/*
=for apidoc valid_utf8_to_uvchr
-Like L</utf8_to_uvchr_buf>(), but should only be called when it is known that
+Like C<L</utf8_to_uvchr_buf>>, but should only be called when it is known that
the next character in the input UTF-8 string C<s> is well-formed (I<e.g.>,
it passes C<L</isUTF8_CHAR>>. Surrogates, non-character code points, and
non-Unicode code points are allowed.
PERL_STATIC_INLINE UV
Perl_valid_utf8_to_uvchr(const U8 *s, STRLEN *retlen)
{
- UV expectlen = UTF8SKIP(s);
+ const UV expectlen = UTF8SKIP(s);
const U8* send = s + expectlen;
UV uv = *s;
/*
=for apidoc is_utf8_invariant_string
-Returns true iff the first C<len> bytes of the string C<s> are the same
+Returns TRUE if the first C<len> bytes of the string C<s> are the same
regardless of the UTF-8 encoding of the string (or UTF-EBCDIC encoding on
-EBCDIC machines). That is, if they are UTF-8 invariant. On ASCII-ish
-machines, all the ASCII characters and only the ASCII characters fit this
-definition. On EBCDIC machines, the ASCII-range characters are invariant, but
-so also are the C1 controls and C<\c?> (which isn't in the ASCII range on
-EBCDIC).
+EBCDIC machines); otherwise it returns FALSE. That is, it returns TRUE if they
+are UTF-8 invariant. On ASCII-ish machines, all the ASCII characters and only
+the ASCII characters fit this definition. On EBCDIC machines, the ASCII-range
+characters are invariant, but so also are the C1 controls.
If C<len> is 0, it will be calculated using C<strlen(s)>, (which means if you
use this option, that C<s> can't have embedded C<NUL> characters and has to
have a terminating C<NUL> byte).
-See also L</is_utf8_string>(), L</is_utf8_string_loclen>(), and
-L</is_utf8_string_loc>().
+See also
+C<L</is_utf8_string>>,
+C<L</is_utf8_string_flags>>,
+C<L</is_utf8_string_loc>>,
+C<L</is_utf8_string_loc_flags>>,
+C<L</is_utf8_string_loclen>>,
+C<L</is_utf8_string_loclen_flags>>,
+C<L</is_utf8_fixed_width_buf_flags>>,
+C<L</is_utf8_fixed_width_buf_loc_flags>>,
+C<L</is_utf8_fixed_width_buf_loclen_flags>>,
+C<L</is_strict_utf8_string>>,
+C<L</is_strict_utf8_string_loc>>,
+C<L</is_strict_utf8_string_loclen>>,
+C<L</is_c9strict_utf8_string>>,
+C<L</is_c9strict_utf8_string_loc>>,
+and
+C<L</is_c9strict_utf8_string_loclen>>.
=cut
*/
/*
=for apidoc is_utf8_string
-Returns true if the first C<len> bytes of string C<s> form a valid
-UTF-8 string, false otherwise. If C<len> is 0, it will be calculated
-using C<strlen(s)> (which means if you use this option, that C<s> can't have
-embedded C<NUL> characters and has to have a terminating C<NUL> byte). Note
-that all characters being ASCII constitute 'a valid UTF-8 string'.
-
-See also L</is_utf8_invariant_string>(), L</is_utf8_string_loclen>(), and
-L</is_utf8_string_loc>().
+Returns TRUE if the first C<len> bytes of string C<s> form a valid
+Perl-extended-UTF-8 string; returns FALSE otherwise. If C<len> is 0, it will
+be calculated using C<strlen(s)> (which means if you use this option, that C<s>
+can't have embedded C<NUL> characters and has to have a terminating C<NUL>
+byte). Note that all characters being ASCII constitute 'a valid UTF-8 string'.
+
+This function considers Perl's extended UTF-8 to be valid. That means that
+code points above Unicode, surrogates, and non-character code points are
+considered valid by this function. Use C<L</is_strict_utf8_string>>,
+C<L</is_c9strict_utf8_string>>, or C<L</is_utf8_string_flags>> to restrict what
+code points are considered valid.
+
+See also
+C<L</is_utf8_invariant_string>>,
+C<L</is_utf8_string_loc>>,
+C<L</is_utf8_string_loclen>>,
+C<L</is_utf8_fixed_width_buf_flags>>,
+C<L</is_utf8_fixed_width_buf_loc_flags>>,
+C<L</is_utf8_fixed_width_buf_loclen_flags>>,
=cut
*/
PERL_STATIC_INLINE bool
-Perl_is_utf8_string(const U8 *s, STRLEN len)
+Perl_is_utf8_string(const U8 *s, const STRLEN len)
{
/* This is now marked pure in embed.fnc, because isUTF8_CHAR now is pure.
* Be aware of possible changes to that */
PERL_ARGS_ASSERT_IS_UTF8_STRING;
while (x < send) {
- STRLEN len = isUTF8_CHAR(x, send);
- if (UNLIKELY(! len)) {
+ const STRLEN cur_len = isUTF8_CHAR(x, send);
+ if (UNLIKELY(! cur_len)) {
+ return FALSE;
+ }
+ x += cur_len;
+ }
+
+ return TRUE;
+}
+
+/*
+=for apidoc is_strict_utf8_string
+
+Returns TRUE if the first C<len> bytes of string C<s> form a valid
+UTF-8-encoded string that is fully interchangeable by any application using
+Unicode rules; otherwise it returns FALSE. If C<len> is 0, it will be
+calculated using C<strlen(s)> (which means if you use this option, that C<s>
+can't have embedded C<NUL> characters and has to have a terminating C<NUL>
+byte). Note that all characters being ASCII constitute 'a valid UTF-8 string'.
+
+This function returns FALSE for strings containing any
+code points above the Unicode max of 0x10FFFF, surrogate code points, or
+non-character code points.
+
+See also
+C<L</is_utf8_invariant_string>>,
+C<L</is_utf8_string>>,
+C<L</is_utf8_string_flags>>,
+C<L</is_utf8_string_loc>>,
+C<L</is_utf8_string_loc_flags>>,
+C<L</is_utf8_string_loclen>>,
+C<L</is_utf8_string_loclen_flags>>,
+C<L</is_utf8_fixed_width_buf_flags>>,
+C<L</is_utf8_fixed_width_buf_loc_flags>>,
+C<L</is_utf8_fixed_width_buf_loclen_flags>>,
+C<L</is_strict_utf8_string_loc>>,
+C<L</is_strict_utf8_string_loclen>>,
+C<L</is_c9strict_utf8_string>>,
+C<L</is_c9strict_utf8_string_loc>>,
+and
+C<L</is_c9strict_utf8_string_loclen>>.
+
+=cut
+*/
+
+PERL_STATIC_INLINE bool
+S_is_strict_utf8_string(const U8 *s, const STRLEN len)
+{
+ const U8* const send = s + (len ? len : strlen((const char *)s));
+ const U8* x = s;
+
+ PERL_ARGS_ASSERT_IS_STRICT_UTF8_STRING;
+
+ while (x < send) {
+ const STRLEN cur_len = isSTRICT_UTF8_CHAR(x, send);
+ if (UNLIKELY(! cur_len)) {
+ return FALSE;
+ }
+ x += cur_len;
+ }
+
+ return TRUE;
+}
+
+/*
+=for apidoc is_c9strict_utf8_string
+
+Returns TRUE if the first C<len> bytes of string C<s> form a valid
+UTF-8-encoded string that conforms to
+L<Unicode Corrigendum #9|http://www.unicode.org/versions/corrigendum9.html>;
+otherwise it returns FALSE. If C<len> is 0, it will be calculated using
+C<strlen(s)> (which means if you use this option, that C<s> can't have embedded
+C<NUL> characters and has to have a terminating C<NUL> byte). Note that all
+characters being ASCII constitute 'a valid UTF-8 string'.
+
+This function returns FALSE for strings containing any code points above the
+Unicode max of 0x10FFFF or surrogate code points, but accepts non-character
+code points per
+L<Corrigendum #9|http://www.unicode.org/versions/corrigendum9.html>.
+
+See also
+C<L</is_utf8_invariant_string>>,
+C<L</is_utf8_string>>,
+C<L</is_utf8_string_flags>>,
+C<L</is_utf8_string_loc>>,
+C<L</is_utf8_string_loc_flags>>,
+C<L</is_utf8_string_loclen>>,
+C<L</is_utf8_string_loclen_flags>>,
+C<L</is_utf8_fixed_width_buf_flags>>,
+C<L</is_utf8_fixed_width_buf_loc_flags>>,
+C<L</is_utf8_fixed_width_buf_loclen_flags>>,
+C<L</is_strict_utf8_string>>,
+C<L</is_strict_utf8_string_loc>>,
+C<L</is_strict_utf8_string_loclen>>,
+C<L</is_c9strict_utf8_string_loc>>,
+and
+C<L</is_c9strict_utf8_string_loclen>>.
+
+=cut
+*/
+
+PERL_STATIC_INLINE bool
+S_is_c9strict_utf8_string(const U8 *s, const STRLEN len)
+{
+ const U8* const send = s + (len ? len : strlen((const char *)s));
+ const U8* x = s;
+
+ PERL_ARGS_ASSERT_IS_C9STRICT_UTF8_STRING;
+
+ while (x < send) {
+ const STRLEN cur_len = isC9_STRICT_UTF8_CHAR(x, send);
+ if (UNLIKELY(! cur_len)) {
return FALSE;
}
- x += len;
+ x += cur_len;
+ }
+
+ return TRUE;
+}
+
+/* The above 3 functions could have been moved into the more general one just
+ * below, and made #defines that call it with the right 'flags'. They are
+ * currently kept separate to increase their chances of getting inlined */
+
+/*
+=for apidoc is_utf8_string_flags
+
+Returns TRUE if the first C<len> bytes of string C<s> form a valid
+UTF-8 string, subject to the restrictions imposed by C<flags>;
+returns FALSE otherwise. If C<len> is 0, it will be calculated
+using C<strlen(s)> (which means if you use this option, that C<s> can't have
+embedded C<NUL> characters and has to have a terminating C<NUL> byte). Note
+that all characters being ASCII constitute 'a valid UTF-8 string'.
+
+If C<flags> is 0, this gives the same results as C<L</is_utf8_string>>; if
+C<flags> is C<UTF8_DISALLOW_ILLEGAL_INTERCHANGE>, this gives the same results
+as C<L</is_strict_utf8_string>>; and if C<flags> is
+C<UTF8_DISALLOW_ILLEGAL_C9_INTERCHANGE>, this gives the same results as
+C<L</is_c9strict_utf8_string>>. Otherwise C<flags> may be any
+combination of the C<UTF8_DISALLOW_I<foo>> flags understood by
+C<L</utf8n_to_uvchr>>, with the same meanings.
+
+See also
+C<L</is_utf8_invariant_string>>,
+C<L</is_utf8_string>>,
+C<L</is_utf8_string_loc>>,
+C<L</is_utf8_string_loc_flags>>,
+C<L</is_utf8_string_loclen>>,
+C<L</is_utf8_string_loclen_flags>>,
+C<L</is_utf8_fixed_width_buf_flags>>,
+C<L</is_utf8_fixed_width_buf_loc_flags>>,
+C<L</is_utf8_fixed_width_buf_loclen_flags>>,
+C<L</is_strict_utf8_string>>,
+C<L</is_strict_utf8_string_loc>>,
+C<L</is_strict_utf8_string_loclen>>,
+C<L</is_c9strict_utf8_string>>,
+C<L</is_c9strict_utf8_string_loc>>,
+and
+C<L</is_c9strict_utf8_string_loclen>>.
+
+=cut
+*/
+
+PERL_STATIC_INLINE bool
+S_is_utf8_string_flags(const U8 *s, const STRLEN len, const U32 flags)
+{
+ const U8* const send = s + (len ? len : strlen((const char *)s));
+ const U8* x = s;
+
+ PERL_ARGS_ASSERT_IS_UTF8_STRING_FLAGS;
+ assert(0 == (flags & ~(UTF8_DISALLOW_ILLEGAL_INTERCHANGE
+ |UTF8_DISALLOW_ABOVE_31_BIT)));
+
+ if (flags == 0) {
+ return is_utf8_string(s, len);
+ }
+
+ if ((flags & ~UTF8_DISALLOW_ABOVE_31_BIT)
+ == UTF8_DISALLOW_ILLEGAL_INTERCHANGE)
+ {
+ return is_strict_utf8_string(s, len);
+ }
+
+ if ((flags & ~UTF8_DISALLOW_ABOVE_31_BIT)
+ == UTF8_DISALLOW_ILLEGAL_C9_INTERCHANGE)
+ {
+ return is_c9strict_utf8_string(s, len);
+ }
+
+ while (x < send) {
+ STRLEN cur_len = isUTF8_CHAR_flags(x, send, flags);
+ if (UNLIKELY(! cur_len)) {
+ return FALSE;
+ }
+ x += cur_len;
}
return TRUE;
}
/*
-Implemented as a macro in utf8.h
=for apidoc is_utf8_string_loc
-Like L</is_utf8_string> but stores the location of the failure (in the
+Like C<L</is_utf8_string>> but stores the location of the failure (in the
case of "utf8ness failure") or the location C<s>+C<len> (in the case of
-"utf8ness success") in the C<ep>.
+"utf8ness success") in the C<ep> pointer.
+
+See also C<L</is_utf8_string_loclen>>.
+
+=cut
+*/
+
+#define is_utf8_string_loc(s, len, ep) is_utf8_string_loclen(s, len, ep, 0)
-See also L</is_utf8_string_loclen>() and L</is_utf8_string>().
+/*
=for apidoc is_utf8_string_loclen
-Like L</is_utf8_string>() but stores the location of the failure (in the
+Like C<L</is_utf8_string>> but stores the location of the failure (in the
case of "utf8ness failure") or the location C<s>+C<len> (in the case of
-"utf8ness success") in the C<ep>, and the number of UTF-8
-encoded characters in the C<el>.
+"utf8ness success") in the C<ep> pointer, and the number of UTF-8
+encoded characters in the C<el> pointer.
-See also L</is_utf8_string_loc>() and L</is_utf8_string>().
+See also C<L</is_utf8_string_loc>>.
=cut
*/
PERL_STATIC_INLINE bool
-Perl_is_utf8_string_loclen(const U8 *s, STRLEN len, const U8 **ep, STRLEN *el)
+Perl_is_utf8_string_loclen(const U8 *s, const STRLEN len, const U8 **ep, STRLEN *el)
{
const U8* const send = s + (len ? len : strlen((const char *)s));
const U8* x = s;
PERL_ARGS_ASSERT_IS_UTF8_STRING_LOCLEN;
while (x < send) {
- STRLEN len = isUTF8_CHAR(x, send);
- if (UNLIKELY(! len)) {
+ const STRLEN cur_len = isUTF8_CHAR(x, send);
+ if (UNLIKELY(! cur_len)) {
+ break;
+ }
+ x += cur_len;
+ outlen++;
+ }
+
+ if (el)
+ *el = outlen;
+
+ if (ep) {
+ *ep = x;
+ }
+
+ return (x == send);
+}
+
+/*
+
+=for apidoc is_strict_utf8_string_loc
+
+Like C<L</is_strict_utf8_string>> but stores the location of the failure (in the
+case of "utf8ness failure") or the location C<s>+C<len> (in the case of
+"utf8ness success") in the C<ep> pointer.
+
+See also C<L</is_strict_utf8_string_loclen>>.
+
+=cut
+*/
+
+#define is_strict_utf8_string_loc(s, len, ep) \
+ is_strict_utf8_string_loclen(s, len, ep, 0)
+
+/*
+
+=for apidoc is_strict_utf8_string_loclen
+
+Like C<L</is_strict_utf8_string>> but stores the location of the failure (in the
+case of "utf8ness failure") or the location C<s>+C<len> (in the case of
+"utf8ness success") in the C<ep> pointer, and the number of UTF-8
+encoded characters in the C<el> pointer.
+
+See also C<L</is_strict_utf8_string_loc>>.
+
+=cut
+*/
+
+PERL_STATIC_INLINE bool
+S_is_strict_utf8_string_loclen(const U8 *s, const 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_STRICT_UTF8_STRING_LOCLEN;
+
+ while (x < send) {
+ const STRLEN cur_len = isSTRICT_UTF8_CHAR(x, send);
+ if (UNLIKELY(! cur_len)) {
+ break;
+ }
+ x += cur_len;
+ outlen++;
+ }
+
+ if (el)
+ *el = outlen;
+
+ if (ep) {
+ *ep = x;
+ }
+
+ return (x == send);
+}
+
+/*
+
+=for apidoc is_c9strict_utf8_string_loc
+
+Like C<L</is_c9strict_utf8_string>> but stores the location of the failure (in
+the case of "utf8ness failure") or the location C<s>+C<len> (in the case of
+"utf8ness success") in the C<ep> pointer.
+
+See also C<L</is_c9strict_utf8_string_loclen>>.
+
+=cut
+*/
+
+#define is_c9strict_utf8_string_loc(s, len, ep) \
+ is_c9strict_utf8_string_loclen(s, len, ep, 0)
+
+/*
+
+=for apidoc is_c9strict_utf8_string_loclen
+
+Like C<L</is_c9strict_utf8_string>> but stores the location of the failure (in
+the case of "utf8ness failure") or the location C<s>+C<len> (in the case of
+"utf8ness success") in the C<ep> pointer, and the number of UTF-8 encoded
+characters in the C<el> pointer.
+
+See also C<L</is_c9strict_utf8_string_loc>>.
+
+=cut
+*/
+
+PERL_STATIC_INLINE bool
+S_is_c9strict_utf8_string_loclen(const U8 *s, const 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_C9STRICT_UTF8_STRING_LOCLEN;
+
+ while (x < send) {
+ const STRLEN cur_len = isC9_STRICT_UTF8_CHAR(x, send);
+ if (UNLIKELY(! cur_len)) {
break;
}
- x += len;
+ x += cur_len;
+ outlen++;
+ }
+
+ if (el)
+ *el = outlen;
+
+ if (ep) {
+ *ep = x;
+ }
+
+ return (x == send);
+}
+
+/*
+
+=for apidoc is_utf8_string_loc_flags
+
+Like C<L</is_utf8_string_flags>> but stores the location of the failure (in the
+case of "utf8ness failure") or the location C<s>+C<len> (in the case of
+"utf8ness success") in the C<ep> pointer.
+
+See also C<L</is_utf8_string_loclen_flags>>.
+
+=cut
+*/
+
+#define is_utf8_string_loc_flags(s, len, ep, flags) \
+ is_utf8_string_loclen_flags(s, len, ep, 0, flags)
+
+
+/* The above 3 actual functions could have been moved into the more general one
+ * just below, and made #defines that call it with the right 'flags'. They are
+ * currently kept separate to increase their chances of getting inlined */
+
+/*
+
+=for apidoc is_utf8_string_loclen_flags
+
+Like C<L</is_utf8_string_flags>> but stores the location of the failure (in the
+case of "utf8ness failure") or the location C<s>+C<len> (in the case of
+"utf8ness success") in the C<ep> pointer, and the number of UTF-8
+encoded characters in the C<el> pointer.
+
+See also C<L</is_utf8_string_loc_flags>>.
+
+=cut
+*/
+
+PERL_STATIC_INLINE bool
+S_is_utf8_string_loclen_flags(const U8 *s, const STRLEN len, const U8 **ep, STRLEN *el, const U32 flags)
+{
+ 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_FLAGS;
+ assert(0 == (flags & ~(UTF8_DISALLOW_ILLEGAL_INTERCHANGE
+ |UTF8_DISALLOW_ABOVE_31_BIT)));
+
+ if (flags == 0) {
+ return is_utf8_string_loclen(s, len, ep, el);
+ }
+
+ if ((flags & ~UTF8_DISALLOW_ABOVE_31_BIT)
+ == UTF8_DISALLOW_ILLEGAL_INTERCHANGE)
+ {
+ return is_strict_utf8_string_loclen(s, len, ep, el);
+ }
+
+ if ((flags & ~UTF8_DISALLOW_ABOVE_31_BIT)
+ == UTF8_DISALLOW_ILLEGAL_C9_INTERCHANGE)
+ {
+ return is_c9strict_utf8_string_loclen(s, len, ep, el);
+ }
+
+ while (x < send) {
+ const STRLEN cur_len = isUTF8_CHAR_flags(x, send, flags);
+ if (UNLIKELY(! cur_len)) {
+ break;
+ }
+ x += cur_len;
outlen++;
}
=cut
*/
-#define is_utf8_valid_partial_char(s, e) is_utf8_valid_partial_char_flags(s, e, 0)
+#define is_utf8_valid_partial_char(s, e) \
+ is_utf8_valid_partial_char_flags(s, e, 0)
/*
of the C<UTF8_DISALLOW_I<foo>> flags accepted by C<L</utf8n_to_uvchr>>. If
there is any sequence of bytes that can complete the input partial character in
such a way that a non-prohibited character is formed, the function returns
-TRUE; otherwise FALSE. Non characters cannot be determined based on partial
-character input. But many of the other possible excluded types can be
+TRUE; otherwise FALSE. Non character code points cannot be determined based on
+partial character input. But many of the other possible excluded types can be
determined from just the first one or two bytes.
=cut
return cBOOL(_is_utf8_char_helper(s, e, flags));
}
+/*
+
+=for apidoc is_utf8_fixed_width_buf_flags
+
+Returns TRUE if the fixed-width buffer starting at C<s> with length C<len>
+is entirely valid UTF-8, subject to the restrictions given by C<flags>;
+otherwise it returns FALSE.
+
+If C<flags> is 0, any well-formed UTF-8, as extended by Perl, is accepted
+without restriction. If the final few bytes of the buffer do not form a
+complete code point, this will return TRUE anyway, provided that
+C<L</is_utf8_valid_partial_char_flags>> returns TRUE for them.
+
+If C<flags> in non-zero, it can be any combination of the
+C<UTF8_DISALLOW_I<foo>> flags accepted by C<L</utf8n_to_uvchr>>, and with the
+same meanings.
+
+This function differs from C<L</is_utf8_string_flags>> only in that the latter
+returns FALSE if the final few bytes of the string don't form a complete code
+point.
+
+=cut
+ */
+#define is_utf8_fixed_width_buf_flags(s, len, flags) \
+ is_utf8_fixed_width_buf_loclen_flags(s, len, 0, 0, flags)
+
+/*
+
+=for apidoc is_utf8_fixed_width_buf_loc_flags
+
+Like C<L</is_utf8_fixed_width_buf_flags>> but stores the location of the
+failure in the C<ep> pointer. If the function returns TRUE, C<*ep> will point
+to the beginning of any partial character at the end of the buffer; if there is
+no partial character C<*ep> will contain C<s>+C<len>.
+
+See also C<L</is_utf8_fixed_width_buf_loclen_flags>>.
+
+=cut
+*/
+
+#define is_utf8_fixed_width_buf_loc_flags(s, len, loc, flags) \
+ is_utf8_fixed_width_buf_loclen_flags(s, len, loc, 0, flags)
+
+/*
+
+=for apidoc is_utf8_fixed_width_buf_loclen_flags
+
+Like C<L</is_utf8_fixed_width_buf_loc_flags>> but stores the number of
+complete, valid characters found in the C<el> pointer.
+
+=cut
+*/
+
+PERL_STATIC_INLINE bool
+S_is_utf8_fixed_width_buf_loclen_flags(const U8 * const s,
+ const STRLEN len,
+ const U8 **ep,
+ STRLEN *el,
+ const U32 flags)
+{
+ const U8 * maybe_partial;
+
+ PERL_ARGS_ASSERT_IS_UTF8_FIXED_WIDTH_BUF_LOCLEN_FLAGS;
+
+ if (! ep) {
+ ep = &maybe_partial;
+ }
+
+ /* If it's entirely valid, return that; otherwise see if the only error is
+ * that the final few bytes are for a partial character */
+ return is_utf8_string_loclen_flags(s, len, ep, el, flags)
+ || is_utf8_valid_partial_char_flags(*ep, s + len, flags);
+}
+
/* ------------------------------- perl.h ----------------------------- */
/*