mirror of
https://github.com/ultimatepp/ultimatepp.git
synced 2026-07-11 22:03:01 -06:00
Core: Charset cleanup and docs
git-svn-id: svn://ultimatepp.org/upp/trunk@11142 f0d560ea-af0d-0410-9eb7-867de7ffcac7
This commit is contained in:
cxl
parent
4ce1932d1c
commit
3e7863cc83
4 changed files with 300 additions and 410 deletions
|
|
@ -2185,295 +2185,6 @@ void ConvertCharset(char *t, byte tcharset, const char *s, byte scharset, int n)
|
|||
}
|
||||
}
|
||||
|
||||
bool utf8check(const char *_s, int len)
|
||||
{
|
||||
const byte *s = (const byte *)_s;
|
||||
const byte *lim = s + len;
|
||||
int codePoint = 0;
|
||||
while(s < lim) {
|
||||
word code = (byte)*s++;
|
||||
if(code >= 0x80) {
|
||||
if(code < 0xC2)
|
||||
return false;
|
||||
else
|
||||
if(code < 0xE0) {
|
||||
if(s >= lim || *s < 0x80 || *s >= 0xc0)
|
||||
return false;
|
||||
codePoint = ((code - 0xC0) << 6) + *s - 0x80;
|
||||
if(codePoint < 0x80 || codePoint > 0x07FF)
|
||||
return false;
|
||||
s++;
|
||||
}
|
||||
else
|
||||
if(code < 0xF0) {
|
||||
if(s + 1 >= lim ||
|
||||
s[0] < 0x80 || s[0] >= 0xc0 ||
|
||||
s[1] < 0x80 || s[1] >= 0xc0)
|
||||
return false;
|
||||
codePoint = ((code - 0xE0) << 12) + ((s[0] - 0x80) << 6) + s[1] - 0x80;
|
||||
if(codePoint < 0x0800 || codePoint > 0xFFFF)
|
||||
return false;
|
||||
s += 2;
|
||||
}
|
||||
else
|
||||
if(code < 0xF5) {
|
||||
if(s + 2 >= lim ||
|
||||
s[0] < 0x80 || s[0] >= 0xc0 ||
|
||||
s[1] < 0x80 || s[1] >= 0xc0 ||
|
||||
s[2] < 0x80 || s[2] >= 0xc0)
|
||||
return false;
|
||||
codePoint = ((code - 0xf0) << 18) + ((s[0] - 0x80) << 12) +
|
||||
((s[1] - 0x80) << 6) + s[2] - 0x80;
|
||||
if(codePoint < 0x010000 || codePoint > 0x10FFFF)
|
||||
return false;
|
||||
s += 3;
|
||||
}
|
||||
else
|
||||
return false;
|
||||
}
|
||||
}
|
||||
return true;
|
||||
}
|
||||
|
||||
int utf8len(const char *_s, int _len)
|
||||
{
|
||||
const byte *s = (const byte *)_s;
|
||||
const byte *lim = s + _len;
|
||||
int len = 0;
|
||||
if(_len > 4)
|
||||
while(s < lim - 4) {
|
||||
word code = (byte)*s++;
|
||||
if(code < 0x80)
|
||||
len++;
|
||||
else
|
||||
if(code < 0xC2)
|
||||
len++;
|
||||
else
|
||||
if(code < 0xE0) {
|
||||
word c = ((code - 0xC0) << 6) + s[0] - 0x80;
|
||||
if(s[0] >= 0x80 && s[0] < 0xc0 && c >= 0x80 && c < 0x800)
|
||||
len++;
|
||||
else
|
||||
len += 2;
|
||||
s += 1;
|
||||
}
|
||||
else
|
||||
if(code < 0xF0) {
|
||||
word c = ((code - 0xE0) << 12) + ((s[0] - 0x80) << 6) + s[1] - 0x80;
|
||||
if(s[0] >= 0x80 && s[0] < 0xc0 && s[1] >= 0x80 && s[1] < 0xc0 && c >= 0x800
|
||||
&& !(c >= 0xEE00 && c <= 0xEEFF))
|
||||
len++;
|
||||
else
|
||||
len += 3;
|
||||
s += 2;
|
||||
}
|
||||
else
|
||||
len++;
|
||||
}
|
||||
while(s < lim) {
|
||||
word code = (byte)*s++;
|
||||
if(code < 0x80)
|
||||
len++;
|
||||
else
|
||||
if(code < 0xC2)
|
||||
len++;
|
||||
else
|
||||
if(code < 0xE0) {
|
||||
if(s > lim - 1) {
|
||||
len++;
|
||||
break;
|
||||
}
|
||||
word c = ((code - 0xC0) << 6) + s[0] - 0x80;
|
||||
if(s[0] >= 0x80 && s[0] < 0xc0 && c >= 0x80 && c < 0x800)
|
||||
len++;
|
||||
else
|
||||
len += 2;
|
||||
s += 1;
|
||||
}
|
||||
else
|
||||
if(code < 0xF0) {
|
||||
if(s > lim - 2) {
|
||||
len += 1 + (int)(lim - s);
|
||||
break;
|
||||
}
|
||||
word c = ((code - 0xE0) << 12) + ((s[0] - 0x80) << 6) + s[1] - 0x80;
|
||||
if(s[0] >= 0x80 && s[0] < 0xc0 && s[1] >= 0x80 && s[1] < 0xc0 && c >= 0x800
|
||||
&& !(c >= 0xEE00 && c <= 0xEEFF))
|
||||
len++;
|
||||
else
|
||||
len += 3;
|
||||
s += 2;
|
||||
}
|
||||
else
|
||||
len++;
|
||||
}
|
||||
return len;
|
||||
}
|
||||
|
||||
WString FromUtf8(const char *_s, int len)
|
||||
{
|
||||
const byte *s = (const byte *)_s;
|
||||
const byte *lim = s + len;
|
||||
int tlen = utf8len(_s, len);
|
||||
WStringBuffer result(tlen);
|
||||
wchar *t = result;
|
||||
if(len > 4)
|
||||
while(s < lim - 4) {
|
||||
word code = (byte)*s++;
|
||||
if(code < 0x80)
|
||||
*t++ = code;
|
||||
else
|
||||
if(code < 0xC2)
|
||||
*t++ = 0xEE00 + code;
|
||||
else
|
||||
if(code < 0xE0) {
|
||||
word c = ((code - 0xC0) << 6) + s[0] - 0x80;
|
||||
if(s[0] >= 0x80 && s[0] < 0xc0 && c >= 0x80 && c < 0x800)
|
||||
*t++ = c;
|
||||
else {
|
||||
*t++ = 0xEE00 + code;
|
||||
*t++ = 0xEE00 + s[0];
|
||||
}
|
||||
s += 1;
|
||||
}
|
||||
else
|
||||
if(code < 0xF0) {
|
||||
word c = ((code - 0xE0) << 12) + ((s[0] - 0x80) << 6) + s[1] - 0x80;
|
||||
if(s[0] >= 0x80 && s[0] < 0xc0 && s[1] >= 0x80 && s[1] < 0xc0 && c >= 0x800
|
||||
&& !(c >= 0xEE00 && c <= 0xEEFF))
|
||||
*t++ = c;
|
||||
else {
|
||||
*t++ = 0xEE00 + code;
|
||||
*t++ = 0xEE00 + s[0];
|
||||
*t++ = 0xEE00 + s[1];
|
||||
}
|
||||
s += 2;
|
||||
}
|
||||
else
|
||||
*t++ = 0xEE00 + code;
|
||||
}
|
||||
while(s < lim) {
|
||||
word code = (byte)*s++;
|
||||
if(code < 0x80)
|
||||
*t++ = code;
|
||||
else
|
||||
if(code < 0xC2)
|
||||
*t++ = 0xEE00 + code;
|
||||
else
|
||||
if(code < 0xE0) {
|
||||
if(s > lim - 1) {
|
||||
*t++ = 0xEE00 + code;
|
||||
break;
|
||||
}
|
||||
word c = ((code - 0xC0) << 6) + s[0] - 0x80;
|
||||
if(s[0] >= 0x80 && s[0] < 0xc0 && c >= 0x80 && c < 0x800)
|
||||
*t++ = c;
|
||||
else {
|
||||
*t++ = 0xEE00 + code;
|
||||
*t++ = 0xEE00 + s[0];
|
||||
}
|
||||
s += 1;
|
||||
}
|
||||
else
|
||||
if(code < 0xF0) {
|
||||
if(s > lim - 2) {
|
||||
*t++ = 0xEE00 + code;
|
||||
while(s < lim)
|
||||
*t++ = 0xEE00 + *s++;
|
||||
break;
|
||||
}
|
||||
word c = ((code - 0xE0) << 12) + ((s[0] - 0x80) << 6) + s[1] - 0x80;
|
||||
if(s[0] >= 0x80 && s[0] < 0xc0 && s[1] >= 0x80 && s[1] < 0xc0 && c >= 0x800
|
||||
&& !(c >= 0xEE00 && c <= 0xEEFF))
|
||||
*t++ = c;
|
||||
else {
|
||||
*t++ = 0xEE00 + code;
|
||||
*t++ = 0xEE00 + s[0];
|
||||
*t++ = 0xEE00 + s[1];
|
||||
}
|
||||
s += 2;
|
||||
}
|
||||
else
|
||||
*t++ = 0xEE00 + code;
|
||||
}
|
||||
ASSERT(t - ~result == tlen);
|
||||
return result;
|
||||
}
|
||||
|
||||
int lenAsUtf8(const wchar *s, int len)
|
||||
{
|
||||
const wchar *lim = s + len;
|
||||
len = 0;
|
||||
while(s < lim) {
|
||||
word code = *s++;
|
||||
if(code < 0x80)
|
||||
len++;
|
||||
else
|
||||
if(code < 0x800)
|
||||
len += 2;
|
||||
else
|
||||
if((code & 0xFF00) == 0xEE00)
|
||||
len++;
|
||||
else
|
||||
len += 3;
|
||||
}
|
||||
return len;
|
||||
}
|
||||
|
||||
int utf8len(const char *s)
|
||||
{
|
||||
return utf8len(s, (int)strlen(s));
|
||||
}
|
||||
|
||||
int lenAsUtf8(const wchar *s)
|
||||
{
|
||||
return lenAsUtf8(s, wstrlen(s));
|
||||
}
|
||||
|
||||
String ToUtf8(int code)
|
||||
{
|
||||
char h[10];
|
||||
char *t = h;
|
||||
if(code < 0x80)
|
||||
*t++ = (char)code;
|
||||
else
|
||||
if(code < 0x800) {
|
||||
*t++ = 0xc0 | (code >> 6);
|
||||
*t++ = 0x80 | (code & 0x3f);
|
||||
}
|
||||
else
|
||||
if((code & 0xFF00) == 0xEE00)
|
||||
*t++ = (char) code;
|
||||
else
|
||||
if(code < 0xFFFF) {
|
||||
*t++ = 0xe0 | (code >> 12);
|
||||
*t++ = 0x80 | ((code >> 6) & 0x3f);
|
||||
*t++ = 0x80 | (code & 0x3f);
|
||||
}
|
||||
else {
|
||||
*t++ = 0xf0 | (code >> 18);
|
||||
*t++ = 0x80 | ((code >> 12) & 0x3f);
|
||||
*t++ = 0x80 | ((code >> 6) & 0x3f);
|
||||
*t++ = 0x80 | (code & 0x3f);
|
||||
}
|
||||
return String(h, t);
|
||||
}
|
||||
|
||||
String ToUtf8(wchar code)
|
||||
{
|
||||
return ToUtf8(&code, 1);
|
||||
}
|
||||
|
||||
WString FromUtf8(const char *s)
|
||||
{
|
||||
return FromUtf8(s, (int)strlen(s));
|
||||
}
|
||||
|
||||
WString FromUtf8(const String& s)
|
||||
{
|
||||
return FromUtf8(s, s.GetLength());
|
||||
}
|
||||
|
||||
#ifdef flagSO
|
||||
bool IsLetter(int c) { return (dword)c < 2048 ? uni__info[c] & 0xc0000000 : 0; }
|
||||
bool IsUpper(int c) { return (dword)c < 2048 ? uni__info[c] & 0x40000000 : 0; }
|
||||
|
|
|
|||
|
|
@ -29,6 +29,11 @@ enum {
|
|||
|
||||
int strlen32(const dword *s);
|
||||
|
||||
inline bool IsUtf8Lead(int c)
|
||||
{
|
||||
return (c & 0xc0) != 0x80;
|
||||
}
|
||||
|
||||
bool CheckUtf8(const char *s, int len);
|
||||
inline bool CheckUtf8(const char *s) { return CheckUtf8(s, (int)strlen(s)); }
|
||||
inline bool CheckUtf8(const String& s) { return CheckUtf8(~s, s.GetCount()); }
|
||||
|
|
@ -38,16 +43,16 @@ inline int Utf8Len(const dword *s) { return Utf8Len(s, strlen
|
|||
inline int Utf8Len(const Vector<dword>& s) { return Utf8Len(s, s.GetCount()); }
|
||||
inline int Utf8Len(dword code) { return Utf8Len(&code, 1); }
|
||||
|
||||
int Utf8Len(const wchar *s, int len);
|
||||
inline int Utf8Len(const wchar *s) { return Utf8Len(s, wstrlen(s)); }
|
||||
inline int Utf8Len(const WString& s) { return Utf8Len(~s, s.GetCount()); }
|
||||
|
||||
void ToUtf8(char *t, const dword *s, int len);
|
||||
String ToUtf8(const dword *s, int len);
|
||||
inline String ToUtf8(const dword *s) { return ToUtf8(s, strlen32(s)); }
|
||||
inline String ToUtf8(const Vector<dword>& s) { return ToUtf8(s, s.GetCount()); }
|
||||
inline String ToUtf8(dword code) { return ToUtf8(&code, 1); }
|
||||
|
||||
int Utf8Len(const wchar *s, int len);
|
||||
inline int Utf8Len(const wchar *s) { return Utf8Len(s, wstrlen(s)); }
|
||||
inline int Utf8Len(const WString& s) { return Utf8Len(~s, s.GetCount()); }
|
||||
|
||||
void ToUtf8(char *t, const wchar *s, int len);
|
||||
String ToUtf8(const wchar *s, int len);
|
||||
inline String ToUtf8(const wchar *s) { return ToUtf8(s, wstrlen(s)); }
|
||||
|
|
@ -58,16 +63,16 @@ inline int Utf16Len(const dword *s) { return Utf16Len(s, strle
|
|||
inline int Utf16Len(const Vector<dword>& s) { return Utf16Len(s, s.GetCount()); }
|
||||
inline int Utf16Len(dword code) { return Utf16Len(&code, 1); }
|
||||
|
||||
int Utf16Len(const char *s, int len);
|
||||
inline int Utf16Len(const char *s) { return Utf16Len(s, (int)strlen(s)); }
|
||||
inline int Utf16Len(const String& s) { return Utf16Len(~s, s.GetCount()); }
|
||||
|
||||
void ToUtf16(wchar *t, const dword *s, int len);
|
||||
WString ToUtf16(const dword *s, int len);
|
||||
inline WString ToUtf16(const dword *s) { return ToUtf16(s, strlen32(s)); }
|
||||
inline WString ToUtf16(const Vector<dword>& s) { return ToUtf16(s, s.GetCount()); }
|
||||
inline WString ToUtf16(dword code) { return ToUtf16(&code, 1); }
|
||||
|
||||
int Utf16Len(const char *s, int len);
|
||||
inline int Utf16Len(const char *s) { return Utf16Len(s, (int)strlen(s)); }
|
||||
inline int Utf16Len(const String& s) { return Utf16Len(~s, s.GetCount()); }
|
||||
|
||||
void ToUtf16(wchar *t, const char *s, int len);
|
||||
WString ToUtf16(const char *s, int len);
|
||||
inline WString ToUtf16(const char *s) { return ToUtf16(s, (int)strlen(s)); }
|
||||
|
|
@ -77,15 +82,15 @@ int Utf32Len(const wchar *s, int len);
|
|||
inline int Utf32Len(const wchar *s) { return Utf32Len(s, wstrlen(s)); }
|
||||
inline int Utf32Len(const WString& s) { return Utf32Len(~s, s.GetCount()); }
|
||||
|
||||
int Utf32Len(const char *s, int len);
|
||||
inline int Utf32Len(const char *s) { return Utf32Len(s, (int)strlen(s)); }
|
||||
inline int Utf32Len(const String& s) { return Utf32Len(~s, s.GetCount()); }
|
||||
|
||||
void ToUtf32(dword *t, const wchar *s, int len);
|
||||
Vector<dword> ToUtf32(const wchar *s, int len);
|
||||
inline Vector<dword> ToUtf32(const wchar *s) { return ToUtf32(s, wstrlen(s)); }
|
||||
inline Vector<dword> ToUtf32(const WString& s) { return ToUtf32(~s, s.GetCount()); }
|
||||
|
||||
int Utf32Len(const char *s, int len);
|
||||
inline int Utf32Len(const char *s) { return Utf32Len(s, (int)strlen(s)); }
|
||||
inline int Utf32Len(const String& s) { return Utf32Len(~s, s.GetCount()); }
|
||||
|
||||
void ToUtf32(dword *t, const char *s, int len);
|
||||
Vector<dword> ToUtf32(const char *s, int len);
|
||||
inline Vector<dword> ToUtf32(const char *s) { return ToUtf32(s, (int)strlen(s)); }
|
||||
|
|
@ -103,32 +108,14 @@ const char *CharsetName(byte charset);
|
|||
int CharsetCount();
|
||||
int CharsetByName(const char *name);
|
||||
|
||||
void ConvertCharset(char *t, byte tcharset, const char *s, byte scharset, int n);
|
||||
|
||||
int ToUnicode(int chr, byte charset);
|
||||
int FromUnicode(wchar wchr, byte charset, int defchar = DEFAULTCHAR);
|
||||
|
||||
void ToUnicode(wchar *ws, const char *s, int n, byte charset);
|
||||
void FromUnicode(char *s, const wchar *ws, int n, byte charset, int defchar = DEFAULTCHAR);
|
||||
|
||||
void ConvertCharset(char *t, byte tcharset, const char *s, byte scharset, int n);
|
||||
|
||||
inline bool IsUtf8Lead(int c)
|
||||
{
|
||||
return (c & 0xc0) != 0x80;
|
||||
}
|
||||
|
||||
WString FromUtf8(const char *_s, int len);
|
||||
WString FromUtf8(const char *_s);
|
||||
WString FromUtf8(const String& s);
|
||||
|
||||
bool utf8check(const char *_s, int len);
|
||||
|
||||
int utf8len(const char *s, int len);
|
||||
int utf8len(const char *s);
|
||||
int lenAsUtf8(const wchar *s, int len);
|
||||
int lenAsUtf8(const wchar *s);
|
||||
|
||||
bool CheckUtf8(const String& src);
|
||||
|
||||
WString ToUnicode(const String& src, byte charset);
|
||||
WString ToUnicode(const char *src, int n, byte charset);
|
||||
String FromUnicodeBuffer(const wchar *src, int len, byte charset = CHARSET_DEFAULT, int defchar = DEFAULTCHAR);
|
||||
|
|
@ -227,13 +214,26 @@ String ToAscii(const char *s, byte charset = CHARSET_DEFAULT);
|
|||
|
||||
WString LoadStreamBOMW(Stream& in, byte def_charset);
|
||||
WString LoadStreamBOMW(Stream& in);
|
||||
String LoadStreamBOM(Stream& in, byte def_charset);
|
||||
String LoadStreamBOM(Stream& in);
|
||||
String LoadStreamBOM(Stream& in, byte def_charset);
|
||||
String LoadStreamBOM(Stream& in);
|
||||
WString LoadFileBOMW(const char *path, byte def_charset);
|
||||
WString LoadFileBOMW(const char *path);
|
||||
String LoadFileBOM(const char *path, byte def_charset);
|
||||
String LoadFileBOM(const char *path);
|
||||
bool SaveStreamBOM(Stream& out, const WString& data);
|
||||
bool SaveFileBOM(const char *path, const WString& data);
|
||||
bool SaveStreamBOMUtf8(Stream& out, const String& data);
|
||||
bool SaveFileBOMUtf8(const char *path, const String& data);
|
||||
String LoadFileBOM(const char *path, byte def_charset);
|
||||
String LoadFileBOM(const char *path);
|
||||
bool SaveStreamBOM(Stream& out, const WString& data);
|
||||
bool SaveFileBOM(const char *path, const WString& data);
|
||||
bool SaveStreamBOMUtf8(Stream& out, const String& data);
|
||||
bool SaveFileBOMUtf8(const char *path, const String& data);
|
||||
|
||||
// Deprecated names
|
||||
|
||||
inline WString FromUtf8(const char *s, int len) { return ToUtf16(s, len); }
|
||||
inline WString FromUtf8(const char *s) { return ToUtf16(s); }
|
||||
inline WString FromUtf8(const String& s) { return ToUtf16(s); }
|
||||
|
||||
inline bool utf8check(const char *s, int len) { return CheckUtf8(s, len); }
|
||||
|
||||
inline int utf8len(const char *s, int len) { return Utf16Len(s, len); }
|
||||
inline int utf8len(const char *s) { return Utf16Len(s); }
|
||||
inline int lenAsUtf8(const wchar *s, int len) { return Utf8Len(s, len); }
|
||||
inline int lenAsUtf8(const wchar *s) { return Utf8Len(s); }
|
||||
|
|
|
|||
|
|
@ -75,7 +75,8 @@ of characters that do not exist in target charset.&]
|
|||
[s4; &]
|
||||
[s5;:SetDefaultCharset`(byte`): [@(0.0.255) void]_[* SetDefaultCharset]([_^byte^ byte]_[*@3 c
|
||||
harset])&]
|
||||
[s2;%% Sets the default [%-*@3 charset].&]
|
||||
[s2;%% Sets the default [%-*@3 charset]. This is to support legacy
|
||||
application; new applications should always use UTF8.&]
|
||||
[s3;%% &]
|
||||
[s4; &]
|
||||
[s5;:ResolveCharset`(byte`): [_^byte^ byte]_[* ResolveCharset]([_^byte^ byte]_[*@3 charset])&]
|
||||
|
|
@ -172,86 +173,6 @@ Both arrays must have (at least) [%-*@3 n] elements. Neither [%-*@3 tcharset]
|
|||
or[%-*@3 scharset ]can be CHARSET`_UTF8.&]
|
||||
[s3;%% &]
|
||||
[s4;%% &]
|
||||
[s5;:IsUtf8Lead`(int`): [@(0.0.255) bool]_[* IsUtf8Lead]([@(0.0.255) int]_[*@3 c])&]
|
||||
[s2;%% Tests whether [%-*@3 c ]is lead UTF`-8 byte.&]
|
||||
[s3;%% &]
|
||||
[s4; &]
|
||||
[s5;:Upp`:`:ToUtf8`(int`): [_^Upp`:`:String^ String]_[* ToUtf8]([@(0.0.255) int]_[*@3 code])&]
|
||||
[s2;%% Converts single unicode character to Utf8. Bytes from private
|
||||
0xEExx range are converted to xx bytes.&]
|
||||
[s3;%% &]
|
||||
[s4;%% &]
|
||||
[s5;:ToUtf8`(const wchar`*`,int`): [_^String^ String]_[* ToUtf8]([@(0.0.255) const]_[_^wchar^ w
|
||||
char]_`*[*@3 s], [@(0.0.255) int]_[*@3 len])&]
|
||||
[s2;%% Converts UNICODE array to UTF`-8. Bytes from private 0xEExx
|
||||
range are converted to xx bytes.&]
|
||||
[s3;%% &]
|
||||
[s4;%% &]
|
||||
[s5;:ToUtf8`(const wchar`*`): [_^String^ String]_[* ToUtf8]([@(0.0.255) const]_[_^wchar^ wcha
|
||||
r]_`*[*@3 s])&]
|
||||
[s2;%% Converts zero`-terminated string [%-*@3 s] to UTF`-8. Bytes
|
||||
from private 0xEExx range are converted to xx bytes.&]
|
||||
[s3;%% &]
|
||||
[s4;%% &]
|
||||
[s5;:ToUtf8`(const WString`&`): [_^String^ String]_[* ToUtf8]([@(0.0.255) const]_[_^WString^ W
|
||||
String][@(0.0.255) `&]_[*@3 w])&]
|
||||
[s2;%% Converts string to UTF`-8. Bytes from private 0xEExx range
|
||||
are converted to xx bytes.&]
|
||||
[s3;%% &]
|
||||
[s4;%% &]
|
||||
[s5;:FromUtf8`(const char`*`,int`): [_^WString^ WString]_[* FromUtf8]([@(0.0.255) const]_[@(0.0.255) c
|
||||
har]_`*[*@3 `_s], [@(0.0.255) int]_[*@3 len])&]
|
||||
[s2;%% Converts UTF`-8 to UNICODE string. Any wrong bytes and sequences
|
||||
are converted to private 0xEExx range.&]
|
||||
[s3;%% &]
|
||||
[s4;%% &]
|
||||
[s5;:FromUtf8`(const char`*`): [_^WString^ WString]_[* FromUtf8]([@(0.0.255) const]_[@(0.0.255) c
|
||||
har]_`*[*@3 `_s])&]
|
||||
[s2;%% Converts zero`-terminted UTF`-8 string to UNICODE. Any wrong
|
||||
bytes and sequences are converted to private 0xEExx range.&]
|
||||
[s3;%% &]
|
||||
[s4;%% &]
|
||||
[s5;:FromUtf8`(const String`&`): [_^WString^ WString]_[* FromUtf8]([@(0.0.255) const]_[_^String^ S
|
||||
tring][@(0.0.255) `&]_[*@3 s])&]
|
||||
[s2;%% Converts UTF`-8 string to UNICODE. Any wrong bytes and sequences
|
||||
are converted to private 0xEExx range.&]
|
||||
[s3;%% &]
|
||||
[s4;%% &]
|
||||
[s5;:utf8check`(const char`*`,int`): [@(0.0.255) bool]_[* utf8check]([@(0.0.255) const]_[@(0.0.255) c
|
||||
har]_`*[*@3 `_s], [@(0.0.255) int]_[*@3 len])&]
|
||||
[s2;%% Checks whether array contains a valid UTF`-8 sequence.&]
|
||||
[s3;%% &]
|
||||
[s4;%% &]
|
||||
[s5;:utf8len`(const char`*`,int`): [@(0.0.255) int]_[* utf8len]([@(0.0.255) const]_[@(0.0.255) c
|
||||
har]_`*[*@3 s], [@(0.0.255) int]_[*@3 len])&]
|
||||
[s2;%% Returns a number of UNICODE characters in UTF`-8 text. Error`-escaped
|
||||
0xEExx characters for ill`-formed parts of UTF`-8 are correctly
|
||||
accounted for.&]
|
||||
[s3;%% &]
|
||||
[s4;%% &]
|
||||
[s5;:utf8len`(const char`*`): [@(0.0.255) int]_[* utf8len]([@(0.0.255) const]_[@(0.0.255) cha
|
||||
r]_`*[*@3 s])&]
|
||||
[s2;%% Returns a number of UNICODE characters in zero`-terminated
|
||||
UTF`-8 text. Error`-escaped 0xEExx characters for ill`-formed
|
||||
parts of UTF`-8 are correctly accounted for.&]
|
||||
[s3;%% &]
|
||||
[s4;%% &]
|
||||
[s5;:lenAsUtf8`(const wchar`*`,int`): [@(0.0.255) int]_[* lenAsUtf8]([@(0.0.255) const]_[_^wchar^ w
|
||||
char]_`*[*@3 s], [@(0.0.255) int]_[*@3 len])&]
|
||||
[s2;%% Returns number of bytes of UNICODE text when UTF`-8 encoded.&]
|
||||
[s3;%% &]
|
||||
[s4;%% &]
|
||||
[s5;:lenAsUtf8`(const wchar`*`): [@(0.0.255) int]_[* lenAsUtf8]([@(0.0.255) const]_[_^wchar^ w
|
||||
char]_`*[*@3 s])&]
|
||||
[s2;%% Returns number of bytes of UNICODE zero`-terminated text when
|
||||
UTF`-8 encoded..&]
|
||||
[s3;%% &]
|
||||
[s4;%% &]
|
||||
[s5;:CheckUtf8`(const String`&`): [@(0.0.255) bool]_[* CheckUtf8]([@(0.0.255) const]_[_^String^ S
|
||||
tring][@(0.0.255) `&]_[*@3 src])&]
|
||||
[s2;%% Checks whether String contains a valid UTF`-8 sequence.&]
|
||||
[s3;%% &]
|
||||
[s4;%% &]
|
||||
[s5;:ToUnicode`(const String`&`,byte`): [_^WString^ WString]_[* ToUnicode]([@(0.0.255) cons
|
||||
t]_[_^String^ String][@(0.0.255) `&]_[*@3 src], [_^byte^ byte]_[*@3 charset])&]
|
||||
[s2;%% Converts [%-*@3 src] encoded in [%-*@3 charset] to UNICODE. [%-*@3 charset]
|
||||
|
|
@ -715,4 +636,55 @@ true on success.&]
|
|||
[s2; Saves 8`-bit string in default encoding to the file. Returns
|
||||
true on success.&]
|
||||
[s3; &]
|
||||
[s4; &]
|
||||
[s5;:FromUtf8`(const char`*`,int`): [_^WString^ WString]_[* FromUtf8]([@(0.0.255) const]_[@(0.0.255) c
|
||||
har]_`*[*@3 `_s], [@(0.0.255) int]_[*@3 len])&]
|
||||
[s2;%% Converts UTF`-8 to UNICODE string. Any wrong bytes and sequences
|
||||
are converted to private 0xEExx range. Deprecated, use ToUtf16.&]
|
||||
[s3;%% &]
|
||||
[s4;%% &]
|
||||
[s5;:FromUtf8`(const char`*`): [_^WString^ WString]_[* FromUtf8]([@(0.0.255) const]_[@(0.0.255) c
|
||||
har]_`*[*@3 `_s])&]
|
||||
[s2;%% Converts zero`-terminted UTF`-8 string to UNICODE. Any wrong
|
||||
bytes and sequences are converted to private 0xEExx range. Deprecated,
|
||||
use ToUtf16.&]
|
||||
[s3;%% &]
|
||||
[s4;%% &]
|
||||
[s5;:FromUtf8`(const String`&`): [_^WString^ WString]_[* FromUtf8]([@(0.0.255) const]_[_^String^ S
|
||||
tring][@(0.0.255) `&]_[*@3 s])&]
|
||||
[s2;%% Converts UTF`-8 string to UNICODE. Any wrong bytes and sequences
|
||||
are converted to private 0xEExx range. Deprecated, use ToUtf16.&]
|
||||
[s3;%% &]
|
||||
[s4;%% &]
|
||||
[s5;:utf8check`(const char`*`,int`): [@(0.0.255) bool]_[* utf8check]([@(0.0.255) const]_[@(0.0.255) c
|
||||
har]_`*[*@3 `_s], [@(0.0.255) int]_[*@3 len])&]
|
||||
[s2;%% Checks whether array contains a valid UTF`-8 sequence. Deprecated,
|
||||
use CheckUtf8.&]
|
||||
[s3;%% &]
|
||||
[s4;%% &]
|
||||
[s5;:utf8len`(const char`*`,int`): [@(0.0.255) int]_[* utf8len]([@(0.0.255) const]_[@(0.0.255) c
|
||||
har]_`*[*@3 s], [@(0.0.255) int]_[*@3 len])&]
|
||||
[s2;%% Returns a number of UNICODE characters in UTF`-8 text. Error`-escaped
|
||||
0xEExx characters for ill`-formed parts of UTF`-8 are correctly
|
||||
accounted for. Deprecated, use Utf16Len.&]
|
||||
[s3;%% &]
|
||||
[s4;%% &]
|
||||
[s5;:utf8len`(const char`*`): [@(0.0.255) int]_[* utf8len]([@(0.0.255) const]_[@(0.0.255) cha
|
||||
r]_`*[*@3 s])&]
|
||||
[s2;%% Returns a number of UNICODE characters in zero`-terminated
|
||||
UTF`-8 text. Error`-escaped 0xEExx characters for ill`-formed
|
||||
parts of UTF`-8 are correctly accounted for. Deprecated, use
|
||||
Utf16Len.&]
|
||||
[s3;%% &]
|
||||
[s4;%% &]
|
||||
[s5;:lenAsUtf8`(const wchar`*`,int`): [@(0.0.255) int]_[* lenAsUtf8]([@(0.0.255) const]_[_^wchar^ w
|
||||
char]_`*[*@3 s], [@(0.0.255) int]_[*@3 len])&]
|
||||
[s2;%% Returns number of bytes of UNICODE text when UTF`-8 encoded.
|
||||
Deprecated, use Utf8Len.&]
|
||||
[s3;%% &]
|
||||
[s4;%% &]
|
||||
[s5;:lenAsUtf8`(const wchar`*`): [@(0.0.255) int]_[* lenAsUtf8]([@(0.0.255) const]_[_^wchar^ w
|
||||
char]_`*[*@3 s])&]
|
||||
[s2;%% Returns number of bytes of UNICODE zero`-terminated text when
|
||||
UTF`-8 encoded. Deprecated, use Utf8Len.&]
|
||||
[s0; ]]
|
||||
207
uppsrc/Core/src.tpp/Utf$en-us.tpp
Normal file
207
uppsrc/Core/src.tpp/Utf$en-us.tpp
Normal file
|
|
@ -0,0 +1,207 @@
|
|||
topic "";
|
||||
[2 $$0,0#00000000000000000000000000000000:Default]
|
||||
[i448;a25;kKO9;2 $$1,0#37138531426314131252341829483380:class]
|
||||
[l288;2 $$2,2#27521748481378242620020725143825:desc]
|
||||
[0 $$3,0#96390100711032703541132217272105:end]
|
||||
[H6;0 $$4,0#05600065144404261032431302351956:begin]
|
||||
[i448;a25;kKO9;2 $$5,0#37138531426314131252341829483370:item]
|
||||
[l288;a4;*@5;1 $$6,6#70004532496200323422659154056402:requirement]
|
||||
[l288;i1121;b17;O9;~~~.1408;2 $$7,0#10431211400427159095818037425705:param]
|
||||
[i448;b42;O9;2 $$8,8#61672508125594000341940100500538:tparam]
|
||||
[b42;2 $$9,9#13035079074754324216151401829390:normal]
|
||||
[{_}
|
||||
[ {{10000@(113.42.0) [s0;%% [*@7;4 Unicode UTF`[8,16,32`] support]]}}&]
|
||||
[s0;%% &]
|
||||
[s5;:IsUtf8Lead`(int`): [@(0.0.255) bool]_[* IsUtf8Lead]([@(0.0.255) int]_[*@3 c])&]
|
||||
[s2;%% Tests whether [%-*@3 c ]is lead UTF`-8 byte.&]
|
||||
[s3;%% &]
|
||||
[s4; &]
|
||||
[s5;:Upp`:`:CheckUtf8`(const char`*`,int`): [@(0.0.255) bool]_[* CheckUtf8]([@(0.0.255) con
|
||||
st]_[@(0.0.255) char]_`*[*@3 s], [@(0.0.255) int]_[*@3 len])&]
|
||||
[s5;:Upp`:`:CheckUtf8`(const char`*`): [@(0.0.255) bool]_[* CheckUtf8]([@(0.0.255) const]_[@(0.0.255) c
|
||||
har]_`*[*@3 s])&]
|
||||
[s5;:CheckUtf8`(const String`&`): [@(0.0.255) bool]_[* CheckUtf8]([@(0.0.255) const]_[_^String^ S
|
||||
tring][@(0.0.255) `&]_[*@3 src])&]
|
||||
[s2;%% Checks whether string contains a valid UTF`-8 sequence. If
|
||||
source is specified as pointer [%-*@3 s] without [%-*@3 len], its
|
||||
must be zero`-terminated.&]
|
||||
[s3;%% &]
|
||||
[s4; &]
|
||||
[s5;:Upp`:`:Utf8Len`(const Upp`:`:dword`*`,int`): [@(0.0.255) int]_[* Utf8Len]([@(0.0.255) c
|
||||
onst]_[_^Upp`:`:dword^ dword]_`*[*@3 s], [@(0.0.255) int]_[*@3 len])&]
|
||||
[s5;:Upp`:`:Utf8Len`(const Upp`:`:dword`*`): [@(0.0.255) int]_[* Utf8Len]([@(0.0.255) const
|
||||
]_[_^Upp`:`:dword^ dword]_`*[*@3 s])&]
|
||||
[s5;:Upp`:`:Utf8Len`(const Upp`:`:Vector`<Upp`:`:dword`>`&`): [@(0.0.255) int]_[* Utf8Len
|
||||
]([@(0.0.255) const]_[_^Upp`:`:Vector^ Vector]<[_^Upp`:`:dword^ dword]>`&_[*@3 s])&]
|
||||
[s2;%% Returns the size in bytes of UTF`-32 Unicode text in UTF`-8.
|
||||
If source is specified as pointer [%-*@3 s] without [%-*@3 len],
|
||||
its must be zero`-terminated.&]
|
||||
[s3; &]
|
||||
[s4; &]
|
||||
[s5;:Upp`:`:Utf8Len`(const Upp`:`:wchar`*`,int`): [@(0.0.255) int]_[* Utf8Len]([@(0.0.255) c
|
||||
onst]_[_^Upp`:`:wchar^ wchar]_`*[*@3 s], [@(0.0.255) int]_[*@3 len])&]
|
||||
[s5;:Upp`:`:Utf8Len`(const Upp`:`:wchar`*`): [@(0.0.255) int]_[* Utf8Len]([@(0.0.255) const
|
||||
]_[_^Upp`:`:wchar^ wchar]_`*[*@3 s])&]
|
||||
[s5;:Upp`:`:Utf8Len`(const Upp`:`:WString`&`): [@(0.0.255) int]_[* Utf8Len]([@(0.0.255) con
|
||||
st]_[_^Upp`:`:WString^ WString][@(0.0.255) `&]_[*@3 s])&]
|
||||
[s2;%% Returns the size in bytes of UTF`-16 Unicode text in UTF`-8.
|
||||
If source is specified as pointer [%-*@3 s] without [%-*@3 len],
|
||||
its must be zero`-terminated.&]
|
||||
[s3;%% &]
|
||||
[s4; &]
|
||||
[s5;:Upp`:`:Utf8Len`(Upp`:`:dword`): [@(0.0.255) int]_[* Utf8Len]([_^Upp`:`:dword^ dword]_[*@3 c
|
||||
ode])&]
|
||||
[s2;%% Returns the size in bytes of single codepoint in UTF`-8.&]
|
||||
[s3;%% &]
|
||||
[s4; &]
|
||||
[s5;:Upp`:`:ToUtf8`(char`*`,const Upp`:`:wchar`*`,int`): [@(0.0.255) void]_[* ToUtf8]([@(0.0.255) c
|
||||
har]_`*[*@3 t], [@(0.0.255) const]_[_^Upp`:`:wchar^ wchar]_`*[*@3 s],
|
||||
[@(0.0.255) int]_[*@3 len])&]
|
||||
[s5;:Upp`:`:ToUtf8`(const Upp`:`:wchar`*`,int`): [_^Upp`:`:String^ String]_[* ToUtf8]([@(0.0.255) c
|
||||
onst]_[_^Upp`:`:wchar^ wchar]_`*[*@3 s], [@(0.0.255) int]_[*@3 len])&]
|
||||
[s5;:Upp`:`:ToUtf8`(const Upp`:`:wchar`*`): [_^Upp`:`:String^ String]_[* ToUtf8]([@(0.0.255) c
|
||||
onst]_[_^Upp`:`:wchar^ wchar]_`*[*@3 s])&]
|
||||
[s5;:Upp`:`:ToUtf8`(const Upp`:`:WString`&`): [_^Upp`:`:String^ String]_[* ToUtf8]([@(0.0.255) c
|
||||
onst]_[_^Upp`:`:WString^ WString][@(0.0.255) `&]_[*@3 s])&]
|
||||
[s2;%% UTF`-16 to UTF`-8 conversion. If target is specified as pointer
|
||||
to buffer [%-*@3 t], the buffer must contain enough space for the
|
||||
output. If source is specified as pointer [%-*@3 s] without [%-*@3 len],
|
||||
its must be zero`-terminated.&]
|
||||
[s3;%% &]
|
||||
[s4; &]
|
||||
[s5;:Upp`:`:ToUtf8`(char`*`,const Upp`:`:dword`*`,int`): [@(0.0.255) void]_[* ToUtf8]([@(0.0.255) c
|
||||
har]_`*[*@3 t], [@(0.0.255) const]_[_^Upp`:`:dword^ dword]_`*[*@3 s],
|
||||
[@(0.0.255) int]_[*@3 len])&]
|
||||
[s5;:Upp`:`:ToUtf8`(const Upp`:`:dword`*`,int`): [_^Upp`:`:String^ String]_[* ToUtf8]([@(0.0.255) c
|
||||
onst]_[_^Upp`:`:dword^ dword]_`*[*@3 s], [@(0.0.255) int]_[*@3 len])&]
|
||||
[s5;:Upp`:`:ToUtf8`(const Upp`:`:dword`*`): [_^Upp`:`:String^ String]_[* ToUtf8]([@(0.0.255) c
|
||||
onst]_[_^Upp`:`:dword^ dword]_`*[*@3 s])&]
|
||||
[s5;:Upp`:`:ToUtf8`(const Upp`:`:Vector`<Upp`:`:dword`>`&`): [_^Upp`:`:String^ String]_
|
||||
[* ToUtf8]([@(0.0.255) const]_[_^Upp`:`:Vector^ Vector]<[_^Upp`:`:dword^ dword]>`&_[*@3 s])
|
||||
&]
|
||||
[s2;%% UTF`-32 to UTF`-8 conversion. If target is specified as pointer
|
||||
to buffer [%-*@3 t], the buffer must contain enough space for the
|
||||
output. If source is specified as pointer [%-*@3 s] without [%-*@3 len],
|
||||
its must be zero`-terminated.&]
|
||||
[s3;%% &]
|
||||
[s4; &]
|
||||
[s5;:Upp`:`:ToUtf8`(Upp`:`:dword`): [_^Upp`:`:String^ String]_[* ToUtf8]([_^Upp`:`:dword^ d
|
||||
word]_[*@3 code])&]
|
||||
[s2;%% Converts single codepoint to UTF`-8.&]
|
||||
[s3; &]
|
||||
[s4; &]
|
||||
[s5;:Upp`:`:Utf16Len`(const Upp`:`:dword`*`,int`): [@(0.0.255) int]_[* Utf16Len]([@(0.0.255) c
|
||||
onst]_[_^Upp`:`:dword^ dword]_`*[*@3 s], [@(0.0.255) int]_[*@3 len])&]
|
||||
[s5;:Upp`:`:Utf16Len`(const Upp`:`:dword`*`): [@(0.0.255) int]_[* Utf16Len]([@(0.0.255) con
|
||||
st]_[_^Upp`:`:dword^ dword]_`*[*@3 s])&]
|
||||
[s5;:Upp`:`:Utf16Len`(const Upp`:`:Vector`<Upp`:`:dword`>`&`): [@(0.0.255) int]_[* Utf16L
|
||||
en]([@(0.0.255) const]_[_^Upp`:`:Vector^ Vector]<[_^Upp`:`:dword^ dword]>`&_[*@3 s])&]
|
||||
[s2;%% Returns the size in wchars of UTF`-32 Unicode text in UTF`-16.
|
||||
If source is specified as pointer [%-*@3 s] without [%-*@3 len],
|
||||
its must be zero`-terminated.&]
|
||||
[s3; &]
|
||||
[s4; &]
|
||||
[s5;:Upp`:`:Utf16Len`(Upp`:`:dword`): [@(0.0.255) int]_[* Utf16Len]([_^Upp`:`:dword^ dword]_
|
||||
[*@3 code])&]
|
||||
[s2;%% Returns the size in wchars of single codepoint in UTF`-16.&]
|
||||
[s3;%% &]
|
||||
[s4; &]
|
||||
[s5;:Upp`:`:Utf16Len`(const char`*`,int`): [@(0.0.255) int]_[* Utf16Len]([@(0.0.255) const]_
|
||||
[@(0.0.255) char]_`*[*@3 s], [@(0.0.255) int]_[*@3 len])&]
|
||||
[s5;:Upp`:`:Utf16Len`(const char`*`): [@(0.0.255) int]_[* Utf16Len]([@(0.0.255) const]_[@(0.0.255) c
|
||||
har]_`*[*@3 s])&]
|
||||
[s5;:Upp`:`:Utf16Len`(const Upp`:`:String`&`): [@(0.0.255) int]_[* Utf16Len]([@(0.0.255) co
|
||||
nst]_[_^Upp`:`:String^ String][@(0.0.255) `&]_[*@3 s])&]
|
||||
[s2;%% Returns the size in wchars of UTF`-8 Unicode text in UTF`-16.
|
||||
If source is specified as pointer [%-*@3 s] without [%-*@3 len],
|
||||
its must be zero`-terminated.&]
|
||||
[s3;%% &]
|
||||
[s4; &]
|
||||
[s5;:Upp`:`:ToUtf16`(Upp`:`:wchar`*`,const Upp`:`:dword`*`,int`): [@(0.0.255) void]_[* To
|
||||
Utf16]([_^Upp`:`:wchar^ wchar]_`*[*@3 t], [@(0.0.255) const]_[_^Upp`:`:dword^ dword]_`*[*@3 s
|
||||
], [@(0.0.255) int]_[*@3 len])&]
|
||||
[s5;:Upp`:`:ToUtf16`(const Upp`:`:dword`*`,int`): [_^Upp`:`:WString^ WString]_[* ToUtf16](
|
||||
[@(0.0.255) const]_[_^Upp`:`:dword^ dword]_`*[*@3 s], [@(0.0.255) int]_[*@3 len])&]
|
||||
[s5;:Upp`:`:ToUtf16`(const Upp`:`:dword`*`): [_^Upp`:`:WString^ WString]_[* ToUtf16]([@(0.0.255) c
|
||||
onst]_[_^Upp`:`:dword^ dword]_`*[*@3 s])&]
|
||||
[s5;:Upp`:`:ToUtf16`(const Upp`:`:Vector`<Upp`:`:dword`>`&`): [_^Upp`:`:WString^ WStrin
|
||||
g]_[* ToUtf16]([@(0.0.255) const]_[_^Upp`:`:Vector^ Vector]<[_^Upp`:`:dword^ dword]>`&_[*@3 s
|
||||
])&]
|
||||
[s2;%% [%- UTF`-32 to UTF`-16 conversion.] If target is specified as
|
||||
pointer to buffer [%-*@3 t], the buffer must contain enough space
|
||||
for the output. If source is specified as pointer [%-*@3 s] without
|
||||
[%-*@3 len], its must be zero`-terminated.&]
|
||||
[s3; &]
|
||||
[s4; &]
|
||||
[s5;:Upp`:`:ToUtf16`(Upp`:`:dword`): [_^Upp`:`:WString^ WString]_[* ToUtf16]([_^Upp`:`:dword^ d
|
||||
word]_[*@3 code])&]
|
||||
[s2;%% Converts single codepoint to UTF`-16.&]
|
||||
[s3;%% &]
|
||||
[s4; &]
|
||||
[s5;:Upp`:`:ToUtf16`(Upp`:`:wchar`*`,const char`*`,int`): [@(0.0.255) void]_[* ToUtf16]([_^Upp`:`:wchar^ w
|
||||
char]_`*[*@3 t], [@(0.0.255) const]_[@(0.0.255) char]_`*[*@3 s], [@(0.0.255) int]_[*@3 len])&]
|
||||
[s5;:Upp`:`:ToUtf16`(const char`*`,int`): [_^Upp`:`:WString^ WString]_[* ToUtf16]([@(0.0.255) c
|
||||
onst]_[@(0.0.255) char]_`*[*@3 s], [@(0.0.255) int]_[*@3 len])&]
|
||||
[s5;:Upp`:`:ToUtf16`(const char`*`): [_^Upp`:`:WString^ WString]_[* ToUtf16]([@(0.0.255) co
|
||||
nst]_[@(0.0.255) char]_`*[*@3 s])&]
|
||||
[s5;:Upp`:`:ToUtf16`(const Upp`:`:String`&`): [_^Upp`:`:WString^ WString]_[* ToUtf16]([@(0.0.255) c
|
||||
onst]_[_^Upp`:`:String^ String][@(0.0.255) `&]_[*@3 s])&]
|
||||
[s2;%% UTF`-8 to UTF`-16 conversion. If target is specified as pointer
|
||||
to buffer [%-*@3 t], the buffer must contain enough space for the
|
||||
output. If source is specified as pointer [%-*@3 s] without [%-*@3 len],
|
||||
its must be zero`-terminated.&]
|
||||
[s3;%% &]
|
||||
[s4; &]
|
||||
[s5;:Upp`:`:Utf32Len`(const Upp`:`:wchar`*`,int`): [@(0.0.255) int]_[* Utf32Len]([@(0.0.255) c
|
||||
onst]_[_^Upp`:`:wchar^ wchar]_`*[*@3 s], [@(0.0.255) int]_[*@3 len])&]
|
||||
[s5;:Upp`:`:Utf32Len`(const Upp`:`:wchar`*`): [@(0.0.255) int]_[* Utf32Len]([@(0.0.255) con
|
||||
st]_[_^Upp`:`:wchar^ wchar]_`*[*@3 s])&]
|
||||
[s5;:Upp`:`:Utf32Len`(const Upp`:`:WString`&`): [@(0.0.255) int]_[* Utf32Len]([@(0.0.255) c
|
||||
onst]_[_^Upp`:`:WString^ WString][@(0.0.255) `&]_[*@3 s])&]
|
||||
[s2;%% 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 [%-*@3 s] without
|
||||
[%-*@3 len], its must be zero`-terminated.&]
|
||||
[s3;%% &]
|
||||
[s4; &]
|
||||
[s5;:Upp`:`:Utf32Len`(const char`*`,int`): [@(0.0.255) int]_[* Utf32Len]([@(0.0.255) const]_
|
||||
[@(0.0.255) char]_`*[*@3 s], [@(0.0.255) int]_[*@3 len])&]
|
||||
[s5;:Upp`:`:Utf32Len`(const char`*`): [@(0.0.255) int]_[* Utf32Len]([@(0.0.255) const]_[@(0.0.255) c
|
||||
har]_`*[*@3 s])&]
|
||||
[s5;:Upp`:`:Utf32Len`(const Upp`:`:String`&`): [@(0.0.255) int]_[* Utf32Len]([@(0.0.255) co
|
||||
nst]_[_^Upp`:`:String^ String][@(0.0.255) `&]_[*@3 s])&]
|
||||
[s2;%% 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 [%-*@3 s] without
|
||||
[%-*@3 len], its must be zero`-terminated.&]
|
||||
[s3;%% &]
|
||||
[s4; &]
|
||||
[s5;:Upp`:`:ToUtf32`(Upp`:`:dword`*`,const Upp`:`:wchar`*`,int`): [@(0.0.255) void]_[* To
|
||||
Utf32]([_^Upp`:`:dword^ dword]_`*[*@3 t], [@(0.0.255) const]_[_^Upp`:`:wchar^ wchar]_`*[*@3 s
|
||||
], [@(0.0.255) int]_[*@3 len])&]
|
||||
[s5;:Upp`:`:ToUtf32`(const Upp`:`:wchar`*`,int`): [_^Upp`:`:Vector^ Vector]<[_^Upp`:`:dword^ d
|
||||
word]>_[* ToUtf32]([@(0.0.255) const]_[_^Upp`:`:wchar^ wchar]_`*[*@3 s],
|
||||
[@(0.0.255) int]_[*@3 len])&]
|
||||
[s5;:Upp`:`:ToUtf32`(const Upp`:`:wchar`*`): [_^Upp`:`:Vector^ Vector]<[_^Upp`:`:dword^ d
|
||||
word]>_[* ToUtf32]([@(0.0.255) const]_[_^Upp`:`:wchar^ wchar]_`*[*@3 s])&]
|
||||
[s5;:Upp`:`:ToUtf32`(const Upp`:`:WString`&`): [_^Upp`:`:Vector^ Vector]<[_^Upp`:`:dword^ d
|
||||
word]>_[* ToUtf32]([@(0.0.255) const]_[_^Upp`:`:WString^ WString][@(0.0.255) `&]_[*@3 s])&]
|
||||
[s2;%% UTF`-16 to UTF`-32 conversion. If target is specified as pointer
|
||||
to buffer [%-*@3 t], the buffer must contain enough space for the
|
||||
output. If source is specified as pointer [%-*@3 s] without [%-*@3 len],
|
||||
its must be zero`-terminated.&]
|
||||
[s3;%% &]
|
||||
[s4; &]
|
||||
[s5;:Upp`:`:ToUtf32`(Upp`:`:dword`*`,const char`*`,int`): [@(0.0.255) void]_[* ToUtf32]([_^Upp`:`:dword^ d
|
||||
word]_`*[*@3 t], [@(0.0.255) const]_[@(0.0.255) char]_`*[*@3 s], [@(0.0.255) int]_[*@3 len])&]
|
||||
[s5;:Upp`:`:ToUtf32`(const char`*`,int`): [_^Upp`:`:Vector^ Vector]<[_^Upp`:`:dword^ dwor
|
||||
d]>_[* ToUtf32]([@(0.0.255) const]_[@(0.0.255) char]_`*[*@3 s], [@(0.0.255) int]_[*@3 len])&]
|
||||
[s5;:Upp`:`:ToUtf32`(const char`*`): [_^Upp`:`:Vector^ Vector]<[_^Upp`:`:dword^ dword]>_[* T
|
||||
oUtf32]([@(0.0.255) const]_[@(0.0.255) char]_`*[*@3 s])&]
|
||||
[s5;:Upp`:`:ToUtf32`(const Upp`:`:String`&`): [_^Upp`:`:Vector^ Vector]<[_^Upp`:`:dword^ d
|
||||
word]>_[* ToUtf32]([@(0.0.255) const]_[_^Upp`:`:String^ String][@(0.0.255) `&]_[*@3 s])&]
|
||||
[s2;%% UTF`-8 to UTF`-32 conversion. If target is specified as pointer
|
||||
to buffer [%-*@3 t], the buffer must contain enough space for the
|
||||
output. If source is specified as pointer [%-*@3 s] without [%-*@3 len],
|
||||
its must be zero`-terminated.&]
|
||||
[s3;%% ]]
|
||||
Loading…
Add table
Add a link
Reference in a new issue