zymon/st
1
0
Fork 0
mirror of https://github.com/LukeSmithxyz/st.git synced 2024-11-22 15:25:58 +01:00
Code Issues Projects Releases Packages Wiki Activity

Support UTF-8 characters as word delimiters

Browse source 
For a higher usefulness of the utf8strchr function, the index of the
UTF-8 character could be returned in addition with a Rune instead of a
char*.  Since utf8strchr is currently only used by ISDELIM I didn't
bother to increase the complexity.
This commit is contained in:
Jan Christoph Ebersbach 2015-05-22 16:06:57 +02:00 committed by Roberto E. Vargas Caballero
parent c03548750b
commit caa97cc781
1 changed files with 17 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

18
st.c
View file

@ -71,7 +71,7 @@ char *argv0;
#define ISCONTROLC0(c) (BETWEEN(c, 0, 0x1f) || (c) == '\177') #define ISCONTROLC0(c) (BETWEEN(c, 0, 0x1f) || (c) == '\177')
#define ISCONTROLC1(c) (BETWEEN(c, 0x80, 0x9f)) #define ISCONTROLC1(c) (BETWEEN(c, 0x80, 0x9f))
#define ISCONTROL(c) (ISCONTROLC0(c) || ISCONTROLC1(c)) #define ISCONTROL(c) (ISCONTROLC0(c) || ISCONTROLC1(c))
#define ISDELIM(u) (BETWEEN(u, 0, 127) && strchr(worddelimiters, u) != NULL) #define ISDELIM(u) (utf8strchr(worddelimiters, u) != NULL)
#define LIMIT(x, a, b) (x) = (x) < (a) ? (a) : (x) > (b) ? (b) : (x) #define LIMIT(x, a, b) (x) = (x) < (a) ? (a) : (x) > (b) ? (b) : (x)
#define ATTRCMP(a, b) ((a).mode != (b).mode || (a).fg != (b).fg || (a).bg != (b).bg) #define ATTRCMP(a, b) ((a).mode != (b).mode || (a).fg != (b).fg || (a).bg != (b).bg)
#define IS_SET(flag) ((term.mode & (flag)) != 0) #define IS_SET(flag) ((term.mode & (flag)) != 0)
@ -473,6 +473,7 @@ static size_t utf8decode(char *, Rune *, size_t);
static Rune utf8decodebyte(char, size_t *); static Rune utf8decodebyte(char, size_t *);
static size_t utf8encode(Rune, char *); static size_t utf8encode(Rune, char *);
static char utf8encodebyte(Rune, size_t); static char utf8encodebyte(Rune, size_t);
static char *utf8strchr(char *s, Rune u);
static size_t utf8validate(Rune *, size_t); static size_t utf8validate(Rune *, size_t);
static ssize_t xwrite(int, const char *, size_t); static ssize_t xwrite(int, const char *, size_t);
@ -640,6 +641,21 @@ utf8encodebyte(Rune u, size_t i) {
return utfbyte[i] | (u & ~utfmask[i]); return utfbyte[i] | (u & ~utfmask[i]);
} }
char *
utf8strchr(char *s, Rune u) {
Rune r;
size_t i, j, len;
len = strlen(s);
for(i = 0, j = 0; i < len; i += j) {
if(!(j = utf8decode(&s[i], &r, len - i)))
break;
if(r == u)
return &(s[i]);
}
return NULL;
}
size_t size_t
utf8validate(Rune *u, size_t i) { utf8validate(Rune *u, size_t i) {
if(!BETWEEN(*u, utfmin[i], utfmax[i]) || BETWEEN(*u, 0xD800, 0xDFFF)) if(!BETWEEN(*u, utfmin[i], utfmax[i]) || BETWEEN(*u, 0xD800, 0xDFFF))