From 79e7a4bbf7055e33b346564db769f03e85f98988 Mon Sep 17 00:00:00 2001
From: Vicent Marti <tanoku@gmail.com>
Date: Wed, 10 Sep 2014 19:40:40 +0200
Subject: Improve invalid UTF8 codepoint skipping
---
src/utf8.c | 10 +++++-----
1 file changed, 5 insertions(+), 5 deletions(-)
(limited to 'src')
diff --git a/src/utf8.c b/src/utf8.c
index 1b0224b..6b34831 100644
--- a/src/utf8.c
+++ b/src/utf8.c
@@ -79,14 +79,14 @@ void utf8proc_detab(strbuf *ob, const uint8_t *line, size_t size)
} else {
int charlen = utf8proc_charlen(line + i, size - i);
- if (charlen < 0) {
- encode_unknown(ob);
- i++;
- } else {
+ if (charlen >= 0) {
strbuf_put(ob, line + i, charlen);
- i += charlen;
+ } else {
+ encode_unknown(ob);
+ charlen = -charlen;
}
+ i += charlen;
tab += 1;
}
}
--
cgit v1.2.3