#include <unicodeutils.h>
This class handles unicode decompositions and correct string comparison using decomposition informations.
Public Types | |
using | DecompositionArray = BaseArray< Utf32Char, 1, BASEARRAYFLAGS::MOVEANDCOPYOBJECTS, FixedBufferAllocator< Utf32Char, 8, DefaultAllocator > > |
using | DecompositionHfsArray = BaseArray< Utf16Char, 1, BASEARRAYFLAGS::MOVEANDCOPYOBJECTS, FixedBufferAllocator< Utf16Char, 8, DefaultAllocator > > |
Static Public Member Functions | |
static MAXON_METHOD Result< String > | DecomposeStringHfs (const String &str) |
static MAXON_METHOD Result< String > | DecomposeString (const String &str) |
static MAXON_METHOD String | GetUnicodeVersion () |
static MAXON_METHOD Result< String > | NormalizeString (NORMALIZATION form, const String &str) |
static MAXON_METHOD Bool | UniCharDecomposition (Utf32Char chr, DecompositionArray &res_decomp) |
static MAXON_METHOD Bool | UniCharHfsDecomposition (Utf16Char chr, DecompositionHfsArray &res_decomp) |
static MAXON_METHOD COMPARERESULT | UniCodeCompare (Utf32Char a, Utf32Char b) |
static MAXON_METHOD CHARACTERTYPE | GetCharacterType (Utf32Char chr) |
static MAXON_METHOD Utf32Char | UpperCase (Utf32Char chr) |
static MAXON_METHOD Utf32Char | TitleCase (Utf32Char chr) |
static MAXON_METHOD Utf32Char | LowerCase (Utf32Char chr) |
Private Member Functions | |
MAXON_INTERFACE_NONVIRTUAL (UnicodeUtils, MAXON_REFERENCE_NONE, "net.maxon.interface.unicodeutils") | |
using DecompositionArray = BaseArray<Utf32Char, 1, BASEARRAYFLAGS::MOVEANDCOPYOBJECTS, FixedBufferAllocator<Utf32Char, 8, DefaultAllocator> > |
Decomposed representation of a unicode character.
using DecompositionHfsArray = BaseArray<Utf16Char, 1, BASEARRAYFLAGS::MOVEANDCOPYOBJECTS, FixedBufferAllocator<Utf16Char, 8, DefaultAllocator> > |
|
private |
|
static |
Normalize a string to HFS+ decomposition.
|
static |
Normalize a string to HFS+ decomposition.
|
static |
Returns the version of Unicode database used internally.
|
static |
Normalize a string.
|
static |
Breaks a unicode character into the decomposited properties. This is e.g. useful for sorting algorithms. A german 'A' umlaut will be decomposed to 'A' and '..'
[in] | chr | Unicode character to be decomposited. |
[out] | res_decomp | Array with the decomposited character elements. |
|
static |
Breaks a unicode character into the decomposited properties. This is e.g. useful for sorting algorithms. A german 'A' umlaut will be decomposed to 'A' and '..'
[in] | chr | Unicode character to be decomposited. |
[out] | res_decomp | Array with the decomposited character elements. |
|
static |
Compares two unicode characters. this function uses the decomposition properties to do advanced unicode sorting.
[in] | a | First character to compare. |
[in] | b | Second character to compare. |
|
static |
Returns the type of a given unicode char. This can be used to determine if a character is a letter, number or symbol
[in] | chr | Character to find. |
|
static |
Returns the uppercase of a given unicode char.
[in] | chr | Character to convert to uppercase. |
|
static |
Returns the titlecase version of a given unicode char.
[in] | chr | Character to convert to titlecase. |
|
static |
Returns the lowercase version of a given unicode char.
[in] | chr | Character to convert to lowercase. |