characters in the ASCII range are unmodified, and a zero byte never appears
within non-zero characters.
+=cut
+*/
+
+/*
+=for apidoc is_ascii_string
+
+Returns true if first C<len> bytes of the given string are ASCII (i.e. none
+of them even raise the question of UTF-8-ness).
+
+See also is_utf8_string(), is_utf8_string_loclen(), and is_utf8_string_loc().
+
+=cut
+*/
+
+bool
+Perl_is_ascii_string(const U8 *s, STRLEN len)
+{
+ const U8* const send = s + (len ? len : strlen((const char *)s));
+ const U8* x = s;
+
+ PERL_ARGS_ASSERT_IS_ASCII_STRING;
+
+ for (; x < send; ++x) {
+ if (!UTF8_IS_INVARIANT(*x))
+ break;
+ }
+
+ return x == send;
+}
+
+/*
=for apidoc uvuni_to_utf8_flags
Adds the UTF-8 representation of the Unicode codepoint C<uv> to the end
=cut */
STRLEN
-Perl_is_utf8_char(pTHX_ const U8 *s)
+Perl_is_utf8_char(const U8 *s)
{
const STRLEN len = UTF8SKIP(s);
PERL_ARGS_ASSERT_IS_UTF8_CHAR;
- PERL_UNUSED_CONTEXT;
#ifdef IS_UTF8_CHAR
if (IS_UTF8_CHAR_FAST(len))
return IS_UTF8_CHAR(s, len) ? len : 0;
return is_utf8_char_slow(s, len);
}
+
/*
=for apidoc is_utf8_string
not mean 'a string that contains code points above 0x7F encoded in UTF-8'
because a valid ASCII string is a valid UTF-8 string.
-See also is_utf8_string_loclen() and is_utf8_string_loc().
+See also is_ascii_string(), is_utf8_string_loclen(), and is_utf8_string_loc().
=cut
*/
bool
-Perl_is_utf8_string(pTHX_ const U8 *s, STRLEN len)
+Perl_is_utf8_string(const U8 *s, STRLEN len)
{
const U8* const send = s + (len ? len : strlen((const char *)s));
const U8* x = s;
PERL_ARGS_ASSERT_IS_UTF8_STRING;
- PERL_UNUSED_CONTEXT;
while (x < send) {
STRLEN c;
*/
bool
-Perl_is_utf8_string_loclen(pTHX_ const U8 *s, STRLEN len, const U8 **ep, STRLEN *el)
+Perl_is_utf8_string_loclen(const U8 *s, STRLEN len, const U8 **ep, STRLEN *el)
{
const U8* const send = s + (len ? len : strlen((const char *)s));
const U8* x = s;
STRLEN outlen = 0;
PERL_ARGS_ASSERT_IS_UTF8_STRING_LOCLEN;
- PERL_UNUSED_CONTEXT;
while (x < send) {
/* Inline the easy bits of is_utf8_char() here for speed... */