Core: IsDoubleWidth (thanks ismail)

git-svn-id: svn://ultimatepp.org/upp/trunk@13710 f0d560ea-af0d-0410-9eb7-867de7ffcac7
This commit is contained in:
cxl 2019-11-23 10:47:03 +00:00
parent e5b004d40a
commit 1bb18b43bd
4 changed files with 34 additions and 10 deletions

View file

@ -2296,4 +2296,25 @@ String ToLowerAscii(const String& s, byte charset)
return r;
}
bool IsDoubleWidth(int c)
{
// This function is taken from Markus Kuhn's wcwidth implementation.
// For license and implementation details, see:
// https://www.cl.cam.ac.uk/~mgk25/ucs/wcwidth.c
return c >= 0x1100
&& (c <= 0x115F // Hangul Jamo init. consonants
|| c == 0x2329
|| c == 0x232A
|| (c >= 0x2E80 && c <= 0xA4CF && c != 0x303F) // CJK ... Yi
|| (c >= 0xAC00 && c <= 0xD7A3) // Hangul syllables
|| (c >= 0xF900 && c <= 0xFAFF) // CJK compatibility ideographs
|| (c >= 0xFE10 && c <= 0xFE19) // Vertical forms
|| (c >= 0xFE30 && c <= 0xFE6F) // CJK compatibility forms
|| (c >= 0xFF00 && c <= 0xFF60) // Fullwidth forms
|| (c >= 0xFFE0 && c <= 0xFFE6)
|| (c >= 0x20000 && c <= 0x2FFFD)
|| (c >= 0x30000 && c <= 0x3FFFD)
);
}
}

View file

@ -190,7 +190,7 @@ inline bool IsPunct(int c) { return c != ' ' && !IsAlNum(c); }
inline bool IsSpace(int c) { return c == ' ' || c == '\f' || c == '\n' || c == '\r' || c == '\v' || c == '\t'; }
inline bool IsXDigit(int c) { return IsDigit(c) || c >= 'A' && c <= 'F' || c >= 'a' && c <= 'f'; }
inline bool IsCJKIdeograph(int c) { return c >= 0x2e80 && c <= 0xdfaf || c >= 0xf900 && c <= 0xfaff; }
bool IsDoubleWidth(int c);
word UnicodeCombine(word chr, word combine);
@ -253,6 +253,8 @@ bool SaveFileBOMUtf8(const char *path, const String& data);
// Deprecated
inline bool IsCJKIdeograph(int c) { return c >= 0x2e80 && c <= 0xdfaf || c >= 0xf900 && c <= 0xfaff; }
int ToUnicode(int chr, byte charset);
int FromUnicode(wchar wchr, byte charset, int defchar = DEFAULTCHAR);

View file

@ -393,10 +393,11 @@ character.&]
[s5;:IsXDigit`(int`): [@(0.0.255) bool]_[* IsXDigit]([@(0.0.255) int]_[*@3 c])&]
[s2;%% Returns true [%-*@3 c].is hexadecimal digit (0`-9, a`-f, A`-F).&]
[s3;%% &]
[s4;%% &]
[s5;:IsCJKIdeograph`(int`): [@(0.0.255) bool]_[* IsCJKIdeograph]([@(0.0.255) int]_[*@3 c])&]
[s2;%% Returns true if [%-*@3 c].is in UNICODE code`-point for CJK
ideogram.&]
[s4; &]
[s5;:Upp`:`:IsDoubleWidth`(int`): [@(0.0.255) bool]_[* IsDoubleWidth]([@(0.0.255) int]_[*@3 c
])&]
[s2;%% Returns true if [%-*@3 c] is a double`-width UNICODE character
(like CJK ideograph).&]
[s3;%% &]
[s4;%% &]
[s5;:UnicodeCombine`(word`,word`): [_^word^ word]_[* UnicodeCombine]([_^word^ word]_[*@3 chr],