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 doEqualsSubstring(int32_t start,
3497 int32_t srcLength)
const;
3499 UBool doEqualsSubstring(int32_t start,
3501 const char16_t *srcChars,
3503 int32_t srcLength)
const;
3506 doCompare(int32_t start,
3510 int32_t srcLength)
const;
3512 int8_t doCompare(int32_t start,
3514 const char16_t *srcChars,
3516 int32_t srcLength)
const;
3519 doCompareCodePointOrder(int32_t start,
3523 int32_t srcLength)
const;
3525 int8_t doCompareCodePointOrder(int32_t start,
3527 const char16_t *srcChars,
3529 int32_t srcLength)
const;
3532 doCaseCompare(int32_t start,
3537 uint32_t options)
const;
3540 doCaseCompare(int32_t start,
3542 const char16_t *srcChars,
3545 uint32_t options)
const;
3547 int32_t doIndexOf(
char16_t c,
3549 int32_t length)
const;
3553 int32_t length)
const;
3555 int32_t doLastIndexOf(
char16_t c,
3557 int32_t length)
const;
3559 int32_t doLastIndexOf(
UChar32 c,
3561 int32_t length)
const;
3563 void doExtract(int32_t start,
3566 int32_t dstStart)
const;
3568 inline void doExtract(int32_t start,
3572 inline char16_t doCharAt(int32_t offset)
const;
3582 const char16_t *srcChars,
3587 UnicodeString& doAppend(
const char16_t *srcChars, int32_t srcStart, int32_t srcLength);
3593 int32_t doHashCode(
void)
const;
3597 inline char16_t* getArrayStart(
void);
3598 inline const char16_t* getArrayStart(
void)
const;
3600 inline UBool hasShortLength()
const;
3601 inline int32_t getShortLength()
const;
3605 inline UBool isWritable()
const;
3608 inline UBool isBufferWritable()
const;
3611 inline void setZeroLength();
3612 inline void setShortLength(int32_t len);
3613 inline void setLength(int32_t len);
3614 inline void setToEmpty();
3615 inline void setArray(
char16_t *array, int32_t len, int32_t capacity);
3622 UBool allocate(int32_t capacity);
3625 void releaseArray(
void);
3637 inline void pinIndex(int32_t& start)
const;
3638 inline void pinIndices(int32_t& start,
3639 int32_t& length)
const;
3641#if !UCONFIG_NO_CONVERSION
3644 int32_t doExtract(int32_t start, int32_t length,
3645 char *dest, int32_t destCapacity,
3659 void doCodepageCreate(
const char *codepageData,
3661 const char *codepage);
3668 doCodepageCreate(
const char *codepageData,
3686 UBool cloneArrayIfNeeded(int32_t newCapacity = -1,
3687 int32_t growCapacity = -1,
3688 UBool doCopyArray =
true,
3689 int32_t **pBufferToDelete = 0,
3690 UBool forceClone =
false);
3698 caseMap(int32_t caseLocale, uint32_t options,
3706 int32_t removeRef(
void);
3707 int32_t refCount(
void)
const;
3717 kInvalidUChar=0xffff,
3723 kUsingStackBuffer=2,
3725 kBufferIsReadonly=8,
3728 kAllStorageFlags=0x1f,
3731 kLength1=1<<kLengthShift,
3732 kMaxShortLength=0x3ff,
3733 kLengthIsLarge=0xffe0,
3736 kShortString=kUsingStackBuffer,
3737 kLongString=kRefCounted,
3738 kReadonlyAlias=kBufferIsReadonly,
3744 union StackBufferOrFields;
3745 friend union StackBufferOrFields;
3788 union StackBufferOrFields {
3792 int16_t fLengthAndFlags;
3793 char16_t fBuffer[US_STACKBUF_SIZE];
3796 int16_t fLengthAndFlags;
3826UnicodeString::pinIndex(int32_t& start)
const
3831 }
else if(start > length()) {
3837UnicodeString::pinIndices(int32_t& start,
3838 int32_t& _length)
const
3841 int32_t len = length();
3844 }
else if(start > len) {
3849 }
else if(_length > (len - start)) {
3850 _length = (len - start);
3855UnicodeString::getArrayStart() {
3856 return (fUnion.fFields.fLengthAndFlags&kUsingStackBuffer) ?
3857 fUnion.fStackFields.fBuffer : fUnion.fFields.fArray;
3860inline const char16_t*
3861UnicodeString::getArrayStart()
const {
3862 return (fUnion.fFields.fLengthAndFlags&kUsingStackBuffer) ?
3863 fUnion.fStackFields.fBuffer : fUnion.fFields.fArray;
3871UnicodeString::UnicodeString() {
3872 fUnion.fStackFields.fLengthAndFlags=kShortString;
3875inline UnicodeString::UnicodeString(
const std::nullptr_t ) {
3876 fUnion.fStackFields.fLengthAndFlags=kShortString;
3879inline UnicodeString::UnicodeString(
const std::nullptr_t , int32_t ) {
3880 fUnion.fStackFields.fLengthAndFlags=kShortString;
3883inline UnicodeString::UnicodeString(std::nullptr_t , int32_t , int32_t ) {
3884 fUnion.fStackFields.fLengthAndFlags=kShortString;
3891UnicodeString::hasShortLength()
const {
3892 return fUnion.fFields.fLengthAndFlags>=0;
3896UnicodeString::getShortLength()
const {
3899 return fUnion.fFields.fLengthAndFlags>>kLengthShift;
3903UnicodeString::length()
const {
3904 return hasShortLength() ? getShortLength() : fUnion.fFields.fLength;
3908UnicodeString::getCapacity()
const {
3909 return (fUnion.fFields.fLengthAndFlags&kUsingStackBuffer) ?
3910 US_STACKBUF_SIZE : fUnion.fFields.fCapacity;
3914UnicodeString::hashCode()
const
3915{
return doHashCode(); }
3918UnicodeString::isBogus()
const
3919{
return (
UBool)(fUnion.fFields.fLengthAndFlags & kIsBogus); }
3922UnicodeString::isWritable()
const
3923{
return (
UBool)!(fUnion.fFields.fLengthAndFlags&(kOpenGetBuffer|kIsBogus)); }
3926UnicodeString::isBufferWritable()
const
3929 !(fUnion.fFields.fLengthAndFlags&(kOpenGetBuffer|kIsBogus|kBufferIsReadonly)) &&
3930 (!(fUnion.fFields.fLengthAndFlags&kRefCounted) || refCount()==1));
3933inline const char16_t *
3934UnicodeString::getBuffer()
const {
3935 if(fUnion.fFields.fLengthAndFlags&(kIsBogus|kOpenGetBuffer)) {
3937 }
else if(fUnion.fFields.fLengthAndFlags&kUsingStackBuffer) {
3938 return fUnion.fStackFields.fBuffer;
3940 return fUnion.fFields.fArray;
3948UnicodeString::doCompare(int32_t start,
3952 int32_t srcLength)
const
3955 return (int8_t)!isBogus();
3957 srcText.pinIndices(srcStart, srcLength);
3958 return doCompare(start, thisLength, srcText.getArrayStart(), srcStart, srcLength);
3963UnicodeString::doEqualsSubstring(int32_t start,
3965 const UnicodeString& srcText,
3967 int32_t srcLength)
const
3969 if(srcText.isBogus()) {
3972 srcText.pinIndices(srcStart, srcLength);
3973 return !isBogus() && doEqualsSubstring(start, thisLength, srcText.getArrayStart(), srcStart, srcLength);
3983 int32_t len = length(), textLength = text.
length();
3984 return !text.
isBogus() && len == textLength && doEquals(text, len);
3990{
return (!
operator==(text)); }
3994{
return doCompare(0, length(), text, 0, text.
length()) == 1; }
3998{
return doCompare(0, length(), text, 0, text.
length()) == -1; }
4002{
return doCompare(0, length(), text, 0, text.
length()) != -1; }
4006{
return doCompare(0, length(), text, 0, text.
length()) != 1; }
4010{
return doCompare(0, length(), text, 0, text.
length()); }
4013UnicodeString::compare(int32_t start,
4016{
return doCompare(start, _length, srcText, 0, srcText.
length()); }
4020 int32_t srcLength)
const
4021{
return doCompare(0, length(), srcChars, 0, srcLength); }
4024UnicodeString::compare(int32_t start,
4028 int32_t srcLength)
const
4029{
return doCompare(start, _length, srcText, srcStart, srcLength); }
4032UnicodeString::compare(int32_t start,
4034 const char16_t *srcChars)
const
4035{
return doCompare(start, _length, srcChars, 0, _length); }
4038UnicodeString::compare(int32_t start,
4040 const char16_t *srcChars,
4042 int32_t srcLength)
const
4043{
return doCompare(start, _length, srcChars, srcStart, srcLength); }
4046UnicodeString::compareBetween(int32_t start,
4050 int32_t srcLimit)
const
4051{
return doCompare(start, limit - start,
4052 srcText, srcStart, srcLimit - srcStart); }
4055UnicodeString::doCompareCodePointOrder(int32_t start,
4059 int32_t srcLength)
const
4062 return (int8_t)!isBogus();
4064 srcText.pinIndices(srcStart, srcLength);
4065 return doCompareCodePointOrder(start, thisLength, srcText.getArrayStart(), srcStart, srcLength);
4071{
return doCompareCodePointOrder(0, length(), text, 0, text.
length()); }
4074UnicodeString::compareCodePointOrder(int32_t start,
4077{
return doCompareCodePointOrder(start, _length, srcText, 0, srcText.
length()); }
4081 int32_t srcLength)
const
4082{
return doCompareCodePointOrder(0, length(), srcChars, 0, srcLength); }
4085UnicodeString::compareCodePointOrder(int32_t start,
4089 int32_t srcLength)
const
4090{
return doCompareCodePointOrder(start, _length, srcText, srcStart, srcLength); }
4093UnicodeString::compareCodePointOrder(int32_t start,
4095 const char16_t *srcChars)
const
4096{
return doCompareCodePointOrder(start, _length, srcChars, 0, _length); }
4099UnicodeString::compareCodePointOrder(int32_t start,
4101 const char16_t *srcChars,
4103 int32_t srcLength)
const
4104{
return doCompareCodePointOrder(start, _length, srcChars, srcStart, srcLength); }
4107UnicodeString::compareCodePointOrderBetween(int32_t start,
4111 int32_t srcLimit)
const
4112{
return doCompareCodePointOrder(start, limit - start,
4113 srcText, srcStart, srcLimit - srcStart); }
4116UnicodeString::doCaseCompare(int32_t start,
4121 uint32_t options)
const
4124 return (int8_t)!isBogus();
4126 srcText.pinIndices(srcStart, srcLength);
4127 return doCaseCompare(start, thisLength, srcText.getArrayStart(), srcStart, srcLength, options);
4133 return doCaseCompare(0, length(), text, 0, text.
length(), options);
4137UnicodeString::caseCompare(int32_t start,
4140 uint32_t options)
const {
4141 return doCaseCompare(start, _length, srcText, 0, srcText.
length(), options);
4147 uint32_t options)
const {
4148 return doCaseCompare(0, length(), srcChars, 0, srcLength, options);
4152UnicodeString::caseCompare(int32_t start,
4157 uint32_t options)
const {
4158 return doCaseCompare(start, _length, srcText, srcStart, srcLength, options);
4162UnicodeString::caseCompare(int32_t start,
4164 const char16_t *srcChars,
4165 uint32_t options)
const {
4166 return doCaseCompare(start, _length, srcChars, 0, _length, options);
4170UnicodeString::caseCompare(int32_t start,
4172 const char16_t *srcChars,
4175 uint32_t options)
const {
4176 return doCaseCompare(start, _length, srcChars, srcStart, srcLength, options);
4180UnicodeString::caseCompareBetween(int32_t start,
4185 uint32_t options)
const {
4186 return doCaseCompare(start, limit - start, srcText, srcStart, srcLimit - srcStart, options);
4194 int32_t _length)
const
4197 srcText.pinIndices(srcStart, srcLength);
4199 return indexOf(srcText.getArrayStart(), srcStart, srcLength, start, _length);
4207{
return indexOf(text, 0, text.
length(), 0, length()); }
4211 int32_t start)
const {
4213 return indexOf(text, 0, text.
length(), start, length() - start);
4219 int32_t _length)
const
4220{
return indexOf(text, 0, text.
length(), start, _length); }
4223UnicodeString::indexOf(
const char16_t *srcChars,
4225 int32_t start)
const {
4227 return indexOf(srcChars, 0, srcLength, start, length() - start);
4234 int32_t _length)
const
4235{
return indexOf(srcChars, 0, srcLength, start, _length); }
4238UnicodeString::indexOf(
char16_t c,
4240 int32_t _length)
const
4241{
return doIndexOf(c, start, _length); }
4246 int32_t _length)
const
4247{
return doIndexOf(c, start, _length); }
4250UnicodeString::indexOf(
char16_t c)
const
4251{
return doIndexOf(c, 0, length()); }
4255{
return indexOf(c, 0, length()); }
4258UnicodeString::indexOf(
char16_t c,
4259 int32_t start)
const {
4261 return doIndexOf(c, start, length() - start);
4266 int32_t start)
const {
4268 return indexOf(c, start, length() - start);
4275 int32_t _length)
const
4276{
return lastIndexOf(srcChars, 0, srcLength, start, _length); }
4279UnicodeString::lastIndexOf(
const char16_t *srcChars,
4281 int32_t start)
const {
4283 return lastIndexOf(srcChars, 0, srcLength, start, length() - start);
4291 int32_t _length)
const
4294 srcText.pinIndices(srcStart, srcLength);
4296 return lastIndexOf(srcText.getArrayStart(), srcStart, srcLength, start, _length);
4305 int32_t _length)
const
4306{
return lastIndexOf(text, 0, text.
length(), start, _length); }
4310 int32_t start)
const {
4312 return lastIndexOf(text, 0, text.
length(), start, length() - start);
4317{
return lastIndexOf(text, 0, text.
length(), 0, length()); }
4320UnicodeString::lastIndexOf(
char16_t c,
4322 int32_t _length)
const
4323{
return doLastIndexOf(c, start, _length); }
4328 int32_t _length)
const {
4329 return doLastIndexOf(c, start, _length);
4333UnicodeString::lastIndexOf(
char16_t c)
const
4334{
return doLastIndexOf(c, 0, length()); }
4338 return lastIndexOf(c, 0, length());
4342UnicodeString::lastIndexOf(
char16_t c,
4343 int32_t start)
const {
4345 return doLastIndexOf(c, start, length() - start);
4350 int32_t start)
const {
4352 return lastIndexOf(c, start, length() - start);
4357{
return doEqualsSubstring(0, text.
length(), text, 0, text.
length()); }
4362 int32_t srcLength)
const
4363{
return doEqualsSubstring(0, srcLength, srcText, srcStart, srcLength); }
4370 return doEqualsSubstring(0, srcLength, srcChars, 0, srcLength);
4374UnicodeString::startsWith(
const char16_t *srcChars, int32_t srcStart, int32_t srcLength)
const {
4378 return doEqualsSubstring(0, srcLength, srcChars, srcStart, srcLength);
4383{
return doEqualsSubstring(length() - text.
length(), text.
length(),
4384 text, 0, text.
length()); }
4389 int32_t srcLength)
const {
4390 srcText.pinIndices(srcStart, srcLength);
4391 return doEqualsSubstring(length() - srcLength, srcLength,
4392 srcText, srcStart, srcLength);
4397 int32_t srcLength)
const {
4401 return doEqualsSubstring(length() - srcLength, srcLength, srcChars, 0, srcLength);
4405UnicodeString::endsWith(
const char16_t *srcChars,
4407 int32_t srcLength)
const {
4411 return doEqualsSubstring(length() - srcLength, srcLength,
4412 srcChars, srcStart, srcLength);
4419UnicodeString::replace(int32_t start,
4422{
return doReplace(start, _length, srcText, 0, srcText.
length()); }
4425UnicodeString::replace(int32_t start,
4430{
return doReplace(start, _length, srcText, srcStart, srcLength); }
4433UnicodeString::replace(int32_t start,
4437{
return doReplace(start, _length, srcChars, 0, srcLength); }
4440UnicodeString::replace(int32_t start,
4442 const char16_t *srcChars,
4445{
return doReplace(start, _length, srcChars, srcStart, srcLength); }
4448UnicodeString::replace(int32_t start,
4451{
return doReplace(start, _length, &srcChar, 0, 1); }
4454UnicodeString::replaceBetween(int32_t start,
4457{
return doReplace(start, limit - start, srcText, 0, srcText.
length()); }
4460UnicodeString::replaceBetween(int32_t start,
4465{
return doReplace(start, limit - start, srcText, srcStart, srcLimit - srcStart); }
4470{
return findAndReplace(0, length(), oldText, 0, oldText.
length(),
4471 newText, 0, newText.
length()); }
4474UnicodeString::findAndReplace(int32_t start,
4478{
return findAndReplace(start, _length, oldText, 0, oldText.
length(),
4479 newText, 0, newText.
length()); }
4485UnicodeString::doExtract(int32_t start,
4488{ target.
replace(0, target.
length(), *
this, start, _length); }
4491UnicodeString::extract(int32_t start,
4494 int32_t targetStart)
const
4495{ doExtract(start, _length, target, targetStart); }
4498UnicodeString::extract(int32_t start,
4501{ doExtract(start, _length, target); }
4503#if !UCONFIG_NO_CONVERSION
4506UnicodeString::extract(int32_t start,
4509 const char *codepage)
const
4513 return extract(start, _length, dst, dst!=0 ? 0xffffffff : 0, codepage);
4519UnicodeString::extractBetween(int32_t start,
4522 int32_t dstStart)
const {
4525 doExtract(start, limit - start, dst, dstStart);
4529UnicodeString::tempSubStringBetween(int32_t start, int32_t limit)
const {
4530 return tempSubString(start, limit - start);
4534UnicodeString::doCharAt(int32_t offset)
const
4536 if((uint32_t)offset < (uint32_t)length()) {
4537 return getArrayStart()[offset];
4539 return kInvalidUChar;
4544UnicodeString::charAt(int32_t offset)
const
4545{
return doCharAt(offset); }
4548UnicodeString::operator[] (int32_t offset)
const
4549{
return doCharAt(offset); }
4552UnicodeString::isEmpty()
const {
4554 return (fUnion.fFields.fLengthAndFlags>>kLengthShift) == 0;
4561UnicodeString::setZeroLength() {
4562 fUnion.fFields.fLengthAndFlags &= kAllStorageFlags;
4566UnicodeString::setShortLength(int32_t len) {
4568 fUnion.fFields.fLengthAndFlags =
4569 (int16_t)((fUnion.fFields.fLengthAndFlags & kAllStorageFlags) | (len << kLengthShift));
4573UnicodeString::setLength(int32_t len) {
4574 if(len <= kMaxShortLength) {
4575 setShortLength(len);
4577 fUnion.fFields.fLengthAndFlags |= kLengthIsLarge;
4578 fUnion.fFields.fLength = len;
4583UnicodeString::setToEmpty() {
4584 fUnion.fFields.fLengthAndFlags = kShortString;
4588UnicodeString::setArray(
char16_t *array, int32_t len, int32_t capacity) {
4590 fUnion.fFields.fArray = array;
4591 fUnion.fFields.fCapacity = capacity;
4594inline UnicodeString&
4595UnicodeString::operator= (
char16_t ch)
4596{
return doReplace(0, length(), &ch, 0, 1); }
4600{
return replace(0, length(), ch); }
4608 return doReplace(0, length(), srcText, srcStart, srcLength);
4616 srcText.pinIndex(srcStart);
4617 return doReplace(0, length(), srcText, srcStart, srcText.
length() - srcStart);
4623 return copyFrom(srcText);
4627UnicodeString::setTo(
const char16_t *srcChars,
4631 return doReplace(0, length(), srcChars, 0, srcLength);
4635UnicodeString::setTo(
char16_t srcChar)
4638 return doReplace(0, length(), &srcChar, 0, 1);
4645 return replace(0, length(), srcChar);
4652{
return doAppend(srcText, srcStart, srcLength); }
4656{
return doAppend(srcText, 0, srcText.
length()); }
4659UnicodeString::append(
const char16_t *srcChars,
4662{
return doAppend(srcChars, srcStart, srcLength); }
4667{
return doAppend(srcChars, 0, srcLength); }
4670UnicodeString::append(
char16_t srcChar)
4671{
return doAppend(&srcChar, 0, 1); }
4674UnicodeString::operator+= (
char16_t ch)
4675{
return doAppend(&ch, 0, 1); }
4684{
return doAppend(srcText, 0, srcText.
length()); }
4687UnicodeString::insert(int32_t start,
4691{
return doReplace(start, 0, srcText, srcStart, srcLength); }
4694UnicodeString::insert(int32_t start,
4696{
return doReplace(start, 0, srcText, 0, srcText.
length()); }
4699UnicodeString::insert(int32_t start,
4700 const char16_t *srcChars,
4703{
return doReplace(start, 0, srcChars, srcStart, srcLength); }
4706UnicodeString::insert(int32_t start,
4709{
return doReplace(start, 0, srcChars, 0, srcLength); }
4712UnicodeString::insert(int32_t start,
4714{
return doReplace(start, 0, &srcChar, 0, 1); }
4717UnicodeString::insert(int32_t start,
4719{
return replace(start, 0, srcChar); }
4723UnicodeString::remove()
4735UnicodeString::remove(int32_t start,
4738 if(start <= 0 && _length ==
INT32_MAX) {
4742 return doReplace(start, _length,
nullptr, 0, 0);
4746UnicodeString::removeBetween(int32_t start,
4748{
return doReplace(start, limit - start,
nullptr, 0, 0); }
4751UnicodeString::retainBetween(int32_t start, int32_t limit) {
4753 return doReplace(0, start,
nullptr, 0, 0);
4757UnicodeString::truncate(int32_t targetLength)
4759 if(isBogus() && targetLength == 0) {
4763 }
else if((uint32_t)targetLength < (uint32_t)length()) {
4764 setLength(targetLength);
4772UnicodeString::reverse()
4773{
return doReverse(0, length()); }
4776UnicodeString::reverse(int32_t start,
4778{
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.
void swap(UnicodeString &other) noexcept
Swap strings.
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.
UnicodeString & operator=(UnicodeString &&src) noexcept
Move assignment operator; might leave src in bogus state.
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.
friend void swap(UnicodeString &s1, UnicodeString &s2) noexcept
Non-member UnicodeString swap function.
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(UnicodeString &&src) noexcept
Move constructor; might leave src in bogus state.
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.
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.
void releaseBuffer(int32_t newLength=-1)
Release a read/write buffer on a UnicodeString object with an "open" getBuffer(minCapacity).
void toUTF8(ByteSink &sink) const
Convert the UnicodeString to UTF-8 and write the result to a ByteSink.
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 (always 2).
#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.
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.