Replace the stray bytes of text that is not UTF-8

A commit whose encoding header names something iconv cannot convert,
or whose text is labelled UTF-8 without being it, reached a page
declared UTF-8 with its bytes untouched. The atom feed already
replaced them, so its UTF-8 reader moves to shared.c and every ident,
subject, message and tag text passes through it.

1 file changed, 1 insertion, 34 deletions

diff --git a/source/ui-atom.c b/source/ui-atom.c
index b3265b7..b536437 100644
--- a/source/ui-atom.c
+++ b/source/ui-atom.c
@@ -28,39 +28,6 @@ static const char *feed_date(timestamp_t when)
 }
 
 /*
- * How many bytes the UTF-8 sequence at p holds, or 0 when invalid. The
- * lead-byte ranges fold in the overlong, surrogate and out-of-range cases,
- * so 0 is the only error signal a caller needs.
- */
-static size_t utf8_seq_len(const unsigned char *p, size_t left)
-{
-	size_t len, i;
-
-	if (p[0] >= 0xc2 && p[0] <= 0xdf)
-		len = 2;
-	else if (p[0] >= 0xe0 && p[0] <= 0xef)
-		len = 3;
-	else if (p[0] >= 0xf0 && p[0] <= 0xf4)
-		len = 4;
-	else
-		return 0;
-	if (left < len)
-		return 0;
-	for (i = 1; i < len; i++)
-		if ((p[i] & 0xc0) != 0x80)
-			return 0;
-	if (p[0] == 0xe0 && p[1] < 0xa0)
-		return 0;
-	if (p[0] == 0xed && p[1] > 0x9f)
-		return 0;
-	if (p[0] == 0xf0 && p[1] < 0x90)
-		return 0;
-	if (p[0] == 0xf4 && p[1] > 0x8f)
-		return 0;
-	return len;
-}
-
-/*
  * The XML counterpart of html_txt. A browser shrugs at a stray control byte
  * or broken UTF-8, but an XML reader must reject the whole feed, so both
  * are replaced instead of passed through.
@@ -85,7 +52,7 @@ static void xml_txt(const char *txt)
 			strbuf_addch(&sb, c);
 		} else if (c < 0x20) {
 			strbuf_addstr(&sb, XML_REPLACEMENT);
-		} else if ((seq = utf8_seq_len(p, left))) {
+		} else if ((seq = cgit_utf8_seq_len(p, left))) {
 			// U+FFFE and U+FFFF are valid UTF-8 but not XML.
 			if (seq == 3 && p[0] == 0xef && p[1] == 0xbf && p[2] >= 0xbe)
 				strbuf_addstr(&sb, XML_REPLACEMENT);