFFSET_LOW_OFFSET_]);
|
||||
@ -251,11 +250,12 @@ final class UCharacterNameDB extends UCharacterDB
|
||||
*/
|
||||
protected String getGroupName(int ch, int choice)
|
||||
{
|
||||
if (choice != UCharacterNameChoice.U_UNICODE_CHAR_NAME && !UNICODE_1_)
|
||||
if (choice != UCharacterNameChoice.U_UNICODE_CHAR_NAME && !UNICODE_1_) {
|
||||
// if not modern name requested and semicolon byte value is a character,
|
||||
// not a token number, otherwise since only modern names are stored in
|
||||
// unames.dat and there is no such requested Unicode 1.0 name here
|
||||
return null;
|
||||
}
|
||||
|
||||
// gets the msb
|
||||
int msb = ch >> GROUP_SHIFT_,
|
||||
@ -264,18 +264,18 @@ final class UCharacterNameDB extends UCharacterDB
|
||||
gindex = 0;
|
||||
|
||||
// binary search for the group of names that contains the one for code
|
||||
for (start = 0; start < end - 1;)
|
||||
{
|
||||
for (start = 0; start < end - 1;) {
|
||||
gindex = (start + end) >> 1;
|
||||
if (msb < getGroupMSB(gindex))
|
||||
if (msb < getGroupMSB(gindex)) {
|
||||
end = gindex;
|
||||
else
|
||||
}
|
||||
else {
|
||||
start = gindex;
|
||||
}
|
||||
}
|
||||
|
||||
// return this if it is an exact match
|
||||
if (msb == getGroupMSB(start))
|
||||
{
|
||||
if (msb == getGroupMSB(start)) {
|
||||
char offsets[] = new char[LINES_PER_GROUP_ + 1];
|
||||
char lengths[] = new char[LINES_PER_GROUP_ + 1];
|
||||
|
||||
@ -298,11 +298,12 @@ final class UCharacterNameDB extends UCharacterDB
|
||||
protected int getGroupChar(int index, String name, int choice)
|
||||
{
|
||||
if (choice != UCharacterNameChoice.U_UNICODE_CHAR_NAME &&
|
||||
!UNICODE_1_)
|
||||
!UNICODE_1_) {
|
||||
// semicolon byte value is a token number , therefore only modern
|
||||
// names are stored in unames.dat and there is no such requested
|
||||
// Unicode 1.0 name here
|
||||
return -1;
|
||||
}
|
||||
|
||||
// populating the data set of grouptable
|
||||
char offsets[] = new char[LINES_PER_GROUP_ + 1];
|
||||
@ -311,8 +312,9 @@ final class UCharacterNameDB extends UCharacterDB
|
||||
|
||||
// shift out to function
|
||||
int result = getGroupChar(startgpstrindex, lengths, name, choice);
|
||||
if (result != -1)
|
||||
if (result != -1) {
|
||||
return (getGroupMSB(index) << GROUP_SHIFT_) | result;
|
||||
}
|
||||
return -1;
|
||||
}
|
||||
|
||||
@ -323,8 +325,7 @@ final class UCharacterNameDB extends UCharacterDB
|
||||
*/
|
||||
protected boolean setAlgorithm(AlgorithmName alg[])
|
||||
{
|
||||
if (alg != null && alg.length != 0)
|
||||
{
|
||||
if (alg != null && alg.length != 0) {
|
||||
m_algorithm_ = alg;
|
||||
return true;
|
||||
}
|
||||
@ -337,8 +338,9 @@ final class UCharacterNameDB extends UCharacterDB
|
||||
*/
|
||||
protected int countAlgorithm()
|
||||
{
|
||||
if (m_algorithm_ == null)
|
||||
if (m_algorithm_ == null) {
|
||||
return 0;
|
||||
}
|
||||
return m_algorithm_.length;
|
||||
}
|
||||
|
||||
@ -350,9 +352,11 @@ final class UCharacterNameDB extends UCharacterDB
|
||||
*/
|
||||
protected int getAlgorithmIndex(int ch)
|
||||
{
|
||||
for (int index = m_algorithm_.length - 1; index >= 0; index --)
|
||||
if (m_algorithm_[index].contains(ch))
|
||||
for (int index = m_algorithm_.length - 1; index >= 0; index --) {
|
||||
if (m_algorithm_[index].contains(ch)) {
|
||||
return index;
|
||||
}
|
||||
}
|
||||
return -1;
|
||||
}
|
||||
|
||||
@ -421,26 +425,27 @@ final class UCharacterNameDB extends UCharacterDB
|
||||
offsets[0] = 0;
|
||||
|
||||
// all 32 lengths must be read to get the offset of the first group string
|
||||
for (int i = 0; i < LINES_PER_GROUP_; stringoffset ++)
|
||||
{
|
||||
for (int i = 0; i < LINES_PER_GROUP_; stringoffset ++) {
|
||||
b = m_groupstring_[stringoffset];
|
||||
shift = 4;
|
||||
|
||||
while (shift >= 0)
|
||||
{
|
||||
while (shift >= 0) {
|
||||
// getting nibble
|
||||
n = (byte)((b >> shift) & 0x0F);
|
||||
if (length == 0xffff && n > SINGLE_NIBBLE_MAX_)
|
||||
if (length == 0xffff && n > SINGLE_NIBBLE_MAX_) {
|
||||
length = (char)((n - 12) << 4);
|
||||
else
|
||||
{
|
||||
if (length != 0xffff)
|
||||
}
|
||||
else {
|
||||
if (length != 0xffff) {
|
||||
lengths[i] = (char)((length | n) + 12);
|
||||
else
|
||||
}
|
||||
else {
|
||||
lengths[i] = (char)n;
|
||||
}
|
||||
|
||||
if (i < LINES_PER_GROUP_)
|
||||
if (i < LINES_PER_GROUP_) {
|
||||
offsets[i + 1] = (char)(offsets[i] + lengths[i]);
|
||||
}
|
||||
|
||||
length = 0xffff;
|
||||
i ++;
|
||||
@ -461,8 +466,7 @@ final class UCharacterNameDB extends UCharacterDB
|
||||
*/
|
||||
private String getGroupName(int index, int length, int choice)
|
||||
{
|
||||
if (choice != UCharacterNameChoice.U_UNICODE_CHAR_NAME)
|
||||
{
|
||||
if (choice != UCharacterNameChoice.U_UNICODE_CHAR_NAME) {
|
||||
int oldindex = index;
|
||||
index += UCharacterUtil.skipByteSubString(m_groupstring_, index, length,
|
||||
(byte)';');
|
||||
@ -472,39 +476,38 @@ final class UCharacterNameDB extends UCharacterDB
|
||||
StringBuffer s = new StringBuffer();
|
||||
byte b;
|
||||
char token;
|
||||
for (int i = 0; i < length;)
|
||||
{
|
||||
for (int i = 0; i < length;) {
|
||||
b = m_groupstring_[index + i];
|
||||
i ++;
|
||||
|
||||
if (b >= m_tokentable_.length)
|
||||
{
|
||||
if (b == ';')
|
||||
if (b >= m_tokentable_.length) {
|
||||
if (b == ';') {
|
||||
break;
|
||||
}
|
||||
s.append(b); // implicit letter
|
||||
}
|
||||
else
|
||||
{
|
||||
else {
|
||||
token = m_tokentable_[b & 0x00ff];
|
||||
if (token == 0xFFFE)
|
||||
{
|
||||
if (token == 0xFFFE) {
|
||||
// this is a lead byte for a double-byte token
|
||||
token = m_tokentable_[b << 8 | (m_groupstring_[index + i] & 0x00ff)];
|
||||
i ++;
|
||||
}
|
||||
if (token == 0xFFFF)
|
||||
{
|
||||
if (b == ';')
|
||||
if (token == 0xFFFF) {
|
||||
if (b == ';') {
|
||||
break;
|
||||
}
|
||||
s.append((char)(b & 0x00ff)); // explicit letter
|
||||
}
|
||||
else // write token word
|
||||
else { // write token word
|
||||
UCharacterUtil.getNullTermByteSubString(s, m_tokenstring_, token);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if (s.length() == 0)
|
||||
if (s.length() == 0) {
|
||||
return null;
|
||||
}
|
||||
return s.toString();
|
||||
}
|
||||
|
||||
@ -527,13 +530,11 @@ final class UCharacterNameDB extends UCharacterDB
|
||||
int nindex;
|
||||
int count;
|
||||
|
||||
for (int result = 0; result <= LINES_PER_GROUP_; result ++)
|
||||
{
|
||||
for (int result = 0; result <= LINES_PER_GROUP_; result ++) {
|
||||
nindex = 0;
|
||||
len = length[result];
|
||||
|
||||
if (choice != UCharacterNameChoice.U_UNICODE_CHAR_NAME)
|
||||
{
|
||||
if (choice != UCharacterNameChoice.U_UNICODE_CHAR_NAME) {
|
||||
int oldindex = index;
|
||||
index += UCharacterUtil.skipByteSubString(m_groupstring_, index, len,
|
||||
(byte)';');
|
||||
@ -542,41 +543,40 @@ final class UCharacterNameDB extends UCharacterDB
|
||||
|
||||
// number of tokens is > the length of the name
|
||||
// write each letter directly, and write a token word per token
|
||||
for (count = 0; count < len && nindex != -1 && nindex < namelen;)
|
||||
{
|
||||
for (count = 0; count < len && nindex != -1 && nindex < namelen;) {
|
||||
b = m_groupstring_[index + count];
|
||||
count ++;
|
||||
|
||||
if (b >= m_tokentable_.length)
|
||||
{
|
||||
if (name.charAt(nindex ++) != (b & 0xFF))
|
||||
if (b >= m_tokentable_.length) {
|
||||
if (name.charAt(nindex ++) != (b & 0xFF)) {
|
||||
nindex = -1;
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
else {
|
||||
token = m_tokentable_[b & 0xFF];
|
||||
if (token == 0xFFFE)
|
||||
{
|
||||
if (token == 0xFFFE) {
|
||||
// this is a lead byte for a double-byte token
|
||||
token = m_tokentable_[b << 8 |
|
||||
(m_groupstring_[index + count] & 0x00ff)];
|
||||
count ++;
|
||||
}
|
||||
if (token == 0xFFFF)
|
||||
{
|
||||
if (name.charAt(nindex ++) != (b & 0xFF))
|
||||
if (token == 0xFFFF) {
|
||||
if (name.charAt(nindex ++) != (b & 0xFF)) {
|
||||
nindex = -1;
|
||||
}
|
||||
}
|
||||
else
|
||||
else {
|
||||
// compare token with name
|
||||
nindex = UCharacterUtil.compareNullTermByteSubString(name,
|
||||
m_tokenstring_, nindex, token);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if (namelen == nindex &&
|
||||
(count == len || m_groupstring_[index + count] == ';'))
|
||||
(count == len || m_groupstring_[index + count] == ';')) {
|
||||
return result;
|
||||
}
|
||||
|
||||
index += len;
|
||||
}
|
||||
@ -637,8 +637,7 @@ final class UCharacterNameDB extends UCharacterDB
|
||||
{
|
||||
if (rangestart >= UCharacter.MIN_VALUE && rangestart <= rangeend &&
|
||||
rangeend <= UCharacter.MAX_VALUE &&
|
||||
(type == TYPE_0_ || type == TYPE_1_))
|
||||
{
|
||||
(type == TYPE_0_ || type == TYPE_1_)) {
|
||||
m_rangestart_ = rangestart;
|
||||
m_rangeend_ = rangeend;
|
||||
m_type_ = type;
|
||||
@ -655,8 +654,7 @@ final class UCharacterNameDB extends UCharacterDB
|
||||
*/
|
||||
protected boolean setFactor(char factor[])
|
||||
{
|
||||
if (factor.length == m_variant_)
|
||||
{
|
||||
if (factor.length == m_variant_) {
|
||||
m_factor_ = factor;
|
||||
return true;
|
||||
}
|
||||
@ -670,8 +668,7 @@ final class UCharacterNameDB extends UCharacterDB
|
||||
*/
|
||||
protected boolean setPrefix(String prefix)
|
||||
{
|
||||
if (prefix != null && prefix.length() > 0)
|
||||
{
|
||||
if (prefix != null && prefix.length() > 0) {
|
||||
m_prefix_ = prefix;
|
||||
return true;
|
||||
}
|
||||
@ -755,8 +752,9 @@ final class UCharacterNameDB extends UCharacterDB
|
||||
{
|
||||
int prefixlen = m_prefix_.length();
|
||||
if (name.length() < prefixlen ||
|
||||
!m_prefix_.equals(name.substring(0, prefixlen)))
|
||||
!m_prefix_.equals(name.substring(0, prefixlen))) {
|
||||
return -1;
|
||||
}
|
||||
|
||||
switch (m_type_)
|
||||
{
|
||||
@ -765,8 +763,9 @@ final class UCharacterNameDB extends UCharacterDB
|
||||
{
|
||||
int result = Integer.parseInt(name.substring(prefixlen), 16);
|
||||
// does it fit into the range?
|
||||
if (m_rangestart_ <= result && result <= m_rangeend_)
|
||||
if (m_rangestart_ <= result && result <= m_rangeend_) {
|
||||
return result;
|
||||
}
|
||||
}
|
||||
catch (NumberFormatException e)
|
||||
{
|
||||
@ -795,8 +794,9 @@ final class UCharacterNameDB extends UCharacterDB
|
||||
indexes[0] = offset;
|
||||
|
||||
// joining up the factorized strings
|
||||
if (compareFactorString(indexes, name.substring(prefixlen)))
|
||||
if (compareFactorString(indexes, name.substring(prefixlen))) {
|
||||
return ch;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@ -813,24 +813,25 @@ final class UCharacterNameDB extends UCharacterDB
|
||||
private String[] getFactorString(int index[])
|
||||
{
|
||||
int size = m_factor_.length;
|
||||
if (index == null || index.length != size)
|
||||
if (index == null || index.length != size) {
|
||||
return null;
|
||||
}
|
||||
|
||||
String result[] = new String[size];
|
||||
StringBuffer str = new StringBuffer();
|
||||
int count = 0;
|
||||
int factor;
|
||||
size --;
|
||||
for (int i = 0; i <= size; i ++)
|
||||
{
|
||||
for (int i = 0; i <= size; i ++) {
|
||||
factor = m_factor_[i];
|
||||
count = UCharacterUtil.skipNullTermByteSubString(m_factorstring_,
|
||||
count, index[i]);
|
||||
count = UCharacterUtil.getNullTermByteSubString(str, m_factorstring_,
|
||||
count);
|
||||
if (i != size)
|
||||
if (i != size) {
|
||||
count = UCharacterUtil.skipNullTermByteSubString(m_factorstring_,
|
||||
count, factor - index[i] - 1);
|
||||
}
|
||||
result[i] = str.toString();
|
||||
str.delete(0, str.length());
|
||||
}
|
||||
@ -861,15 +862,18 @@ final class UCharacterNameDB extends UCharacterDB
|
||||
count, index[i]);
|
||||
strcount = UCharacterUtil.compareNullTermByteSubString(str,
|
||||
m_factorstring_, strcount, count);
|
||||
if (strcount < 0)
|
||||
if (strcount < 0) {
|
||||
return false;
|
||||
}
|
||||
|
||||
if (i != size)
|
||||
if (i != size) {
|
||||
count = UCharacterUtil.skipNullTermByteSubString(m_factorstring_,
|
||||
count, factor - index[i]);
|
||||
}
|
||||
}
|
||||
if (strcount != str.length())
|
||||
if (strcount != str.length()) {
|
||||
return false;
|
||||
}
|
||||
return true;
|
||||
}
|
||||
}
|
||||
|
||||
@ -6,8 +6,8 @@
|
||||
*
|
||||
* $Source:
|
||||
* /usr/cvs/icu4j/icu4j/src/com/ibm/icu/text/UCharacterPropertyDB.java $
|
||||
* $Date: 2001/02/28 20:59:44 $
|
||||
* $Revision: 1.1 $
|
||||
* $Date: 2001/03/07 02:52:05 $
|
||||
* $Revision: 1.2 $
|
||||
*
|
||||
*******************************************************************************
|
||||
*/
|
||||
@ -17,6 +17,7 @@ package com.ibm.text;
|
||||
import java.io.InputStream;
|
||||
import java.io.DataInputStream;
|
||||
import java.io.BufferedInputStream;
|
||||
import java.io.IOException;
|
||||
|
||||
/**
|
||||
* Internal class used for Unicode character property database.
|
||||
@ -189,15 +190,14 @@ final class UCharacterPropertyDB extends UCharacterDB
|
||||
* Constructor
|
||||
* @exception thrown when data reading fails or data corrupted
|
||||
*/
|
||||
protected UCharacterPropertyDB() throws Exception
|
||||
protected UCharacterPropertyDB() throws IOException
|
||||
{
|
||||
UGenPropReader reader = new UGenPropReader();
|
||||
|
||||
InputStream i = getClass().getResourceAsStream(DATA_FILE_NAME_);
|
||||
BufferedInputStream b = new BufferedInputStream(i, DATA_BUFFER_SIZE_);
|
||||
DataInputStream d = new DataInputStream(b);
|
||||
if (!reader.read(d, this))
|
||||
throw new Exception("Data corrupted in " + DATA_FILE_NAME_);
|
||||
reader.read(d, this);
|
||||
d.close();
|
||||
}
|
||||
|
||||
@ -263,8 +263,9 @@ final class UCharacterPropertyDB extends UCharacterDB
|
||||
*/
|
||||
protected boolean setStage(char stages[])
|
||||
{
|
||||
if (stages == null || stages.length <= 0)
|
||||
if (stages == null || stages.length <= 0) {
|
||||
return false;
|
||||
}
|
||||
m_stages_ = stages;
|
||||
return true;
|
||||
}
|
||||
@ -276,8 +277,9 @@ final class UCharacterPropertyDB extends UCharacterDB
|
||||
*/
|
||||
protected boolean setProperty(int property[])
|
||||
{
|
||||
if (property == null || property.length <= 0)
|
||||
if (property == null || property.length <= 0) {
|
||||
return false;
|
||||
}
|
||||
m_property_ = property;
|
||||
return true;
|
||||
}
|
||||
@ -289,8 +291,9 @@ final class UCharacterPropertyDB extends UCharacterDB
|
||||
*/
|
||||
protected boolean setCase(char casetable[])
|
||||
{
|
||||
if (casetable == null || casetable.length <= 0)
|
||||
if (casetable == null || casetable.length == 0) {
|
||||
return false;
|
||||
}
|
||||
m_case_ = casetable;
|
||||
return true;
|
||||
}
|
||||
@ -303,8 +306,9 @@ final class UCharacterPropertyDB extends UCharacterDB
|
||||
*/
|
||||
protected boolean setException(int exception[])
|
||||
{
|
||||
if (exception == null || exception.length <= 0)
|
||||
if (exception == null || exception.length <= 0) {
|
||||
return false;
|
||||
}
|
||||
m_exception_ = exception;
|
||||
return true;
|
||||
}
|
||||
@ -340,8 +344,9 @@ final class UCharacterPropertyDB extends UCharacterDB
|
||||
index += (count & LAST_5_BIT_MASK_) + 1;
|
||||
count = (count >> SHIFT_5_) & LAST_5_BIT_MASK_;
|
||||
|
||||
for (int j = 0; j < count; j ++)
|
||||
for (int j = 0; j < count; j ++) {
|
||||
buffer.append(m_case_[index + j]);
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
@ -355,8 +360,9 @@ final class UCharacterPropertyDB extends UCharacterDB
|
||||
// last 5 bits of the first char in m_case_ gives the size of the
|
||||
// lowercase characters
|
||||
index ++;
|
||||
for (int j = 0; j < count; j ++)
|
||||
for (int j = 0; j < count; j ++) {
|
||||
buffer.append(m_case_[index + j]);
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
@ -419,8 +425,9 @@ final class UCharacterPropertyDB extends UCharacterDB
|
||||
*/
|
||||
protected static boolean isExceptionIndicator(int props)
|
||||
{
|
||||
if ((props & EXCEPTION_MASK_) != 0)
|
||||
if ((props & EXCEPTION_MASK_) != 0) {
|
||||
return true;
|
||||
}
|
||||
return false;
|
||||
}
|
||||
|
||||
@ -487,8 +494,9 @@ final class UCharacterPropertyDB extends UCharacterDB
|
||||
private int addExceptionOffset(int evalue, int indicator, int address)
|
||||
{
|
||||
int result = address;
|
||||
if (indicator >= EXC_GROUP_)
|
||||
if (indicator >= EXC_GROUP_) {
|
||||
result += (FLAGS_OFFSET_[evalue & EXC_GROUP_MASK_] << 1);
|
||||
}
|
||||
// evalue >>= EXC_GROUP_;
|
||||
// indicator -= EXC_GROUP_;
|
||||
else
|
||||
|
||||
@ -5,8 +5,8 @@
|
||||
*******************************************************************************
|
||||
*
|
||||
* $Source: /xsrl/Nsvn/icu/icu4j/src/com/ibm/text/Attic/UCharacterUtil.java,v $
|
||||
* $Date: 2001/02/28 20:59:44 $
|
||||
* $Revision: 1.1 $
|
||||
* $Date: 2001/03/07 02:52:05 $
|
||||
* $Revision: 1.2 $
|
||||
*
|
||||
*******************************************************************************
|
||||
*/
|
||||
@ -51,10 +51,12 @@ final class UCharacterUtil
|
||||
*/
|
||||
protected static char toChar(byte bytes[])
|
||||
{
|
||||
if (bytes == null || bytes.length == 0)
|
||||
if (bytes == null || bytes.length == 0) {
|
||||
return 0;
|
||||
if (bytes.length == 1)
|
||||
}
|
||||
if (bytes.length == 1) {
|
||||
return toChar(bytes[0]);
|
||||
}
|
||||
|
||||
char firstbyte = (char)(toChar(bytes[0]) << 8);
|
||||
char secondbyte = toChar(bytes[1]);
|
||||
@ -141,8 +143,9 @@ final class UCharacterUtil
|
||||
while (b != 0)
|
||||
{
|
||||
b = array[index];
|
||||
if (b != 0)
|
||||
if (b != 0) {
|
||||
str.append((char)(b & 0x00FF));
|
||||
}
|
||||
index ++;
|
||||
}
|
||||
return index;
|
||||
@ -170,12 +173,14 @@ final class UCharacterUtil
|
||||
{
|
||||
b = array[aindex];
|
||||
aindex ++;
|
||||
if (b == 0)
|
||||
if (b == 0) {
|
||||
break;
|
||||
}
|
||||
// if we have reached the end of the string and yet the array has not
|
||||
// reached the end of their substring yet, abort
|
||||
if (strindex == length || (str.charAt(strindex) != (char)(b & 0xFF)))
|
||||
if (strindex == length || (str.charAt(strindex) != (char)(b & 0xFF))) {
|
||||
return -1;
|
||||
}
|
||||
strindex ++;
|
||||
}
|
||||
return strindex;
|
||||
@ -255,8 +260,9 @@ final class UCharacterUtil
|
||||
{
|
||||
b = array[index + result];
|
||||
result ++;
|
||||
if (b == skipend)
|
||||
if (b == skipend) {
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
return result;
|
||||
|
||||
@ -5,14 +5,15 @@
|
||||
*******************************************************************************
|
||||
*
|
||||
* $Source: /xsrl/Nsvn/icu/icu4j/src/com/ibm/text/Attic/UGenNameReader.java,v $
|
||||
* $Date: 2001/02/28 20:59:44 $
|
||||
* $Revision: 1.1 $
|
||||
* $Date: 2001/03/07 02:52:05 $
|
||||
* $Revision: 1.2 $
|
||||
*
|
||||
*******************************************************************************
|
||||
*/
|
||||
package com.ibm.text;
|
||||
|
||||
import java.io.DataInputStream;
|
||||
import java.io.IOException;
|
||||
|
||||
/**
|
||||
* Internal reader class reading binary data from unames.dat created by ICU
|
||||
@ -63,6 +64,12 @@ final class UGenNameReader extends UGenReader
|
||||
{(byte)0x1, (byte)0x0, (byte)0x0, (byte)0x0};
|
||||
private static final byte DATA_FORMAT_ID_[] = {(byte)0x75, (byte)0x6E,
|
||||
(byte)0x61, (byte)0x6D};
|
||||
|
||||
/**
|
||||
* Corrupted error string
|
||||
*/
|
||||
private static final String CORRUPTED_DATA_ERROR_ =
|
||||
"Data corrupted in character name data file";
|
||||
|
||||
// constructor ==================================================
|
||||
|
||||
@ -81,20 +88,16 @@ final class UGenNameReader extends UGenReader
|
||||
* If unsuccessful false will be returned.
|
||||
* @param input data input stream
|
||||
* @param data instance of datablock
|
||||
* @return true if successfully filled UCharacterNameDB
|
||||
* @exception thrown if there is a failure reading file
|
||||
* @exception thrown when there's a data error.
|
||||
*/
|
||||
protected boolean read(DataInputStream input, UCharacterNameDB data)
|
||||
throws Exception
|
||||
protected void read(DataInputStream input, UCharacterNameDB data)
|
||||
throws IOException
|
||||
{
|
||||
if (super.read(input, data))
|
||||
{
|
||||
// read the indexes
|
||||
if (readIndex(input) && readToken(input, data) && readGroup(input, data)
|
||||
&& readAlg(input, data))
|
||||
return true;
|
||||
if (!(super.read(input, data) && readIndex(input) &&
|
||||
readToken(input, data) && readGroup(input, data) &&
|
||||
readAlg(input, data))) {
|
||||
throw new IOException(CORRUPTED_DATA_ERROR_);
|
||||
}
|
||||
return false;
|
||||
}
|
||||
|
||||
/**
|
||||
@ -107,13 +110,17 @@ final class UGenNameReader extends UGenReader
|
||||
byte dataformatversion[])
|
||||
{
|
||||
int size = DATA_FORMAT_ID_.length;
|
||||
for (int i = 0; i < size; i ++)
|
||||
if (DATA_FORMAT_ID_[i] != dataformatid[i])
|
||||
for (int i = 0; i < size; i ++) {
|
||||
if (DATA_FORMAT_ID_[i] != dataformatid[i]) {
|
||||
return false;
|
||||
}
|
||||
}
|
||||
size = DATA_FORMAT_VERSION_.length;
|
||||
for (int i = 0; i < size; i ++)
|
||||
if (DATA_FORMAT_VERSION_[i] != dataformatversion[i])
|
||||
for (int i = 0; i < size; i ++) {
|
||||
if (DATA_FORMAT_VERSION_[i] != dataformatversion[i]) {
|
||||
return false;
|
||||
}
|
||||
}
|
||||
return true;
|
||||
}
|
||||
|
||||
@ -143,7 +150,7 @@ final class UGenNameReader extends UGenReader
|
||||
* @return true if successfully read
|
||||
* @exception thrown when data reading fails
|
||||
*/
|
||||
private boolean readIndex(DataInputStream input) throws Exception
|
||||
private boolean readIndex(DataInputStream input) throws IOException
|
||||
{
|
||||
m_tokenstringindex_ = input.readInt();
|
||||
m_groupindex_ = input.readInt();
|
||||
@ -160,12 +167,13 @@ final class UGenNameReader extends UGenReader
|
||||
* @exception thrown when data reading fails
|
||||
*/
|
||||
private boolean readToken(DataInputStream input, UCharacterNameDB data)
|
||||
throws Exception
|
||||
throws IOException
|
||||
{
|
||||
char count = input.readChar();
|
||||
char token[] = new char[count];
|
||||
for (char i = 0; i < count; i ++)
|
||||
for (char i = 0; i < count; i ++) {
|
||||
token[i] = input.readChar();
|
||||
}
|
||||
|
||||
int size = m_groupindex_ - m_tokenstringindex_;
|
||||
byte tokenstr[] = new byte[size];
|
||||
@ -181,15 +189,16 @@ final class UGenNameReader extends UGenReader
|
||||
* @exception thrown when data reading fails
|
||||
*/
|
||||
private boolean readGroup(DataInputStream input, UCharacterNameDB data)
|
||||
throws Exception
|
||||
throws IOException
|
||||
{
|
||||
// reading the group information records
|
||||
int count = input.readChar();
|
||||
data.setGroupCountSize(count, GROUP_INFO_SIZE_);
|
||||
count *= GROUP_INFO_SIZE_;
|
||||
char group[] = new char[count];
|
||||
for (int i = 0; i < count; i ++)
|
||||
for (int i = 0; i < count; i ++) {
|
||||
group[i] = input.readChar();
|
||||
}
|
||||
|
||||
int size = m_algnamesindex_ - m_groupstringindex_;
|
||||
byte groupstring[] = new byte[size];
|
||||
@ -205,7 +214,7 @@ final class UGenNameReader extends UGenReader
|
||||
* @exception thrown when data reading fails
|
||||
*/
|
||||
private boolean readAlg(DataInputStream input, UCharacterNameDB data)
|
||||
throws Exception
|
||||
throws IOException
|
||||
{
|
||||
int count = input.readInt();
|
||||
UCharacterNameDB.AlgorithmName alg[] =
|
||||
@ -214,8 +223,9 @@ final class UGenNameReader extends UGenReader
|
||||
for (int i = 0; i < count; i ++)
|
||||
{
|
||||
UCharacterNameDB.AlgorithmName an = readAlg(input);
|
||||
if (an == null)
|
||||
if (an == null) {
|
||||
return false;
|
||||
}
|
||||
alg[i] = an;
|
||||
}
|
||||
data.setAlgorithm(alg);
|
||||
@ -229,7 +239,7 @@ final class UGenNameReader extends UGenReader
|
||||
* @exception thrown when file read error occurs or data is corrupted
|
||||
*/
|
||||
private UCharacterNameDB.AlgorithmName readAlg(DataInputStream input)
|
||||
throws Exception
|
||||
throws IOException
|
||||
{
|
||||
UCharacterNameDB.AlgorithmName result =
|
||||
new UCharacterNameDB.AlgorithmName();
|
||||
@ -237,15 +247,17 @@ final class UGenNameReader extends UGenReader
|
||||
int rangeend = input.readInt();
|
||||
byte type = input.readByte();
|
||||
byte variant = input.readByte();
|
||||
if (!result.setInfo(rangestart, rangeend, type, variant))
|
||||
if (!result.setInfo(rangestart, rangeend, type, variant)) {
|
||||
return null;
|
||||
}
|
||||
|
||||
int size = input.readChar();
|
||||
if (type == UCharacterNameDB.AlgorithmName.TYPE_1_)
|
||||
{
|
||||
char factor[] = new char[variant];
|
||||
for (int j = 0; j < variant; j ++)
|
||||
for (int j = 0; j < variant; j ++) {
|
||||
factor[j] = input.readChar();
|
||||
}
|
||||
|
||||
result.setFactor(factor);
|
||||
size -= (variant << 1);
|
||||
|
||||
@ -5,8 +5,8 @@
|
||||
*******************************************************************************
|
||||
*
|
||||
* $Source: /xsrl/Nsvn/icu/icu4j/src/com/ibm/text/Attic/UGenPropReader.java,v $
|
||||
* $Date: 2001/02/28 20:59:44 $
|
||||
* $Revision: 1.1 $
|
||||
* $Date: 2001/03/07 02:52:05 $
|
||||
* $Revision: 1.2 $
|
||||
*
|
||||
*******************************************************************************
|
||||
*/
|
||||
@ -14,6 +14,7 @@ package com.ibm.text;
|
||||
|
||||
import java.io.DataInputStream;
|
||||
import java.util.Arrays;
|
||||
import java.io.IOException;
|
||||
|
||||
/**
|
||||
* Internal reader class reading binary data from uprops.dat created by ICU
|
||||
@ -66,6 +67,12 @@ final class UGenPropReader extends UGenReader
|
||||
(byte)0x72, (byte)0x6F};
|
||||
private static final byte DATA_FORMAT_VERSION_[] =
|
||||
{(byte)0x1, (byte)0x2, (byte)0x0, (byte)0x0};
|
||||
|
||||
/**
|
||||
* Corrupted error string
|
||||
*/
|
||||
private static final String CORRUPTED_DATA_ERROR_ =
|
||||
"Data corrupted in character property data file";
|
||||
|
||||
// constructor =============================================
|
||||
|
||||
@ -83,13 +90,12 @@ final class UGenPropReader extends UGenReader
|
||||
* If unsuccessful false will be returned
|
||||
* @param input data stream
|
||||
* @param data data instance
|
||||
* @return true if successfully filled
|
||||
* @exception thrown when data reading fails
|
||||
*/
|
||||
protected boolean read(DataInputStream input, UCharacterPropertyDB data)
|
||||
throws Exception
|
||||
protected void read(DataInputStream input, UCharacterPropertyDB data)
|
||||
throws IOException
|
||||
{
|
||||
if (super.read(input, data) &&
|
||||
if (!(super.read(input, data) &&
|
||||
// read the indexes
|
||||
readIndex(input, data) &&
|
||||
// read the stages block
|
||||
@ -99,9 +105,9 @@ final class UGenPropReader extends UGenReader
|
||||
// read the exception data
|
||||
readException(input, data) &&
|
||||
// read the case data
|
||||
readCase(input,data))
|
||||
return true;
|
||||
return false;
|
||||
readCase(input,data))) {
|
||||
throw new IOException(CORRUPTED_DATA_ERROR_);
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
@ -143,10 +149,10 @@ final class UGenPropReader extends UGenReader
|
||||
* @param input data stream
|
||||
* @param data instance of UCharacterPropertyDB
|
||||
* @return true if successfully read
|
||||
* @exception thrown when data reading fails
|
||||
* @exception thrown when there's an IOException
|
||||
*/
|
||||
private boolean readIndex(DataInputStream input, UCharacterPropertyDB data)
|
||||
throws Exception
|
||||
private boolean readIndex(DataInputStream input, UCharacterPropertyDB data)
|
||||
throws IOException
|
||||
{
|
||||
int count = INDEX_SIZE_;
|
||||
m_stage2indexsize_ = input.readChar();
|
||||
@ -180,7 +186,7 @@ final class UGenPropReader extends UGenReader
|
||||
* @exception thrown when data reading fails
|
||||
*/
|
||||
private boolean readStage(DataInputStream input, UCharacterPropertyDB data)
|
||||
throws Exception
|
||||
throws IOException
|
||||
{
|
||||
// size of the 3 stages
|
||||
int stagesize = (m_prop_ << 1) - INDEX_SIZE_;
|
||||
@ -193,23 +199,19 @@ final class UGenPropReader extends UGenReader
|
||||
for (int count = 0; count < stagesize; count ++)
|
||||
{
|
||||
array[count] = (char)(input.readChar() - INDEX_SIZE_);
|
||||
if (max < array[count] && count < 0x448)
|
||||
if (max < array[count] && count < 0x448) {
|
||||
max = array[count];
|
||||
}
|
||||
|
||||
// setting up the property index for stage 3
|
||||
// uprops.dat contain data that includes the address from the top of
|
||||
// index to property data. since the blocks are split up, so now i have
|
||||
// to subtract the excess address from it.
|
||||
if (count >= m_stage3_ - INDEX_SIZE_)
|
||||
if (count >= m_stage3_ - INDEX_SIZE_) {
|
||||
array[count] -= props;
|
||||
}
|
||||
}
|
||||
|
||||
// synwee : hmm... gaps in stage 2.
|
||||
/*
|
||||
System.out.println("stage 3 " + (int)m_stage3_);
|
||||
System.out.println("stage 2 top " + (max - 0x440 - INDEX_SIZE_));
|
||||
*/
|
||||
|
||||
// setting up the stages block in the instance of UCharacterPropertyDB
|
||||
return data.setStage(array);
|
||||
}
|
||||
@ -223,13 +225,14 @@ final class UGenPropReader extends UGenReader
|
||||
* @exception thrown when data reading fails
|
||||
*/
|
||||
private boolean readProperty(DataInputStream input,
|
||||
UCharacterPropertyDB data) throws Exception
|
||||
UCharacterPropertyDB data) throws IOException
|
||||
{
|
||||
// getting size of the property block
|
||||
int size = m_exception_ - m_prop_;
|
||||
int ppty[] = new int[size];
|
||||
for (int i = 0; i < size; i ++)
|
||||
for (int i = 0; i < size; i ++) {
|
||||
ppty[i] = input.readInt();
|
||||
}
|
||||
|
||||
// setting up the property block in the instance of UCharacterPropertyDB
|
||||
return data.setProperty(ppty);
|
||||
@ -244,13 +247,14 @@ final class UGenPropReader extends UGenReader
|
||||
* @exception thrown when data reading fails
|
||||
*/
|
||||
private boolean readCase(DataInputStream input,
|
||||
UCharacterPropertyDB data) throws Exception
|
||||
UCharacterPropertyDB data) throws IOException
|
||||
{
|
||||
// getting size of the case block
|
||||
int size = (m_end_ - m_case_) << 1;
|
||||
char casetable[] = new char[size];
|
||||
for (int i = 0; i < size; i ++)
|
||||
for (int i = 0; i < size; i ++) {
|
||||
casetable[i] = input.readChar();
|
||||
}
|
||||
|
||||
// setting up the case block in the instance of UCharacterPropertyDB
|
||||
return data.setCase(casetable);
|
||||
@ -265,12 +269,13 @@ final class UGenPropReader extends UGenReader
|
||||
* @exception thrown when data reading fails
|
||||
*/
|
||||
private boolean readException(DataInputStream input,
|
||||
UCharacterPropertyDB data) throws Exception
|
||||
UCharacterPropertyDB data) throws IOException
|
||||
{
|
||||
int size = m_case_ - m_exception_;
|
||||
int exception[] = new int[size];
|
||||
for (int i = 0; i < size; i ++)
|
||||
exception[i] = input.readInt();
|
||||
for (int i = 0; i < size; i ++) {
|
||||
exception[i] = input.readInt();
|
||||
}
|
||||
|
||||
// setting up the property block in the instance of UCharacterPropertyDB
|
||||
return data.setException(exception);
|
||||
|
||||
@ -5,8 +5,8 @@
|
||||
*******************************************************************************
|
||||
*
|
||||
* $Source: /xsrl/Nsvn/icu/icu4j/src/com/ibm/text/Attic/UGenReader.java,v $
|
||||
* $Date: 2001/02/28 20:59:44 $
|
||||
* $Revision: 1.1 $
|
||||
* $Date: 2001/03/07 02:52:05 $
|
||||
* $Revision: 1.2 $
|
||||
*
|
||||
*******************************************************************************
|
||||
*/
|
||||
@ -72,45 +72,49 @@ abstract class UGenReader
|
||||
* @param input data stream
|
||||
* @param data data instance
|
||||
* @return true if successfully filled
|
||||
* @exception thrown when error reading data
|
||||
*/
|
||||
protected boolean read(DataInputStream input, UCharacterDB data)
|
||||
throws Exception
|
||||
protected boolean read(DataInputStream input, UCharacterDB data)
|
||||
{
|
||||
char headersize = input.readChar();
|
||||
headersize -= 2;
|
||||
//reading the header format
|
||||
byte magic1 = input.readByte();
|
||||
headersize --;
|
||||
byte magic2 = input.readByte();
|
||||
headersize --;
|
||||
input.skipBytes(SKIP_BYTES_);
|
||||
headersize -= SKIP_BYTES_;
|
||||
if (authenticate(magic1, magic2))
|
||||
try
|
||||
{
|
||||
byte bigendian = input.readByte();
|
||||
char headersize = input.readChar();
|
||||
headersize -= 2;
|
||||
//reading the header format
|
||||
byte magic1 = input.readByte();
|
||||
headersize --;
|
||||
byte charset = input.readByte();
|
||||
byte magic2 = input.readByte();
|
||||
headersize --;
|
||||
byte charsize = input.readByte();
|
||||
headersize --;
|
||||
byte reserved = input.readByte();
|
||||
headersize --;
|
||||
|
||||
byte dataformatid[] = new byte[getFileFormatIDSize()];
|
||||
input.readFully(dataformatid);
|
||||
headersize -= getFileFormatIDSize();
|
||||
byte dataformatversion[] = new byte[getFileFormatVersionSize()];
|
||||
input.readFully(dataformatversion);
|
||||
headersize -= getFileFormatVersionSize();
|
||||
byte unicodeversion[] = new byte[UNICODE_VERSION_.length];
|
||||
input.readFully(unicodeversion);
|
||||
headersize -= UNICODE_VERSION_.length;
|
||||
input.skipBytes(headersize);
|
||||
|
||||
if (authenticate(bigendian, charset, charsize, unicodeversion) &&
|
||||
authenticate(dataformatid, dataformatversion))
|
||||
return setUCharacterDB(data, unicodeversion);
|
||||
input.skipBytes(SKIP_BYTES_);
|
||||
headersize -= SKIP_BYTES_;
|
||||
if (authenticate(magic1, magic2))
|
||||
{
|
||||
byte bigendian = input.readByte();
|
||||
headersize --;
|
||||
byte charset = input.readByte();
|
||||
headersize --;
|
||||
byte charsize = input.readByte();
|
||||
headersize --;
|
||||
byte reserved = input.readByte();
|
||||
headersize --;
|
||||
|
||||
byte dataformatid[] = new byte[getFileFormatIDSize()];
|
||||
input.readFully(dataformatid);
|
||||
headersize -= getFileFormatIDSize();
|
||||
byte dataformatversion[] = new byte[getFileFormatVersionSize()];
|
||||
input.readFully(dataformatversion);
|
||||
headersize -= getFileFormatVersionSize();
|
||||
byte unicodeversion[] = new byte[UNICODE_VERSION_.length];
|
||||
input.readFully(unicodeversion);
|
||||
headersize -= UNICODE_VERSION_.length;
|
||||
input.skipBytes(headersize);
|
||||
|
||||
if (authenticate(bigendian, charset, charsize, unicodeversion) &&
|
||||
authenticate(dataformatid, dataformatversion)) {
|
||||
return setUCharacterDB(data, unicodeversion);
|
||||
}
|
||||
}
|
||||
}
|
||||
catch (Exception e) {
|
||||
}
|
||||
return false;
|
||||
}
|
||||
@ -146,8 +150,9 @@ abstract class UGenReader
|
||||
*/
|
||||
private boolean authenticate(byte m1, byte m2)
|
||||
{
|
||||
if (m1 == MAGIC1 && m2 == MAGIC2)
|
||||
if (m1 == MAGIC1 && m2 == MAGIC2) {
|
||||
return true;
|
||||
}
|
||||
return false;
|
||||
}
|
||||
|
||||
@ -167,8 +172,9 @@ abstract class UGenReader
|
||||
byte unicodeversion[])
|
||||
{
|
||||
if (bigendian != BIG_ENDIAN_ || charset != CHAR_SET_ ||
|
||||
charsize != CHAR_SIZE_)
|
||||
charsize != CHAR_SIZE_) {
|
||||
return false;
|
||||
}
|
||||
return Arrays.equals(UNICODE_VERSION_, unicodeversion);
|
||||
}
|
||||
|
||||
|
||||
@ -5,8 +5,8 @@
|
||||
*******************************************************************************
|
||||
*
|
||||
* $Source: /xsrl/Nsvn/icu/icu4j/src/com/ibm/text/Attic/UTF16.java,v $
|
||||
* $Date: 2001/02/28 20:59:44 $
|
||||
* $Revision: 1.1 $
|
||||
* $Date: 2001/03/07 02:52:05 $
|
||||
* $Revision: 1.2 $
|
||||
*
|
||||
*******************************************************************************
|
||||
*/
|
||||
@ -149,7 +149,7 @@ public final class UTF16
|
||||
* <code>UTF16.getCharCount()</code>, as well as random access. If a validity
|
||||
* check is required, use <code><a href="../UCharacter.html#isLegal(char)">
|
||||
* UCharacter.isLegal()</a></code> on the return value.
|
||||
* If tbe char retrieved is part of a surrogate pair, its supplementary
|
||||
* If the char retrieved is part of a surrogate pair, its supplementary
|
||||
* character will be returned. If a complete supplementary character is not
|
||||
* found the incomplete character will be returned
|
||||
* @param source array of UTF-16 chars
|
||||
@ -161,7 +161,7 @@ public final class UTF16
|
||||
*/
|
||||
public static int charAt(String source, int offset16)
|
||||
{
|
||||
if (offset16 >= source.length())
|
||||
if (offset16 < 0 || offset16 >= source.length())
|
||||
return -1;
|
||||
|
||||
char single = source.charAt(offset16);
|
||||
@ -211,9 +211,9 @@ public final class UTF16
|
||||
* @param offset32 UTF-32 offset to the start of the character.
|
||||
* @return a single UTF32 value, otherwise -1 if there's an error
|
||||
*/
|
||||
public static int charAtCPOffset(String source, int offset32)
|
||||
public static int charAtCodePointOffset(String source, int offset32)
|
||||
{
|
||||
int offset16 = findOffsetFromCP(source, offset32);
|
||||
int offset16 = findOffsetFromCodePoint(source, offset32);
|
||||
return charAt(source, offset16);
|
||||
}
|
||||
|
||||
@ -227,8 +227,9 @@ public final class UTF16
|
||||
*/
|
||||
public static int getCharCount(int char32)
|
||||
{
|
||||
if (char32 < UCharacter.SUPPLEMENTARY_MIN_VALUE)
|
||||
if (char32 < UCharacter.SUPPLEMENTARY_MIN_VALUE) {
|
||||
return 1;
|
||||
}
|
||||
return 2;
|
||||
}
|
||||
|
||||
@ -260,13 +261,15 @@ public final class UTF16
|
||||
if (isLeadSurrogate(ch))
|
||||
{
|
||||
if (++ offset16 < source.length() &&
|
||||
isTrailSurrogate(source.charAt(offset16)))
|
||||
isTrailSurrogate(source.charAt(offset16))) {
|
||||
return LEAD_SURROGATE_BOUNDARY;
|
||||
}
|
||||
}
|
||||
else
|
||||
// isTrailSurrogate(ch), so
|
||||
if (-- offset16 >= 0 && isLeadSurrogate(source.charAt(offset16)))
|
||||
if (-- offset16 >= 0 && isLeadSurrogate(source.charAt(offset16))) {
|
||||
return TRAIL_SURROGATE_BOUNDARY;
|
||||
}
|
||||
|
||||
return SINGLE_CHAR_BOUNDARY;
|
||||
}
|
||||
@ -292,9 +295,9 @@ public final class UTF16
|
||||
* [offset32 - (value >> 2), offset32 + (value & 3)].
|
||||
* @exception StringIndexOutOfBoundsException if offset32 is out of bounds.
|
||||
*/
|
||||
public static int boundsAtCPOffset(String source, int offset32)
|
||||
public static int boundsAtCodePointOffset(String source, int offset32)
|
||||
{
|
||||
int offset16 = findOffsetFromCP(source, offset32);
|
||||
int offset16 = findOffsetFromCodePoint(source, offset32);
|
||||
return bounds(source, offset16);
|
||||
}
|
||||
|
||||
@ -342,9 +345,10 @@ public final class UTF16
|
||||
*/
|
||||
public static int getLeadSurrogate(int char32)
|
||||
{
|
||||
if (char32 >= UCharacter.SUPPLEMENTARY_MIN_VALUE)
|
||||
if (char32 >= UCharacter.SUPPLEMENTARY_MIN_VALUE) {
|
||||
return LEAD_SURROGATE_OFFSET_ +
|
||||
(char32 >> UCharacter.LEAD_SURROGATE_SHIFT_);
|
||||
}
|
||||
|
||||
return 0;
|
||||
}
|
||||
@ -360,9 +364,10 @@ public final class UTF16
|
||||
*/
|
||||
public static int getTrailSurrogate(int char32)
|
||||
{
|
||||
if (char32 >= UCharacter.SUPPLEMENTARY_MIN_VALUE)
|
||||
if (char32 >= UCharacter.SUPPLEMENTARY_MIN_VALUE) {
|
||||
return TRAIL_SURROGATE_MIN_VALUE_ + (char32 &
|
||||
UCharacter.TRAIL_SURROGATE_MASK_);
|
||||
}
|
||||
|
||||
return (char)char32;
|
||||
}
|
||||
@ -379,10 +384,12 @@ public final class UTF16
|
||||
*/
|
||||
public static String valueOf(int char32)
|
||||
{
|
||||
if (char32 < UCharacter.MIN_VALUE || char32 > UCharacter.MAX_VALUE)
|
||||
if (char32 < UCharacter.MIN_VALUE || char32 > UCharacter.MAX_VALUE) {
|
||||
throw new IllegalArgumentException("Illegal codepoint");
|
||||
if (char32 < UCharacter.SUPPLEMENTARY_MIN_VALUE)
|
||||
}
|
||||
if (char32 < UCharacter.SUPPLEMENTARY_MIN_VALUE) {
|
||||
return String.valueOf((char)char32);
|
||||
}
|
||||
char str[] = new char[2];
|
||||
str[0] = (char)(LEAD_SURROGATE_OFFSET_ +
|
||||
(char32 >> UCharacter.LEAD_SURROGATE_SHIFT_));
|
||||
@ -400,7 +407,7 @@ public final class UTF16
|
||||
* @return UTF-16 offset
|
||||
* @exception StringIndexOutOfBoundsException if offset32 is out of bounds.
|
||||
*/
|
||||
public static int findOffsetFromCP(String source, int offset32)
|
||||
public static int findOffsetFromCodePoint(String source, int offset32)
|
||||
{
|
||||
char ch;
|
||||
int size = source.length(),
|
||||
@ -410,14 +417,16 @@ public final class UTF16
|
||||
{
|
||||
ch = source.charAt(result);
|
||||
if (isLeadSurrogate(ch) && ((result + 1) < size) &&
|
||||
isTrailSurrogate(source.charAt(result + 1)))
|
||||
isTrailSurrogate(source.charAt(result + 1))) {
|
||||
result ++;
|
||||
}
|
||||
|
||||
count --;
|
||||
result ++;
|
||||
}
|
||||
if (result >= size)
|
||||
if (result >= size) {
|
||||
throw new StringIndexOutOfBoundsException(offset32);
|
||||
}
|
||||
return result;
|
||||
}
|
||||
|
||||
@ -440,10 +449,11 @@ public final class UTF16
|
||||
* @return UTF-32 offset
|
||||
* @exception StringIndexOutOfBoundsException if offset16 is out of bounds.
|
||||
*/
|
||||
public static int findCPOffset(String source, int offset16)
|
||||
public static int findCodePointOffset(String source, int offset16)
|
||||
{
|
||||
if (offset16 >= source.length())
|
||||
throw new StringIndexOutOfBoundsException(offset16);
|
||||
if (offset16 >= source.length()) {
|
||||
throw new StringIndexOutOfBoundsException(offset16);
|
||||
}
|
||||
|
||||
int result = 0;
|
||||
char ch;
|
||||
@ -452,8 +462,9 @@ public final class UTF16
|
||||
for (int i = 0; i < offset16; ++ i)
|
||||
{
|
||||
ch = source.charAt(i);
|
||||
if (hadLeadSurrogate && isTrailSurrogate(ch))
|
||||
if (hadLeadSurrogate && isTrailSurrogate(ch)) {
|
||||
hadLeadSurrogate = false; // count valid trail as zero
|
||||
}
|
||||
else
|
||||
{
|
||||
hadLeadSurrogate = isLeadSurrogate(ch);
|
||||
@ -462,8 +473,9 @@ public final class UTF16
|
||||
}
|
||||
// end of source being a supplementary character
|
||||
// shift result back to the start of the supplementary character
|
||||
if (hadLeadSurrogate && isTrailSurrogate(source.charAt(offset16)))
|
||||
if (hadLeadSurrogate && isTrailSurrogate(source.charAt(offset16))) {
|
||||
result --;
|
||||
}
|
||||
|
||||
return result;
|
||||
}
|
||||
@ -480,8 +492,9 @@ public final class UTF16
|
||||
public static StringBuffer append(StringBuffer target, int char32)
|
||||
{
|
||||
// Check for irregular values
|
||||
if (char32 < UCharacter.MIN_VALUE || char32 > UCharacter.MAX_VALUE)
|
||||
if (char32 < UCharacter.MIN_VALUE || char32 > UCharacter.MAX_VALUE) {
|
||||
throw new IllegalArgumentException("Illegal codepoint");
|
||||
}
|
||||
|
||||
// Write the UTF-16 values
|
||||
if (char32 >= UCharacter.SUPPLEMENTARY_MIN_VALUE)
|
||||
@ -491,8 +504,9 @@ public final class UTF16
|
||||
target.append((char)(TRAIL_SURROGATE_MIN_VALUE_ +
|
||||
(char32 & UCharacter.TRAIL_SURROGATE_MASK_)));
|
||||
}
|
||||
else
|
||||
else {
|
||||
target.append((char)char32);
|
||||
}
|
||||
return target;
|
||||
}
|
||||
|
||||
@ -508,49 +522,59 @@ public final class UTF16
|
||||
*/
|
||||
public int compare(Object a, Object b)
|
||||
{
|
||||
if (a == b)
|
||||
if (a == b) {
|
||||
return 0;
|
||||
if (a == null)
|
||||
}
|
||||
if (a == null) {
|
||||
return -1;
|
||||
if (b == null)
|
||||
}
|
||||
if (b == null) {
|
||||
return 1;
|
||||
}
|
||||
|
||||
String sa = (String) a;
|
||||
String sb = (String) b;
|
||||
int lena = sa.length();
|
||||
int lenb = sb.length();
|
||||
int len = lena;
|
||||
if (len > lenb)
|
||||
if (len > lenb) {
|
||||
len = lenb;
|
||||
}
|
||||
|
||||
for (int i = 0; i < len; ++i)
|
||||
{
|
||||
char ca = sa.charAt(i);
|
||||
char cb = sb.charAt(i);
|
||||
if (ca == cb)
|
||||
if (ca == cb) {
|
||||
continue; // skip remap if equal
|
||||
}
|
||||
|
||||
// start of only different section
|
||||
// what this part does is to rearrange the characters 0xE000 to 0xFFFF
|
||||
// to the region starting from 0xD800
|
||||
// and shift the surrogate characters to above this region
|
||||
if (ca >= LEAD_SURROGATE_MIN_VALUE_)
|
||||
if (ca >= LEAD_SURROGATE_MIN_VALUE_) {
|
||||
ca += (ca <= TRAIL_SURROGATE_MAX_VALUE_) ? 0x2000 : -0x800;
|
||||
if (cb >= LEAD_SURROGATE_MIN_VALUE_)
|
||||
}
|
||||
if (cb >= LEAD_SURROGATE_MIN_VALUE_) {
|
||||
cb += (cb <= TRAIL_SURROGATE_MAX_VALUE_) ? 0x2000 : -0x800;
|
||||
}
|
||||
// end of only different section
|
||||
|
||||
if (ca < cb)
|
||||
if (ca < cb) {
|
||||
return -1;
|
||||
}
|
||||
|
||||
return 1; // wasn't equal, so return 1
|
||||
}
|
||||
|
||||
if (lena < lenb)
|
||||
if (lena < lenb) {
|
||||
return -1;
|
||||
}
|
||||
|
||||
if (lena > lenb)
|
||||
if (lena > lenb) {
|
||||
return 1;
|
||||
}
|
||||
|
||||
return 0;
|
||||
}
|
||||
@ -561,9 +585,9 @@ public final class UTF16
|
||||
* @param s UTF16 string
|
||||
* @return number of codepoint in string
|
||||
*/
|
||||
public static int countCP(String s)
|
||||
public static int countCodePoint(String s)
|
||||
{
|
||||
return findCPOffset(s, s.length() - 1) + 1;
|
||||
return findCodePointOffset(s, s.length() - 1) + 1;
|
||||
}
|
||||
|
||||
/**
|
||||
@ -572,10 +596,10 @@ public final class UTF16
|
||||
* @param offset32 UTF32 position to insert into
|
||||
* @param char32 code point
|
||||
*/
|
||||
public static void setCharAtCPOffset(StringBuffer str, int offset32,
|
||||
public static void setCharAtCodePointOffset(StringBuffer str, int offset32,
|
||||
int char32)
|
||||
{
|
||||
int offset16 = findOffsetFromCP(str.toString(), offset32);
|
||||
int offset16 = findOffsetFromCodePoint(str.toString(), offset32);
|
||||
setCharAt(str, offset16, char32);
|
||||
}
|
||||
|
||||
@ -587,9 +611,6 @@ public final class UTF16
|
||||
*/
|
||||
public static void setCharAt(StringBuffer source, int offset16, int char32)
|
||||
{
|
||||
if (offset16 >= source.length())
|
||||
throw new StringIndexOutOfBoundsException(offset16);
|
||||
|
||||
int count = 1;
|
||||
|
||||
char single = source.charAt(offset16);
|
||||
@ -598,9 +619,10 @@ public final class UTF16
|
||||
{
|
||||
// pairs of the surrogate with offset16 at the lead char found
|
||||
if (isLeadSurrogate(single) && (source.length() > offset16 + 1) &&
|
||||
isTrailSurrogate(source.charAt(offset16 + 1)))
|
||||
isTrailSurrogate(source.charAt(offset16 + 1))) {
|
||||
count ++;
|
||||
else
|
||||
}
|
||||
else {
|
||||
// pairs of the surrogate with offset16 at the trail char found
|
||||
if (isTrailSurrogate(single) && (offset16 > 0) &&
|
||||
isLeadSurrogate(source.charAt(offset16 -1)))
|
||||
@ -608,6 +630,7 @@ public final class UTF16
|
||||
offset16 --;
|
||||
count ++;
|
||||
}
|
||||
}
|
||||
}
|
||||
source.replace(offset16, offset16 + count, valueOf(char32));
|
||||
}
|
||||
|
||||
Loading…
Reference in New Issue
Block a user