=for apidoc A|U8 *|uvuni_to_utf8_flags|U8 *d|UV uv|UV flags
Adds the UTF-8 representation of the Unicode codepoint C<uv> to the end
-of the string C<d>; C<d> should be have at least C<UTF8_MAXLEN+1> free
+of the string C<d>; C<d> should be have at least C<UTF8_MAXBYTES+1> free
bytes available. The return value is the pointer to the byte after the
end of the new character. In other words,
UV
Perl_utf8_to_uvchr(pTHX_ U8 *s, STRLEN *retlen)
{
- return Perl_utf8n_to_uvchr(aTHX_ s, UTF8_MAXLEN, retlen,
+ return Perl_utf8n_to_uvchr(aTHX_ s, UTF8_MAXBYTES, retlen,
ckWARN(WARN_UTF8) ? 0 : UTF8_ALLOW_ANY);
}
Perl_utf8_to_uvuni(pTHX_ U8 *s, STRLEN *retlen)
{
/* Call the low level routine asking for checks */
- return Perl_utf8n_to_uvuni(aTHX_ s, UTF8_MAXLEN, retlen,
+ return Perl_utf8n_to_uvuni(aTHX_ s, UTF8_MAXBYTES, retlen,
ckWARN(WARN_UTF8) ? 0 : UTF8_ALLOW_ANY);
}
bool
Perl_is_uni_alnum(pTHX_ UV c)
{
- U8 tmpbuf[UTF8_MAXLEN+1];
+ U8 tmpbuf[UTF8_MAXBYTES+1];
uvchr_to_utf8(tmpbuf, c);
return is_utf8_alnum(tmpbuf);
}
bool
Perl_is_uni_alnumc(pTHX_ UV c)
{
- U8 tmpbuf[UTF8_MAXLEN+1];
+ U8 tmpbuf[UTF8_MAXBYTES+1];
uvchr_to_utf8(tmpbuf, c);
return is_utf8_alnumc(tmpbuf);
}
bool
Perl_is_uni_idfirst(pTHX_ UV c)
{
- U8 tmpbuf[UTF8_MAXLEN+1];
+ U8 tmpbuf[UTF8_MAXBYTES+1];
uvchr_to_utf8(tmpbuf, c);
return is_utf8_idfirst(tmpbuf);
}
bool
Perl_is_uni_alpha(pTHX_ UV c)
{
- U8 tmpbuf[UTF8_MAXLEN+1];
+ U8 tmpbuf[UTF8_MAXBYTES+1];
uvchr_to_utf8(tmpbuf, c);
return is_utf8_alpha(tmpbuf);
}
bool
Perl_is_uni_ascii(pTHX_ UV c)
{
- U8 tmpbuf[UTF8_MAXLEN+1];
+ U8 tmpbuf[UTF8_MAXBYTES+1];
uvchr_to_utf8(tmpbuf, c);
return is_utf8_ascii(tmpbuf);
}
bool
Perl_is_uni_space(pTHX_ UV c)
{
- U8 tmpbuf[UTF8_MAXLEN+1];
+ U8 tmpbuf[UTF8_MAXBYTES+1];
uvchr_to_utf8(tmpbuf, c);
return is_utf8_space(tmpbuf);
}
bool
Perl_is_uni_digit(pTHX_ UV c)
{
- U8 tmpbuf[UTF8_MAXLEN+1];
+ U8 tmpbuf[UTF8_MAXBYTES+1];
uvchr_to_utf8(tmpbuf, c);
return is_utf8_digit(tmpbuf);
}
bool
Perl_is_uni_upper(pTHX_ UV c)
{
- U8 tmpbuf[UTF8_MAXLEN+1];
+ U8 tmpbuf[UTF8_MAXBYTES+1];
uvchr_to_utf8(tmpbuf, c);
return is_utf8_upper(tmpbuf);
}
bool
Perl_is_uni_lower(pTHX_ UV c)
{
- U8 tmpbuf[UTF8_MAXLEN+1];
+ U8 tmpbuf[UTF8_MAXBYTES+1];
uvchr_to_utf8(tmpbuf, c);
return is_utf8_lower(tmpbuf);
}
bool
Perl_is_uni_cntrl(pTHX_ UV c)
{
- U8 tmpbuf[UTF8_MAXLEN+1];
+ U8 tmpbuf[UTF8_MAXBYTES+1];
uvchr_to_utf8(tmpbuf, c);
return is_utf8_cntrl(tmpbuf);
}
bool
Perl_is_uni_graph(pTHX_ UV c)
{
- U8 tmpbuf[UTF8_MAXLEN+1];
+ U8 tmpbuf[UTF8_MAXBYTES+1];
uvchr_to_utf8(tmpbuf, c);
return is_utf8_graph(tmpbuf);
}
bool
Perl_is_uni_print(pTHX_ UV c)
{
- U8 tmpbuf[UTF8_MAXLEN+1];
+ U8 tmpbuf[UTF8_MAXBYTES+1];
uvchr_to_utf8(tmpbuf, c);
return is_utf8_print(tmpbuf);
}
bool
Perl_is_uni_punct(pTHX_ UV c)
{
- U8 tmpbuf[UTF8_MAXLEN+1];
+ U8 tmpbuf[UTF8_MAXBYTES+1];
uvchr_to_utf8(tmpbuf, c);
return is_utf8_punct(tmpbuf);
}
bool
Perl_is_uni_xdigit(pTHX_ UV c)
{
- U8 tmpbuf[UTF8_MAXLEN_UCLC+1];
+ U8 tmpbuf[UTF8_MAXBYTES_CASE+1];
uvchr_to_utf8(tmpbuf, c);
return is_utf8_xdigit(tmpbuf);
}
/* XXX returns only the first character -- do not use XXX */
/* XXX no locale support yet */
STRLEN len;
- U8 tmpbuf[UTF8_MAXLEN_UCLC+1];
+ U8 tmpbuf[UTF8_MAXBYTES_CASE+1];
return (U32)to_uni_upper(c, tmpbuf, &len);
}
/* XXX returns only the first character XXX -- do not use XXX */
/* XXX no locale support yet */
STRLEN len;
- U8 tmpbuf[UTF8_MAXLEN_UCLC+1];
+ U8 tmpbuf[UTF8_MAXBYTES_CASE+1];
return (U32)to_uni_title(c, tmpbuf, &len);
}
/* XXX returns only the first character -- do not use XXX */
/* XXX no locale support yet */
STRLEN len;
- U8 tmpbuf[UTF8_MAXLEN_UCLC+1];
+ U8 tmpbuf[UTF8_MAXBYTES_CASE+1];
return (U32)to_uni_lower(c, tmpbuf, &len);
}
Perl_to_utf8_case(pTHX_ U8 *p, U8* ustrp, STRLEN *lenp, SV **swashp, char *normal, char *special)
{
UV uv0, uv1;
- U8 tmpbuf[UTF8_MAXLEN_FOLD+1];
+ U8 tmpbuf[UTF8_MAXBYTES_CASE+1];
STRLEN len = 0;
uv0 = utf8_to_uvchr(p, 0);
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
-that the ustrp needs to be at least UTF8_MAXLEN_UCLC+1 bytes since the
-uppercase version may be longer than the original character (up to two
-characters).
+that the ustrp needs to be at least UTF8_MAXBYTES_CASE+1 bytes since
+the uppercase version may be longer than the original character.
The first character of the uppercased version is returned
(but note, as explained above, that there may be more.)
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
-that the ustrp needs to be at least UTF8_MAXLEN_UCLC+1 bytes since the
-titlecase version may be longer than the original character (up to two
-characters).
+that the ustrp needs to be at least UTF8_MAXBYTES_CASE+1 bytes since the
+titlecase version may be longer than the original character.
The first character of the titlecased version is returned
(but note, as explained above, that there may be more.)
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
-that the ustrp needs to be at least UTF8_MAXLEN_UCLC+1 bytes since the
-lowercase version may be longer than the original character (up to two
-characters).
+that the ustrp needs to be at least UTF8_MAXBYTES_CASE+1 bytes since the
+lowercase version may be longer than the original character.
The first character of the lowercased version is returned
(but note, as explained above, that there may be more.)
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
-that the ustrp needs to be at least UTF8_MAXLEN_FOLD+1 bytes since the
+that the ustrp needs to be at least UTF8_MAXBYTES_CASE+1 bytes since the
foldcase version may be longer than the original character (up to
three characters).
/* We use utf8n_to_uvuni() as we want an index into
Unicode tables, not a native character number.
*/
- UV code_point = utf8n_to_uvuni(ptr, UTF8_MAXLEN, 0,
+ UV code_point = utf8n_to_uvuni(ptr, UTF8_MAXBYTES, 0,
ckWARN(WARN_UTF8) ?
0 : UTF8_ALLOW_ANY);
SV *errsv_save;
=for apidoc A|U8 *|uvchr_to_utf8|U8 *d|UV uv
Adds the UTF-8 representation of the Native codepoint C<uv> to the end
-of the string C<d>; C<d> should be have at least C<UTF8_MAXLEN+1> free
+of the string C<d>; C<d> should be have at least C<UTF8_MAXBYTES+1> free
bytes available. The return value is the pointer to the byte after the
end of the new character. In other words,
register U8 *e1 = 0, *f1 = 0, *q1 = 0;
register U8 *e2 = 0, *f2 = 0, *q2 = 0;
STRLEN n1 = 0, n2 = 0;
- U8 foldbuf1[UTF8_MAXLEN_FOLD+1];
- U8 foldbuf2[UTF8_MAXLEN_FOLD+1];
+ U8 foldbuf1[UTF8_MAXBYTES_CASE+1];
+ U8 foldbuf2[UTF8_MAXBYTES_CASE+1];
U8 natbuf[1+1];
STRLEN foldlen1, foldlen2;
bool match;
projects / p5sagit/p5-mst-13.2.git / blobdiff