/* utf8.c
*
- * Copyright (c) 1998-2001, Larry Wall
+ * Copyright (c) 1998-2002, Larry Wall
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
#define PERL_IN_UTF8_C
#include "perl.h"
-/* Unicode support */
+/*
+=head1 Unicode Support
-/*
-=for apidoc A|U8 *|uvuni_to_utf8|U8 *d|UV uv
+=for apidoc A|U8 *|uvuni_to_utf8_flags|U8 *d|UV uv|UV flags
Adds the UTF8 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
bytes available. The return value is the pointer to the byte after the
end of the new character. In other words,
+ d = uvuni_to_utf8_flags(d, uv, flags);
+
+or, in most cases,
+
d = uvuni_to_utf8(d, uv);
+(which is equivalent to)
+
+ d = uvuni_to_utf8_flags(d, uv, 0);
+
is the recommended Unicode-aware way of saying
*(d++) = uv;
*/
U8 *
-Perl_uvuni_to_utf8(pTHX_ U8 *d, UV uv)
-{
+Perl_uvuni_to_utf8_flags(pTHX_ U8 *d, UV uv, UV flags)
+{
+ if (ckWARN(WARN_UTF8)) {
+ if (UNICODE_IS_SURROGATE(uv) &&
+ !(flags & UNICODE_ALLOW_SURROGATE))
+ Perl_warner(aTHX_ WARN_UTF8, "UTF-16 surrogate 0x%04"UVxf, uv);
+ else if (
+ ((uv >= 0xFDD0 && uv <= 0xFDEF &&
+ !(flags & UNICODE_ALLOW_FDD0))
+ ||
+ ((uv & 0xFFFF) == 0xFFFE &&
+ !(flags & UNICODE_ALLOW_FFFE))
+ ||
+ ((uv & 0xFFFF) == 0xFFFF &&
+ !(flags & UNICODE_ALLOW_FFFF))) &&
+ /* UNICODE_ALLOW_SUPER includes
+ * FFFEs and FFFFs beyond 0x10FFFF. */
+ ((uv <= PERL_UNICODE_MAX) ||
+ !(flags & UNICODE_ALLOW_SUPER))
+ )
+ Perl_warner(aTHX_ WARN_UTF8,
+ "Unicode character 0x%04"UVxf" is illegal", uv);
+ }
if (UNI_IS_INVARIANT(uv)) {
*d++ = UTF_TO_NATIVE(uv);
return d;
#endif
#endif /* Loop style */
}
-
+
+U8 *
+Perl_uvuni_to_utf8(pTHX_ U8 *d, UV uv)
+{
+ return Perl_uvuni_to_utf8_flags(aTHX_ d, uv, 0);
+}
/*
UV
Perl_utf8n_to_uvuni(pTHX_ U8 *s, STRLEN curlen, STRLEN *retlen, U32 flags)
{
+ U8 *s0 = s;
UV uv = *s, ouv = 0;
STRLEN len = 1;
bool dowarn = ckWARN_d(WARN_UTF8);
+ UV startbyte = *s;
STRLEN expectlen = 0;
U32 warning = 0;
Perl_sv_catpvf(aTHX_ sv, "(empty string)");
break;
case UTF8_WARN_CONTINUATION:
- Perl_sv_catpvf(aTHX_ sv, "(unexpected continuation byte 0x%02"UVxf")", uv);
+ Perl_sv_catpvf(aTHX_ sv, "(unexpected continuation byte 0x%02"UVxf", with no preceding start byte)", uv);
break;
case UTF8_WARN_NON_CONTINUATION:
- Perl_sv_catpvf(aTHX_ sv, "(unexpected non-continuation byte 0x%02"UVxf" after start byte 0x%02"UVxf")",
- (UV)s[1], uv);
+ if (s == s0)
+ Perl_sv_catpvf(aTHX_ sv, "(unexpected non-continuation byte 0x%02"UVxf", immediately after start byte 0x%02"UVxf")",
+ (UV)s[1], startbyte);
+ else
+ Perl_sv_catpvf(aTHX_ sv, "(unexpected non-continuation byte 0x%02"UVxf", %d byte%s after start byte 0x%02"UVxf", expected %d bytes)",
+ (UV)s[1], s - s0, s - s0 > 1 ? "s" : "", startbyte, expectlen);
+
break;
case UTF8_WARN_FE_FF:
Perl_sv_catpvf(aTHX_ sv, "(byte 0x%02"UVxf")", uv);
break;
case UTF8_WARN_SHORT:
- Perl_sv_catpvf(aTHX_ sv, "(%d byte%s, need %d)",
- curlen, curlen == 1 ? "" : "s", expectlen);
+ Perl_sv_catpvf(aTHX_ sv, "(%d byte%s, need %d, after start byte 0x%02"UVxf")",
+ curlen, curlen == 1 ? "" : "s", expectlen, startbyte);
expectlen = curlen; /* distance for caller to skip */
break;
case UTF8_WARN_OVERFLOW:
- Perl_sv_catpvf(aTHX_ sv, "(overflow at 0x%"UVxf", byte 0x%02x)",
- ouv, *s);
+ Perl_sv_catpvf(aTHX_ sv, "(overflow at 0x%"UVxf", byte 0x%02x, after start byte 0x%02"UVxf")",
+ ouv, *s, startbyte);
break;
case UTF8_WARN_SURROGATE:
Perl_sv_catpvf(aTHX_ sv, "(UTF-16 surrogate 0x%04"UVxf")", uv);
Perl_sv_catpvf(aTHX_ sv, "(byte order mark 0x%04"UVxf")", uv);
break;
case UTF8_WARN_LONG:
- Perl_sv_catpvf(aTHX_ sv, "(%d byte%s, need %d)",
- expectlen, expectlen == 1 ? "": "s", UNISKIP(uv));
+ Perl_sv_catpvf(aTHX_ sv, "(%d byte%s, need %d, after start byte 0x%02"UVxf")",
+ expectlen, expectlen == 1 ? "": "s", UNISKIP(uv), startbyte);
break;
case UTF8_WARN_FFFF:
Perl_sv_catpvf(aTHX_ sv, "(character 0x%04"UVxf")", uv);
return is_uni_xdigit(c); /* XXX no locale support yet */
}
+U32
+Perl_to_uni_upper_lc(pTHX_ U32 c)
+{
+ /* XXX returns only the first character -- do not use XXX */
+ /* XXX no locale support yet */
+ STRLEN len;
+ U8 tmpbuf[UTF8_MAXLEN_UCLC+1];
+ return (U32)to_uni_upper(c, tmpbuf, &len);
+}
+
+U32
+Perl_to_uni_title_lc(pTHX_ U32 c)
+{
+ /* XXX returns only the first character XXX -- do not use XXX */
+ /* XXX no locale support yet */
+ STRLEN len;
+ U8 tmpbuf[UTF8_MAXLEN_UCLC+1];
+ return (U32)to_uni_title(c, tmpbuf, &len);
+}
+
+U32
+Perl_to_uni_lower_lc(pTHX_ U32 c)
+{
+ /* XXX returns only the first character -- do not use XXX */
+ /* XXX no locale support yet */
+ STRLEN len;
+ U8 tmpbuf[UTF8_MAXLEN_UCLC+1];
+ return (U32)to_uni_lower(c, tmpbuf, &len);
+}
+
bool
Perl_is_utf8_alnum(pTHX_ U8 *p)
{
if (!*swashp)
*swashp = swash_init("utf8", normal, &PL_sv_undef, 4, 0);
uv = swash_fetch(*swashp, p, TRUE);
- if (uv)
- uv = UNI_TO_NATIVE(uv);
- else {
+ if (!uv) {
HV *hv;
SV *keysv;
HE *he;
ustrp[1] = UTF8_EIGHT_BIT_LO(c);
*lenp = 2;
}
- return 0;
+#ifdef EBCDIC
+ {
+ U8 tmpbuf[UTF8_MAXLEN_FOLD+1];
+ U8 *d = tmpbuf;
+ U8 *t, *tend;
+ STRLEN tlen;
+
+ for (t = ustrp, tend = t + *lenp; t < tend; t += tlen) {
+ UV c = utf8_to_uvchr(t, &tlen);
+ d = uvchr_to_utf8(d, UNI_TO_NATIVE(c));
+ }
+ *lenp = d - tmpbuf;
+ Copy(tmpbuf, ustrp, *lenp, U8);
+ }
+#endif
+ return utf8_to_uvchr(ustrp, 0);
}
+ uv = NATIVE_TO_UNI(uv);
}
- if *lenp)
+ if (lenp)
*lenp = UNISKIP(uv);
uvuni_to_utf8(ustrp, uv);
return uv;
}
+/*
+=for apidoc A|UV|to_utf8_upper|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
+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).
+
+The first character of the uppercased version is returned
+(but note, as explained above, that there may be more.)
+
+=cut */
+
UV
Perl_to_utf8_upper(pTHX_ U8 *p, U8* ustrp, STRLEN *lenp)
{
&PL_utf8_toupper, "ToUpper", "utf8::ToSpecUpper");
}
+/*
+=for apidoc A|UV|to_utf8_title|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
+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).
+
+The first character of the titlecased version is returned
+(but note, as explained above, that there may be more.)
+
+=cut */
+
UV
Perl_to_utf8_title(pTHX_ U8 *p, U8* ustrp, STRLEN *lenp)
{
&PL_utf8_totitle, "ToTitle", "utf8::ToSpecTitle");
}
+/*
+=for apidoc A|UV|to_utf8_lower|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
+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).
+
+The first character of the lowercased version is returned
+(but note, as explained above, that there may be more.)
+
+=cut */
+
UV
Perl_to_utf8_lower(pTHX_ U8 *p, U8* ustrp, STRLEN *lenp)
{
&PL_utf8_tolower, "ToLower", "utf8::ToSpecLower");
}
+/*
+=for apidoc A|UV|to_utf8_fold|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
+that the ustrp needs to be at least UTF8_MAXLEN_FOLD+1 bytes since the
+foldcase version may be longer than the original character (up to
+three characters).
+
+The first character of the foldcased version is returned
+(but note, as explained above, that there may be more.)
+
+=cut */
+
UV
Perl_to_utf8_fold(pTHX_ U8 *p, U8* ustrp, STRLEN *lenp)
{
U8 *
Perl_uvchr_to_utf8(pTHX_ U8 *d, UV uv)
{
- return Perl_uvuni_to_utf8(aTHX_ d, NATIVE_TO_UNI(uv));
+ return Perl_uvuni_to_utf8_flags(aTHX_ d, NATIVE_TO_UNI(uv), 0);
}
+U8 *
+Perl_uvchr_to_utf8_flags(pTHX_ U8 *d, UV uv, UV flags)
+{
+ return Perl_uvuni_to_utf8_flags(aTHX_ d, NATIVE_TO_UNI(uv), flags);
+}
/*
=for apidoc A|UV|utf8n_to_uvchr|U8 *s|STRLEN curlen|STRLEN *retlen|U32 flags
=cut
*/
-/* On ASCII machines this is normally a macro but we want a
- real function in case XS code wants it
+/* On ASCII machines this is normally a macro but we want
+ a real function in case XS code wants it
*/
#undef Perl_utf8n_to_uvchr
UV
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 flags argument can have UNI_DISPLAY_ISPRINT set to display
+isPRINT()able characters as themselves, UNI_DISPLAY_BACKSLASH
+to display the \\[nrfta\\] as the backslashed versions (like '\n')
+(UNI_DISPLAY_BACKSLASH is preferred over UNI_DISPLAY_ISPRINT for \\).
+UNI_DISPLAY_QQ (and its alias UNI_DISPLAY_REGEX) have both
+UNI_DISPLAY_BACKSLASH and UNI_DISPLAY_ISPRINT turned on.
+
The pointer to the PV of the dsv is returned.
=cut */
sv_setpvn(dsv, "", 0);
for (s = (char *)spv, e = s + len; s < e; s += UTF8SKIP(s)) {
UV u;
+ bool ok = FALSE;
+
if (pvlim && SvCUR(dsv) >= pvlim) {
truncated++;
break;
}
u = utf8_to_uvchr((U8*)s, 0);
- Perl_sv_catpvf(aTHX_ dsv, "\\x{%"UVxf"}", u);
+ if (u < 256) {
+ if (!ok && (flags & UNI_DISPLAY_BACKSLASH)) {
+ switch (u & 0xFF) {
+ case '\n':
+ Perl_sv_catpvf(aTHX_ dsv, "\\n"); ok = TRUE; break;
+ case '\r':
+ Perl_sv_catpvf(aTHX_ dsv, "\\r"); ok = TRUE; break;
+ case '\t':
+ Perl_sv_catpvf(aTHX_ dsv, "\\t"); ok = TRUE; break;
+ case '\f':
+ Perl_sv_catpvf(aTHX_ dsv, "\\f"); ok = TRUE; break;
+ case '\a':
+ Perl_sv_catpvf(aTHX_ dsv, "\\a"); ok = TRUE; break;
+ case '\\':
+ Perl_sv_catpvf(aTHX_ dsv, "\\" ); ok = TRUE; break;
+ default: break;
+ }
+ }
+ /* isPRINT() is the locale-blind version. */
+ if (!ok && (flags & UNI_DISPLAY_ISPRINT) && isPRINT(u & 0xFF)) {
+ Perl_sv_catpvf(aTHX_ dsv, "%c", u);
+ ok = TRUE;
+ }
+ }
+ if (!ok)
+ Perl_sv_catpvf(aTHX_ dsv, "\\x{%"UVxf"}", u);
}
if (truncated)
sv_catpvn(dsv, "...", 3);
=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
+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 flags argument is as in pv_uni_display().
+
The pointer to the PV of the dsv is returned.
=cut */
}
/*
-=for apidoc A|I32|ibcmp_utf8|const char *s1|bool u1|const char *s2|bool u2|register I32 len
+=for apidoc A|I32|ibcmp_utf8|const char *s1|char **pe1|register UV l1|bool u1|const char *s2|char **pe2|register UV l2|bool u2
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.
+the string s2 is assumed to be in UTF-8-encoded Unicode. If u1 or u2
+are false, the respective string is assumed to be in native 8-bit
+encoding.
+
+If the pe1 and pe2 are non-NULL, the scanning pointers will be copied
+in there (they will point at the beginning of the I<next> character).
+If the pointers behind pe1 or pe2 are non-NULL, they are the end
+pointers beyond which scanning will not continue under any
+circustances. If the byte lengths l1 and l2 are non-zero, s1+l1 and
+s2+l2 will be used as goal end pointers that will also stop the scan,
+and which qualify towards defining a successful match: all the scans
+that define an explicit length must reach their goal pointers for
+a match to succeed).
For case-insensitiveness, the "casefolding" of Unicode is used
instead of upper/lowercasing both the characters, see
=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];
+Perl_ibcmp_utf8(pTHX_ const char *s1, char **pe1, register UV l1, bool u1, const char *s2, char **pe2, register UV l2, bool u2)
+{
+ register U8 *p1 = (U8*)s1;
+ register U8 *p2 = (U8*)s2;
+ 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 natbuf[1+1];
+ STRLEN foldlen1, foldlen2;
+ bool match;
- 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 (pe1)
+ e1 = *(U8**)pe1;
+ if (e1 == 0 || (l1 && l1 < e1 - (U8*)s1))
+ f1 = (U8*)s1 + l1;
+ if (pe2)
+ e2 = *(U8**)pe2;
+ if (e2 == 0 || (l2 && l2 < e2 - (U8*)s2))
+ f2 = (U8*)s2 + l2;
+
+ if ((e1 == 0 && f1 == 0) || (e2 == 0 && f2 == 0) || (f1 == 0 && f2 == 0))
+ return 1; /* mismatch; possible infinite loop or false positive */
+
+ while ((e1 == 0 || p1 < e1) &&
+ (f1 == 0 || p1 < f1) &&
+ (e2 == 0 || p2 < e2) &&
+ (f2 == 0 || p2 < f2)) {
+ if (n1 == 0) {
if (u1)
- to_uni_fold(NATIVE_TO_UNI(ca), tmpbuf1, &ulen1);
- else
- ulen1 = 1;
+ to_utf8_fold(p1, foldbuf1, &foldlen1);
+ else {
+ natbuf[0] = NATIVE_TO_UNI(*p1);
+ to_utf8_fold(natbuf, foldbuf1, &foldlen1);
+ }
+ q1 = foldbuf1;
+ n1 = foldlen1;
+ }
+ if (n2 == 0) {
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 */
+ to_utf8_fold(p2, foldbuf2, &foldlen2);
+ else {
+ natbuf[0] = NATIVE_TO_UNI(*p2);
+ to_utf8_fold(natbuf, foldbuf2, &foldlen2);
+ }
+ q2 = foldbuf2;
+ n2 = foldlen2;
}
- a += la;
- b += lb;
+ while (n1 && n2) {
+ if ( UTF8SKIP(q1) != UTF8SKIP(q2) ||
+ (UTF8SKIP(q1) == 1 && *q1 != *q2) ||
+ memNE((char*)q1, (char*)q2, UTF8SKIP(q1)) )
+ return 1; /* mismatch */
+ n1 -= UTF8SKIP(q1);
+ q1 += UTF8SKIP(q1);
+ n2 -= UTF8SKIP(q2);
+ q2 += UTF8SKIP(q2);
+ }
+ if (n1 == 0)
+ p1 += u1 ? UTF8SKIP(p1) : 1;
+ if (n2 == 0)
+ p2 += u2 ? UTF8SKIP(p2) : 1;
+
}
- return a == ae && b == be ? 0 : 1; /* 0 match, 1 mismatch */
+
+ /* A match is defined by all the scans that specified
+ * an explicit length reaching their final goals. */
+ match = (f1 == 0 || p1 == f1) && (f2 == 0 || p2 == f2);
+
+ if (match) {
+ if (pe1)
+ *pe1 = (char*)p1;
+ if (pe2)
+ *pe2 = (char*)p2;
+ }
+
+ return match ? 0 : 1; /* 0 match, 1 mismatch */
}