Add is_utf8_valid_partial_char()

This new function can test some purported UTF-8 to see if it is
well-formed as far as it goes.  That is there aren't enough bytes for
the character they start, but what is there is legal so far.  This can
be useful in a fixed width buffer, where the final character is split in
the middle, and we want to test without waiting for the next read that
the entire buffer is valid.

1 files changed, 5 insertions, 0 deletions

diff --git a/proto.h b/proto.h
index 8f2371806a..9a4fa58459 100644
--- a/proto.h
+++ b/proto.h
@@ -1625,6 +1625,11 @@ PERL_CALLCONV bool	Perl_is_utf8_upper(pTHX_ const U8 *p)
 #define PERL_ARGS_ASSERT_IS_UTF8_UPPER	\
 	assert(p)
 
+PERL_STATIC_INLINE bool	S_is_utf8_valid_partial_char(const U8 * const s, const U8 * const e)
+			__attribute__pure__;
+#define PERL_ARGS_ASSERT_IS_UTF8_VALID_PARTIAL_CHAR	\
+	assert(s); assert(e)
+
 PERL_CALLCONV bool	Perl_is_utf8_xdigit(pTHX_ const U8 *p)
 			__attribute__deprecated__
 			__attribute__warn_unused_result__;