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, 12 insertions, 0 deletions

diff --git a/source/shared.h b/source/shared.h
index d61c1f1..ca2ac6a 100644
--- a/source/shared.h
+++ b/source/shared.h
@@ -90,6 +90,18 @@ extern int cgit_read_first_line(const char *path, char **buf, size_t *size);
 extern char *cgit_strdup_first_line(const char *text);
 
 /*
+ * How many bytes the UTF-8 sequence at p holds, or 0 when it is invalid,
+ * looking at most left bytes ahead.
+ */
+extern size_t cgit_utf8_seq_len(const unsigned char *p, size_t left);
+
+/*
+ * Replace every byte of text that is not part of a valid UTF-8 sequence with
+ * a question mark, in place.
+ */
+extern void cgit_utf8_sanitize(char *text);
+
+/*
  * Replace every $token in text with the matching environment variable. The
  * result is a static buffer, so a caller that needs to keep it must copy it.
  */