#include <unistr.h>
Data Structures | |
union | StackBufferOrFields |
Public Types | |
enum | EInvariant { kInvariant } |
Constant to be used in the UnicodeString(char *, int32_t, EInvariant) constructor which constructs a Unicode string from an invariant-character char * string. More... | |
Public Member Functions | |
UBool | operator== (const UnicodeString &text) const |
Equality operator. | |
UBool | operator!= (const UnicodeString &text) const |
Inequality operator. | |
UBool | operator> (const UnicodeString &text) const |
Greater than operator. | |
UBool | operator< (const UnicodeString &text) const |
Less than operator. | |
UBool | operator>= (const UnicodeString &text) const |
Greater than or equal operator. | |
UBool | operator<= (const UnicodeString &text) const |
Less than or equal operator. | |
int8_t | compare (const UnicodeString &text) const |
Compare the characters bitwise in this UnicodeString to the characters in text . | |
int8_t | compare (int32_t start, int32_t length, const UnicodeString &text) const |
Compare the characters bitwise in the range [start , start + length ) with the characters in text . | |
int8_t | compare (int32_t start, int32_t length, const UnicodeString &srcText, int32_t srcStart, int32_t srcLength) const |
Compare the characters bitwise in the range [start , start + length ) with the characters in srcText in the range [srcStart , srcStart + srcLength ). | |
int8_t | compare (const UChar *srcChars, int32_t srcLength) const |
Compare the characters bitwise in this UnicodeString with the first srcLength characters in srcChars . | |
int8_t | compare (int32_t start, int32_t length, const UChar *srcChars) const |
Compare the characters bitwise in the range [start , start + length ) with the first length characters in srcChars . | |
int8_t | compare (int32_t start, int32_t length, const UChar *srcChars, int32_t srcStart, int32_t srcLength) const |
Compare the characters bitwise in the range [start , start + length ) with the characters in srcChars in the range [srcStart , srcStart + srcLength ). | |
int8_t | compareBetween (int32_t start, int32_t limit, const UnicodeString &srcText, int32_t srcStart, int32_t srcLimit) const |
Compare the characters bitwise in the range [start , limit ) with the characters in srcText in the range [srcStart , srcLimit ). | |
int8_t | compareCodePointOrder (const UnicodeString &text) const |
Compare two Unicode strings in code point order. | |
int8_t | compareCodePointOrder (int32_t start, int32_t length, const UnicodeString &srcText) const |
Compare two Unicode strings in code point order. | |
int8_t | compareCodePointOrder (int32_t start, int32_t length, const UnicodeString &srcText, int32_t srcStart, int32_t srcLength) const |
Compare two Unicode strings in code point order. | |
int8_t | compareCodePointOrder (const UChar *srcChars, int32_t srcLength) const |
Compare two Unicode strings in code point order. | |
int8_t | compareCodePointOrder (int32_t start, int32_t length, const UChar *srcChars) const |
Compare two Unicode strings in code point order. | |
int8_t | compareCodePointOrder (int32_t start, int32_t length, const UChar *srcChars, int32_t srcStart, int32_t srcLength) const |
Compare two Unicode strings in code point order. | |
int8_t | compareCodePointOrderBetween (int32_t start, int32_t limit, const UnicodeString &srcText, int32_t srcStart, int32_t srcLimit) const |
Compare two Unicode strings in code point order. | |
int8_t | caseCompare (const UnicodeString &text, uint32_t options) const |
Compare two strings case-insensitively using full case folding. | |
int8_t | caseCompare (int32_t start, int32_t length, const UnicodeString &srcText, uint32_t options) const |
Compare two strings case-insensitively using full case folding. | |
int8_t | caseCompare (int32_t start, int32_t length, const UnicodeString &srcText, int32_t srcStart, int32_t srcLength, uint32_t options) const |
Compare two strings case-insensitively using full case folding. | |
int8_t | caseCompare (const UChar *srcChars, int32_t srcLength, uint32_t options) const |
Compare two strings case-insensitively using full case folding. | |
int8_t | caseCompare (int32_t start, int32_t length, const UChar *srcChars, uint32_t options) const |
Compare two strings case-insensitively using full case folding. | |
int8_t | caseCompare (int32_t start, int32_t length, const UChar *srcChars, int32_t srcStart, int32_t srcLength, uint32_t options) const |
Compare two strings case-insensitively using full case folding. | |
int8_t | caseCompareBetween (int32_t start, int32_t limit, const UnicodeString &srcText, int32_t srcStart, int32_t srcLimit, uint32_t options) const |
Compare two strings case-insensitively using full case folding. | |
UBool | startsWith (const UnicodeString &text) const |
Determine if this starts with the characters in text . | |
UBool | startsWith (const UnicodeString &srcText, int32_t srcStart, int32_t srcLength) const |
Determine if this starts with the characters in srcText in the range [srcStart , srcStart + srcLength ). | |
UBool | startsWith (const UChar *srcChars, int32_t srcLength) const |
Determine if this starts with the characters in srcChars . | |
UBool | startsWith (const UChar *srcChars, int32_t srcStart, int32_t srcLength) const |
Determine if this ends with the characters in srcChars in the range [srcStart , srcStart + srcLength ). | |
UBool | endsWith (const UnicodeString &text) const |
Determine if this ends with the characters in text . | |
UBool | endsWith (const UnicodeString &srcText, int32_t srcStart, int32_t srcLength) const |
Determine if this ends with the characters in srcText in the range [srcStart , srcStart + srcLength ). | |
UBool | endsWith (const UChar *srcChars, int32_t srcLength) const |
Determine if this ends with the characters in srcChars . | |
UBool | endsWith (const UChar *srcChars, int32_t srcStart, int32_t srcLength) const |
Determine if this ends with the characters in srcChars in the range [srcStart , srcStart + srcLength ). | |
int32_t | indexOf (const UnicodeString &text) const |
Locate in this the first occurrence of the characters in text , using bitwise comparison. | |
int32_t | indexOf (const UnicodeString &text, int32_t start) const |
Locate in this the first occurrence of the characters in text starting at offset start , using bitwise comparison. | |
int32_t | indexOf (const UnicodeString &text, int32_t start, int32_t length) const |
Locate in this the first occurrence in the range [start , start + length ) of the characters in text , using bitwise comparison. | |
int32_t | indexOf (const UnicodeString &srcText, 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 srcText in the range [srcStart , srcStart + srcLength ), using bitwise comparison. | |
int32_t | indexOf (const UChar *srcChars, int32_t srcLength, int32_t start) const |
Locate in this the first occurrence of the characters in srcChars starting at offset start , using bitwise comparison. | |
int32_t | indexOf (const UChar *srcChars, 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 srcChars , using bitwise comparison. | |
int32_t | indexOf (const UChar *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 srcChars in the range [srcStart , srcStart + srcLength ), using bitwise comparison. | |
int32_t | indexOf (UChar c) const |
Locate in this the first occurrence of the BMP code point c , using bitwise comparison. | |
int32_t | indexOf (UChar32 c) const |
Locate in this the first occurrence of the code point c , using bitwise comparison. | |
int32_t | indexOf (UChar c, int32_t start) const |
Locate in this the first occurrence of the BMP code point c , starting at offset start , using bitwise comparison. | |
int32_t | indexOf (UChar32 c, int32_t start) const |
Locate in this the first occurrence of the code point c starting at offset start , using bitwise comparison. | |
int32_t | indexOf (UChar c, int32_t start, int32_t length) const |
Locate in this the first occurrence of the BMP code point c in the range [start , start + length ), using bitwise comparison. | |
int32_t | indexOf (UChar32 c, int32_t start, int32_t length) const |
Locate in this the first occurrence of the code point c in the range [start , start + length ), using bitwise comparison. | |
int32_t | lastIndexOf (const UnicodeString &text) const |
Locate in this the last occurrence of the characters in text , using bitwise comparison. | |
int32_t | lastIndexOf (const UnicodeString &text, int32_t start) const |
Locate in this the last occurrence of the characters in text starting at offset start , using bitwise comparison. | |
int32_t | lastIndexOf (const UnicodeString &text, int32_t start, int32_t length) const |
Locate in this the last occurrence in the range [start , start + length ) of the characters in text , using bitwise comparison. | |
int32_t | lastIndexOf (const UnicodeString &srcText, 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 srcText in the range [srcStart , srcStart + srcLength ), using bitwise comparison. | |
int32_t | lastIndexOf (const UChar *srcChars, int32_t srcLength, int32_t start) const |
Locate in this the last occurrence of the characters in srcChars starting at offset start , using bitwise comparison. | |
int32_t | lastIndexOf (const UChar *srcChars, 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 , using bitwise comparison. | |
int32_t | lastIndexOf (const UChar *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 in the range [srcStart , srcStart + srcLength ), using bitwise comparison. | |
int32_t | lastIndexOf (UChar c) const |
Locate in this the last occurrence of the BMP code point c , using bitwise comparison. | |
int32_t | lastIndexOf (UChar32 c) const |
Locate in this the last occurrence of the code point c , using bitwise comparison. | |
int32_t | lastIndexOf (UChar c, int32_t start) const |
Locate in this the last occurrence of the BMP code point c starting at offset start , using bitwise comparison. | |
int32_t | lastIndexOf (UChar32 c, int32_t start) const |
Locate in this the last occurrence of the code point c starting at offset start , using bitwise comparison. | |
int32_t | lastIndexOf (UChar c, int32_t start, int32_t length) const |
Locate in this the last occurrence of the BMP code point c in the range [start , start + length ), using bitwise comparison. | |
int32_t | lastIndexOf (UChar32 c, int32_t start, int32_t length) const |
Locate in this the last occurrence of the code point c in the range [start , start + length ), using bitwise comparison. | |
UChar | charAt (int32_t offset) const |
Return the code unit at offset offset . | |
UChar | operator[] (int32_t offset) const |
Return the code unit at offset offset . | |
UChar32 | char32At (int32_t offset) const |
Return the code point that contains the code unit at offset offset . | |
int32_t | getChar32Start (int32_t offset) const |
Adjust a random-access offset so that it points to the beginning of a Unicode character. | |
int32_t | getChar32Limit (int32_t offset) const |
Adjust a random-access offset so that it points behind a Unicode character. | |
int32_t | moveIndex32 (int32_t index, int32_t delta) const |
Move the code unit index along the string by delta code points. | |
void | extract (int32_t start, int32_t length, UChar *dst, int32_t dstStart=0) const |
Copy the characters in the range [start , start + length ) into the array dst , beginning at dstStart . | |
int32_t | extract (UChar *dest, int32_t destCapacity, UErrorCode &errorCode) const |
Copy the contents of the string into dest. | |
void | extract (int32_t start, int32_t length, UnicodeString &target) const |
Copy the characters in the range [start , start + length ) into the UnicodeString target . | |
void | extractBetween (int32_t start, int32_t limit, UChar *dst, int32_t dstStart=0) const |
Copy the characters in the range [start , limit ) into the array dst , beginning at dstStart . | |
virtual void | extractBetween (int32_t start, int32_t limit, UnicodeString &target) const |
Copy the characters in the range [start , limit ) into the UnicodeString target . | |
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 + length ) into an array of characters. | |
int32_t | extract (int32_t start, int32_t startLength, char *target, const char *codepage=0) const |
Copy the characters in the range [start , start + length ) into an array of characters in a specified codepage. | |
int32_t | extract (int32_t start, int32_t startLength, char *target, uint32_t targetLength, const char *codepage=0) const |
Copy the characters in the range [start , start + length ) into an array of characters in a specified codepage. | |
int32_t | extract (char *dest, int32_t destCapacity, UConverter *cnv, UErrorCode &errorCode) const |
Convert the UnicodeString into a codepage string using an existing UConverter. | |
int32_t | length (void) const |
Return the length of the UnicodeString object. | |
int32_t | countChar32 (int32_t start=0, int32_t length=INT32_MAX) const |
Count Unicode code points in the length UChar code units of the string. | |
UBool | hasMoreChar32Than (int32_t start, int32_t length, int32_t number) const |
Check if the length UChar code units of the string contain more Unicode code points than a certain number. | |
UBool | isEmpty (void) const |
Determine if this string is empty. | |
int32_t | getCapacity (void) const |
Return the capacity of the internal buffer of the UnicodeString object. | |
int32_t | hashCode (void) const |
Generate a hash code for this object. | |
UBool | isBogus (void) const |
Determine if this object contains a valid string. | |
UnicodeString & | operator= (const UnicodeString &srcText) |
Assignment operator. | |
UnicodeString & | fastCopyFrom (const UnicodeString &src) |
Almost the same as the assignment operator. | |
UnicodeString & | operator= (UChar ch) |
Assignment operator. | |
UnicodeString & | operator= (UChar32 ch) |
Assignment operator. | |
UnicodeString & | setTo (const UnicodeString &srcText, int32_t srcStart) |
Set the text in the UnicodeString object to the characters in srcText in the range [srcStart , srcText.length() ). | |
UnicodeString & | setTo (const UnicodeString &srcText, int32_t srcStart, int32_t srcLength) |
Set the text in the UnicodeString object to the characters in srcText in the range [srcStart , srcStart + srcLength ). | |
UnicodeString & | setTo (const UnicodeString &srcText) |
Set the text in the UnicodeString object to the characters in srcText . | |
UnicodeString & | setTo (const UChar *srcChars, int32_t srcLength) |
Set the characters in the UnicodeString object to the characters in srcChars . | |
UnicodeString & | setTo (UChar srcChar) |
Set the characters in the UnicodeString object to the code unit srcChar . | |
UnicodeString & | setTo (UChar32 srcChar) |
Set the characters in the UnicodeString object to the code point srcChar . | |
UnicodeString & | setTo (UBool isTerminated, const UChar *text, int32_t textLength) |
Aliasing setTo() function, analogous to the readonly-aliasing UChar* constructor. | |
UnicodeString & | setTo (UChar *buffer, int32_t buffLength, int32_t buffCapacity) |
Aliasing setTo() function, analogous to the writable-aliasing UChar* constructor. | |
void | setToBogus () |
Make this UnicodeString object invalid. | |
UnicodeString & | setCharAt (int32_t offset, UChar ch) |
Set the character at the specified offset to the specified character. | |
UnicodeString & | operator+= (UChar ch) |
Append operator. | |
UnicodeString & | operator+= (UChar32 ch) |
Append operator. | |
UnicodeString & | operator+= (const UnicodeString &srcText) |
Append operator. | |
UnicodeString & | append (const UnicodeString &srcText, int32_t srcStart, int32_t srcLength) |
Append the characters in srcText in the range [srcStart , srcStart + srcLength ) to the UnicodeString object at offset start . | |
UnicodeString & | append (const UnicodeString &srcText) |
Append the characters in srcText to the UnicodeString object at offset start . | |
UnicodeString & | append (const UChar *srcChars, int32_t srcStart, int32_t srcLength) |
Append the characters in srcChars in the range [srcStart , srcStart + srcLength ) to the UnicodeString object at offset start . | |
UnicodeString & | append (const UChar *srcChars, int32_t srcLength) |
Append the characters in srcChars to the UnicodeString object at offset start . | |
UnicodeString & | append (UChar srcChar) |
Append the code unit srcChar to the UnicodeString object. | |
UnicodeString & | append (UChar32 srcChar) |
Append the code point srcChar to the UnicodeString object. | |
UnicodeString & | insert (int32_t start, const UnicodeString &srcText, int32_t srcStart, int32_t srcLength) |
Insert the characters in srcText in the range [srcStart , srcStart + srcLength ) into the UnicodeString object at offset start . | |
UnicodeString & | insert (int32_t start, const UnicodeString &srcText) |
Insert the characters in srcText into the UnicodeString object at offset start . | |
UnicodeString & | insert (int32_t start, const UChar *srcChars, int32_t srcStart, int32_t srcLength) |
Insert the characters in srcChars in the range [srcStart , srcStart + srcLength ) into the UnicodeString object at offset start . | |
UnicodeString & | insert (int32_t start, const UChar *srcChars, int32_t srcLength) |
Insert the characters in srcChars into the UnicodeString object at offset start . | |
UnicodeString & | insert (int32_t start, UChar srcChar) |
Insert the code unit srcChar into the UnicodeString object at offset start . | |
UnicodeString & | insert (int32_t start, UChar32 srcChar) |
Insert the code point srcChar into the UnicodeString object at offset start . | |
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 range [srcStart , srcStart + srcLength ). | |
UnicodeString & | replace (int32_t start, int32_t length, const UnicodeString &srcText) |
Replace the characters in the range [start , start + length ) with the characters in srcText . | |
UnicodeString & | replace (int32_t start, int32_t length, const UChar *srcChars, int32_t srcStart, int32_t srcLength) |
Replace the characters in the range [start , start + length ) with the characters in srcChars in the range [srcStart , srcStart + srcLength ). | |
UnicodeString & | replace (int32_t start, int32_t length, const UChar *srcChars, int32_t srcLength) |
Replace the characters in the range [start , start + length ) with the characters in srcChars . | |
UnicodeString & | replace (int32_t start, int32_t length, UChar srcChar) |
Replace the characters in the range [start , start + length ) with the code unit srcChar . | |
UnicodeString & | replace (int32_t start, int32_t length, UChar32 srcChar) |
Replace the characters in the range [start , start + length ) with the code point srcChar . | |
UnicodeString & | replaceBetween (int32_t start, int32_t limit, const UnicodeString &srcText) |
Replace the characters in the range [start , limit ) with the characters in srcText . | |
UnicodeString & | replaceBetween (int32_t start, int32_t limit, const UnicodeString &srcText, int32_t srcStart, int32_t srcLimit) |
Replace the characters in the range [start , limit ) with the characters in srcText in the range [srcStart , srcLimit ). | |
virtual void | handleReplaceBetween (int32_t start, int32_t limit, const UnicodeString &text) |
Replace a substring of this object with the given text. | |
virtual UBool | hasMetaData () const |
Replaceable API. | |
virtual void | copy (int32_t start, int32_t limit, int32_t dest) |
Copy a substring of this object, retaining attribute (out-of-band) information. | |
UnicodeString & | findAndReplace (const UnicodeString &oldText, const UnicodeString &newText) |
Replace all occurrences of characters in oldText with the characters in newText. | |
UnicodeString & | findAndReplace (int32_t start, int32_t length, const UnicodeString &oldText, const UnicodeString &newText) |
Replace all occurrences of characters in oldText with characters in newText in the range [start , start + length ). | |
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 the characters in newText in the range [newStart , newStart + newLength ) in the range [start , start + length ). | |
UnicodeString & | remove (void) |
Remove all characters from the UnicodeString object. | |
UnicodeString & | remove (int32_t start, int32_t length=(int32_t) INT32_MAX) |
Remove the characters in the range [start , start + length ) from the UnicodeString object. | |
UnicodeString & | removeBetween (int32_t start, int32_t limit=(int32_t) INT32_MAX) |
Remove the characters in the range [start , limit ) from the UnicodeString object. | |
UBool | padLeading (int32_t targetLength, UChar padChar=0x0020) |
Pad the start of this UnicodeString with the character padChar . | |
UBool | padTrailing (int32_t targetLength, UChar padChar=0x0020) |
Pad the end of this UnicodeString with the character padChar . | |
UBool | truncate (int32_t targetLength) |
Truncate this UnicodeString to the targetLength . | |
UnicodeString & | trim (void) |
Trims leading and trailing whitespace from this UnicodeString. | |
UnicodeString & | reverse (void) |
Reverse this UnicodeString in place. | |
UnicodeString & | reverse (int32_t start, int32_t length) |
Reverse the range [start , start + length ) in this UnicodeString. | |
UnicodeString & | toUpper (void) |
Convert the characters in this to UPPER CASE following the conventions of the default locale. | |
UnicodeString & | toUpper (const Locale &locale) |
Convert the characters in this to UPPER CASE following the conventions of a specific locale. | |
UnicodeString & | toLower (void) |
Convert the characters in this to lower case following the conventions of the default locale. | |
UnicodeString & | toLower (const Locale &locale) |
Convert the characters in this to lower case following the conventions of a specific locale. | |
UnicodeString & | toTitle (BreakIterator *titleIter) |
Titlecase this string, convenience function using the default locale. | |
UnicodeString & | toTitle (BreakIterator *titleIter, const Locale &locale) |
Titlecase this string. | |
UnicodeString & | toTitle (BreakIterator *titleIter, const Locale &locale, uint32_t options) |
Titlecase this string, with options. | |
UnicodeString & | foldCase (uint32_t options=0) |
Case-fold the characters in this string. | |
UChar * | getBuffer (int32_t minCapacity) |
Get a read/write pointer to the internal buffer. | |
void | releaseBuffer (int32_t newLength=-1) |
Release a read/write buffer on a UnicodeString object with an "open" getBuffer(minCapacity). | |
const UChar * | getBuffer () const |
Get a read-only pointer to the internal buffer. | |
const UChar * | getTerminatedBuffer () |
Get a read-only pointer to the internal buffer, making sure that it is NUL-terminated. | |
UnicodeString () | |
Construct an empty UnicodeString. | |
UnicodeString (int32_t capacity, UChar32 c, int32_t count) | |
Construct a UnicodeString with capacity to hold capacity UChars. | |
UnicodeString (UChar ch) | |
Single UChar (code unit) constructor. | |
UnicodeString (UChar32 ch) | |
Single UChar32 (code point) constructor. | |
UnicodeString (const UChar *text) | |
UChar* constructor. | |
UnicodeString (const UChar *text, int32_t textLength) | |
UChar* constructor. | |
UnicodeString (UBool isTerminated, const UChar *text, int32_t textLength) | |
Readonly-aliasing UChar* constructor. | |
UnicodeString (UChar *buffer, int32_t buffLength, int32_t buffCapacity) | |
Writable-aliasing UChar* constructor. | |
UnicodeString (const char *codepageData, const char *codepage=0) | |
char* constructor. | |
UnicodeString (const char *codepageData, int32_t dataLength, const char *codepage=0) | |
char* constructor. | |
UnicodeString (const char *src, int32_t srcLength, UConverter *cnv, UErrorCode &errorCode) | |
char * / UConverter constructor. | |
UnicodeString (const char *src, int32_t length, enum EInvariant inv) | |
Constructs a Unicode string from an invariant-character char * string. | |
UnicodeString (const UnicodeString &that) | |
Copy constructor. | |
UnicodeString (const UnicodeString &src, int32_t srcStart) | |
'Substring' constructor from tail of source string. | |
UnicodeString (const UnicodeString &src, int32_t srcStart, int32_t srcLength) | |
'Substring' constructor from subrange of source string. | |
virtual Replaceable * | clone () const |
Clone this object, an instance of a subclass of Replaceable. | |
virtual | ~UnicodeString () |
Destructor. | |
UnicodeString | unescape () const |
Unescape a string of characters and return a string containing the result. | |
UChar32 | unescapeAt (int32_t &offset) const |
Unescape a single escape sequence and return the represented character. | |
virtual UClassID | getDynamicClassID () const |
ICU "poor man's RTTI", returns a UClassID for the actual class. | |
Static Public Member Functions | |
static UClassID | getStaticClassID () |
ICU "poor man's RTTI", returns a UClassID for this class. | |
Protected Member Functions | |
virtual int32_t | getLength () const |
Implement Replaceable::getLength() (see jitterbug 1027). | |
virtual UChar | getCharAt (int32_t offset) const |
The change in Replaceable to use virtual getCharAt() allows UnicodeString::charAt() to be inline again (see jitterbug 709). | |
virtual UChar32 | getChar32At (int32_t offset) const |
The change in Replaceable to use virtual getChar32At() allows UnicodeString::char32At() to be inline again (see jitterbug 709). | |
Friends | |
class | StringThreadTest |
union | StackBufferOrFields |
It is a concrete implementation of the abstract class Replaceable (for transliteration).
The UnicodeString class is not suitable for subclassing.
For an overview of Unicode strings in C and C++ see the User Guide Strings chapter.
In ICU, a Unicode string consists of 16-bit Unicode code units. A Unicode character may be stored with either one code unit (the most common case) or with a matched pair of special code units ("surrogates"). The data type for code units is UChar. For single-character handling, a Unicode character code point is a value in the range 0..0x10ffff. ICU uses the UChar32 type for code points.
Indexes and offsets into and lengths of strings always count code units, not code points. This is the same as with multi-byte char* strings in traditional string handling. Operations on partial strings typically do not test for code point boundaries. If necessary, the user needs to take care of such boundaries by testing for the code unit values or by using functions like UnicodeString::getChar32Start() and UnicodeString::getChar32Limit() (or, in C, the equivalent macros U16_SET_CP_START() and U16_SET_CP_LIMIT(), see utf.h).
UnicodeString methods are more lenient with regard to input parameter values than other ICU APIs. In particular:
In string comparisons, two UnicodeString objects that are both "bogus" compare equal (to be transitive and prevent endless loops in sorting), and a "bogus" string compares less than any non-"bogus" one.
Const UnicodeString methods are thread-safe. Multiple threads can use const methods on the same UnicodeString object simultaneously, but non-const methods must not be called concurrently (in multiple threads) with any other (const or non-const) methods.
Similarly, const UnicodeString & parameters are thread-safe. One object may be passed in as such a parameter concurrently in multiple threads. This includes the const UnicodeString & parameters for copy construction, assignment, and cloning.
UnicodeString uses several storage methods. String contents can be stored inside the UnicodeString object itself, in an allocated and shared buffer, or in an outside buffer that is "aliased". Most of this is done transparently, but careful aliasing in particular provides significant performance improvements. Also, the internal buffer is accessible via special functions. For details see the User Guide Strings chapter.
Definition at line 183 of file unistr.h.
Constant to be used in the UnicodeString(char *, int32_t, EInvariant) constructor which constructs a Unicode string from an invariant-character char * string.
Use the macro US_INV instead of the full qualification for this value.
kInvariant |
|
UnicodeString::UnicodeString | ( | ) |
UnicodeString::UnicodeString | ( | int32_t | capacity, | |
UChar32 | c, | |||
int32_t | count | |||
) |
Construct a UnicodeString with capacity to hold capacity
UChars.
capacity | the number of UChars this UnicodeString should hold before a resize is necessary; if count is greater than 0 and count code points c take up more space than capacity, then capacity is adjusted accordingly. | |
c | is used to initially fill the string | |
count | specifies how many code points c are to be written in the string |
UnicodeString::UnicodeString | ( | UChar | ch | ) |
Single UChar (code unit) constructor.
ch | the character to place in the UnicodeString |
UnicodeString::UnicodeString | ( | UChar32 | ch | ) |
Single UChar32 (code point) constructor.
ch | the character to place in the UnicodeString |
UnicodeString::UnicodeString | ( | const UChar * | text | ) |
UChar* constructor.
text | The characters to place in the UnicodeString. text must be NULL (U+0000) terminated. |
UnicodeString::UnicodeString | ( | const UChar * | text, | |
int32_t | textLength | |||
) |
UChar* constructor.
text | The characters to place in the UnicodeString. | |
textLength | The number of Unicode characters in text to copy. |
UnicodeString::UnicodeString | ( | UBool | isTerminated, | |
const UChar * | text, | |||
int32_t | textLength | |||
) |
Readonly-aliasing UChar* constructor.
The text will be used for the UnicodeString object, but it will not be released when the UnicodeString is destroyed. This has copy-on-write semantics: When the string is modified, then the buffer is first copied into newly allocated memory. The aliased buffer is never modified. In an assignment to another UnicodeString, the text will be aliased again, so that both strings then alias the same readonly-text.
isTerminated | specifies if text is NUL -terminated. This must be true if textLength==-1 . | |
text | The characters to alias for the UnicodeString. | |
textLength | The number of Unicode characters in text to alias. If -1, then this constructor will determine the length by calling u_strlen() . |
UnicodeString::UnicodeString | ( | UChar * | buffer, | |
int32_t | buffLength, | |||
int32_t | buffCapacity | |||
) |
Writable-aliasing UChar* constructor.
The text will be used for the UnicodeString object, but it will not be released when the UnicodeString is destroyed. This has write-through semantics: For as long as the capacity of the buffer is sufficient, write operations will directly affect the buffer. When more capacity is necessary, then a new buffer will be allocated and the contents copied as with regularly constructed strings. In an assignment to another UnicodeString, the buffer will be copied. The extract(UChar *dst) function detects whether the dst pointer is the same as the string buffer itself and will in this case not copy the contents.
buffer | The characters to alias for the UnicodeString. | |
buffLength | The number of Unicode characters in buffer to alias. | |
buffCapacity | The size of buffer in UChars. |
UnicodeString::UnicodeString | ( | const char * | codepageData, | |
const char * | codepage = 0 | |||
) |
char* constructor.
codepageData | an array of bytes, null-terminated | |
codepage | the encoding of codepageData . The special value 0 for codepage indicates that the text is in the platform's default codepage. |
codepage
is an empty string (""
), then a simple conversion is performed on the codepage-invariant subset ("invariant characters") of the platform encoding. See utypes.h. Recommendation: For invariant-character strings use the constructor UnicodeString(const char *src, int32_t length, enum EInvariant inv) because it avoids object code dependencies of UnicodeString on the conversion code.
UnicodeString::UnicodeString | ( | const char * | codepageData, | |
int32_t | dataLength, | |||
const char * | codepage = 0 | |||
) |
char* constructor.
codepageData | an array of bytes. | |
dataLength | The number of bytes in codepageData . | |
codepage | the encoding of codepageData . The special value 0 for codepage indicates that the text is in the platform's default codepage. If codepage is an empty string ("" ), then a simple conversion is performed on the codepage-invariant subset ("invariant characters") of the platform encoding. See utypes.h. Recommendation: For invariant-character strings use the constructor UnicodeString(const char *src, int32_t length, enum EInvariant inv) because it avoids object code dependencies of UnicodeString on the conversion code. |
UnicodeString::UnicodeString | ( | const char * | src, | |
int32_t | srcLength, | |||
UConverter * | cnv, | |||
UErrorCode & | errorCode | |||
) |
char * / UConverter constructor.
This constructor uses an existing UConverter object to convert the codepage string to Unicode and construct a UnicodeString from that.
The converter is reset at first. If the error code indicates a failure before this constructor is called, or if an error occurs during conversion or construction, then the string will be bogus.
This function avoids the overhead of opening and closing a converter if multiple strings are constructed.
src | input codepage string | |
srcLength | length of the input string, can be -1 for NUL-terminated strings | |
cnv | converter object (ucnv_resetToUnicode() will be called), can be NULL for the default converter | |
errorCode | normal ICU error code |
UnicodeString::UnicodeString | ( | const char * | src, | |
int32_t | length, | |||
enum EInvariant | inv | |||
) |
Constructs a Unicode string from an invariant-character char * string.
About invariant characters see utypes.h. This constructor has no runtime dependency on conversion code and is therefore recommended over ones taking a charset name string (where the empty string "" indicates invariant-character conversion).
Use the macro US_INV as the third, signature-distinguishing parameter.
For example:
void fn(const char *s) { UnicodeString ustr(s, -1, US_INV); // use ustr ... }
src | String using only invariant characters. | |
length | Length of src, or -1 if NUL-terminated. | |
inv | Signature-distinguishing paramater, use US_INV. |
UnicodeString::UnicodeString | ( | const UnicodeString & | that | ) |
UnicodeString::UnicodeString | ( | const UnicodeString & | src, | |
int32_t | srcStart | |||
) |
'Substring' constructor from tail of source string.
src | The UnicodeString object to copy. | |
srcStart | The offset into src at which to start copying. |
UnicodeString::UnicodeString | ( | const UnicodeString & | src, | |
int32_t | srcStart, | |||
int32_t | srcLength | |||
) |
'Substring' constructor from subrange of source string.
src | The UnicodeString object to copy. | |
srcStart | The offset into src at which to start copying. | |
srcLength | The number of characters from src to copy. |
virtual UnicodeString::~UnicodeString | ( | ) | [virtual] |
UnicodeString & UnicodeString::append | ( | UChar32 | srcChar | ) | [inline] |
Append the code point srcChar
to the UnicodeString object.
srcChar | the code point to append |
Definition at line 4119 of file unistr.h.
References FALSE, length(), U16_APPEND, and U16_MAX_LENGTH.
UnicodeString & UnicodeString::append | ( | UChar | srcChar | ) | [inline] |
Append the code unit srcChar
to the UnicodeString object.
srcChar | the code unit to append |
Definition at line 4115 of file unistr.h.
References length().
UnicodeString & UnicodeString::append | ( | const UChar * | srcChars, | |
int32_t | srcLength | |||
) | [inline] |
Append the characters in srcChars
to the UnicodeString object at offset start
.
srcChars
is not modified.
srcChars | the source for the new characters | |
srcLength | the number of Unicode characters in srcChars |
Definition at line 4110 of file unistr.h.
References length().
UnicodeString & UnicodeString::append | ( | const UChar * | srcChars, | |
int32_t | srcStart, | |||
int32_t | srcLength | |||
) | [inline] |
Append the characters in srcChars
in the range [srcStart
, srcStart + srcLength
) to the UnicodeString object at offset start
.
srcChars
is not modified.
srcChars | the source for the new characters | |
srcStart | the offset into srcChars where new characters will be obtained | |
srcLength | the number of characters in srcChars in the append string |
Definition at line 4104 of file unistr.h.
References length().
UnicodeString & UnicodeString::append | ( | const UnicodeString & | srcText | ) | [inline] |
Append the characters in srcText
to the UnicodeString object at offset start
.
srcText
is not modified.
srcText | the source for the new characters |
Definition at line 4100 of file unistr.h.
References length().
UnicodeString & UnicodeString::append | ( | const UnicodeString & | srcText, | |
int32_t | srcStart, | |||
int32_t | srcLength | |||
) | [inline] |
Append the characters in srcText
in the range [srcStart
, srcStart + srcLength
) to the UnicodeString object at offset start
.
srcText
is not modified.
srcText | the source for the new characters | |
srcStart | the offset into srcText where new characters will be obtained | |
srcLength | the number of characters in srcText in the append string |
Definition at line 4094 of file unistr.h.
References length().
Referenced by operator+=(), and Transliterator::setID().
int8_t UnicodeString::caseCompare | ( | int32_t | start, | |
int32_t | length, | |||
const UChar * | srcChars, | |||
int32_t | srcStart, | |||
int32_t | srcLength, | |||
uint32_t | options | |||
) | const [inline] |
Compare two strings case-insensitively using full case folding.
This is equivalent to this->foldCase(options).compare(srcChars.foldCase(options)).
start | The start offset in this string at which the compare operation begins. | |
length | The number of code units from this string to compare. | |
srcChars | A pointer to another string to compare this one to. | |
srcStart | The start offset in that string at which the compare operation begins. | |
srcLength | The number of code units from that string to compare. | |
options | A bit set of options:
|
int8_t UnicodeString::caseCompare | ( | int32_t | start, | |
int32_t | length, | |||
const UChar * | srcChars, | |||
uint32_t | options | |||
) | const [inline] |
Compare two strings case-insensitively using full case folding.
This is equivalent to this->foldCase(options).compare(srcChars.foldCase(options)).
start | The start offset in this string at which the compare operation begins. | |
length | The number of code units from this string to compare. | |
srcChars | A pointer to another string to compare this one to. | |
options | A bit set of options:
|
int8_t UnicodeString::caseCompare | ( | const UChar * | srcChars, | |
int32_t | srcLength, | |||
uint32_t | options | |||
) | const [inline] |
Compare two strings case-insensitively using full case folding.
This is equivalent to this->foldCase(options).compare(srcChars.foldCase(options)).
srcChars | A pointer to another string to compare this one to. | |
srcLength | The number of code units from that string to compare. | |
options | A bit set of options:
|
Definition at line 3537 of file unistr.h.
References length().
int8_t UnicodeString::caseCompare | ( | int32_t | start, | |
int32_t | length, | |||
const UnicodeString & | srcText, | |||
int32_t | srcStart, | |||
int32_t | srcLength, | |||
uint32_t | options | |||
) | const [inline] |
Compare two strings case-insensitively using full case folding.
This is equivalent to this->foldCase(options).compare(srcText.foldCase(options)).
start | The start offset in this string at which the compare operation begins. | |
length | The number of code units from this string to compare. | |
srcText | Another string to compare this one to. | |
srcStart | The start offset in that string at which the compare operation begins. | |
srcLength | The number of code units from that string to compare. | |
options | A bit set of options:
|
int8_t UnicodeString::caseCompare | ( | int32_t | start, | |
int32_t | length, | |||
const UnicodeString & | srcText, | |||
uint32_t | options | |||
) | const [inline] |
Compare two strings case-insensitively using full case folding.
This is equivalent to this->foldCase(options).compare(srcText.foldCase(options)).
start | The start offset in this string at which the compare operation begins. | |
length | The number of code units from this string to compare. | |
srcText | Another string to compare this one to. | |
options | A bit set of options:
|
Definition at line 3529 of file unistr.h.
References length().
int8_t UnicodeString::caseCompare | ( | const UnicodeString & | text, | |
uint32_t | options | |||
) | const [inline] |
Compare two strings case-insensitively using full case folding.
This is equivalent to this->foldCase(options).compare(text.foldCase(options)).
text | Another string to compare this one to. | |
options | A bit set of options:
|
Definition at line 3524 of file unistr.h.
References length().
int8_t UnicodeString::caseCompareBetween | ( | int32_t | start, | |
int32_t | limit, | |||
const UnicodeString & | srcText, | |||
int32_t | srcStart, | |||
int32_t | srcLimit, | |||
uint32_t | options | |||
) | const [inline] |
Compare two strings case-insensitively using full case folding.
This is equivalent to this->foldCase(options).compareBetween(text.foldCase(options)).
start | The start offset in this string at which the compare operation begins. | |
limit | The offset after the last code unit from this string to compare. | |
srcText | Another string to compare this one to. | |
srcStart | The start offset in that string at which the compare operation begins. | |
srcLimit | The offset after the last code unit from that string to compare. | |
options | A bit set of options:
|
UChar32 UnicodeString::char32At | ( | int32_t | offset | ) | const [inline] |
Return the code point that contains the code unit at offset offset
.
If the offset is not valid (0..length()-1) then U+ffff is returned.
offset | a valid offset into the text that indicates the text offset of any of the code units that will be assembled into a code point (21-bit value) and returned |
offset
or 0xffff if the offset is not valid for this string Reimplemented from Replaceable.
UChar UnicodeString::charAt | ( | int32_t | offset | ) | const [inline] |
Return the code unit at offset offset
.
If the offset is not valid (0..length()-1) then U+ffff is returned.
offset | a valid offset into the text |
offset
or 0xffff if the offset is not valid for this string Reimplemented from Replaceable.
virtual Replaceable* UnicodeString::clone | ( | ) | const [virtual] |
Clone this object, an instance of a subclass of Replaceable.
Clones can be used concurrently in multiple threads. If a subclass does not implement clone(), or if an error occurs, then NULL is returned. The clone functions in all subclasses return a pointer to a Replaceable because some compilers do not support covariant (same-as-this) return types; cast to the appropriate subclass if necessary. The caller must delete the clone.
Reimplemented from Replaceable.
int8_t UnicodeString::compare | ( | int32_t | start, | |
int32_t | length, | |||
const UChar * | srcChars, | |||
int32_t | srcStart, | |||
int32_t | srcLength | |||
) | const [inline] |
Compare the characters bitwise in the range [start
, start + length
) with the characters in srcChars
in the range [srcStart
, srcStart + srcLength
).
start | the offset at which the compare operation begins | |
length | the number of characters in this to compare | |
srcChars | the characters to be compared | |
srcStart | the offset into srcChars to start comparison | |
srcLength | the number of characters in srcChars to compare |
srcChars
, -1 if the characters in this are bitwise less than the characters in srcChars
, +1 if the characters in this are bitwise greater than the characters in srcChars
. int8_t UnicodeString::compare | ( | int32_t | start, | |
int32_t | length, | |||
const UChar * | srcChars | |||
) | const [inline] |
Compare the characters bitwise in the range [start
, start + length
) with the first length
characters in srcChars
.
start | the offset at which the compare operation begins | |
length | the number of characters to compare. | |
srcChars | the characters to be compared |
srcChars
, -1 if the characters in this are bitwise less than the characters in srcChars
, +1 if the characters in this are bitwise greater than the characters in srcChars
. int8_t UnicodeString::compare | ( | const UChar * | srcChars, | |
int32_t | srcLength | |||
) | const [inline] |
Compare the characters bitwise in this UnicodeString with the first srcLength
characters in srcChars
.
srcChars | The characters to compare to this UnicodeString. | |
srcLength | the number of characters in srcChars to compare |
srcChars
, -1 if the characters in this are bitwise less than the characters in srcChars
, +1 if the characters in this are bitwise greater than the characters in srcChars
. Definition at line 3411 of file unistr.h.
References length().
int8_t UnicodeString::compare | ( | int32_t | start, | |
int32_t | length, | |||
const UnicodeString & | srcText, | |||
int32_t | srcStart, | |||
int32_t | srcLength | |||
) | const [inline] |
Compare the characters bitwise in the range [start
, start + length
) with the characters in srcText
in the range [srcStart
, srcStart + srcLength
).
start | the offset at which the compare operation begins | |
length | the number of characters in this to compare. | |
srcText | the text to be compared | |
srcStart | the offset into srcText to start comparison | |
srcLength | the number of characters in src to compare |
srcText
, -1 if the characters in this are bitwise less than the characters in srcText
, +1 if the characters in this are bitwise greater than the characters in srcText
. int8_t UnicodeString::compare | ( | int32_t | start, | |
int32_t | length, | |||
const UnicodeString & | text | |||
) | const [inline] |
Compare the characters bitwise in the range [start
, start + length
) with the characters in text
.
start | the offset at which the compare operation begins | |
length | the number of characters of text to compare. | |
text | the other text to be compared against this string. |
text
, -1 if the characters in this are bitwise less than the characters in text
, +1 if the characters in this are bitwise greater than the characters in text
. Definition at line 3405 of file unistr.h.
References length().
int8_t UnicodeString::compare | ( | const UnicodeString & | text | ) | const [inline] |
Compare the characters bitwise in this UnicodeString to the characters in text
.
text | The UnicodeString to compare to this one. |
text
, -1 if the characters in this are bitwise less than the characters in text
, +1 if the characters in this are bitwise greater than the characters in text
. Definition at line 3401 of file unistr.h.
References length().
Referenced by startsWith().
int8_t UnicodeString::compareBetween | ( | int32_t | start, | |
int32_t | limit, | |||
const UnicodeString & | srcText, | |||
int32_t | srcStart, | |||
int32_t | srcLimit | |||
) | const [inline] |
Compare the characters bitwise in the range [start
, limit
) with the characters in srcText
in the range [srcStart
, srcLimit
).
start | the offset at which the compare operation begins | |
limit | the offset immediately following the compare operation | |
srcText | the text to be compared | |
srcStart | the offset into srcText to start comparison | |
srcLimit | the offset into srcText to limit comparison |
srcText
, -1 if the characters in this are bitwise less than the characters in srcText
, +1 if the characters in this are bitwise greater than the characters in srcText
. int8_t UnicodeString::compareCodePointOrder | ( | int32_t | start, | |
int32_t | length, | |||
const UChar * | srcChars, | |||
int32_t | srcStart, | |||
int32_t | srcLength | |||
) | const [inline] |
Compare two Unicode strings in code point order.
The result may be different from the results of compare(), operator<, etc. if supplementary characters are present:
In UTF-16, supplementary characters (with code points U+10000 and above) are stored with pairs of surrogate code units. These have values from 0xd800 to 0xdfff, which means that they compare as less than some other BMP characters like U+feff. This function compares Unicode strings in code point order. If either of the UTF-16 strings is malformed (i.e., it contains unpaired surrogates), then the result is not defined.
start | The start offset in this string at which the compare operation begins. | |
length | The number of code units from this string to compare. | |
srcChars | A pointer to another string to compare this one to. | |
srcStart | The start offset in that string at which the compare operation begins. | |
srcLength | The number of code units from that string to compare. |
int8_t UnicodeString::compareCodePointOrder | ( | int32_t | start, | |
int32_t | length, | |||
const UChar * | srcChars | |||
) | const [inline] |
Compare two Unicode strings in code point order.
The result may be different from the results of compare(), operator<, etc. if supplementary characters are present:
In UTF-16, supplementary characters (with code points U+10000 and above) are stored with pairs of surrogate code units. These have values from 0xd800 to 0xdfff, which means that they compare as less than some other BMP characters like U+feff. This function compares Unicode strings in code point order. If either of the UTF-16 strings is malformed (i.e., it contains unpaired surrogates), then the result is not defined.
start | The start offset in this string at which the compare operation begins. | |
length | The number of code units from this string to compare. | |
srcChars | A pointer to another string to compare this one to. |
int8_t UnicodeString::compareCodePointOrder | ( | const UChar * | srcChars, | |
int32_t | srcLength | |||
) | const [inline] |
Compare two Unicode strings in code point order.
The result may be different from the results of compare(), operator<, etc. if supplementary characters are present:
In UTF-16, supplementary characters (with code points U+10000 and above) are stored with pairs of surrogate code units. These have values from 0xd800 to 0xdfff, which means that they compare as less than some other BMP characters like U+feff. This function compares Unicode strings in code point order. If either of the UTF-16 strings is malformed (i.e., it contains unpaired surrogates), then the result is not defined.
srcChars | A pointer to another string to compare this one to. | |
srcLength | The number of code units from that string to compare. |
Definition at line 3472 of file unistr.h.
References length().
int8_t UnicodeString::compareCodePointOrder | ( | int32_t | start, | |
int32_t | length, | |||
const UnicodeString & | srcText, | |||
int32_t | srcStart, | |||
int32_t | srcLength | |||
) | const [inline] |
Compare two Unicode strings in code point order.
The result may be different from the results of compare(), operator<, etc. if supplementary characters are present:
In UTF-16, supplementary characters (with code points U+10000 and above) are stored with pairs of surrogate code units. These have values from 0xd800 to 0xdfff, which means that they compare as less than some other BMP characters like U+feff. This function compares Unicode strings in code point order. If either of the UTF-16 strings is malformed (i.e., it contains unpaired surrogates), then the result is not defined.
start | The start offset in this string at which the compare operation begins. | |
length | The number of code units from this string to compare. | |
srcText | Another string to compare this one to. | |
srcStart | The start offset in that string at which the compare operation begins. | |
srcLength | The number of code units from that string to compare. |
int8_t UnicodeString::compareCodePointOrder | ( | int32_t | start, | |
int32_t | length, | |||
const UnicodeString & | srcText | |||
) | const [inline] |
Compare two Unicode strings in code point order.
The result may be different from the results of compare(), operator<, etc. if supplementary characters are present:
In UTF-16, supplementary characters (with code points U+10000 and above) are stored with pairs of surrogate code units. These have values from 0xd800 to 0xdfff, which means that they compare as less than some other BMP characters like U+feff. This function compares Unicode strings in code point order. If either of the UTF-16 strings is malformed (i.e., it contains unpaired surrogates), then the result is not defined.
start | The start offset in this string at which the compare operation begins. | |
length | The number of code units from this string to compare. | |
srcText | Another string to compare this one to. |
Definition at line 3466 of file unistr.h.
References length().
int8_t UnicodeString::compareCodePointOrder | ( | const UnicodeString & | text | ) | const [inline] |
Compare two Unicode strings in code point order.
The result may be different from the results of compare(), operator<, etc. if supplementary characters are present:
In UTF-16, supplementary characters (with code points U+10000 and above) are stored with pairs of surrogate code units. These have values from 0xd800 to 0xdfff, which means that they compare as less than some other BMP characters like U+feff. This function compares Unicode strings in code point order. If either of the UTF-16 strings is malformed (i.e., it contains unpaired surrogates), then the result is not defined.
text | Another string to compare this one to. |
Definition at line 3462 of file unistr.h.
References length().
int8_t UnicodeString::compareCodePointOrderBetween | ( | int32_t | start, | |
int32_t | limit, | |||
const UnicodeString & | srcText, | |||
int32_t | srcStart, | |||
int32_t | srcLimit | |||
) | const [inline] |
Compare two Unicode strings in code point order.
The result may be different from the results of compare(), operator<, etc. if supplementary characters are present:
In UTF-16, supplementary characters (with code points U+10000 and above) are stored with pairs of surrogate code units. These have values from 0xd800 to 0xdfff, which means that they compare as less than some other BMP characters like U+feff. This function compares Unicode strings in code point order. If either of the UTF-16 strings is malformed (i.e., it contains unpaired surrogates), then the result is not defined.
start | The start offset in this string at which the compare operation begins. | |
limit | The offset after the last code unit from this string to compare. | |
srcText | Another string to compare this one to. | |
srcStart | The start offset in that string at which the compare operation begins. | |
srcLimit | The offset after the last code unit from that string to compare. |
virtual void UnicodeString::copy | ( | int32_t | start, | |
int32_t | limit, | |||
int32_t | dest | |||
) | [virtual] |
Copy a substring of this object, retaining attribute (out-of-band) information.
This method is used to duplicate or reorder substrings. The destination index must not overlap the source range.
start | the beginning index, inclusive; 0 <= start <= limit . | |
limit | the ending index, exclusive; start <= limit <= length() . | |
dest | the destination index. The characters from start..limit-1 will be copied to dest . Implementations of this method may assume that dest <= start || dest >= limit . |
Implements Replaceable.
int32_t UnicodeString::countChar32 | ( | int32_t | start = 0 , |
|
int32_t | length = INT32_MAX | |||
) | const |
Count Unicode code points in the length UChar code units of the string.
A code point may occupy either one or two UChar code units. Counting code points involves reading all code units.
This functions is basically the inverse of moveIndex32().
start | the index of the first code unit to check | |
length | the number of UChar code units to check |
UBool UnicodeString::endsWith | ( | const UChar * | srcChars, | |
int32_t | srcStart, | |||
int32_t | srcLength | |||
) | const [inline] |
Determine if this ends with the characters in srcChars
in the range [srcStart
, srcStart + srcLength
).
srcChars | The characters to match. | |
srcStart | the offset into srcText to start matching | |
srcLength | the number of characters in srcChars to match |
srcChars
, FALSE otherwise Definition at line 3793 of file unistr.h.
References length(), and u_strlen().
UBool UnicodeString::endsWith | ( | const UChar * | srcChars, | |
int32_t | srcLength | |||
) | const [inline] |
Determine if this ends with the characters in srcChars
.
srcChars | The characters to match. | |
srcLength | the number of characters in srcChars |
srcChars
, FALSE otherwise Definition at line 3783 of file unistr.h.
References length(), and u_strlen().
UBool UnicodeString::endsWith | ( | const UnicodeString & | srcText, | |
int32_t | srcStart, | |||
int32_t | srcLength | |||
) | const [inline] |
Determine if this ends with the characters in srcText
in the range [srcStart
, srcStart + srcLength
).
srcText | The text to match. | |
srcStart | the offset into srcText to start matching | |
srcLength | the number of characters in srcText to match |
text
, FALSE otherwise Definition at line 3774 of file unistr.h.
References length(), and pinIndices().
UBool UnicodeString::endsWith | ( | const UnicodeString & | text | ) | const [inline] |
int32_t UnicodeString::extract | ( | char * | dest, | |
int32_t | destCapacity, | |||
UConverter * | cnv, | |||
UErrorCode & | errorCode | |||
) | const |
Convert the UnicodeString into a codepage string using an existing UConverter.
The output string is NUL-terminated if possible.
This function avoids the overhead of opening and closing a converter if multiple strings are extracted.
dest | destination string buffer, can be NULL if destCapacity==0 | |
destCapacity | the number of chars available at dest | |
cnv | the converter object to be used (ucnv_resetFromUnicode() will be called), or NULL for the default converter | |
errorCode | normal ICU error code |
int32_t UnicodeString::extract | ( | int32_t | start, | |
int32_t | startLength, | |||
char * | target, | |||
uint32_t | targetLength, | |||
const char * | codepage = 0 | |||
) | const |
Copy the characters in the range [start
, start + length
) into an array of characters in a specified codepage.
This function does not write any more than targetLength
characters but returns the length of the entire output string so that one can allocate a larger buffer and call the function again if necessary. The output string is NUL-terminated if possible.
Recommendation: For invariant-character strings use extract(int32_t start, int32_t length, char *target, int32_t targetCapacity, enum EInvariant inv) const because it avoids object code dependencies of UnicodeString on the conversion code.
start | offset of first character which will be copied | |
startLength | the number of characters to extract | |
target | the target buffer for extraction | |
targetLength | the length of the target buffer | |
codepage | the desired codepage for the characters. 0 has the special meaning of the default codepage If codepage is an empty string ("" ), then a simple conversion is performed on the codepage-invariant subset ("invariant characters") of the platform encoding. See utypes.h. If target is NULL, then the number of bytes required for target is returned. |
int32_t UnicodeString::extract | ( | int32_t | start, | |
int32_t | startLength, | |||
char * | target, | |||
const char * | codepage = 0 | |||
) | const [inline] |
Copy the characters in the range [start
, start + length
) into an array of characters in a specified codepage.
The output string is NUL-terminated.
Recommendation: For invariant-character strings use extract(int32_t start, int32_t length, char *target, int32_t targetCapacity, enum EInvariant inv) const because it avoids object code dependencies of UnicodeString on the conversion code.
start | offset of first character which will be copied | |
startLength | the number of characters to extract | |
target | the target buffer for extraction | |
codepage | the desired codepage for the characters. 0 has the special meaning of the default codepage If codepage is an empty string ("" ), then a simple conversion is performed on the codepage-invariant subset ("invariant characters") of the platform encoding. See utypes.h. If target is NULL, then the number of bytes required for target is returned. It is assumed that the target is big enough to fit all of the characters. |
Definition at line 3905 of file unistr.h.
References extract().
int32_t UnicodeString::extract | ( | int32_t | start, | |
int32_t | startLength, | |||
char * | target, | |||
int32_t | targetCapacity, | |||
enum EInvariant | inv | |||
) | const |
Copy the characters in the range [start
, start + length
) into an array of characters.
All characters must be invariant (see utypes.h). Use US_INV as the last, signature-distinguishing parameter.
This function does not write any more than targetLength
characters but returns the length of the entire output string so that one can allocate a larger buffer and call the function again if necessary. The output string is NUL-terminated if possible.
start | offset of first character which will be copied | |
startLength | the number of characters to extract | |
target | the target buffer for extraction, can be NULL if targetLength is 0 | |
targetCapacity | the length of the target buffer | |
inv | Signature-distinguishing paramater, use US_INV. |
void UnicodeString::extract | ( | int32_t | start, | |
int32_t | length, | |||
UnicodeString & | target | |||
) | const [inline] |
Copy the characters in the range [start
, start + length
) into the UnicodeString target
.
start | offset of first character which will be copied | |
length | the number of characters to extract | |
target | UnicodeString into which to copy characters. |
target
int32_t UnicodeString::extract | ( | UChar * | dest, | |
int32_t | destCapacity, | |||
UErrorCode & | errorCode | |||
) | const |
Copy the contents of the string into dest.
This is a convenience function that checks if there is enough space in dest, extracts the entire string if possible, and NUL-terminates dest if possible.
If the string fits into dest but cannot be NUL-terminated (length()==destCapacity) then the error code is set to U_STRING_NOT_TERMINATED_WARNING. If the string itself does not fit into dest (length()>destCapacity) then the error code is set to U_BUFFER_OVERFLOW_ERROR.
If the string aliases to dest
itself as an external buffer, then extract() will not copy the contents.
dest | Destination string buffer. | |
destCapacity | Number of UChars available at dest. | |
errorCode | ICU error code. |
void UnicodeString::extract | ( | int32_t | start, | |
int32_t | length, | |||
UChar * | dst, | |||
int32_t | dstStart = 0 | |||
) | const [inline] |
Copy the characters in the range [start
, start + length
) into the array dst
, beginning at dstStart
.
If the string aliases to dst
itself as an external buffer, then extract() will not copy the contents.
start | offset of first character which will be copied into the array | |
length | the number of characters to extract | |
dst | array in which to copy characters. The length of dst must be at least (dstStart + length ). | |
dstStart | the offset in dst where the first character will be extracted |
Definition at line 3890 of file unistr.h.
Referenced by extract().
virtual void UnicodeString::extractBetween | ( | int32_t | start, | |
int32_t | limit, | |||
UnicodeString & | target | |||
) | const [virtual] |
Copy the characters in the range [start
, limit
) into the UnicodeString target
.
Replaceable API.
start | offset of first character which will be copied | |
limit | offset immediately following the last character to be copied | |
target | UnicodeString into which to copy characters. |
target
Implements Replaceable.
void UnicodeString::extractBetween | ( | int32_t | start, | |
int32_t | limit, | |||
UChar * | dst, | |||
int32_t | dstStart = 0 | |||
) | const [inline] |
Copy the characters in the range [start
, limit
) into the array dst
, beginning at dstStart
.
start | offset of first character which will be copied into the array | |
limit | offset immediately following the last character to be copied | |
dst | array in which to copy characters. The length of dst must be at least (dstStart + (limit - start) ). | |
dstStart | the offset in dst where the first character will be extracted |
UnicodeString& UnicodeString::fastCopyFrom | ( | const UnicodeString & | src | ) |
Almost the same as the assignment operator.
Replace the characters in this UnicodeString with the characters from srcText
.
This function works the same for all strings except for ones that are readonly aliases. Starting with ICU 2.4, the assignment operator and the copy constructor allocate a new buffer and copy the buffer contents even for readonly aliases. This function implements the old, more efficient but less safe behavior of making this string also a readonly alias to the same buffer. The fastCopyFrom function must be used only if it is known that the lifetime of this UnicodeString is at least as long as the lifetime of the aliased buffer including its contents, for example for strings from resource bundles or aliases to string contents.
src | The text containing the characters to replace. |
UnicodeString& 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 the characters in newText in the range [newStart
, newStart + newLength
) in the range [start
, start + length
).
start | the start of the range in which replace will performed | |
length | the length of the range in which replace will be performed | |
oldText | the text containing the search text | |
oldStart | the start of the search range in oldText | |
oldLength | the length of the search range in oldText | |
newText | the text containing the replacement text | |
newStart | the start of the replacement range in newText | |
newLength | the length of the replacement range in newText |
UnicodeString & UnicodeString::findAndReplace | ( | int32_t | start, | |
int32_t | length, | |||
const UnicodeString & | oldText, | |||
const UnicodeString & | newText | |||
) | [inline] |
Replace all occurrences of characters in oldText with characters in newText in the range [start
, start + length
).
start | the start of the range in which replace will performed | |
length | the length of the range in which replace will be performed | |
oldText | the text containing the search text | |
newText | the text containing the replacement text |
Definition at line 3873 of file unistr.h.
References findAndReplace(), and length().
UnicodeString & UnicodeString::findAndReplace | ( | const UnicodeString & | oldText, | |
const UnicodeString & | newText | |||
) | [inline] |
Replace all occurrences of characters in oldText with the characters in newText.
oldText | the text containing the search text | |
newText | the text containing the replacement text |
Definition at line 3867 of file unistr.h.
References length().
Referenced by findAndReplace().
UnicodeString& UnicodeString::foldCase | ( | uint32_t | options = 0 |
) |
Case-fold the characters in this string.
Case-folding is locale-independent and not context-sensitive, but there is an option for whether to include or exclude mappings for dotted I and dotless i that are marked with 'I' in CaseFolding.txt. The result may be longer or shorter than the original.
options | Either U_FOLD_CASE_DEFAULT or U_FOLD_CASE_EXCLUDE_SPECIAL_I |
const UChar * UnicodeString::getBuffer | ( | ) | const [inline] |
Get a read-only pointer to the internal buffer.
This can be called at any time on a valid UnicodeString.
It returns 0 if the string is bogus, or during an "open" getBuffer(minCapacity).
It can be called as many times as desired. The pointer that it returns will remain valid until the UnicodeString object is modified, at which time the pointer is semantically invalidated and must not be used any more.
The capacity of the buffer can be determined with getCapacity(). The part after length() may or may not be initialized and valid, depending on the history of the UnicodeString object.
The buffer contents is (probably) not NUL-terminated. You can check if it is with (s.length()<s.getCapacity() && buffer[s.length()]==0)
. (See getTerminatedBuffer().)
The buffer may reside in read-only memory. Its contents must not be modified.
UChar* UnicodeString::getBuffer | ( | int32_t | minCapacity | ) |
Get a read/write pointer to the internal buffer.
The buffer is guaranteed to be large enough for at least minCapacity UChars, writable, and is still owned by the UnicodeString object. Calls to getBuffer(minCapacity) must not be nested, and must be matched with calls to releaseBuffer(newLength). If the string buffer was read-only or shared, then it will be reallocated and copied.
An attempted nested call will return 0, and will not further modify the state of the UnicodeString object. It also returns 0 if the string is bogus.
The actual capacity of the string buffer may be larger than minCapacity. getCapacity() returns the actual capacity. For many operations, the full capacity should be used to avoid reallocations.
While the buffer is "open" between getBuffer(minCapacity) and releaseBuffer(newLength), the following applies:
minCapacity | the minimum number of UChars that are to be available in the buffer, starting at the returned pointer; default to the current string capacity if minCapacity==-1 |
Referenced by Normalizer::compare(), Normalizer::isNormalized(), and Normalizer::quickCheck().
int32_t UnicodeString::getCapacity | ( | void | ) | const [inline] |
Return the capacity of the internal buffer of the UnicodeString object.
This is useful together with the getBuffer functions. See there for details.
Definition at line 3314 of file unistr.h.
Referenced by getTerminatedBuffer().
virtual UChar32 UnicodeString::getChar32At | ( | int32_t | offset | ) | const [protected, virtual] |
The change in Replaceable to use virtual getChar32At() allows UnicodeString::char32At() to be inline again (see jitterbug 709).
Implements Replaceable.
int32_t UnicodeString::getChar32Limit | ( | int32_t | offset | ) | const [inline] |
Adjust a random-access offset so that it points behind a Unicode character.
The offset that is passed in points behind any code unit of a code point, while the returned offset will point behind the last code unit of the same code point. In UTF-16, if the input offset points behind the first surrogate (i.e., to the second surrogate) of a surrogate pair, then the returned offset will point behind the second surrogate (i.e., to the first surrogate).
offset | a valid offset after any code unit of a code point of the text |
Definition at line 3971 of file unistr.h.
References length(), and U16_SET_CP_LIMIT.
int32_t UnicodeString::getChar32Start | ( | int32_t | offset | ) | const [inline] |
Adjust a random-access offset so that it points to the beginning of a Unicode character.
The offset that is passed in points to any code unit of a code point, while the returned offset will point to the first code unit of the same code point. In UTF-16, if the input offset points to a second surrogate of a surrogate pair, then the returned offset will point to the first surrogate.
offset | a valid offset into one code point of the text |
Definition at line 3960 of file unistr.h.
References length(), and U16_SET_CP_START.
virtual UChar UnicodeString::getCharAt | ( | int32_t | offset | ) | const [protected, virtual] |
The change in Replaceable to use virtual getCharAt() allows UnicodeString::charAt() to be inline again (see jitterbug 709).
Implements Replaceable.
virtual UClassID UnicodeString::getDynamicClassID | ( | ) | const [virtual] |
virtual int32_t UnicodeString::getLength | ( | ) | const [protected, virtual] |
static UClassID UnicodeString::getStaticClassID | ( | ) | [static] |
const UChar * UnicodeString::getTerminatedBuffer | ( | ) | [inline] |
Get a read-only pointer to the internal buffer, making sure that it is NUL-terminated.
This can be called at any time on a valid UnicodeString.
It returns 0 if the string is bogus, or during an "open" getBuffer(minCapacity), or if the buffer cannot be NUL-terminated (because memory allocation failed).
It can be called as many times as desired. The pointer that it returns will remain valid until the UnicodeString object is modified, at which time the pointer is semantically invalidated and must not be used any more.
The capacity of the buffer can be determined with getCapacity(). The part after length()+1 may or may not be initialized and valid, depending on the history of the UnicodeString object.
The buffer contents is guaranteed to be NUL-terminated. getTerminatedBuffer() may reallocate the buffer if a terminating NUL is written. For this reason, this function is not const, unlike getBuffer(). Note that a UnicodeString may also contain NUL characters as part of its contents.
The buffer may reside in read-only memory. Its contents must not be modified.
Definition at line 4020 of file unistr.h.
References getCapacity(), and length().
virtual void UnicodeString::handleReplaceBetween | ( | int32_t | start, | |
int32_t | limit, | |||
const UnicodeString & | text | |||
) | [virtual] |
Replace a substring of this object with the given text.
start | the beginning index, inclusive; 0 <= start <= limit . | |
limit | the ending index, exclusive; start <= limit <= length() . | |
text | the text to replace characters start to limit - 1 |
Implements Replaceable.
int32_t UnicodeString::hashCode | ( | void | ) | const [inline] |
virtual UBool UnicodeString::hasMetaData | ( | ) | const [virtual] |
UBool UnicodeString::hasMoreChar32Than | ( | int32_t | start, | |
int32_t | length, | |||
int32_t | number | |||
) | const |
Check if the length UChar code units of the string contain more Unicode code points than a certain number.
This is more efficient than counting all code points in this part of the string and comparing that number with a threshold. This function may not need to scan the string at all if the length falls within a certain range, and never needs to count more than 'number+1' code points. Logically equivalent to (countChar32(start, length)>number). A Unicode code point may occupy either one or two UChar code units.
start | the index of the first code unit to check (0 for the entire string) | |
length | the number of UChar code units to check (use INT32_MAX for the entire string; remember that start/length values are pinned) | |
number | The number of code points in the (sub)string is compared against the 'number' parameter. |
int32_t UnicodeString::indexOf | ( | UChar32 | c, | |
int32_t | start, | |||
int32_t | length | |||
) | const [inline] |
Locate in this the first occurrence of the code point c
in the range [start
, start + length
), using bitwise comparison.
c | The code point to search for. | |
start | the offset into this at which to start matching | |
length | the number of characters in this to search |
c
, or -1 if not found. int32_t UnicodeString::indexOf | ( | UChar | c, | |
int32_t | start, | |||
int32_t | length | |||
) | const [inline] |
Locate in this the first occurrence of the BMP code point c
in the range [start
, start + length
), using bitwise comparison.
c | The code unit to search for. | |
start | the offset into this at which to start matching | |
length | the number of characters in this to search |
c
, or -1 if not found. int32_t UnicodeString::indexOf | ( | UChar32 | c, | |
int32_t | start | |||
) | const [inline] |
Locate in this the first occurrence of the code point c
starting at offset start
, using bitwise comparison.
c | The code point to search for. | |
start | The offset at which searching will start. |
c
, or -1 if not found. int32_t UnicodeString::indexOf | ( | UChar | c, | |
int32_t | start | |||
) | const [inline] |
Locate in this the first occurrence of the BMP code point c
, starting at offset start
, using bitwise comparison.
c | The code unit to search for. | |
start | The offset at which searching will start. |
c
, or -1 if not found. Definition at line 3650 of file unistr.h.
References length().
int32_t UnicodeString::indexOf | ( | UChar32 | c | ) | const [inline] |
int32_t UnicodeString::indexOf | ( | UChar | c | ) | const [inline] |
int32_t UnicodeString::indexOf | ( | const UChar * | 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 srcChars
in the range [srcStart
, srcStart + srcLength
), using bitwise comparison.
srcChars | The text to search for. | |
srcStart | the offset into srcChars at which to start matching | |
srcLength | the number of characters in srcChars to match | |
start | the offset into this at which to start matching | |
length | the number of characters in this to search |
text
, or -1 if not found. int32_t UnicodeString::indexOf | ( | const UChar * | srcChars, | |
int32_t | srcLength, | |||
int32_t | start, | |||
int32_t | length | |||
) | const [inline] |
Locate in this the first occurrence in the range [start
, start + length
) of the characters in srcChars
, using bitwise comparison.
srcChars | The text to search for. | |
srcLength | the number of characters in srcChars | |
start | The offset at which searching will start. | |
length | The number of characters to search |
srcChars
, or -1 if not found. Definition at line 3623 of file unistr.h.
References indexOf().
int32_t UnicodeString::indexOf | ( | const UChar * | srcChars, | |
int32_t | srcLength, | |||
int32_t | start | |||
) | const [inline] |
Locate in this the first occurrence of the characters in srcChars
starting at offset start
, using bitwise comparison.
srcChars | The text to search for. | |
srcLength | the number of characters in srcChars to match | |
start | the offset into this at which to start matching |
text
, or -1 if not found. int32_t UnicodeString::indexOf | ( | const UnicodeString & | srcText, | |
int32_t | srcStart, | |||
int32_t | srcLength, | |||
int32_t | start, | |||
int32_t | length | |||
) | const [inline] |
Locate in this the first occurrence in the range [start
, start + length
) of the characters in srcText
in the range [srcStart
, srcStart + srcLength
), using bitwise comparison.
srcText | The text to search for. | |
srcStart | the offset into srcText at which to start matching | |
srcLength | the number of characters in srcText to match | |
start | the offset into this at which to start matching | |
length | the number of characters in this to search |
text
, or -1 if not found. Definition at line 3582 of file unistr.h.
References getArrayStart(), indexOf(), isBogus(), and pinIndices().
int32_t UnicodeString::indexOf | ( | const UnicodeString & | text, | |
int32_t | start, | |||
int32_t | length | |||
) | const [inline] |
Locate in this the first occurrence in the range [start
, start + length
) of the characters in text
, using bitwise comparison.
text | The text to search for. | |
start | The offset at which searching will start. | |
length | The number of characters to search |
text
, or -1 if not found. int32_t UnicodeString::indexOf | ( | const UnicodeString & | text, | |
int32_t | start | |||
) | const [inline] |
Locate in this the first occurrence of the characters in text
starting at offset start
, using bitwise comparison.
text | The text to search for. | |
start | The offset at which searching will start. |
text
, or -1 if not found. int32_t UnicodeString::indexOf | ( | const UnicodeString & | text | ) | const [inline] |
Locate in this the first occurrence of the characters in text
, using bitwise comparison.
text | The text to search for. |
text
, or -1 if not found. Definition at line 3598 of file unistr.h.
References length().
Referenced by indexOf().
UnicodeString & UnicodeString::insert | ( | int32_t | start, | |
UChar32 | srcChar | |||
) | [inline] |
Insert the code point srcChar
into the UnicodeString object at offset start
.
start | the offset at which the insertion occurs | |
srcChar | the code point to insert |
Definition at line 4171 of file unistr.h.
References replace().
UnicodeString & UnicodeString::insert | ( | int32_t | start, | |
UChar | srcChar | |||
) | [inline] |
Insert the code unit srcChar
into the UnicodeString object at offset start
.
start | the offset at which the insertion occurs | |
srcChar | the code unit to insert |
UnicodeString & UnicodeString::insert | ( | int32_t | start, | |
const UChar * | srcChars, | |||
int32_t | srcLength | |||
) | [inline] |
Insert the characters in srcChars
into the UnicodeString object at offset start
.
srcChars
is not modified.
start | the offset where the insertion begins | |
srcChars | the source for the new characters | |
srcLength | the number of Unicode characters in srcChars. |
UnicodeString & UnicodeString::insert | ( | int32_t | start, | |
const UChar * | srcChars, | |||
int32_t | srcStart, | |||
int32_t | srcLength | |||
) | [inline] |
Insert the characters in srcChars
in the range [srcStart
, srcStart + srcLength
) into the UnicodeString object at offset start
.
srcChars
is not modified.
start | the offset at which the insertion begins | |
srcChars | the source for the new characters | |
srcStart | the offset into srcChars where new characters will be obtained | |
srcLength | the number of characters in srcChars in the insert string |
UnicodeString & UnicodeString::insert | ( | int32_t | start, | |
const UnicodeString & | srcText | |||
) | [inline] |
Insert the characters in srcText
into the UnicodeString object at offset start
.
srcText
is not modified.
start | the offset where the insertion begins | |
srcText | the source for the new characters |
Definition at line 4148 of file unistr.h.
References length().
UnicodeString & UnicodeString::insert | ( | int32_t | start, | |
const UnicodeString & | srcText, | |||
int32_t | srcStart, | |||
int32_t | srcLength | |||
) | [inline] |
Insert the characters in srcText
in the range [srcStart
, srcStart + srcLength
) into the UnicodeString object at offset start
.
srcText
is not modified.
start | the offset where the insertion begins | |
srcText | the source for the new characters | |
srcStart | the offset into srcText where new characters will be obtained | |
srcLength | the number of characters in srcText in the insert string |
UBool UnicodeString::isBogus | ( | void | ) | const [inline] |
Determine if this object contains a valid string.
A bogus string has no value. It is different from an empty string. It can be used to indicate that no string value is available. getBuffer() and getTerminatedBuffer() return NULL, and length() returns 0.
Definition at line 3322 of file unistr.h.
Referenced by indexOf(), lastIndexOf(), operator==(), remove(), and truncate().
UBool UnicodeString::isEmpty | ( | void | ) | const [inline] |
int32_t UnicodeString::lastIndexOf | ( | UChar32 | c, | |
int32_t | start, | |||
int32_t | length | |||
) | const [inline] |
Locate in this the last occurrence of the code point c
in the range [start
, start + length
), using bitwise comparison.
c | The code point to search for. | |
start | the offset into this at which to start matching | |
length | the number of characters in this to search |
c
, or -1 if not found. int32_t UnicodeString::lastIndexOf | ( | UChar | c, | |
int32_t | start, | |||
int32_t | length | |||
) | const [inline] |
Locate in this the last occurrence of the BMP code point c
in the range [start
, start + length
), using bitwise comparison.
c | The code unit to search for. | |
start | the offset into this at which to start matching | |
length | the number of characters in this to search |
c
, or -1 if not found. int32_t UnicodeString::lastIndexOf | ( | UChar32 | c, | |
int32_t | start | |||
) | const [inline] |
Locate in this the last occurrence of the code point c
starting at offset start
, using bitwise comparison.
c | The code point to search for. | |
start | The offset at which searching will start. |
c
, or -1 if not found. Definition at line 3741 of file unistr.h.
References lastIndexOf(), and length().
int32_t UnicodeString::lastIndexOf | ( | UChar | c, | |
int32_t | start | |||
) | const [inline] |
Locate in this the last occurrence of the BMP code point c
starting at offset start
, using bitwise comparison.
c | The code unit to search for. | |
start | The offset at which searching will start. |
c
, or -1 if not found. Definition at line 3734 of file unistr.h.
References length().
int32_t UnicodeString::lastIndexOf | ( | UChar32 | c | ) | const [inline] |
Locate in this the last occurrence of the code point c
, using bitwise comparison.
c | The code point to search for. |
c
, or -1 if not found. Definition at line 3729 of file unistr.h.
References lastIndexOf(), and length().
int32_t UnicodeString::lastIndexOf | ( | UChar | c | ) | const [inline] |
int32_t UnicodeString::lastIndexOf | ( | const UChar * | 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
in the range [srcStart
, srcStart + srcLength
), using bitwise comparison.
srcChars | The text to search for. | |
srcStart | the offset into srcChars at which to start matching | |
srcLength | the number of characters in srcChars to match | |
start | the offset into this at which to start matching | |
length | the number of characters in this to search |
text
, or -1 if not found. int32_t UnicodeString::lastIndexOf | ( | const UChar * | srcChars, | |
int32_t | srcLength, | |||
int32_t | start, | |||
int32_t | length | |||
) | const [inline] |
Locate in this the last occurrence in the range [start
, start + length
) of the characters in srcChars
, using bitwise comparison.
srcChars | The text to search for. | |
srcLength | the number of characters in srcChars | |
start | The offset at which searching will start. | |
length | The number of characters to search |
srcChars
, or -1 if not found. Definition at line 3664 of file unistr.h.
References lastIndexOf().
int32_t UnicodeString::lastIndexOf | ( | const UChar * | srcChars, | |
int32_t | srcLength, | |||
int32_t | start | |||
) | const [inline] |
Locate in this the last occurrence of the characters in srcChars
starting at offset start
, using bitwise comparison.
srcChars | The text to search for. | |
srcLength | the number of characters in srcChars to match | |
start | the offset into this at which to start matching |
text
, or -1 if not found. Definition at line 3671 of file unistr.h.
References lastIndexOf(), and length().
int32_t UnicodeString::lastIndexOf | ( | const UnicodeString & | srcText, | |
int32_t | srcStart, | |||
int32_t | srcLength, | |||
int32_t | start, | |||
int32_t | length | |||
) | const [inline] |
Locate in this the last occurrence in the range [start
, start + length
) of the characters in srcText
in the range [srcStart
, srcStart + srcLength
), using bitwise comparison.
srcText | The text to search for. | |
srcStart | the offset into srcText at which to start matching | |
srcLength | the number of characters in srcText to match | |
start | the offset into this at which to start matching | |
length | the number of characters in this to search |
text
, or -1 if not found. Definition at line 3679 of file unistr.h.
References getArrayStart(), isBogus(), lastIndexOf(), and pinIndices().
int32_t UnicodeString::lastIndexOf | ( | const UnicodeString & | text, | |
int32_t | start, | |||
int32_t | length | |||
) | const [inline] |
Locate in this the last occurrence in the range [start
, start + length
) of the characters in text
, using bitwise comparison.
text | The text to search for. | |
start | The offset at which searching will start. | |
length | The number of characters to search |
text
, or -1 if not found. Definition at line 3695 of file unistr.h.
References lastIndexOf(), and length().
int32_t UnicodeString::lastIndexOf | ( | const UnicodeString & | text, | |
int32_t | start | |||
) | const [inline] |
Locate in this the last occurrence of the characters in text
starting at offset start
, using bitwise comparison.
text | The text to search for. | |
start | The offset at which searching will start. |
text
, or -1 if not found. Definition at line 3701 of file unistr.h.
References lastIndexOf(), and length().
int32_t UnicodeString::lastIndexOf | ( | const UnicodeString & | text | ) | const [inline] |
Locate in this the last occurrence of the characters in text
, using bitwise comparison.
text | The text to search for. |
text
, or -1 if not found. Definition at line 3708 of file unistr.h.
References length().
Referenced by lastIndexOf().
int32_t UnicodeString::length | ( | void | ) | const [inline] |
Return the length of the UnicodeString object.
The length is the number of UChar code units are in the UnicodeString. If you want the number of code points, please use countChar32().
Reimplemented from Replaceable.
Definition at line 3310 of file unistr.h.
Referenced by append(), caseCompare(), char32At(), compare(), Normalizer::compare(), compareCodePointOrder(), endsWith(), findAndReplace(), getChar32Limit(), getChar32Start(), getTerminatedBuffer(), indexOf(), insert(), Normalizer::isNormalized(), lastIndexOf(), operator+=(), operator<(), operator<=(), operator=(), operator==(), operator>(), operator>=(), Normalizer::quickCheck(), replace(), replaceBetween(), reverse(), Transliterator::setID(), setTo(), startsWith(), and truncate().
int32_t UnicodeString::moveIndex32 | ( | int32_t | index, | |
int32_t | delta | |||
) | const |
Move the code unit index along the string by delta code points.
Interpret the input index as a code unit-based offset into the string, move the index forward or backward by delta code points, and return the resulting index. The input index should point to the first code unit of a code point, if there is more than one.
Both input and output indexes are code unit-based as for all string indexes/offsets in ICU (and other libraries, like MBCS char*). If delta<0 then the index is moved backward (toward the start of the string). If delta>0 then the index is moved forward (toward the end of the string).
This behaves like CharacterIterator::move32(delta, kCurrent).
Behavior for out-of-bounds indexes: moveIndex32
pins the input index to 0..length(), i.e., if the input index<0 then it is pinned to 0; if it is index>length() then it is pinned to length(). Afterwards, the index is moved by delta
code points forward or backward, but no further backward than to 0 and no further forward than to length(). The resulting index return value will be in between 0 and length(), inclusively.
Examples:
// s has code points 'a' U+10000 'b' U+10ffff U+2029 UnicodeString s=UNICODE_STRING("a\\U00010000b\\U0010ffff\\u2029", 31).unescape();
// initial index: position of U+10000 int32_t index=1;
// the following examples will all result in index==4, position of U+10ffff
// skip 2 code points from some position in the string index=s.moveIndex32(index, 2); // skips U+10000 and 'b'
// go to the 3rd code point from the start of s (0-based) index=s.moveIndex32(0, 3); // skips 'a', U+10000, and 'b'
// go to the next-to-last code point of s index=s.moveIndex32(s.length(), -2); // backward-skips U+2029 and U+10ffff
index | input code unit index | |
delta | (signed) code point count to move the index forward or backward in the string |
UBool UnicodeString::operator!= | ( | const UnicodeString & | text | ) | const [inline] |
Inequality operator.
Performs only bitwise comparison.
text | The UnicodeString to compare to this one. |
text
contains the same characters as this one, TRUE otherwise. UnicodeString & UnicodeString::operator+= | ( | const UnicodeString & | srcText | ) | [inline] |
Append operator.
Append the characters in srcText
to the UnicodeString object at offset start
. srcText
is not modified.
srcText | the source for the new characters |
Definition at line 4137 of file unistr.h.
References length().
UnicodeString & UnicodeString::operator+= | ( | UChar32 | ch | ) | [inline] |
Append operator.
Append the code point ch
to the UnicodeString object.
ch | the code point to be appended |
Definition at line 4132 of file unistr.h.
References append().
UnicodeString & UnicodeString::operator+= | ( | UChar | ch | ) | [inline] |
Append operator.
Append the code unit ch
to the UnicodeString object.
ch | the code unit to be appended |
Definition at line 4128 of file unistr.h.
References length().
UBool UnicodeString::operator< | ( | const UnicodeString & | text | ) | const [inline] |
Less than operator.
Performs only bitwise comparison.
text | The UnicodeString to compare to this one. |
text
, FALSE otherwise Definition at line 3389 of file unistr.h.
References length().
UBool UnicodeString::operator<= | ( | const UnicodeString & | text | ) | const [inline] |
Less than or equal operator.
Performs only bitwise comparison.
text | The UnicodeString to compare to this one. |
text
, FALSE otherwise Definition at line 3397 of file unistr.h.
References length().
UnicodeString & UnicodeString::operator= | ( | UChar32 | ch | ) | [inline] |
UnicodeString & UnicodeString::operator= | ( | UChar | ch | ) | [inline] |
Assignment operator.
Replace the characters in this UnicodeString with the code unit ch
.
ch | the code unit to replace |
Definition at line 4039 of file unistr.h.
References length().
UnicodeString& UnicodeString::operator= | ( | const UnicodeString & | srcText | ) |
Assignment operator.
Replace the characters in this UnicodeString with the characters from srcText
.
srcText | The text containing the characters to replace |
UBool UnicodeString::operator== | ( | const UnicodeString & | text | ) | const [inline] |
UBool UnicodeString::operator> | ( | const UnicodeString & | text | ) | const [inline] |
Greater than operator.
Performs only bitwise comparison.
text | The UnicodeString to compare to this one. |
text
, FALSE otherwise Definition at line 3385 of file unistr.h.
References length().
UBool UnicodeString::operator>= | ( | const UnicodeString & | text | ) | const [inline] |
Greater than or equal operator.
Performs only bitwise comparison.
text | The UnicodeString to compare to this one. |
text
, FALSE otherwise Definition at line 3393 of file unistr.h.
References length().
UChar UnicodeString::operator[] | ( | int32_t | offset | ) | const [inline] |
UBool UnicodeString::padLeading | ( | int32_t | targetLength, | |
UChar | padChar = 0x0020 | |||
) |
Pad the start of this UnicodeString with the character padChar
.
If the length of this UnicodeString is less than targetLength, length() - targetLength copies of padChar will be added to the beginning of this UnicodeString.
targetLength | the desired length of the string | |
padChar | the character to use for padding. Defaults to space (U+0020) |
UBool UnicodeString::padTrailing | ( | int32_t | targetLength, | |
UChar | padChar = 0x0020 | |||
) |
Pad the end of this UnicodeString with the character padChar
.
If the length of this UnicodeString is less than targetLength, length() - targetLength copies of padChar will be added to the end of this UnicodeString.
targetLength | the desired length of the string | |
padChar | the character to use for padding. Defaults to space (U+0020) |
void UnicodeString::releaseBuffer | ( | int32_t | newLength = -1 |
) |
Release a read/write buffer on a UnicodeString object with an "open" getBuffer(minCapacity).
This function must be called in a matched pair with getBuffer(minCapacity). releaseBuffer(newLength) must be called if and only if a getBuffer(minCapacity) is "open".
It will set the string length to newLength, at most to the current capacity. If newLength==-1 then it will set the length according to the first NUL in the buffer, or to the capacity if there is no NUL.
After calling releaseBuffer(newLength) the UnicodeString is back to normal operation.
newLength | the new length of the UnicodeString object; defaults to the current capacity if newLength is greater than that; if newLength==-1, it defaults to u_strlen(buffer) but not more than the current capacity of the string |
UnicodeString & UnicodeString::remove | ( | int32_t | start, | |
int32_t | length = (int32_t)INT32_MAX | |||
) | [inline] |
Remove the characters in the range [start
, start + length
) from the UnicodeString object.
start | the offset of the first character to remove | |
length | the number of characters to remove |
UnicodeString & UnicodeString::remove | ( | void | ) | [inline] |
Remove all characters from the UnicodeString object.
Definition at line 4177 of file unistr.h.
References isBogus().
UnicodeString & UnicodeString::removeBetween | ( | int32_t | start, | |
int32_t | limit = (int32_t)INT32_MAX | |||
) | [inline] |
Remove the characters in the range [start
, limit
) from the UnicodeString object.
start | the offset of the first character to remove | |
limit | the offset immediately following the range to remove |
Definition at line 4200 of file unistr.h.
References NULL.
UnicodeString & UnicodeString::replace | ( | int32_t | start, | |
int32_t | length, | |||
UChar32 | srcChar | |||
) | [inline] |
Replace the characters in the range [start
, start + length
) with the code point srcChar
.
start | the offset at which the replace operation begins | |
length | the number of characters to replace. The character at start + length is not modified. | |
srcChar | the new code point |
Definition at line 3842 of file unistr.h.
References FALSE, U16_APPEND, and U16_MAX_LENGTH.
UnicodeString & UnicodeString::replace | ( | int32_t | start, | |
int32_t | length, | |||
UChar | srcChar | |||
) | [inline] |
Replace the characters in the range [start
, start + length
) with the code unit srcChar
.
start | the offset at which the replace operation begins | |
length | the number of characters to replace. The character at start + length is not modified. | |
srcChar | the new code unit |
UnicodeString & UnicodeString::replace | ( | int32_t | start, | |
int32_t | length, | |||
const UChar * | srcChars, | |||
int32_t | srcLength | |||
) | [inline] |
Replace the characters in the range [start
, start + length
) with the characters in srcChars
.
srcChars
is not modified.
start | the offset at which the replace operation begins | |
length | number of characters to replace. The character at start + length is not modified. | |
srcChars | the source for the new characters | |
srcLength | the number of Unicode characters in srcChars |
UnicodeString & UnicodeString::replace | ( | int32_t | start, | |
int32_t | length, | |||
const UChar * | srcChars, | |||
int32_t | srcStart, | |||
int32_t | srcLength | |||
) | [inline] |
Replace the characters in the range [start
, start + length
) with the characters in srcChars
in the range [srcStart
, srcStart + srcLength
).
srcChars
is not modified.
start | the offset at which the replace operation begins | |
length | the number of characters to replace. The character at start + length is not modified. | |
srcChars | the source for the new characters | |
srcStart | the offset into srcChars where new characters will be obtained | |
srcLength | the number of characters in srcChars in the replace string |
UnicodeString & UnicodeString::replace | ( | int32_t | start, | |
int32_t | length, | |||
const UnicodeString & | srcText | |||
) | [inline] |
Replace the characters in the range [start
, start + length
) with the characters in srcText
.
srcText
is not modified.
start | the offset at which the replace operation begins | |
length | the number of characters to replace. The character at start + length is not modified. | |
srcText | the source for the new characters |
Definition at line 3807 of file unistr.h.
References length().
UnicodeString & UnicodeString::replace | ( | int32_t | start, | |
int32_t | length, | |||
const UnicodeString & | srcText, | |||
int32_t | srcStart, | |||
int32_t | srcLength | |||
) | [inline] |
Replace the characters in the range [start
, start + length
) with the characters in srcText
in the range [srcStart
, srcStart + srcLength
).
srcText
is not modified.
start | the offset at which the replace operation begins | |
length | the number of characters to replace. The character at start + length is not modified. | |
srcText | the source for the new characters | |
srcStart | the offset into srcText where new characters will be obtained | |
srcLength | the number of characters in srcText in the replace string |
Definition at line 3813 of file unistr.h.
Referenced by insert(), operator=(), and setTo().
UnicodeString & UnicodeString::replaceBetween | ( | int32_t | start, | |
int32_t | limit, | |||
const UnicodeString & | srcText, | |||
int32_t | srcStart, | |||
int32_t | srcLimit | |||
) | [inline] |
Replace the characters in the range [start
, limit
) with the characters in srcText
in the range [srcStart
, srcLimit
).
srcText
is not modified.
start | the offset at which the replace operation begins | |
limit | the offset immediately following the replace range | |
srcText | the source for the new characters | |
srcStart | the offset into srcChars where new characters will be obtained | |
srcLimit | the offset immediately following the range to copy in srcText |
UnicodeString & UnicodeString::replaceBetween | ( | int32_t | start, | |
int32_t | limit, | |||
const UnicodeString & | srcText | |||
) | [inline] |
Replace the characters in the range [start
, limit
) with the characters in srcText
.
srcText
is not modified.
start | the offset at which the replace operation begins | |
limit | the offset immediately following the replace range | |
srcText | the source for the new characters |
Definition at line 3853 of file unistr.h.
References length().
UnicodeString & UnicodeString::reverse | ( | int32_t | start, | |
int32_t | length | |||
) | [inline] |
Reverse the range [start
, start + length
) in this UnicodeString.
start | the start of the range to reverse | |
length | the number of characters to to reverse |
UnicodeString & UnicodeString::reverse | ( | void | ) | [inline] |
Reverse this UnicodeString in place.
Definition at line 4220 of file unistr.h.
References length().
UnicodeString& UnicodeString::setCharAt | ( | int32_t | offset, | |
UChar | ch | |||
) |
Set the character at the specified offset to the specified character.
offset | A valid offset into the text of the character to set | |
ch | The new character |
UnicodeString& UnicodeString::setTo | ( | UChar * | buffer, | |
int32_t | buffLength, | |||
int32_t | buffCapacity | |||
) |
Aliasing setTo() function, analogous to the writable-aliasing UChar* constructor.
The text will be used for the UnicodeString object, but it will not be released when the UnicodeString is destroyed. This has write-through semantics: For as long as the capacity of the buffer is sufficient, write operations will directly affect the buffer. When more capacity is necessary, then a new buffer will be allocated and the contents copied as with regularly constructed strings. In an assignment to another UnicodeString, the buffer will be copied. The extract(UChar *dst) function detects whether the dst pointer is the same as the string buffer itself and will in this case not copy the contents.
buffer | The characters to alias for the UnicodeString. | |
buffLength | The number of Unicode characters in buffer to alias. | |
buffCapacity | The size of buffer in UChars. |
UnicodeString& UnicodeString::setTo | ( | UBool | isTerminated, | |
const UChar * | text, | |||
int32_t | textLength | |||
) |
Aliasing setTo() function, analogous to the readonly-aliasing UChar* constructor.
The text will be used for the UnicodeString object, but it will not be released when the UnicodeString is destroyed. This has copy-on-write semantics: When the string is modified, then the buffer is first copied into newly allocated memory. The aliased buffer is never modified. In an assignment to another UnicodeString, the text will be aliased again, so that both strings then alias the same readonly-text.
isTerminated | specifies if text is NUL -terminated. This must be true if textLength==-1 . | |
text | The characters to alias for the UnicodeString. | |
textLength | The number of Unicode characters in text to alias. If -1, then this constructor will determine the length by calling u_strlen() . |
UnicodeString & UnicodeString::setTo | ( | UChar32 | srcChar | ) | [inline] |
UnicodeString & UnicodeString::setTo | ( | UChar | srcChar | ) | [inline] |
Set the characters in the UnicodeString object to the code unit srcChar
.
srcChar | the code unit which becomes the UnicodeString's character content |
Definition at line 4080 of file unistr.h.
References length().
UnicodeString & UnicodeString::setTo | ( | const UChar * | srcChars, | |
int32_t | srcLength | |||
) | [inline] |
Set the characters in the UnicodeString object to the characters in srcChars
.
srcChars
is not modified.
srcChars | the source for the new characters | |
srcLength | the number of Unicode characters in srcChars. |
Definition at line 4072 of file unistr.h.
References length().
UnicodeString & UnicodeString::setTo | ( | const UnicodeString & | srcText | ) | [inline] |
Set the text in the UnicodeString object to the characters in srcText
.
srcText
is not modified.
srcText | the source for the new characters |
Definition at line 4065 of file unistr.h.
References length().
UnicodeString & UnicodeString::setTo | ( | const UnicodeString & | srcText, | |
int32_t | srcStart, | |||
int32_t | srcLength | |||
) | [inline] |
Set the text in the UnicodeString object to the characters in srcText
in the range [srcStart
, srcStart + srcLength
).
srcText
is not modified.
srcText | the source for the new characters | |
srcStart | the offset into srcText where new characters will be obtained | |
srcLength | the number of characters in srcText in the replace string. |
Definition at line 4047 of file unistr.h.
References length().
UnicodeString & UnicodeString::setTo | ( | const UnicodeString & | srcText, | |
int32_t | srcStart | |||
) | [inline] |
Set the text in the UnicodeString object to the characters in srcText
in the range [srcStart
, srcText.length()
).
srcText
is not modified.
srcText | the source for the new characters | |
srcStart | the offset into srcText where new characters will be obtained |
Definition at line 4056 of file unistr.h.
References length(), and pinIndex().
void UnicodeString::setToBogus | ( | ) |
Make this UnicodeString object invalid.
The string will test TRUE with isBogus().
A bogus string has no value. It is different from an empty string. It can be used to indicate that no string value is available. getBuffer() and getTerminatedBuffer() return NULL, and length() returns 0.
This utility function is used throughout the UnicodeString implementation to indicate that a UnicodeString operation failed, and may be used in other functions, especially but not exclusively when such functions do not take a UErrorCode for simplicity.
The following methods, and no others, will clear a string object's bogus flag:
The simplest ways to turn a bogus string into an empty one is to use the remove() function. Examples for other functions that are equivalent to "set to empty string":
if(s.isBogus()) { s.remove(); // set to an empty string (remove all), or s.remove(0, INT32_MAX); // set to an empty string (remove all), or s.truncate(0); // set to an empty string (complete truncation), or s=UnicodeString(); // assign an empty string, or s.setTo((UChar32)-1); // set to a pseudo code point that is out of range, or static const UChar nul=0; s.setTo(&nul, 0); // set to an empty C Unicode string }
UBool UnicodeString::startsWith | ( | const UChar * | srcChars, | |
int32_t | srcStart, | |||
int32_t | srcLength | |||
) | const [inline] |
Determine if this ends with the characters in srcChars
in the range [srcStart
, srcStart + srcLength
).
srcChars | The characters to match. | |
srcStart | the offset into srcText to start matching | |
srcLength | the number of characters in srcChars to match |
srcChars
, FALSE otherwise UBool UnicodeString::startsWith | ( | const UChar * | srcChars, | |
int32_t | srcLength | |||
) | const [inline] |
UBool UnicodeString::startsWith | ( | const UnicodeString & | srcText, | |
int32_t | srcStart, | |||
int32_t | srcLength | |||
) | const [inline] |
Determine if this starts with the characters in srcText
in the range [srcStart
, srcStart + srcLength
).
srcText | The text to match. | |
srcStart | the offset into srcText to start matching | |
srcLength | the number of characters in srcText to match |
text
, FALSE otherwise UBool UnicodeString::startsWith | ( | const UnicodeString & | text | ) | const [inline] |
UnicodeString& UnicodeString::toLower | ( | const Locale & | locale | ) |
Convert the characters in this to lower case following the conventions of a specific locale.
locale | The locale containing the conventions to use. |
UnicodeString& UnicodeString::toLower | ( | void | ) |
Convert the characters in this to lower case following the conventions of the default locale.
UnicodeString& UnicodeString::toTitle | ( | BreakIterator * | titleIter, | |
const Locale & | locale, | |||
uint32_t | options | |||
) |
Titlecase this string, with options.
Casing is locale-dependent and context-sensitive. Titlecasing uses a break iterator to find the first characters of words that are to be titlecased. It titlecases those characters and lowercases all others. (This can be modified with options.)
The titlecase break iterator can be provided to customize for arbitrary styles, using rules and dictionaries beyond the standard iterators. It may be more efficient to always provide an iterator to avoid opening and closing one for each string. The standard titlecase iterator for the root locale implements the algorithm of Unicode TR 21.
This function uses only the setText(), first() and next() methods of the provided break iterator.
titleIter | A break iterator to find the first characters of words that are to be titlecased. If none is provided (0), then a standard titlecase break iterator is opened. Otherwise the provided iterator is set to the string's text. | |
locale | The locale to consider. | |
options | Options bit set, see ucasemap_open(). |
UnicodeString& UnicodeString::toTitle | ( | BreakIterator * | titleIter, | |
const Locale & | locale | |||
) |
Titlecase this string.
Casing is locale-dependent and context-sensitive. Titlecasing uses a break iterator to find the first characters of words that are to be titlecased. It titlecases those characters and lowercases all others.
The titlecase break iterator can be provided to customize for arbitrary styles, using rules and dictionaries beyond the standard iterators. It may be more efficient to always provide an iterator to avoid opening and closing one for each string. The standard titlecase iterator for the root locale implements the algorithm of Unicode TR 21.
This function uses only the setText(), first() and next() methods of the provided break iterator.
titleIter | A break iterator to find the first characters of words that are to be titlecased. If none is provided (0), then a standard titlecase break iterator is opened. Otherwise the provided iterator is set to the string's text. | |
locale | The locale to consider. |
UnicodeString& UnicodeString::toTitle | ( | BreakIterator * | titleIter | ) |
Titlecase this string, convenience function using the default locale.
Casing is locale-dependent and context-sensitive. Titlecasing uses a break iterator to find the first characters of words that are to be titlecased. It titlecases those characters and lowercases all others.
The titlecase break iterator can be provided to customize for arbitrary styles, using rules and dictionaries beyond the standard iterators. It may be more efficient to always provide an iterator to avoid opening and closing one for each string. The standard titlecase iterator for the root locale implements the algorithm of Unicode TR 21.
This function uses only the setText(), first() and next() methods of the provided break iterator.
titleIter | A break iterator to find the first characters of words that are to be titlecased. If none is provided (0), then a standard titlecase break iterator is opened. Otherwise the provided iterator is set to the string's text. |
UnicodeString& UnicodeString::toUpper | ( | const Locale & | locale | ) |
Convert the characters in this to UPPER CASE following the conventions of a specific locale.
locale | The locale containing the conventions to use. |
UnicodeString& UnicodeString::toUpper | ( | void | ) |
Convert the characters in this to UPPER CASE following the conventions of the default locale.
UnicodeString& UnicodeString::trim | ( | void | ) |
Trims leading and trailing whitespace from this UnicodeString.
UBool UnicodeString::truncate | ( | int32_t | targetLength | ) | [inline] |
Truncate this UnicodeString to the targetLength
.
targetLength | the desired length of this UnicodeString. |
Definition at line 4205 of file unistr.h.
References FALSE, isBogus(), length(), and TRUE.
Referenced by Transliterator::setID().
UnicodeString UnicodeString::unescape | ( | ) | const |
Unescape a string of characters and return a string containing the result.
The following escape sequences are recognized:
\uhhhh 4 hex digits; h in [0-9A-Fa-f] \Uhhhhhhhh 8 hex digits \xhh 1-2 hex digits \ooo 1-3 octal digits; o in [0-7] \cX control-X; X is masked with 0x1F
as well as the standard ANSI C escapes:
\a => U+0007, \b => U+0008, \t => U+0009, \n => U+000A, \v => U+000B, \f => U+000C, \r => U+000D, \e => U+001B, \" => U+0022, \' => U+0027, \? => U+003F, \\ => U+005C
Anything else following a backslash is generically escaped. For example, "[a\\-z]" returns "[a-z]".
If an escape sequence is ill-formed, this method returns an empty string. An example of an ill-formed sequence is "\\u" followed by fewer than 4 hex digits.
This function is similar to u_unescape() but not identical to it. The latter takes a source char*, so it does escape recognition and also invariant conversion.
UChar32 UnicodeString::unescapeAt | ( | int32_t & | offset | ) | const |
Unescape a single escape sequence and return the represented character.
See unescape() for a listing of the recognized escape sequences. The character at offset-1 is assumed (without checking) to be a backslash. If the escape sequence is ill-formed, or the offset is out of range, (UChar32)0xFFFFFFFF is returned.
offset | an input output parameter. On input, it is the offset into this string where the escape sequence is located, after the initial backslash. On output, it is advanced after the last character parsed. On error, it is not advanced at all. |