/* utf8.c
*
- * Copyright (C) 2000, 2001, 2002, 2003, 2004, by Larry Wall and others
+ * Copyright (C) 2000, 2001, 2002, 2003, 2004, 2005 by Larry Wall and
+ * others
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
/*
-=for apidoc A|STRLEN|is_utf8_char|U8 *s
+=for apidoc A|STRLEN|is_utf8_char|const U8 *s
Tests if some arbitrary number of bytes begins in a valid UTF-8
character. Note that an INVARIANT (i.e. ASCII) character is a valid
=cut */
STRLEN
-Perl_is_utf8_char(pTHX_ U8 *s)
+Perl_is_utf8_char(pTHX_ const U8 *s)
{
U8 u = *s;
STRLEN slen, len;
}
/*
-=for apidoc A|bool|is_utf8_string|U8 *s|STRLEN len
+=for apidoc A|bool|is_utf8_string|const U8 *s|STRLEN len
Returns true if first C<len> bytes of the given string form a valid
UTF-8 string, false otherwise. Note that 'a valid UTF-8 string' does
*/
bool
-Perl_is_utf8_string(pTHX_ U8 *s, STRLEN len)
+Perl_is_utf8_string(pTHX_ const U8 *s, STRLEN len)
{
- U8* x = s;
- U8* send;
+ const U8* x = s;
+ const U8* send;
STRLEN c;
if (!len && s)
}
/*
-=for apidoc A|bool|is_utf8_string_loc|U8 *s|STRLEN len|U8 **p
+=for apidoc A|bool|is_utf8_string_loc|const U8 *s|STRLEN len|const U8 **p
Like is_ut8_string but store the location of the failure in
the last argument.
*/
bool
-Perl_is_utf8_string_loc(pTHX_ U8 *s, STRLEN len, U8 **p)
+Perl_is_utf8_string_loc(pTHX_ const U8 *s, STRLEN len, const U8 **p)
{
- U8* x = s;
- U8* send;
+ const U8* x = s;
+ const U8* send;
STRLEN c;
if (!len && s)
}
/*
-=for apidoc A|UV|utf8n_to_uvuni|U8 *s|STRLEN curlen|STRLEN *retlen|U32 flags
+=for apidoc A|UV|utf8n_to_uvuni|const U8 *s|STRLEN curlen|STRLEN *retlen|U32 flags
Bottom level UTF-8 decode routine.
Returns the unicode code point value of the first character in the string C<s>
*/
UV
-Perl_utf8n_to_uvuni(pTHX_ U8 *s, STRLEN curlen, STRLEN *retlen, U32 flags)
+Perl_utf8n_to_uvuni(pTHX_ const U8 *s, STRLEN curlen, STRLEN *retlen, U32 flags)
{
- U8 *s0 = s;
+ const U8 *s0 = s;
UV uv = *s, ouv = 0;
STRLEN len = 1;
- bool dowarn = ckWARN_d(WARN_UTF8);
- UV startbyte = *s;
+ const bool dowarn = ckWARN_d(WARN_UTF8);
+ const UV startbyte = *s;
STRLEN expectlen = 0;
U32 warning = 0;
}
/*
-=for apidoc A|UV|utf8_to_uvchr|U8 *s|STRLEN *retlen
+=for apidoc A|UV|utf8_to_uvchr|const U8 *s|STRLEN *retlen
Returns the native character value of the first character in the string C<s>
which is assumed to be in UTF-8 encoding; C<retlen> will be set to the
*/
UV
-Perl_utf8_to_uvchr(pTHX_ U8 *s, STRLEN *retlen)
+Perl_utf8_to_uvchr(pTHX_ const U8 *s, STRLEN *retlen)
{
return Perl_utf8n_to_uvchr(aTHX_ s, UTF8_MAXBYTES, retlen,
ckWARN(WARN_UTF8) ? 0 : UTF8_ALLOW_ANY);
}
/*
-=for apidoc A|UV|utf8_to_uvuni|U8 *s|STRLEN *retlen
+=for apidoc A|UV|utf8_to_uvuni|const U8 *s|STRLEN *retlen
Returns the Unicode code point of the first character in the string C<s>
which is assumed to be in UTF-8 encoding; C<retlen> will be set to the
*/
UV
-Perl_utf8_to_uvuni(pTHX_ U8 *s, STRLEN *retlen)
+Perl_utf8_to_uvuni(pTHX_ const U8 *s, STRLEN *retlen)
{
/* Call the low level routine asking for checks */
return Perl_utf8n_to_uvuni(aTHX_ s, UTF8_MAXBYTES, retlen,
}
/*
-=for apidoc A|STRLEN|utf8_length|U8 *s|U8 *e
+=for apidoc A|STRLEN|utf8_length|const U8 *s|const U8 *e
Return the length of the UTF-8 char encoded string C<s> in characters.
Stops at C<e> (inclusive). If C<e E<lt> s> or if the scan would end
*/
STRLEN
-Perl_utf8_length(pTHX_ U8 *s, U8 *e)
+Perl_utf8_length(pTHX_ const U8 *s, const U8 *e)
{
STRLEN len = 0;
}
/*
-=for apidoc A|IV|utf8_distance|U8 *a|U8 *b
+=for apidoc A|IV|utf8_distance|const U8 *a|const U8 *b
Returns the number of UTF-8 characters between the UTF-8 pointers C<a>
and C<b>.
*/
IV
-Perl_utf8_distance(pTHX_ U8 *a, U8 *b)
+Perl_utf8_distance(pTHX_ const U8 *a, const U8 *b)
{
IV off = 0;
if (a < b) {
while (a < b) {
- U8 c = UTF8SKIP(a);
+ const U8 c = UTF8SKIP(a);
if (b - a < c) {
if (ckWARN_d(WARN_UTF8)) {
=for apidoc A|U8 *|bytes_from_utf8|U8 *s|STRLEN *len|bool *is_utf8
Converts a string C<s> of length C<len> from UTF-8 into byte encoding.
-Unlike <utf8_to_bytes> but like C<bytes_to_utf8>, returns a pointer to
+Unlike C<utf8_to_bytes> but like C<bytes_to_utf8>, returns a pointer to
the newly-created string, and updates C<len> to contain the new
length. Returns the original string if no conversion occurs, C<len>
is unchanged. Do nothing if C<is_utf8> points to 0. Sets C<is_utf8> to
}
/*
-=for apidoc A|U8 *|bytes_to_utf8|U8 *s|STRLEN *len
+=for apidoc A|U8 *|bytes_to_utf8|const U8 *s|STRLEN *len
Converts a string C<s> of length C<len> from ASCII into UTF-8 encoding.
Returns a pointer to the newly-created string, and sets C<len> to
*/
U8*
-Perl_bytes_to_utf8(pTHX_ U8 *s, STRLEN *len)
+Perl_bytes_to_utf8(pTHX_ const U8 *s, STRLEN *len)
{
- U8 *send;
+ const U8 * const send = s + (*len);
U8 *d;
U8 *dst;
- send = s + (*len);
Newz(801, d, (*len) * 2 + 1, U8);
dst = d;
while (s < send) {
- UV uv = NATIVE_TO_ASCII(*s++);
+ const UV uv = NATIVE_TO_ASCII(*s++);
if (UNI_IS_INVARIANT(uv))
*d++ = (U8)UTF_TO_NATIVE(uv);
else {
}
bool
-Perl_is_utf8_alnum(pTHX_ U8 *p)
+Perl_is_utf8_alnum(pTHX_ const U8 *p)
{
if (!is_utf8_char(p))
return FALSE;
}
bool
-Perl_is_utf8_alnumc(pTHX_ U8 *p)
+Perl_is_utf8_alnumc(pTHX_ const U8 *p)
{
if (!is_utf8_char(p))
return FALSE;
}
bool
-Perl_is_utf8_idfirst(pTHX_ U8 *p) /* The naming is historical. */
+Perl_is_utf8_idfirst(pTHX_ const U8 *p) /* The naming is historical. */
{
if (*p == '_')
return TRUE;
}
bool
-Perl_is_utf8_idcont(pTHX_ U8 *p)
+Perl_is_utf8_idcont(pTHX_ const U8 *p)
{
if (*p == '_')
return TRUE;
}
bool
-Perl_is_utf8_alpha(pTHX_ U8 *p)
+Perl_is_utf8_alpha(pTHX_ const U8 *p)
{
if (!is_utf8_char(p))
return FALSE;
}
bool
-Perl_is_utf8_ascii(pTHX_ U8 *p)
+Perl_is_utf8_ascii(pTHX_ const U8 *p)
{
if (!is_utf8_char(p))
return FALSE;
}
bool
-Perl_is_utf8_space(pTHX_ U8 *p)
+Perl_is_utf8_space(pTHX_ const U8 *p)
{
if (!is_utf8_char(p))
return FALSE;
}
bool
-Perl_is_utf8_digit(pTHX_ U8 *p)
+Perl_is_utf8_digit(pTHX_ const U8 *p)
{
if (!is_utf8_char(p))
return FALSE;
}
bool
-Perl_is_utf8_upper(pTHX_ U8 *p)
+Perl_is_utf8_upper(pTHX_ const U8 *p)
{
if (!is_utf8_char(p))
return FALSE;
}
bool
-Perl_is_utf8_lower(pTHX_ U8 *p)
+Perl_is_utf8_lower(pTHX_ const U8 *p)
{
if (!is_utf8_char(p))
return FALSE;
}
bool
-Perl_is_utf8_cntrl(pTHX_ U8 *p)
+Perl_is_utf8_cntrl(pTHX_ const U8 *p)
{
if (!is_utf8_char(p))
return FALSE;
}
bool
-Perl_is_utf8_graph(pTHX_ U8 *p)
+Perl_is_utf8_graph(pTHX_ const U8 *p)
{
if (!is_utf8_char(p))
return FALSE;
}
bool
-Perl_is_utf8_print(pTHX_ U8 *p)
+Perl_is_utf8_print(pTHX_ const U8 *p)
{
if (!is_utf8_char(p))
return FALSE;
}
bool
-Perl_is_utf8_punct(pTHX_ U8 *p)
+Perl_is_utf8_punct(pTHX_ const U8 *p)
{
if (!is_utf8_char(p))
return FALSE;
}
bool
-Perl_is_utf8_xdigit(pTHX_ U8 *p)
+Perl_is_utf8_xdigit(pTHX_ const U8 *p)
{
if (!is_utf8_char(p))
return FALSE;
}
bool
-Perl_is_utf8_mark(pTHX_ U8 *p)
+Perl_is_utf8_mark(pTHX_ const U8 *p)
{
if (!is_utf8_char(p))
return FALSE;
=cut */
UV
-Perl_to_utf8_case(pTHX_ U8 *p, U8* ustrp, STRLEN *lenp, SV **swashp, char *normal, char *special)
+Perl_to_utf8_case(pTHX_ const U8 *p, U8* ustrp, STRLEN *lenp, SV **swashp, char *normal, char *special)
{
- UV uv0, uv1;
+ UV uv1;
U8 tmpbuf[UTF8_MAXBYTES_CASE+1];
STRLEN len = 0;
- uv0 = utf8_to_uvchr(p, 0);
+ const UV uv0 = utf8_to_uvchr(p, 0);
/* The NATIVE_TO_UNI() and UNI_TO_NATIVE() mappings
* are necessary in EBCDIC, they are redundant no-ops
* in ASCII-ish platforms, and hopefully optimized away. */
}
/*
-=for apidoc A|UV|to_utf8_upper|U8 *p|U8 *ustrp|STRLEN *lenp
+=for apidoc A|UV|to_utf8_upper|const U8 *p|U8 *ustrp|STRLEN *lenp
Convert the UTF-8 encoded character at p to its uppercase version and
store that in UTF-8 in ustrp and its length in bytes in lenp. Note
=cut */
UV
-Perl_to_utf8_upper(pTHX_ U8 *p, U8* ustrp, STRLEN *lenp)
+Perl_to_utf8_upper(pTHX_ const U8 *p, U8* ustrp, STRLEN *lenp)
{
return Perl_to_utf8_case(aTHX_ p, ustrp, lenp,
&PL_utf8_toupper, "ToUpper", "utf8::ToSpecUpper");
}
/*
-=for apidoc A|UV|to_utf8_title|U8 *p|U8 *ustrp|STRLEN *lenp
+=for apidoc A|UV|to_utf8_title|const U8 *p|U8 *ustrp|STRLEN *lenp
Convert the UTF-8 encoded character at p to its titlecase version and
store that in UTF-8 in ustrp and its length in bytes in lenp. Note
=cut */
UV
-Perl_to_utf8_title(pTHX_ U8 *p, U8* ustrp, STRLEN *lenp)
+Perl_to_utf8_title(pTHX_ const U8 *p, U8* ustrp, STRLEN *lenp)
{
return Perl_to_utf8_case(aTHX_ p, ustrp, lenp,
&PL_utf8_totitle, "ToTitle", "utf8::ToSpecTitle");
}
/*
-=for apidoc A|UV|to_utf8_lower|U8 *p|U8 *ustrp|STRLEN *lenp
+=for apidoc A|UV|to_utf8_lower|const U8 *p|U8 *ustrp|STRLEN *lenp
Convert the UTF-8 encoded character at p to its lowercase version and
store that in UTF-8 in ustrp and its length in bytes in lenp. Note
=cut */
UV
-Perl_to_utf8_lower(pTHX_ U8 *p, U8* ustrp, STRLEN *lenp)
+Perl_to_utf8_lower(pTHX_ const U8 *p, U8* ustrp, STRLEN *lenp)
{
return Perl_to_utf8_case(aTHX_ p, ustrp, lenp,
&PL_utf8_tolower, "ToLower", "utf8::ToSpecLower");
}
/*
-=for apidoc A|UV|to_utf8_fold|U8 *p|U8 *ustrp|STRLEN *lenp
+=for apidoc A|UV|to_utf8_fold|const U8 *p|U8 *ustrp|STRLEN *lenp
Convert the UTF-8 encoded character at p to its foldcase version and
store that in UTF-8 in ustrp and its length in bytes in lenp. Note
=cut */
UV
-Perl_to_utf8_fold(pTHX_ U8 *p, U8* ustrp, STRLEN *lenp)
+Perl_to_utf8_fold(pTHX_ const U8 *p, U8* ustrp, STRLEN *lenp)
{
return Perl_to_utf8_case(aTHX_ p, ustrp, lenp,
&PL_utf8_tofold, "ToFold", "utf8::ToSpecFold");
/* a "swash" is a swatch hash */
SV*
-Perl_swash_init(pTHX_ char* pkg, char* name, SV *listsv, I32 minbits, I32 none)
+Perl_swash_init(pTHX_ const char* pkg, const char* name, SV *listsv, I32 minbits, I32 none)
{
SV* retval;
SV* tokenbufsv = sv_newmortal();
dSP;
- size_t pkg_len = strlen(pkg);
- size_t name_len = strlen(name);
+ const size_t pkg_len = strlen(pkg);
+ const size_t name_len = strlen(name);
HV *stash = gv_stashpvn(pkg, pkg_len, FALSE);
SV* errsv_save;
* the lower-level routine, and it is similarly broken for returning
* multiple values. --jhi */
UV
-Perl_swash_fetch(pTHX_ SV *sv, U8 *ptr, bool do_utf8)
+Perl_swash_fetch(pTHX_ SV *sv, const U8 *ptr, bool do_utf8)
{
HV* hv = (HV*)SvRV(sv);
U32 klen;
*/
#undef Perl_utf8n_to_uvchr
UV
-Perl_utf8n_to_uvchr(pTHX_ U8 *s, STRLEN curlen, STRLEN *retlen, U32 flags)
+Perl_utf8n_to_uvchr(pTHX_ const U8 *s, STRLEN curlen, STRLEN *retlen, U32 flags)
{
UV uv = Perl_utf8n_to_uvuni(aTHX_ s, curlen, retlen, flags);
return UNI_TO_NATIVE(uv);
projects / p5sagit/p5-mst-13.2.git / blobdiff