33#if U_SHOW_CPLUSPLUS_API
55#if !UCONFIG_NO_BREAK_ITERATION
74 char16_t *dest, int32_t destCapacity,
75 const char16_t *src, int32_t srcLength,
82class StringCharacterIterator;
83class UnicodeStringAppendable;
97#define US_INV icu::UnicodeString::kInvariant
116#if !U_CHAR16_IS_TYPEDEF
117# define UNICODE_STRING(cs, _length) icu::UnicodeString(true, u ## cs, _length)
119# define UNICODE_STRING(cs, _length) icu::UnicodeString(true, (const char16_t*)u ## cs, _length)
135#define UNICODE_STRING_SIMPLE(cs) UNICODE_STRING(cs, -1)
144#ifndef UNISTR_FROM_CHAR_EXPLICIT
145# if defined(U_COMBINED_IMPLEMENTATION) || defined(U_COMMON_IMPLEMENTATION) || defined(U_I18N_IMPLEMENTATION) || defined(U_IO_IMPLEMENTATION)
147# define UNISTR_FROM_CHAR_EXPLICIT explicit
150# define UNISTR_FROM_CHAR_EXPLICIT
164#ifndef UNISTR_FROM_STRING_EXPLICIT
165# if defined(U_COMBINED_IMPLEMENTATION) || defined(U_COMMON_IMPLEMENTATION) || defined(U_I18N_IMPLEMENTATION) || defined(U_IO_IMPLEMENTATION)
167# define UNISTR_FROM_STRING_EXPLICIT explicit
170# define UNISTR_FROM_STRING_EXPLICIT
207#ifndef UNISTR_OBJECT_SIZE
208# define UNISTR_OBJECT_SIZE 64
403 inline int8_t compare(int32_t start,
424 inline int8_t compare(int32_t start,
428 int32_t srcLength)
const;
443 int32_t srcLength)
const;
459 inline int8_t compare(int32_t start,
461 const char16_t *srcChars)
const;
480 inline int8_t compare(int32_t start,
482 const char16_t *srcChars,
484 int32_t srcLength)
const;
503 inline int8_t compareBetween(int32_t start,
507 int32_t srcLimit)
const;
526 inline int8_t compareCodePointOrder(
const UnicodeString& text)
const;
547 inline int8_t compareCodePointOrder(int32_t start,
572 inline int8_t compareCodePointOrder(int32_t start,
576 int32_t srcLength)
const;
597 int32_t srcLength)
const;
618 inline int8_t compareCodePointOrder(int32_t start,
620 const char16_t *srcChars)
const;
643 inline int8_t compareCodePointOrder(int32_t start,
645 const char16_t *srcChars,
647 int32_t srcLength)
const;
670 inline int8_t compareCodePointOrderBetween(int32_t start,
674 int32_t srcLimit)
const;
694 inline int8_t caseCompare(
const UnicodeString& text, uint32_t options)
const;
716 inline int8_t caseCompare(int32_t start,
719 uint32_t options)
const;
743 inline int8_t caseCompare(int32_t start,
748 uint32_t options)
const;
771 uint32_t options)
const;
793 inline int8_t caseCompare(int32_t start,
795 const char16_t *srcChars,
796 uint32_t options)
const;
820 inline int8_t caseCompare(int32_t start,
822 const char16_t *srcChars,
825 uint32_t options)
const;
849 inline int8_t caseCompareBetween(int32_t start,
854 uint32_t options)
const;
877 int32_t srcLength)
const;
888 int32_t srcLength)
const;
899 inline UBool startsWith(
const char16_t *srcChars,
901 int32_t srcLength)
const;
924 int32_t srcLength)
const;
935 int32_t srcLength)
const;
947 inline UBool endsWith(
const char16_t *srcChars,
949 int32_t srcLength)
const;
974 int32_t start)
const;
989 int32_t length)
const;
1011 int32_t length)
const;
1024 inline int32_t indexOf(
const char16_t *srcChars,
1026 int32_t start)
const;
1043 int32_t length)
const;
1065 int32_t length)
const;
1074 inline int32_t indexOf(
char16_t c)
const;
1084 inline int32_t indexOf(
UChar32 c)
const;
1094 inline int32_t indexOf(
char16_t c,
1095 int32_t start)
const;
1106 inline int32_t indexOf(
UChar32 c,
1107 int32_t start)
const;
1119 inline int32_t indexOf(
char16_t c,
1121 int32_t length)
const;
1134 inline int32_t indexOf(
UChar32 c,
1136 int32_t length)
const;
1146 inline int32_t lastIndexOf(
const UnicodeString& text)
const;
1158 int32_t start)
const;
1173 int32_t length)
const;
1195 int32_t length)
const;
1207 inline int32_t lastIndexOf(
const char16_t *srcChars,
1209 int32_t start)
const;
1226 int32_t length)
const;
1248 int32_t length)
const;
1257 inline int32_t lastIndexOf(
char16_t c)
const;
1267 inline int32_t lastIndexOf(
UChar32 c)
const;
1277 inline int32_t lastIndexOf(
char16_t c,
1278 int32_t start)
const;
1289 inline int32_t lastIndexOf(
UChar32 c,
1290 int32_t start)
const;
1302 inline int32_t lastIndexOf(
char16_t c,
1304 int32_t length)
const;
1317 inline int32_t lastIndexOf(
UChar32 c,
1319 int32_t length)
const;
1332 inline char16_t charAt(int32_t offset)
const;
1341 inline char16_t operator[] (int32_t offset)
const;
1460 inline void extract(int32_t start,
1463 int32_t dstStart = 0)
const;
1499 inline void extract(int32_t start,
1517 int32_t dstStart = 0)
const;
1553 int32_t startLength,
1555 int32_t targetCapacity,
1558#if U_CHARSET_IS_UTF8 || !UCONFIG_NO_CONVERSION
1580 int32_t startLength,
1582 uint32_t targetLength)
const;
1586#if !UCONFIG_NO_CONVERSION
1613 inline int32_t extract(int32_t start,
1614 int32_t startLength,
1616 const char *codepage = 0)
const;
1648 int32_t startLength,
1650 uint32_t targetLength,
1651 const char *codepage)
const;
1728 template<
typename StringClass>
1762 inline int32_t
length(
void)
const;
1811 inline UBool isEmpty(
void)
const;
1822 inline int32_t getCapacity(
void)
const;
1831 inline int32_t hashCode(
void)
const;
1845 inline UBool isBogus(
void)
const;
1924 friend inline void U_EXPORT2
2044 int32_t textLength);
2067 int32_t buffCapacity);
2268 const char16_t *srcChars,
2368 const char16_t *srcChars,
2481 virtual void copy(int32_t start, int32_t limit, int32_t dest)
override;
2598 char16_t padChar = 0x0020);
2612 char16_t padChar = 0x0020);
2620 inline UBool truncate(int32_t targetLength);
2684#if !UCONFIG_NO_BREAK_ITERATION
2893 inline const char16_t *getBuffer()
const;
2986#if !U_CHAR16_IS_TYPEDEF
3001#if U_SIZEOF_WCHAR_T==2 || defined(U_IN_DOXYGEN)
3037 int32_t textLength);
3039#if !U_CHAR16_IS_TYPEDEF
3051#if U_SIZEOF_WCHAR_T==2 || defined(U_IN_DOXYGEN)
3071 inline UnicodeString(
const std::nullptr_t text, int32_t textLength);
3097 int32_t textLength);
3119#if !U_CHAR16_IS_TYPEDEF
3132#if U_SIZEOF_WCHAR_T==2 || defined(U_IN_DOXYGEN)
3154 inline UnicodeString(std::nullptr_t buffer, int32_t buffLength, int32_t buffCapacity);
3156#if U_CHARSET_IS_UTF8 || !UCONFIG_NO_CONVERSION
3191#if !UCONFIG_NO_CONVERSION
3229 UnicodeString(
const char *codepageData, int32_t dataLength,
const char *codepage);
3253 const char *src, int32_t srcLength,
3483 toUTF8(int32_t start, int32_t len,
3484 char *target, int32_t capacity)
const;
3493 doCompare(int32_t start,
3497 int32_t srcLength)
const;
3499 int8_t doCompare(int32_t start,
3501 const char16_t *srcChars,
3503 int32_t srcLength)
const;
3506 doCompareCodePointOrder(int32_t start,
3510 int32_t srcLength)
const;
3512 int8_t doCompareCodePointOrder(int32_t start,
3514 const char16_t *srcChars,
3516 int32_t srcLength)
const;
3519 doCaseCompare(int32_t start,
3524 uint32_t options)
const;
3527 doCaseCompare(int32_t start,
3529 const char16_t *srcChars,
3532 uint32_t options)
const;
3534 int32_t doIndexOf(
char16_t c,
3536 int32_t length)
const;
3540 int32_t length)
const;
3542 int32_t doLastIndexOf(
char16_t c,
3544 int32_t length)
const;
3546 int32_t doLastIndexOf(
UChar32 c,
3548 int32_t length)
const;
3550 void doExtract(int32_t start,
3553 int32_t dstStart)
const;
3555 inline void doExtract(int32_t start,
3559 inline char16_t doCharAt(int32_t offset)
const;
3569 const char16_t *srcChars,
3574 UnicodeString& doAppend(
const char16_t *srcChars, int32_t srcStart, int32_t srcLength);
3580 int32_t doHashCode(
void)
const;
3584 inline char16_t* getArrayStart(
void);
3585 inline const char16_t* getArrayStart(
void)
const;
3587 inline UBool hasShortLength()
const;
3588 inline int32_t getShortLength()
const;
3592 inline UBool isWritable()
const;
3595 inline UBool isBufferWritable()
const;
3598 inline void setZeroLength();
3599 inline void setShortLength(int32_t len);
3600 inline void setLength(int32_t len);
3601 inline void setToEmpty();
3602 inline void setArray(
char16_t *array, int32_t len, int32_t capacity);
3609 UBool allocate(int32_t capacity);
3612 void releaseArray(
void);
3624 inline void pinIndex(int32_t& start)
const;
3625 inline void pinIndices(int32_t& start,
3626 int32_t& length)
const;
3628#if !UCONFIG_NO_CONVERSION
3631 int32_t doExtract(int32_t start, int32_t length,
3632 char *dest, int32_t destCapacity,
3646 void doCodepageCreate(
const char *codepageData,
3648 const char *codepage);
3655 doCodepageCreate(
const char *codepageData,
3673 UBool cloneArrayIfNeeded(int32_t newCapacity = -1,
3674 int32_t growCapacity = -1,
3675 UBool doCopyArray =
true,
3676 int32_t **pBufferToDelete = 0,
3677 UBool forceClone =
false);
3685 caseMap(int32_t caseLocale, uint32_t options,
3693 int32_t removeRef(
void);
3694 int32_t refCount(
void)
const;
3704 kInvalidUChar=0xffff,
3710 kUsingStackBuffer=2,
3712 kBufferIsReadonly=8,
3715 kAllStorageFlags=0x1f,
3718 kLength1=1<<kLengthShift,
3719 kMaxShortLength=0x3ff,
3720 kLengthIsLarge=0xffe0,
3723 kShortString=kUsingStackBuffer,
3724 kLongString=kRefCounted,
3725 kReadonlyAlias=kBufferIsReadonly,
3731 union StackBufferOrFields;
3732 friend union StackBufferOrFields;
3775 union StackBufferOrFields {
3779 int16_t fLengthAndFlags;
3780 char16_t fBuffer[US_STACKBUF_SIZE];
3783 int16_t fLengthAndFlags;
3813UnicodeString::pinIndex(int32_t& start)
const
3818 }
else if(start > length()) {
3824UnicodeString::pinIndices(int32_t& start,
3825 int32_t& _length)
const
3828 int32_t len = length();
3831 }
else if(start > len) {
3836 }
else if(_length > (len - start)) {
3837 _length = (len - start);
3842UnicodeString::getArrayStart() {
3843 return (fUnion.fFields.fLengthAndFlags&kUsingStackBuffer) ?
3844 fUnion.fStackFields.fBuffer : fUnion.fFields.fArray;
3847inline const char16_t*
3848UnicodeString::getArrayStart()
const {
3849 return (fUnion.fFields.fLengthAndFlags&kUsingStackBuffer) ?
3850 fUnion.fStackFields.fBuffer : fUnion.fFields.fArray;
3858UnicodeString::UnicodeString() {
3859 fUnion.fStackFields.fLengthAndFlags=kShortString;
3862inline UnicodeString::UnicodeString(
const std::nullptr_t ) {
3863 fUnion.fStackFields.fLengthAndFlags=kShortString;
3866inline UnicodeString::UnicodeString(
const std::nullptr_t , int32_t ) {
3867 fUnion.fStackFields.fLengthAndFlags=kShortString;
3870inline UnicodeString::UnicodeString(std::nullptr_t , int32_t , int32_t ) {
3871 fUnion.fStackFields.fLengthAndFlags=kShortString;
3878UnicodeString::hasShortLength()
const {
3879 return fUnion.fFields.fLengthAndFlags>=0;
3883UnicodeString::getShortLength()
const {
3886 return fUnion.fFields.fLengthAndFlags>>kLengthShift;
3890UnicodeString::length()
const {
3891 return hasShortLength() ? getShortLength() : fUnion.fFields.fLength;
3895UnicodeString::getCapacity()
const {
3896 return (fUnion.fFields.fLengthAndFlags&kUsingStackBuffer) ?
3897 US_STACKBUF_SIZE : fUnion.fFields.fCapacity;
3901UnicodeString::hashCode()
const
3902{
return doHashCode(); }
3905UnicodeString::isBogus()
const
3906{
return (
UBool)(fUnion.fFields.fLengthAndFlags & kIsBogus); }
3909UnicodeString::isWritable()
const
3910{
return (
UBool)!(fUnion.fFields.fLengthAndFlags&(kOpenGetBuffer|kIsBogus)); }
3913UnicodeString::isBufferWritable()
const
3916 !(fUnion.fFields.fLengthAndFlags&(kOpenGetBuffer|kIsBogus|kBufferIsReadonly)) &&
3917 (!(fUnion.fFields.fLengthAndFlags&kRefCounted) || refCount()==1));
3920inline const char16_t *
3921UnicodeString::getBuffer()
const {
3922 if(fUnion.fFields.fLengthAndFlags&(kIsBogus|kOpenGetBuffer)) {
3924 }
else if(fUnion.fFields.fLengthAndFlags&kUsingStackBuffer) {
3925 return fUnion.fStackFields.fBuffer;
3927 return fUnion.fFields.fArray;
3935UnicodeString::doCompare(int32_t start,
3939 int32_t srcLength)
const
3942 return (int8_t)!isBogus();
3944 srcText.pinIndices(srcStart, srcLength);
3945 return doCompare(start, thisLength, srcText.getArrayStart(), srcStart, srcLength);
3955 int32_t len = length(), textLength = text.
length();
3956 return !text.
isBogus() && len == textLength && doEquals(text, len);
3962{
return (!
operator==(text)); }
3966{
return doCompare(0, length(), text, 0, text.
length()) == 1; }
3970{
return doCompare(0, length(), text, 0, text.
length()) == -1; }
3974{
return doCompare(0, length(), text, 0, text.
length()) != -1; }
3978{
return doCompare(0, length(), text, 0, text.
length()) != 1; }
3982{
return doCompare(0, length(), text, 0, text.
length()); }
3985UnicodeString::compare(int32_t start,
3988{
return doCompare(start, _length, srcText, 0, srcText.
length()); }
3992 int32_t srcLength)
const
3993{
return doCompare(0, length(), srcChars, 0, srcLength); }
3996UnicodeString::compare(int32_t start,
4000 int32_t srcLength)
const
4001{
return doCompare(start, _length, srcText, srcStart, srcLength); }
4004UnicodeString::compare(int32_t start,
4006 const char16_t *srcChars)
const
4007{
return doCompare(start, _length, srcChars, 0, _length); }
4010UnicodeString::compare(int32_t start,
4012 const char16_t *srcChars,
4014 int32_t srcLength)
const
4015{
return doCompare(start, _length, srcChars, srcStart, srcLength); }
4018UnicodeString::compareBetween(int32_t start,
4022 int32_t srcLimit)
const
4023{
return doCompare(start, limit - start,
4024 srcText, srcStart, srcLimit - srcStart); }
4027UnicodeString::doCompareCodePointOrder(int32_t start,
4031 int32_t srcLength)
const
4034 return (int8_t)!isBogus();
4036 srcText.pinIndices(srcStart, srcLength);
4037 return doCompareCodePointOrder(start, thisLength, srcText.getArrayStart(), srcStart, srcLength);
4043{
return doCompareCodePointOrder(0, length(), text, 0, text.
length()); }
4046UnicodeString::compareCodePointOrder(int32_t start,
4049{
return doCompareCodePointOrder(start, _length, srcText, 0, srcText.
length()); }
4053 int32_t srcLength)
const
4054{
return doCompareCodePointOrder(0, length(), srcChars, 0, srcLength); }
4057UnicodeString::compareCodePointOrder(int32_t start,
4061 int32_t srcLength)
const
4062{
return doCompareCodePointOrder(start, _length, srcText, srcStart, srcLength); }
4065UnicodeString::compareCodePointOrder(int32_t start,
4067 const char16_t *srcChars)
const
4068{
return doCompareCodePointOrder(start, _length, srcChars, 0, _length); }
4071UnicodeString::compareCodePointOrder(int32_t start,
4073 const char16_t *srcChars,
4075 int32_t srcLength)
const
4076{
return doCompareCodePointOrder(start, _length, srcChars, srcStart, srcLength); }
4079UnicodeString::compareCodePointOrderBetween(int32_t start,
4083 int32_t srcLimit)
const
4084{
return doCompareCodePointOrder(start, limit - start,
4085 srcText, srcStart, srcLimit - srcStart); }
4088UnicodeString::doCaseCompare(int32_t start,
4093 uint32_t options)
const
4096 return (int8_t)!isBogus();
4098 srcText.pinIndices(srcStart, srcLength);
4099 return doCaseCompare(start, thisLength, srcText.getArrayStart(), srcStart, srcLength, options);
4105 return doCaseCompare(0, length(), text, 0, text.
length(), options);
4109UnicodeString::caseCompare(int32_t start,
4112 uint32_t options)
const {
4113 return doCaseCompare(start, _length, srcText, 0, srcText.
length(), options);
4119 uint32_t options)
const {
4120 return doCaseCompare(0, length(), srcChars, 0, srcLength, options);
4124UnicodeString::caseCompare(int32_t start,
4129 uint32_t options)
const {
4130 return doCaseCompare(start, _length, srcText, srcStart, srcLength, options);
4134UnicodeString::caseCompare(int32_t start,
4136 const char16_t *srcChars,
4137 uint32_t options)
const {
4138 return doCaseCompare(start, _length, srcChars, 0, _length, options);
4142UnicodeString::caseCompare(int32_t start,
4144 const char16_t *srcChars,
4147 uint32_t options)
const {
4148 return doCaseCompare(start, _length, srcChars, srcStart, srcLength, options);
4152UnicodeString::caseCompareBetween(int32_t start,
4157 uint32_t options)
const {
4158 return doCaseCompare(start, limit - start, srcText, srcStart, srcLimit - srcStart, options);
4166 int32_t _length)
const
4169 srcText.pinIndices(srcStart, srcLength);
4171 return indexOf(srcText.getArrayStart(), srcStart, srcLength, start, _length);
4179{
return indexOf(text, 0, text.
length(), 0, length()); }
4183 int32_t start)
const {
4185 return indexOf(text, 0, text.
length(), start, length() - start);
4191 int32_t _length)
const
4192{
return indexOf(text, 0, text.
length(), start, _length); }
4195UnicodeString::indexOf(
const char16_t *srcChars,
4197 int32_t start)
const {
4199 return indexOf(srcChars, 0, srcLength, start, length() - start);
4206 int32_t _length)
const
4207{
return indexOf(srcChars, 0, srcLength, start, _length); }
4210UnicodeString::indexOf(
char16_t c,
4212 int32_t _length)
const
4213{
return doIndexOf(c, start, _length); }
4218 int32_t _length)
const
4219{
return doIndexOf(c, start, _length); }
4222UnicodeString::indexOf(
char16_t c)
const
4223{
return doIndexOf(c, 0, length()); }
4227{
return indexOf(c, 0, length()); }
4230UnicodeString::indexOf(
char16_t c,
4231 int32_t start)
const {
4233 return doIndexOf(c, start, length() - start);
4238 int32_t start)
const {
4240 return indexOf(c, start, length() - start);
4247 int32_t _length)
const
4248{
return lastIndexOf(srcChars, 0, srcLength, start, _length); }
4251UnicodeString::lastIndexOf(
const char16_t *srcChars,
4253 int32_t start)
const {
4255 return lastIndexOf(srcChars, 0, srcLength, start, length() - start);
4263 int32_t _length)
const
4266 srcText.pinIndices(srcStart, srcLength);
4268 return lastIndexOf(srcText.getArrayStart(), srcStart, srcLength, start, _length);
4277 int32_t _length)
const
4278{
return lastIndexOf(text, 0, text.
length(), start, _length); }
4282 int32_t start)
const {
4284 return lastIndexOf(text, 0, text.
length(), start, length() - start);
4289{
return lastIndexOf(text, 0, text.
length(), 0, length()); }
4292UnicodeString::lastIndexOf(
char16_t c,
4294 int32_t _length)
const
4295{
return doLastIndexOf(c, start, _length); }
4300 int32_t _length)
const {
4301 return doLastIndexOf(c, start, _length);
4305UnicodeString::lastIndexOf(
char16_t c)
const
4306{
return doLastIndexOf(c, 0, length()); }
4310 return lastIndexOf(c, 0, length());
4314UnicodeString::lastIndexOf(
char16_t c,
4315 int32_t start)
const {
4317 return doLastIndexOf(c, start, length() - start);
4322 int32_t start)
const {
4324 return lastIndexOf(c, start, length() - start);
4329{
return compare(0, text.
length(), text, 0, text.
length()) == 0; }
4334 int32_t srcLength)
const
4335{
return doCompare(0, srcLength, srcText, srcStart, srcLength) == 0; }
4342 return doCompare(0, srcLength, srcChars, 0, srcLength) == 0;
4346UnicodeString::startsWith(
const char16_t *srcChars, int32_t srcStart, int32_t srcLength)
const {
4350 return doCompare(0, srcLength, srcChars, srcStart, srcLength) == 0;
4355{
return doCompare(length() - text.
length(), text.
length(),
4356 text, 0, text.
length()) == 0; }
4361 int32_t srcLength)
const {
4362 srcText.pinIndices(srcStart, srcLength);
4363 return doCompare(length() - srcLength, srcLength,
4364 srcText, srcStart, srcLength) == 0;
4369 int32_t srcLength)
const {
4373 return doCompare(length() - srcLength, srcLength,
4374 srcChars, 0, srcLength) == 0;
4378UnicodeString::endsWith(
const char16_t *srcChars,
4380 int32_t srcLength)
const {
4384 return doCompare(length() - srcLength, srcLength,
4385 srcChars, srcStart, srcLength) == 0;
4392UnicodeString::replace(int32_t start,
4395{
return doReplace(start, _length, srcText, 0, srcText.
length()); }
4398UnicodeString::replace(int32_t start,
4403{
return doReplace(start, _length, srcText, srcStart, srcLength); }
4406UnicodeString::replace(int32_t start,
4410{
return doReplace(start, _length, srcChars, 0, srcLength); }
4413UnicodeString::replace(int32_t start,
4415 const char16_t *srcChars,
4418{
return doReplace(start, _length, srcChars, srcStart, srcLength); }
4421UnicodeString::replace(int32_t start,
4424{
return doReplace(start, _length, &srcChar, 0, 1); }
4427UnicodeString::replaceBetween(int32_t start,
4430{
return doReplace(start, limit - start, srcText, 0, srcText.
length()); }
4433UnicodeString::replaceBetween(int32_t start,
4438{
return doReplace(start, limit - start, srcText, srcStart, srcLimit - srcStart); }
4443{
return findAndReplace(0, length(), oldText, 0, oldText.
length(),
4444 newText, 0, newText.
length()); }
4447UnicodeString::findAndReplace(int32_t start,
4451{
return findAndReplace(start, _length, oldText, 0, oldText.
length(),
4452 newText, 0, newText.
length()); }
4458UnicodeString::doExtract(int32_t start,
4461{ target.
replace(0, target.
length(), *
this, start, _length); }
4464UnicodeString::extract(int32_t start,
4467 int32_t targetStart)
const
4468{ doExtract(start, _length, target, targetStart); }
4471UnicodeString::extract(int32_t start,
4474{ doExtract(start, _length, target); }
4476#if !UCONFIG_NO_CONVERSION
4479UnicodeString::extract(int32_t start,
4482 const char *codepage)
const
4486 return extract(start, _length, dst, dst!=0 ? 0xffffffff : 0, codepage);
4492UnicodeString::extractBetween(int32_t start,
4495 int32_t dstStart)
const {
4498 doExtract(start, limit - start, dst, dstStart);
4502UnicodeString::tempSubStringBetween(int32_t start, int32_t limit)
const {
4503 return tempSubString(start, limit - start);
4507UnicodeString::doCharAt(int32_t offset)
const
4509 if((uint32_t)offset < (uint32_t)length()) {
4510 return getArrayStart()[offset];
4512 return kInvalidUChar;
4517UnicodeString::charAt(int32_t offset)
const
4518{
return doCharAt(offset); }
4521UnicodeString::operator[] (int32_t offset)
const
4522{
return doCharAt(offset); }
4525UnicodeString::isEmpty()
const {
4527 return (fUnion.fFields.fLengthAndFlags>>kLengthShift) == 0;
4534UnicodeString::setZeroLength() {
4535 fUnion.fFields.fLengthAndFlags &= kAllStorageFlags;
4539UnicodeString::setShortLength(int32_t len) {
4541 fUnion.fFields.fLengthAndFlags =
4542 (int16_t)((fUnion.fFields.fLengthAndFlags & kAllStorageFlags) | (len << kLengthShift));
4546UnicodeString::setLength(int32_t len) {
4547 if(len <= kMaxShortLength) {
4548 setShortLength(len);
4550 fUnion.fFields.fLengthAndFlags |= kLengthIsLarge;
4551 fUnion.fFields.fLength = len;
4556UnicodeString::setToEmpty() {
4557 fUnion.fFields.fLengthAndFlags = kShortString;
4561UnicodeString::setArray(
char16_t *array, int32_t len, int32_t capacity) {
4563 fUnion.fFields.fArray = array;
4564 fUnion.fFields.fCapacity = capacity;
4567inline UnicodeString&
4568UnicodeString::operator= (
char16_t ch)
4569{
return doReplace(0, length(), &ch, 0, 1); }
4573{
return replace(0, length(), ch); }
4581 return doReplace(0, length(), srcText, srcStart, srcLength);
4589 srcText.pinIndex(srcStart);
4590 return doReplace(0, length(), srcText, srcStart, srcText.
length() - srcStart);
4596 return copyFrom(srcText);
4600UnicodeString::setTo(
const char16_t *srcChars,
4604 return doReplace(0, length(), srcChars, 0, srcLength);
4608UnicodeString::setTo(
char16_t srcChar)
4611 return doReplace(0, length(), &srcChar, 0, 1);
4618 return replace(0, length(), srcChar);
4625{
return doAppend(srcText, srcStart, srcLength); }
4629{
return doAppend(srcText, 0, srcText.
length()); }
4632UnicodeString::append(
const char16_t *srcChars,
4635{
return doAppend(srcChars, srcStart, srcLength); }
4640{
return doAppend(srcChars, 0, srcLength); }
4643UnicodeString::append(
char16_t srcChar)
4644{
return doAppend(&srcChar, 0, 1); }
4647UnicodeString::operator+= (
char16_t ch)
4648{
return doAppend(&ch, 0, 1); }
4657{
return doAppend(srcText, 0, srcText.
length()); }
4660UnicodeString::insert(int32_t start,
4664{
return doReplace(start, 0, srcText, srcStart, srcLength); }
4667UnicodeString::insert(int32_t start,
4669{
return doReplace(start, 0, srcText, 0, srcText.
length()); }
4672UnicodeString::insert(int32_t start,
4673 const char16_t *srcChars,
4676{
return doReplace(start, 0, srcChars, srcStart, srcLength); }
4679UnicodeString::insert(int32_t start,
4682{
return doReplace(start, 0, srcChars, 0, srcLength); }
4685UnicodeString::insert(int32_t start,
4687{
return doReplace(start, 0, &srcChar, 0, 1); }
4690UnicodeString::insert(int32_t start,
4692{
return replace(start, 0, srcChar); }
4696UnicodeString::remove()
4708UnicodeString::remove(int32_t start,
4711 if(start <= 0 && _length ==
INT32_MAX) {
4715 return doReplace(start, _length,
NULL, 0, 0);
4719UnicodeString::removeBetween(int32_t start,
4721{
return doReplace(start, limit - start,
NULL, 0, 0); }
4724UnicodeString::retainBetween(int32_t start, int32_t limit) {
4726 return doReplace(0, start,
NULL, 0, 0);
4730UnicodeString::truncate(int32_t targetLength)
4732 if(isBogus() && targetLength == 0) {
4736 }
else if((uint32_t)targetLength < (uint32_t)length()) {
4737 setLength(targetLength);
4745UnicodeString::reverse()
4746{
return doReverse(0, length()); }
4749UnicodeString::reverse(int32_t start,
4751{
return doReverse(start, _length); }
C++ API: Interface for writing bytes, and implementation classes.
C++ API: char16_t pointer wrappers with implicit conversion from bit-compatible raw pointer types.
The BreakIterator class implements methods for finding the location of boundaries in text.
A ByteSink can be filled with bytes.
char16_t * wrapper with implicit conversion from distinct but bit-compatible pointer types.
const char16_t * wrapper with implicit conversion from distinct but bit-compatible pointer types.
Records lengths of string edits but not replacement text.
A Locale object represents a specific geographical, political, or cultural region.
Replaceable is an abstract base class representing a string of characters that supports the replaceme...
virtual void extractBetween(int32_t start, int32_t limit, UnicodeString &target) const =0
Copies characters in the range [start, limit) into the UnicodeString target.
char16_t charAt(int32_t offset) const
Returns the 16-bit code unit at the given offset into the text.
int32_t length() const
Returns the number of 16-bit code units in the text.
Implementation of ByteSink that writes to a "string".
A string-like object that points to a sized piece of memory.
An Appendable implementation which writes to a UnicodeString.
UnicodeString is a string class that stores Unicode characters directly and provides similar function...
int32_t indexOf(const char16_t *srcChars, int32_t srcStart, int32_t srcLength, int32_t start, int32_t length) const
Locate in this the first occurrence in the range [start, start + length) of the characters in srcChar...
UnicodeString(const UnicodeString &that)
Copy constructor.
virtual char16_t getCharAt(int32_t offset) const override
The change in Replaceable to use virtual getCharAt() allows UnicodeString::charAt() to be inline agai...
virtual int32_t getLength() const override
Implement Replaceable::getLength() (see jitterbug 1027).
UnicodeString & setTo(char16_t *buffer, int32_t buffLength, int32_t buffCapacity)
Aliasing setTo() function, analogous to the writable-aliasing char16_t* constructor.
UChar32 unescapeAt(int32_t &offset) const
Unescape a single escape sequence and return the represented character.
UnicodeString(const wchar_t *text, int32_t textLength)
wchar_t * constructor.
virtual void handleReplaceBetween(int32_t start, int32_t limit, const UnicodeString &text) override
Replace a substring of this object with the given text.
UBool hasMoreChar32Than(int32_t start, int32_t length, int32_t number) const
Check if the length char16_t code units of the string contain more Unicode code points than a certain...
UnicodeString(const UnicodeString &src, int32_t srcStart, int32_t srcLength)
'Substring' constructor from subrange of source string.
virtual ~UnicodeString()
Destructor.
UnicodeString(const char *codepageData, int32_t dataLength, const char *codepage)
char* constructor.
UnicodeString(const char *codepageData, const char *codepage)
char* constructor.
UnicodeString(UBool isTerminated, ConstChar16Ptr text, int32_t textLength)
Readonly-aliasing char16_t* constructor.
UnicodeString & toTitle(BreakIterator *titleIter, const Locale &locale, uint32_t options)
Titlecase this string, with options.
UnicodeString & append(UChar32 srcChar)
Append the code point srcChar to the UnicodeString object.
EInvariant
Constant to be used in the UnicodeString(char *, int32_t, EInvariant) constructor which constructs a ...
UnicodeString unescape() const
Unescape a string of characters and return a string containing the result.
UnicodeString(const UnicodeString &src, int32_t srcStart)
'Substring' constructor from tail of source string.
int32_t getChar32Limit(int32_t offset) const
Adjust a random-access offset so that it points behind a Unicode character.
UnicodeString(char16_t *buffer, int32_t buffLength, int32_t buffCapacity)
Writable-aliasing char16_t* constructor.
UnicodeString & findAndReplace(int32_t start, int32_t length, const UnicodeString &oldText, int32_t oldStart, int32_t oldLength, const UnicodeString &newText, int32_t newStart, int32_t newLength)
Replace all occurrences of characters in oldText in the range [oldStart, oldStart + oldLength) with t...
UnicodeString(int32_t capacity, UChar32 c, int32_t count)
Construct a UnicodeString with capacity to hold capacity char16_ts.
UNISTR_FROM_STRING_EXPLICIT UnicodeString(const uint16_t *text)
uint16_t * constructor.
int32_t extract(int32_t start, int32_t startLength, char *target, uint32_t targetLength, const char *codepage) const
Copy the characters in the range [start, start + length) into an array of characters in a specified c...
virtual void copy(int32_t start, int32_t limit, int32_t dest) override
Copy a substring of this object, retaining attribute (out-of-band) information.
virtual void extractBetween(int32_t start, int32_t limit, UnicodeString &target) const override
Copy the characters in the range [start, limit) into the UnicodeString target.
UnicodeString & replace(int32_t start, int32_t length, const UnicodeString &srcText, int32_t srcStart, int32_t srcLength)
Replace the characters in the range [start, start + length) with the characters in srcText in the ran...
UnicodeString & toTitle(BreakIterator *titleIter)
Titlecase this string, convenience function using the default locale.
UnicodeString & fastCopyFrom(const UnicodeString &src)
Almost the same as the assignment operator.
virtual UnicodeString * clone() const override
Clone this object, an instance of a subclass of Replaceable.
UBool padLeading(int32_t targetLength, char16_t padChar=0x0020)
Pad the start of this UnicodeString with the character padChar.
int32_t getChar32Start(int32_t offset) const
Adjust a random-access offset so that it points to the beginning of a Unicode character.
UChar32 char32At(int32_t offset) const
Return the code point that contains the code unit at offset offset.
UnicodeString(const char *src, int32_t textLength, enum EInvariant inv)
Constructs a Unicode string from an invariant-character char * string.
UnicodeString & trim(void)
Trims leading and trailing whitespace from this UnicodeString.
int32_t length(void) const
Return the length of the UnicodeString object.
UnicodeString tempSubString(int32_t start=0, int32_t length=INT32_MAX) const
Create a temporary substring for the specified range.
int32_t extract(Char16Ptr dest, int32_t destCapacity, UErrorCode &errorCode) const
Copy the contents of the string into dest.
virtual UChar32 getChar32At(int32_t offset) const override
The change in Replaceable to use virtual getChar32At() allows UnicodeString::char32At() to be inline ...
int32_t extract(int32_t start, int32_t startLength, char *target, uint32_t targetLength) const
Copy the characters in the range [start, start + length) into an array of characters in the platform'...
static UnicodeString fromUTF8(StringPiece utf8)
Create a UnicodeString from a UTF-8 string.
UNISTR_FROM_CHAR_EXPLICIT UnicodeString(char16_t ch)
Single char16_t (code unit) constructor.
int32_t lastIndexOf(const char16_t *srcChars, int32_t srcStart, int32_t srcLength, int32_t start, int32_t length) const
Locate in this the last occurrence in the range [start, start + length) of the characters in srcChars...
UnicodeString(wchar_t *buffer, int32_t buffLength, int32_t buffCapacity)
Writable-aliasing wchar_t * constructor.
void setToBogus()
Make this UnicodeString object invalid.
int32_t moveIndex32(int32_t index, int32_t delta) const
Move the code unit index along the string by delta code points.
static UnicodeString fromUTF32(const UChar32 *utf32, int32_t length)
Create a UnicodeString from a UTF-32 string.
UnicodeString & replace(int32_t start, int32_t length, UChar32 srcChar)
Replace the characters in the range [start, start + length) with the code point srcChar.
int32_t countChar32(int32_t start=0, int32_t length=INT32_MAX) const
Count Unicode code points in the length char16_t code units of the string.
UnicodeString & toUpper(void)
Convert the characters in this to UPPER CASE following the conventions of the default locale.
UNISTR_FROM_CHAR_EXPLICIT UnicodeString(UChar32 ch)
Single UChar32 (code point) constructor.
UnicodeString & operator=(const UnicodeString &srcText)
Assignment operator.
UnicodeString & setTo(UBool isTerminated, ConstChar16Ptr text, int32_t textLength)
Aliasing setTo() function, analogous to the readonly-aliasing char16_t* constructor.
int32_t extract(char *dest, int32_t destCapacity, UConverter *cnv, UErrorCode &errorCode) const
Convert the UnicodeString into a codepage string using an existing UConverter.
StringClass & toUTF8String(StringClass &result) const
Convert the UnicodeString to UTF-8 and append the result to a standard string.
UnicodeString(const char16_t *text, int32_t textLength)
char16_t* constructor.
UnicodeString(const char *src, int32_t srcLength, UConverter *cnv, UErrorCode &errorCode)
char * / UConverter constructor.
UnicodeString(const char *codepageData, int32_t dataLength)
char* constructor.
static UClassID getStaticClassID()
ICU "poor man's RTTI", returns a UClassID for this class.
UnicodeString(uint16_t *buffer, int32_t buffLength, int32_t buffCapacity)
Writable-aliasing uint16_t * constructor.
int32_t toUTF32(UChar32 *utf32, int32_t capacity, UErrorCode &errorCode) const
Convert the UnicodeString to UTF-32.
UnicodeString & toLower(const Locale &locale)
Convert the characters in this to lower case following the conventions of a specific locale.
UnicodeString & toTitle(BreakIterator *titleIter, const Locale &locale)
Titlecase this string.
UnicodeString & foldCase(uint32_t options=0)
Case-folds the characters in this string.
const char16_t * getTerminatedBuffer()
Get a read-only pointer to the internal buffer, making sure that it is NUL-terminated.
UnicodeString(const uint16_t *text, int32_t textLength)
uint16_t * constructor.
UNISTR_FROM_STRING_EXPLICIT UnicodeString(const char16_t *text)
char16_t* constructor.
UnicodeString & toUpper(const Locale &locale)
Convert the characters in this to UPPER CASE following the conventions of a specific locale.
UnicodeString & setCharAt(int32_t offset, char16_t ch)
Set the character at the specified offset to the specified character.
virtual UClassID getDynamicClassID() const override
ICU "poor man's RTTI", returns a UClassID for the actual class.
int32_t extract(int32_t start, int32_t startLength, char *target, int32_t targetCapacity, enum EInvariant inv) const
Copy the characters in the range [start, start + startLength) into an array of characters.
UNISTR_FROM_STRING_EXPLICIT UnicodeString(const wchar_t *text)
wchar_t * constructor.
UBool isBogus(void) const
Determine if this object contains a valid string.
char16_t * getBuffer(int32_t minCapacity)
Get a read/write pointer to the internal buffer.
friend void swap(UnicodeString &s1, UnicodeString &s2) U_NOEXCEPT
Non-member UnicodeString swap function.
UBool padTrailing(int32_t targetLength, char16_t padChar=0x0020)
Pad the end of this UnicodeString with the character padChar.
UNISTR_FROM_STRING_EXPLICIT UnicodeString(const char *codepageData)
char* constructor.
UnicodeString(UnicodeString &&src) U_NOEXCEPT
Move constructor; might leave src in bogus state.
void releaseBuffer(int32_t newLength=-1)
Release a read/write buffer on a UnicodeString object with an "open" getBuffer(minCapacity).
void swap(UnicodeString &other) U_NOEXCEPT
Swap strings.
void toUTF8(ByteSink &sink) const
Convert the UnicodeString to UTF-8 and write the result to a ByteSink.
UnicodeString & operator=(UnicodeString &&src) U_NOEXCEPT
Move assignment operator; might leave src in bogus state.
virtual UBool hasMetaData() const override
Replaceable API.
UnicodeString & toLower(void)
Convert the characters in this to lower case following the conventions of the default locale.
U_CAPI int32_t u_strlen(const UChar *s)
U_EXPORT UBool operator==(const StringPiece &x, const StringPiece &y)
Global operator == for StringPiece.
bool operator!=(const StringPiece &x, const StringPiece &y)
Global operator != for StringPiece.
U_COMMON_API UnicodeString operator+(const UnicodeString &s1, const UnicodeString &s2)
Create a new UnicodeString with the concatenation of two others.
const UChar * toUCharPtr(const char16_t *p)
Converts from const char16_t * to const UChar *.
C++ API: Replaceable String.
C++ API: Central ICU header for including the C++ standard <string> header and for related definition...
C++ API: StringPiece: Read-only byte string wrapper class.
struct UConverter UConverter
#define UCONFIG_NO_BREAK_ITERATION
This switch turns off break iteration.
int32_t UChar32
Define UChar32 as a type for single Unicode code points.
#define INT32_MAX
The largest value a 32 bit signed integer can hold.
int8_t UBool
The ICU boolean type, a signed-byte integer.
#define U_CAPI
This is used to declare a function as a public ICU C API.
char16_t UChar
The base type for UTF-16 code units and pointers.
#define U_SIZEOF_UCHAR
Number of bytes in a UChar.
#define UNISTR_FROM_CHAR_EXPLICIT
This can be defined to be empty or "explicit".
int32_t UStringCaseMapper(int32_t caseLocale, uint32_t options, icu::BreakIterator *iter, char16_t *dest, int32_t destCapacity, const char16_t *src, int32_t srcLength, icu::Edits *edits, UErrorCode &errorCode)
Internal string case mapping function type.
#define UNISTR_FROM_STRING_EXPLICIT
This can be defined to be empty or "explicit".
#define UNISTR_OBJECT_SIZE
Desired sizeof(UnicodeString) in bytes.
void * UClassID
UClassID is used to identify classes without using the compiler's RTTI.
Basic definitions for ICU, for both C and C++ APIs.
#define NULL
Define NULL if necessary, to nullptr for C++ and to ((void *)0) for C.
UErrorCode
Standard ICU4C error code type, a substitute for exceptions.
#define U_COMMON_API
Set to export library symbols from inside the common library, and to import them from outside.