Support UTF-8 characters as word delimiters - st - Personal fork of st
(HTM) git clone git://git.drkhsh.at/st.git
(DIR) Log
(DIR) Files
(DIR) Refs
(DIR) README
(DIR) LICENSE
---
(DIR) commit caa97cc781ccf29f28c3d9e6683a66eb3f70e2bd
(DIR) parent c03548750b2527a6ddb5edfd945c5799066a6224
(HTM) Author: Jan Christoph Ebersbach <jceb@e-jc.de>
Date: Fri, 22 May 2015 16:06:57 +0200
Support UTF-8 characters as word delimiters
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.
Diffstat:
M st.c | 18 +++++++++++++++++-
1 file changed, 17 insertions(+), 1 deletion(-)
---
(DIR) diff --git a/st.c b/st.c
@@ -71,7 +71,7 @@ char *argv0;
#define ISCONTROLC0(c) (BETWEEN(c, 0, 0x1f) || (c) == '\177')
#define ISCONTROLC1(c) (BETWEEN(c, 0x80, 0x9f))
#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 ATTRCMP(a, b) ((a).mode != (b).mode || (a).fg != (b).fg || (a).bg != (b).bg)
#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 size_t utf8encode(Rune, char *);
static char utf8encodebyte(Rune, size_t);
+static char *utf8strchr(char *s, Rune u);
static size_t utf8validate(Rune *, 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]);
}
+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
utf8validate(Rune *u, size_t i) {
if(!BETWEEN(*u, utfmin[i], utfmax[i]) || BETWEEN(*u, 0xD800, 0xDFFF))