bool IsUtf8Lead(int c)

Tests whether c is lead UTF-8 byte.

dword FetchUtf8(const char *&s, const char *lim, bool& ok)

dword FetchUtf8(const char *&s, const char *lim)

Reads a single UTF-32 codepoint from UTF-8 string s with end at lim. s must be less than lim. s is advanced accordingly. ok is set to false if UTF-8 is invalid - in that case, error-escape of single byte is returned (but it is NOT set to true if valid UTF-8 character is read).

bool CheckUtf8(const char *s, int len)

bool CheckUtf8(const char *s)

bool CheckUtf8(const String& src)

Checks whether string contains a valid UTF-8 sequence. If source is specified as pointer s without len, its must be zero-terminated.

int Utf8Len(const dword *s, int len)

int Utf8Len(const dword *s)

int Utf8Len(const Vector<dword>& s)

Returns the size in bytes of UTF-32 Unicode text in UTF-8. If source is specified as pointer s without len, its must be zero-terminated.

int Utf8Len(const wchar *s, int len)

int Utf8Len(const wchar *s)

int Utf8Len(const WString& s)

Returns the size in bytes of UTF-16 Unicode text in UTF-8. If source is specified as pointer s without len, its must be zero-terminated.

int Utf8Len(dword code)

Returns the size in bytes of single codepoint in UTF-8.

void ToUtf8(char *t, const wchar *s, int len)

String ToUtf8(const wchar *s, int len)

String ToUtf8(const wchar *s)

String ToUtf8(const WString& s)

UTF-16 to UTF-8 conversion. If target is specified as pointer to buffer t, the buffer must contain enough space for the output. If source is specified as pointer s without len, its must be zero-terminated.

void ToUtf8(char *t, const dword *s, int len)

String ToUtf8(const dword *s, int len)

String ToUtf8(const dword *s)

String ToUtf8(const Vector<dword>& s)

UTF-32 to UTF-8 conversion. If target is specified as pointer to buffer t, the buffer must contain enough space for the output. If source is specified as pointer s without len, its must be zero-terminated.

String ToUtf8(dword code)

Converts single codepoint to UTF-8.

int Utf16Len(const dword *s, int len)

int Utf16Len(const dword *s)

int Utf16Len(const Vector<dword>& s)

Returns the size in wchars of UTF-32 Unicode text in UTF-16. If source is specified as pointer s without len, its must be zero-terminated.

int Utf16Len(dword code)

Returns the size in wchars of single codepoint in UTF-16.

int Utf16Len(const char *s, int len)

int Utf16Len(const char *s)

int Utf16Len(const String& s)

Returns the size in wchars of UTF-8 Unicode text in UTF-16. If source is specified as pointer s without len, its must be zero-terminated.

void ToUtf16(wchar *t, const dword *s, int len)

WString ToUtf16(const dword *s, int len)

WString ToUtf16(const dword *s)

WString ToUtf16(const Vector<dword>& s)

UTF-32 to UTF-16 conversion. If target is specified as pointer to buffer t, the buffer must contain enough space for the output. If source is specified as pointer s without len, its must be zero-terminated.

WString ToUtf16(dword code)

Converts single codepoint to UTF-16.

void ToUtf16(wchar *t, const char *s, int len)

WString ToUtf16(const char *s, int len)

WString ToUtf16(const char *s)

WString ToUtf16(const String& s)

UTF-8 to UTF-16 conversion. If target is specified as pointer to buffer t, the buffer must contain enough space for the output. If source is specified as pointer s without len, its must be zero-terminated.

int Utf32Len(const wchar *s, int len)

int Utf32Len(const wchar *s)

int Utf32Len(const WString& s)

Returns the size in dwords of UTF-16 Unicode text in UTF-32. Note that this is the same as the number of Unicode codepoints in the text. If source is specified as pointer s without len, its must be zero-terminated.

int Utf32Len(const char *s, int len)

int Utf32Len(const char *s)

int Utf32Len(const String& s)

Returns the size in dwords of UTF-8 Unicode text in UTF-32. Note that this is the same as the number of Unicode codepoints in the text. If source is specified as pointer s without len, its must be zero-terminated.

dword ReadSurrogatePair(const wchar *s, const wchar *lim)

Reads single utf32 codepoint from s, lim. Returns 0 if there is no surrogate pair at s.

void ToUtf32(dword *t, const wchar *s, int len)

Vector<dword> ToUtf32(const wchar *s, int len)

Vector<dword> ToUtf32(const wchar *s)

Vector<dword> ToUtf32(const WString& s)

UTF-16 to UTF-32 conversion. If target is specified as pointer to buffer t, the buffer must contain enough space for the output. If source is specified as pointer s without len, its must be zero-terminated.

void ToUtf32(dword *t, const char *s, int len)

Vector<dword> ToUtf32(const char *s, int len)

Vector<dword> ToUtf32(const char *s)

Vector<dword> ToUtf32(const String& s)

UTF-8 to UTF-32 conversion. If target is specified as pointer to buffer t, the buffer must contain enough space for the output. If source is specified as pointer s without len, its must be zero-terminated.

int UnicodeDecompose(dword codepoint, dword t[MAX_DECOMPOSED], bool only_canonical)

Vector<dword> UnicodeDecompose(dword codepoint, bool only_canonical)

Returns UNICODE decomposition of given codepoint into base and combining characters. If only_canonical is true, only canonical decomposition is allowed.

dword UnicodeCompose(const dword *t, int count)

dword UnicodeCompose(const Vector<dword>& t)

Tries to compose multi-codepoint grapheme into single codepoint if it exists. If such codepoint does not exist, returns 0.

Do you want to contribute?