*d++ = UTF_TO_NATIVE(uv);
return d;
}
-#if defined(EBCDIC) || 1 /* always for testing */
+#if defined(EBCDIC)
else {
STRLEN len = UNISKIP(uv);
U8 *p = d+len-1;
case UTF8_WARN_SHORT:
Perl_sv_catpvf(aTHX_ sv, "(%d byte%s, need %d)",
curlen, curlen == 1 ? "" : "s", expectlen);
+ expectlen = curlen; /* distance for caller to skip */
break;
case UTF8_WARN_OVERFLOW:
Perl_sv_catpvf(aTHX_ sv, "(overflow at 0x%"UVxf", byte 0x%02x)",
/* for now these are all defined (inefficiently) in terms of the utf8 versions */
bool
-Perl_is_uni_alnum(pTHX_ U32 c)
+Perl_is_uni_alnum(pTHX_ UV c)
{
U8 tmpbuf[UTF8_MAXLEN+1];
uvchr_to_utf8(tmpbuf, (UV)c);
}
bool
-Perl_is_uni_alnumc(pTHX_ U32 c)
+Perl_is_uni_alnumc(pTHX_ UV c)
{
U8 tmpbuf[UTF8_MAXLEN+1];
uvchr_to_utf8(tmpbuf, (UV)c);
}
bool
-Perl_is_uni_idfirst(pTHX_ U32 c)
+Perl_is_uni_idfirst(pTHX_ UV c)
{
U8 tmpbuf[UTF8_MAXLEN+1];
uvchr_to_utf8(tmpbuf, (UV)c);
}
bool
-Perl_is_uni_alpha(pTHX_ U32 c)
+Perl_is_uni_alpha(pTHX_ UV c)
{
U8 tmpbuf[UTF8_MAXLEN+1];
uvchr_to_utf8(tmpbuf, (UV)c);
}
bool
-Perl_is_uni_ascii(pTHX_ U32 c)
+Perl_is_uni_ascii(pTHX_ UV c)
{
U8 tmpbuf[UTF8_MAXLEN+1];
uvchr_to_utf8(tmpbuf, (UV)c);
}
bool
-Perl_is_uni_space(pTHX_ U32 c)
+Perl_is_uni_space(pTHX_ UV c)
{
U8 tmpbuf[UTF8_MAXLEN+1];
uvchr_to_utf8(tmpbuf, (UV)c);
}
bool
-Perl_is_uni_digit(pTHX_ U32 c)
+Perl_is_uni_digit(pTHX_ UV c)
{
U8 tmpbuf[UTF8_MAXLEN+1];
uvchr_to_utf8(tmpbuf, (UV)c);
}
bool
-Perl_is_uni_upper(pTHX_ U32 c)
+Perl_is_uni_upper(pTHX_ UV c)
{
U8 tmpbuf[UTF8_MAXLEN+1];
uvchr_to_utf8(tmpbuf, (UV)c);
}
bool
-Perl_is_uni_lower(pTHX_ U32 c)
+Perl_is_uni_lower(pTHX_ UV c)
{
U8 tmpbuf[UTF8_MAXLEN+1];
uvchr_to_utf8(tmpbuf, (UV)c);
}
bool
-Perl_is_uni_cntrl(pTHX_ U32 c)
+Perl_is_uni_cntrl(pTHX_ UV c)
{
U8 tmpbuf[UTF8_MAXLEN+1];
uvchr_to_utf8(tmpbuf, (UV)c);
}
bool
-Perl_is_uni_graph(pTHX_ U32 c)
+Perl_is_uni_graph(pTHX_ UV c)
{
U8 tmpbuf[UTF8_MAXLEN+1];
uvchr_to_utf8(tmpbuf, (UV)c);
}
bool
-Perl_is_uni_print(pTHX_ U32 c)
+Perl_is_uni_print(pTHX_ UV c)
{
U8 tmpbuf[UTF8_MAXLEN+1];
uvchr_to_utf8(tmpbuf, (UV)c);
}
bool
-Perl_is_uni_punct(pTHX_ U32 c)
+Perl_is_uni_punct(pTHX_ UV c)
{
U8 tmpbuf[UTF8_MAXLEN+1];
uvchr_to_utf8(tmpbuf, (UV)c);
}
bool
-Perl_is_uni_xdigit(pTHX_ U32 c)
+Perl_is_uni_xdigit(pTHX_ UV c)
{
- U8 tmpbuf[UTF8_MAXLEN*2+1];
+ U8 tmpbuf[UTF8_MAXLEN_UCLC+1];
uvchr_to_utf8(tmpbuf, (UV)c);
return is_utf8_xdigit(tmpbuf);
}
-U32
-Perl_to_uni_upper(pTHX_ U32 c, U8* p, STRLEN *lenp)
+UV
+Perl_to_uni_upper(pTHX_ UV c, U8* p, STRLEN *lenp)
{
- U8 tmpbuf[UTF8_MAXLEN*2+1];
+ U8 tmpbuf[UTF8_MAXLEN_UCLC+1];
uvchr_to_utf8(tmpbuf, (UV)c);
return to_utf8_upper(tmpbuf, p, lenp);
}
-U32
-Perl_to_uni_title(pTHX_ U32 c, U8* p, STRLEN *lenp)
+UV
+Perl_to_uni_title(pTHX_ UV c, U8* p, STRLEN *lenp)
{
- U8 tmpbuf[UTF8_MAXLEN*2+1];
+ U8 tmpbuf[UTF8_MAXLEN_UCLC+1];
uvchr_to_utf8(tmpbuf, (UV)c);
return to_utf8_title(tmpbuf, p, lenp);
}
-U32
-Perl_to_uni_lower(pTHX_ U32 c, U8* p, STRLEN *lenp)
+UV
+Perl_to_uni_lower(pTHX_ UV c, U8* p, STRLEN *lenp)
{
- U8 tmpbuf[UTF8_MAXLEN+1];
+ U8 tmpbuf[UTF8_MAXLEN_UCLC+1];
uvchr_to_utf8(tmpbuf, (UV)c);
return to_utf8_lower(tmpbuf, p, lenp);
}
+UV
+Perl_to_uni_fold(pTHX_ UV c, U8* p, STRLEN *lenp)
+{
+ U8 tmpbuf[UTF8_MAXLEN_FOLD+1];
+ uvchr_to_utf8(tmpbuf, (UV)c);
+ return to_utf8_fold(tmpbuf, p, lenp);
+}
+
/* for now these all assume no locale info available for Unicode > 255 */
bool
-Perl_is_uni_alnum_lc(pTHX_ U32 c)
+Perl_is_uni_alnum_lc(pTHX_ UV c)
{
return is_uni_alnum(c); /* XXX no locale support yet */
}
bool
-Perl_is_uni_alnumc_lc(pTHX_ U32 c)
+Perl_is_uni_alnumc_lc(pTHX_ UV c)
{
return is_uni_alnumc(c); /* XXX no locale support yet */
}
bool
-Perl_is_uni_idfirst_lc(pTHX_ U32 c)
+Perl_is_uni_idfirst_lc(pTHX_ UV c)
{
return is_uni_idfirst(c); /* XXX no locale support yet */
}
bool
-Perl_is_uni_alpha_lc(pTHX_ U32 c)
+Perl_is_uni_alpha_lc(pTHX_ UV c)
{
return is_uni_alpha(c); /* XXX no locale support yet */
}
bool
-Perl_is_uni_ascii_lc(pTHX_ U32 c)
+Perl_is_uni_ascii_lc(pTHX_ UV c)
{
return is_uni_ascii(c); /* XXX no locale support yet */
}
bool
-Perl_is_uni_space_lc(pTHX_ U32 c)
+Perl_is_uni_space_lc(pTHX_ UV c)
{
return is_uni_space(c); /* XXX no locale support yet */
}
bool
-Perl_is_uni_digit_lc(pTHX_ U32 c)
+Perl_is_uni_digit_lc(pTHX_ UV c)
{
return is_uni_digit(c); /* XXX no locale support yet */
}
bool
-Perl_is_uni_upper_lc(pTHX_ U32 c)
+Perl_is_uni_upper_lc(pTHX_ UV c)
{
return is_uni_upper(c); /* XXX no locale support yet */
}
bool
-Perl_is_uni_lower_lc(pTHX_ U32 c)
+Perl_is_uni_lower_lc(pTHX_ UV c)
{
return is_uni_lower(c); /* XXX no locale support yet */
}
bool
-Perl_is_uni_cntrl_lc(pTHX_ U32 c)
+Perl_is_uni_cntrl_lc(pTHX_ UV c)
{
return is_uni_cntrl(c); /* XXX no locale support yet */
}
bool
-Perl_is_uni_graph_lc(pTHX_ U32 c)
+Perl_is_uni_graph_lc(pTHX_ UV c)
{
return is_uni_graph(c); /* XXX no locale support yet */
}
bool
-Perl_is_uni_print_lc(pTHX_ U32 c)
+Perl_is_uni_print_lc(pTHX_ UV c)
{
return is_uni_print(c); /* XXX no locale support yet */
}
bool
-Perl_is_uni_punct_lc(pTHX_ U32 c)
+Perl_is_uni_punct_lc(pTHX_ UV c)
{
return is_uni_punct(c); /* XXX no locale support yet */
}
bool
-Perl_is_uni_xdigit_lc(pTHX_ U32 c)
+Perl_is_uni_xdigit_lc(pTHX_ UV c)
{
return is_uni_xdigit(c); /* XXX no locale support yet */
}
return 0;
}
}
- *lenp = UNISKIP(uv);
+ if (lenp)
+ *lenp = UNISKIP(uv);
uvuni_to_utf8(ustrp, uv);
return uv;
}
return UNI_TO_NATIVE(uv);
}
+/*
+=for apidoc A|char *|pv_uni_display|SV *dsv|U8 *spv|STRLEN len|STRLEN pvlim|UV flags
+
+Build to the scalar dsv a displayable version of the string spv,
+length len, the displayable version being at most pvlim bytes long
+(if longer, the rest is truncated and "..." will be appended).
+The flags argument is currently unused but available for future extensions.
+The pointer to the PV of the dsv is returned.
+
+=cut */
char *
Perl_pv_uni_display(pTHX_ SV *dsv, U8 *spv, STRLEN len, STRLEN pvlim, UV flags)
{
return SvPVX(dsv);
}
+/*
+=for apidoc A|char *|sv_uni_display|SV *dsv|SV *ssv|STRLEN pvlim|UV flags
+
+Build to the scalar dsv a displayable version of the scalar sv,
+he displayable version being at most pvlim bytes long
+(if longer, the rest is truncated and "..." will be appended).
+The flags argument is currently unused but available for future extensions.
+The pointer to the PV of the dsv is returned.
+
+=cut */
char *
Perl_sv_uni_display(pTHX_ SV *dsv, SV *ssv, STRLEN pvlim, UV flags)
{
- return Perl_pv_uni_display(aTHX_ dsv, (U8*)SvPVX(ssv), SvCUR(ssv),
- pvlim, flags);
+ return Perl_pv_uni_display(aTHX_ dsv, (U8*)SvPVX(ssv), SvCUR(ssv),
+ pvlim, flags);
}
+
+/*
+=for apidoc A|I32|ibcmp_utf8|const char *s1|bool u1|const char *s2|bool u2|register I32 len
+
+Return true if the strings s1 and s2 differ case-insensitively, false
+if not (if they are equal case-insensitively). If u1 is true, the
+string s1 is assumed to be in UTF-8-encoded Unicode. If u2 is true,
+the string s2 is assumed to be in UTF-8-encoded Unicode.
+
+For case-insensitiveness, the "casefolding" of Unicode is used
+instead of upper/lowercasing both the characters, see
+http://www.unicode.org/unicode/reports/tr21/ (Case Mappings).
+
+=cut */
+I32
+Perl_ibcmp_utf8(pTHX_ const char *s1, bool u1, register I32 len1, const char *s2, bool u2, register I32 len2)
+{
+ register U8 *a = (U8*)s1;
+ register U8 *b = (U8*)s2;
+ register U8 *ae = b + len1;
+ register U8 *be = b + len2;
+ STRLEN la, lb;
+ UV ca, cb;
+ STRLEN ulen1, ulen2;
+ U8 tmpbuf1[UTF8_MAXLEN_FOLD+1];
+ U8 tmpbuf2[UTF8_MAXLEN_FOLD+1];
+
+ while (a < ae && b < be) {
+ if (u1) {
+ if (a + UTF8SKIP(a) > ae)
+ break;
+ ca = utf8_to_uvchr((U8*)a, &la);
+ } else {
+ ca = *a;
+ la = 1;
+ }
+ if (u2) {
+ if (b + UTF8SKIP(b) > be)
+ break;
+ cb = utf8_to_uvchr((U8*)b, &lb);
+ } else {
+ cb = *b;
+ lb = 1;
+ }
+ if (ca != cb) {
+ if (u1)
+ to_uni_fold(NATIVE_TO_UNI(ca), tmpbuf1, &ulen1);
+ else
+ ulen1 = 1;
+ if (u2)
+ to_uni_fold(NATIVE_TO_UNI(cb), tmpbuf2, &ulen2);
+ else
+ ulen2 = 1;
+ if (ulen1 != ulen2
+ || (ulen1 == 1 && PL_fold[ca] != PL_fold[cb])
+ || memNE((char *)tmpbuf1, (char *)tmpbuf2, ulen1))
+ return 1; /* mismatch */
+ }
+ a += la;
+ b += lb;
+ }
+ return a == ae && b == be ? 0 : 1; /* 0 match, 1 mismatch */
+}
+