summaryrefslogtreecommitdiff
path: root/utf8.c
diff options
context:
space:
mode:
Diffstat (limited to 'utf8.c')
-rw-r--r--utf8.c39
1 files changed, 39 insertions, 0 deletions
diff --git a/utf8.c b/utf8.c
index 8f6e84b7b3..7f648574a5 100644
--- a/utf8.c
+++ b/utf8.c
@@ -531,3 +531,42 @@ char *reencode_string(const char *in, const char *out_encoding, const char *in_e
return out;
}
#endif
+
+/*
+ * Returns first character length in bytes for multi-byte `text` according to
+ * `encoding`.
+ *
+ * - The `text` pointer is updated to point at the next character.
+ * - When `remainder_p` is not NULL, on entry `*remainder_p` is how much bytes
+ * we can consume from text, and on exit `*remainder_p` is reduced by returned
+ * character length. Otherwise `text` is treated as limited by NUL.
+ */
+int mbs_chrlen(const char **text, size_t *remainder_p, const char *encoding)
+{
+ int chrlen;
+ const char *p = *text;
+ size_t r = (remainder_p ? *remainder_p : SIZE_MAX);
+
+ if (r < 1)
+ return 0;
+
+ if (is_encoding_utf8(encoding)) {
+ pick_one_utf8_char(&p, &r);
+
+ chrlen = p ? (p - *text)
+ : 1 /* not valid UTF-8 -> raw byte sequence */;
+ }
+ else {
+ /*
+ * TODO use iconv to decode one char and obtain its chrlen
+ * for now, let's treat encodings != UTF-8 as one-byte
+ */
+ chrlen = 1;
+ }
+
+ *text += chrlen;
+ if (remainder_p)
+ *remainder_p -= chrlen;
+
+ return chrlen;
+}