summaryrefslogtreecommitdiffhomepage
path: root/src/string.c
diff options
context:
space:
mode:
authorYukihiro "Matz" Matsumoto <[email protected]>2020-04-28 13:16:27 +0900
committerHiroshi Mimaki <[email protected]>2020-05-07 09:31:07 +0900
commitf5ee7df7f34774e398816cac6d7a9f093907b430 (patch)
treee74fe459e33c7c1461b485f0de28051592c2c536 /src/string.c
parente77e6e9d1237a6999a1e1bb6dcd2c7fa8e6187b4 (diff)
downloadmruby-f5ee7df7f34774e398816cac6d7a9f093907b430.tar.gz
mruby-f5ee7df7f34774e398816cac6d7a9f093907b430.zip
Rename (and expose) UTF-8 related functions; ref #4712
- mrb_utf8len() - returns the size of a UTF-8 char (in bytes) - mrb_utf8_strlen() - returns the length of a UTF-8 string (in char)
Diffstat (limited to 'src/string.c')
-rw-r--r--src/string.c26
1 files changed, 13 insertions, 13 deletions
diff --git a/src/string.c b/src/string.c
index 2ef1ad95a..458c511dc 100644
--- a/src/string.c
+++ b/src/string.c
@@ -301,8 +301,8 @@ static const char utf8len_codepage[256] =
3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,4,4,4,4,4,1,1,1,1,1,1,1,1,1,1,1,
};
-static mrb_int
-utf8len(const char* p, const char* e)
+mrb_int
+mrb_utf8len(const char* p, const char* e)
{
mrb_int len;
mrb_int i;
@@ -318,14 +318,14 @@ utf8len(const char* p, const char* e)
}
mrb_int
-mrb_utf8_len(const char *str, mrb_int byte_len)
+mrb_utf8_strlen(const char *str, mrb_int byte_len)
{
mrb_int total = 0;
const char *p = str;
const char *e = p + byte_len;
while (p < e) {
- p += utf8len(p, e);
+ p += mrb_utf8len(p, e);
total++;
}
return total;
@@ -341,7 +341,7 @@ utf8_strlen(mrb_value str)
return byte_len;
}
else {
- mrb_int utf8_len = mrb_utf8_len(RSTR_PTR(s), byte_len);
+ mrb_int utf8_len = mrb_utf8_strlen(RSTR_PTR(s), byte_len);
if (byte_len == utf8_len) RSTR_SET_ASCII_FLAG(s);
return utf8_len;
}
@@ -362,7 +362,7 @@ chars2bytes(mrb_value s, mrb_int off, mrb_int idx)
const char *e = RSTRING_END(s);
for (b=i=0; p<e && i<idx; i++) {
- n = utf8len(p, e);
+ n = mrb_utf8len(p, e);
b += n;
p += n;
}
@@ -379,7 +379,7 @@ bytes2chars(char *p, mrb_int len, mrb_int bi)
mrb_int i;
for (i = 0; p < pivot; i ++) {
- p += utf8len(p, e);
+ p += mrb_utf8len(p, e);
}
if (p != pivot) return -1;
return i;
@@ -400,7 +400,7 @@ char_adjust(const char *beg, const char *end, const char *ptr)
while (p > beg) {
p --;
if ((*p & 0xc0) != 0x80) {
- int clen = utf8len(p, end);
+ int clen = mrb_utf8len(p, end);
if (clen > ptr - p) return p;
break;
}
@@ -466,7 +466,7 @@ str_index_str_by_char_search(mrb_state *mrb, const char *p, const char *pend, co
if (pivot >= pend || pivot < p /* overflowed */) { return -1; }
do {
- p += utf8len(p, pend);
+ p += mrb_utf8len(p, pend);
off ++;
} while (p < pivot);
}
@@ -485,7 +485,7 @@ str_index_str_by_char(mrb_state *mrb, mrb_value str, mrb_value sub, mrb_int pos)
for (; pos > 0; pos --) {
if (pend - p < 1) { return -1; }
- p += utf8len(p, pend);
+ p += mrb_utf8len(p, pend);
}
if (slen < 1) { return off; }
@@ -1362,7 +1362,7 @@ str_escape(mrb_state *mrb, mrb_value str, mrb_bool inspect)
unsigned char c, cc;
#ifdef MRB_UTF8_STRING
if (inspect) {
- mrb_int clen = utf8len(p, pend);
+ mrb_int clen = mrb_utf8len(p, pend);
if (clen > 1) {
mrb_int i;
@@ -1665,7 +1665,7 @@ mrb_str_chop_bang(mrb_state *mrb, mrb_value str)
const char* t = RSTR_PTR(s), *p = t;
const char* e = p + RSTR_LEN(s);
while (p<e) {
- mrb_int clen = utf8len(p, e);
+ mrb_int clen = mrb_utf8len(p, e);
if (p + clen>=e) break;
p += clen;
}
@@ -2037,7 +2037,7 @@ mrb_str_reverse_bang(mrb_state *mrb, mrb_value str)
p = RSTR_PTR(s);
e = p + RSTR_LEN(s);
while (p<e) {
- mrb_int clen = utf8len(p, e);
+ mrb_int clen = mrb_utf8len(p, e);
str_reverse(p, p + clen - 1);
p += clen;
}