/* 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 */
+static char unees[] = "Malformed UTF-8 character (unexpected end of string)";
-/*
-=for apidoc A|U8 *|uvuni_to_utf8|U8 *d|UV uv
+/*
+=head1 Unicode Support
+
+=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_ packWARN(WARN_UTF8), "UTF-16 surrogate 0x%04"UVxf, uv);
+ else if (
+ ((uv >= 0xFDD0 && uv <= 0xFDEF &&
+ !(flags & UNICODE_ALLOW_FDD0))
+ ||
+ ((uv & 0xFFFE) == 0xFFFE && /* Either FFFE or FFFF. */
+ !(flags & UNICODE_ALLOW_FFFF))) &&
+ /* UNICODE_ALLOW_SUPER includes
+ * FFFEs and FFFFs beyond 0x10FFFF. */
+ ((uv <= PERL_UNICODE_MAX) ||
+ !(flags & UNICODE_ALLOW_SUPER))
+ )
+ Perl_warner(aTHX_ packWARN(WARN_UTF8),
+ "Unicode character 0x%04"UVxf" is illegal", uv);
+ }
if (UNI_IS_INVARIANT(uv)) {
- *d++ = UTF_TO_NATIVE(uv);
+ *d++ = (U8)UTF_TO_NATIVE(uv);
return d;
}
#if defined(EBCDIC)
STRLEN len = UNISKIP(uv);
U8 *p = d+len-1;
while (p > d) {
- *p-- = UTF_TO_NATIVE((uv & UTF_CONTINUATION_MASK) | UTF_CONTINUATION_MARK);
+ *p-- = (U8)UTF_TO_NATIVE((uv & UTF_CONTINUATION_MASK) | UTF_CONTINUATION_MARK);
uv >>= UTF_ACCUMULATION_SHIFT;
}
- *p = UTF_TO_NATIVE((uv & UTF_START_MASK(len)) | UTF_START_MARK(len));
+ *p = (U8)UTF_TO_NATIVE((uv & UTF_START_MASK(len)) | UTF_START_MARK(len));
return d+len;
}
#else /* Non loop style */
if (uv < 0x800) {
- *d++ = (( uv >> 6) | 0xc0);
- *d++ = (( uv & 0x3f) | 0x80);
+ *d++ = (U8)(( uv >> 6) | 0xc0);
+ *d++ = (U8)(( uv & 0x3f) | 0x80);
return d;
}
if (uv < 0x10000) {
- *d++ = (( uv >> 12) | 0xe0);
- *d++ = (((uv >> 6) & 0x3f) | 0x80);
- *d++ = (( uv & 0x3f) | 0x80);
+ *d++ = (U8)(( uv >> 12) | 0xe0);
+ *d++ = (U8)(((uv >> 6) & 0x3f) | 0x80);
+ *d++ = (U8)(( uv & 0x3f) | 0x80);
return d;
}
if (uv < 0x200000) {
- *d++ = (( uv >> 18) | 0xf0);
- *d++ = (((uv >> 12) & 0x3f) | 0x80);
- *d++ = (((uv >> 6) & 0x3f) | 0x80);
- *d++ = (( uv & 0x3f) | 0x80);
+ *d++ = (U8)(( uv >> 18) | 0xf0);
+ *d++ = (U8)(((uv >> 12) & 0x3f) | 0x80);
+ *d++ = (U8)(((uv >> 6) & 0x3f) | 0x80);
+ *d++ = (U8)(( uv & 0x3f) | 0x80);
return d;
}
if (uv < 0x4000000) {
- *d++ = (( uv >> 24) | 0xf8);
- *d++ = (((uv >> 18) & 0x3f) | 0x80);
- *d++ = (((uv >> 12) & 0x3f) | 0x80);
- *d++ = (((uv >> 6) & 0x3f) | 0x80);
- *d++ = (( uv & 0x3f) | 0x80);
+ *d++ = (U8)(( uv >> 24) | 0xf8);
+ *d++ = (U8)(((uv >> 18) & 0x3f) | 0x80);
+ *d++ = (U8)(((uv >> 12) & 0x3f) | 0x80);
+ *d++ = (U8)(((uv >> 6) & 0x3f) | 0x80);
+ *d++ = (U8)(( uv & 0x3f) | 0x80);
return d;
}
if (uv < 0x80000000) {
- *d++ = (( uv >> 30) | 0xfc);
- *d++ = (((uv >> 24) & 0x3f) | 0x80);
- *d++ = (((uv >> 18) & 0x3f) | 0x80);
- *d++ = (((uv >> 12) & 0x3f) | 0x80);
- *d++ = (((uv >> 6) & 0x3f) | 0x80);
- *d++ = (( uv & 0x3f) | 0x80);
+ *d++ = (U8)(( uv >> 30) | 0xfc);
+ *d++ = (U8)(((uv >> 24) & 0x3f) | 0x80);
+ *d++ = (U8)(((uv >> 18) & 0x3f) | 0x80);
+ *d++ = (U8)(((uv >> 12) & 0x3f) | 0x80);
+ *d++ = (U8)(((uv >> 6) & 0x3f) | 0x80);
+ *d++ = (U8)(( uv & 0x3f) | 0x80);
return d;
}
#ifdef HAS_QUAD
if (uv < UTF8_QUAD_MAX)
#endif
{
- *d++ = 0xfe; /* Can't match U+FEFF! */
- *d++ = (((uv >> 30) & 0x3f) | 0x80);
- *d++ = (((uv >> 24) & 0x3f) | 0x80);
- *d++ = (((uv >> 18) & 0x3f) | 0x80);
- *d++ = (((uv >> 12) & 0x3f) | 0x80);
- *d++ = (((uv >> 6) & 0x3f) | 0x80);
- *d++ = (( uv & 0x3f) | 0x80);
+ *d++ = 0xfe; /* Can't match U+FEFF! */
+ *d++ = (U8)(((uv >> 30) & 0x3f) | 0x80);
+ *d++ = (U8)(((uv >> 24) & 0x3f) | 0x80);
+ *d++ = (U8)(((uv >> 18) & 0x3f) | 0x80);
+ *d++ = (U8)(((uv >> 12) & 0x3f) | 0x80);
+ *d++ = (U8)(((uv >> 6) & 0x3f) | 0x80);
+ *d++ = (U8)(( uv & 0x3f) | 0x80);
return d;
}
#ifdef HAS_QUAD
{
- *d++ = 0xff; /* Can't match U+FFFE! */
- *d++ = 0x80; /* 6 Reserved bits */
- *d++ = (((uv >> 60) & 0x0f) | 0x80); /* 2 Reserved bits */
- *d++ = (((uv >> 54) & 0x3f) | 0x80);
- *d++ = (((uv >> 48) & 0x3f) | 0x80);
- *d++ = (((uv >> 42) & 0x3f) | 0x80);
- *d++ = (((uv >> 36) & 0x3f) | 0x80);
- *d++ = (((uv >> 30) & 0x3f) | 0x80);
- *d++ = (((uv >> 24) & 0x3f) | 0x80);
- *d++ = (((uv >> 18) & 0x3f) | 0x80);
- *d++ = (((uv >> 12) & 0x3f) | 0x80);
- *d++ = (((uv >> 6) & 0x3f) | 0x80);
- *d++ = (( uv & 0x3f) | 0x80);
+ *d++ = 0xff; /* Can't match U+FFFE! */
+ *d++ = 0x80; /* 6 Reserved bits */
+ *d++ = (U8)(((uv >> 60) & 0x0f) | 0x80); /* 2 Reserved bits */
+ *d++ = (U8)(((uv >> 54) & 0x3f) | 0x80);
+ *d++ = (U8)(((uv >> 48) & 0x3f) | 0x80);
+ *d++ = (U8)(((uv >> 42) & 0x3f) | 0x80);
+ *d++ = (U8)(((uv >> 36) & 0x3f) | 0x80);
+ *d++ = (U8)(((uv >> 30) & 0x3f) | 0x80);
+ *d++ = (U8)(((uv >> 24) & 0x3f) | 0x80);
+ *d++ = (U8)(((uv >> 18) & 0x3f) | 0x80);
+ *d++ = (U8)(((uv >> 12) & 0x3f) | 0x80);
+ *d++ = (U8)(((uv >> 6) & 0x3f) | 0x80);
+ *d++ = (U8)(( uv & 0x3f) | 0x80);
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);
+}
/*
=for apidoc A|STRLEN|is_utf8_char|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 UTF-8 character.
-The actual number of bytes in the UTF-8 character will be returned if
-it is valid, otherwise 0.
+character. Note that an INVARIANT (i.e. ASCII) character is a valid
+UTF-8 character. The actual number of bytes in the UTF-8 character
+will be returned if it is valid, otherwise 0.
-=cut
-*/
+=cut */
STRLEN
Perl_is_utf8_char(pTHX_ U8 *s)
{
s++;
}
- if (UNISKIP(uv) < len)
+ if ((STRLEN)UNISKIP(uv) < len)
return 0;
return len;
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;
#define UTF8_WARN_SHORT 5
#define UTF8_WARN_OVERFLOW 6
#define UTF8_WARN_SURROGATE 7
-#define UTF8_WARN_BOM 8
-#define UTF8_WARN_LONG 9
-#define UTF8_WARN_FFFF 10
+#define UTF8_WARN_LONG 8
+#define UTF8_WARN_FFFF 9 /* Also FFFE. */
if (curlen == 0 &&
!(flags & UTF8_ALLOW_EMPTY)) {
!(flags & UTF8_ALLOW_SURROGATE)) {
warning = UTF8_WARN_SURROGATE;
goto malformed;
- } else if (UNICODE_IS_BYTE_ORDER_MARK(uv) &&
- !(flags & UTF8_ALLOW_BOM)) {
- warning = UTF8_WARN_BOM;
- goto malformed;
- } else if ((expectlen > UNISKIP(uv)) &&
+ } else if ((expectlen > (STRLEN)UNISKIP(uv)) &&
!(flags & UTF8_ALLOW_LONG)) {
warning = UTF8_WARN_LONG;
goto malformed;
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);
break;
- case UTF8_WARN_BOM:
- 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);
char *s = SvPVX(sv);
if (PL_op)
- Perl_warner(aTHX_ WARN_UTF8,
+ Perl_warner(aTHX_ packWARN(WARN_UTF8),
"%s in %s", s, OP_DESC(PL_op));
else
- Perl_warner(aTHX_ WARN_UTF8, "%s", s);
+ Perl_warner(aTHX_ packWARN(WARN_UTF8), "%s", s);
}
}
UV
Perl_utf8_to_uvchr(pTHX_ U8 *s, STRLEN *retlen)
{
- return Perl_utf8n_to_uvchr(aTHX_ s, UTF8_MAXLEN, retlen, 0);
+ return Perl_utf8n_to_uvchr(aTHX_ s, UTF8_MAXLEN, 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, 0);
+ return Perl_utf8n_to_uvuni(aTHX_ s, UTF8_MAXLEN, retlen,
+ ckWARN(WARN_UTF8) ? 0 : UTF8_ALLOW_ANY);
}
/*
* the bitops (especially ~) can create illegal UTF-8.
* In other words: in Perl UTF-8 is not just for Unicode. */
- if (e < s)
- Perl_croak(aTHX_ "panic: utf8_length: unexpected end");
+ if (e < s) {
+ if (ckWARN_d(WARN_UTF8)) {
+ if (PL_op)
+ Perl_warner(aTHX_ packWARN(WARN_UTF8),
+ "%s in %s", unees, OP_DESC(PL_op));
+ else
+ Perl_warner(aTHX_ packWARN(WARN_UTF8), unees);
+ }
+ return 0;
+ }
while (s < e) {
U8 t = UTF8SKIP(s);
- if (e - s < t)
- Perl_croak(aTHX_ "panic: utf8_length: unaligned end");
+ if (e - s < t) {
+ if (ckWARN_d(WARN_UTF8)) {
+ if (PL_op)
+ Perl_warner(aTHX_ packWARN(WARN_UTF8),
+ unees, OP_DESC(PL_op));
+ else
+ Perl_warner(aTHX_ packWARN(WARN_UTF8), unees);
+ }
+ return len;
+ }
s += t;
len++;
}
while (a < b) {
U8 c = UTF8SKIP(a);
- if (b - a < c)
- Perl_croak(aTHX_ "panic: utf8_distance: unaligned end");
+ if (b - a < c) {
+ if (ckWARN_d(WARN_UTF8)) {
+ if (PL_op)
+ Perl_warner(aTHX_ packWARN(WARN_UTF8),
+ "%s in %s", unees, OP_DESC(PL_op));
+ else
+ Perl_warner(aTHX_ packWARN(WARN_UTF8), unees);
+ }
+ return off;
+ }
a += c;
off--;
}
while (b < a) {
U8 c = UTF8SKIP(b);
- if (a - b < c)
- Perl_croak(aTHX_ "panic: utf8_distance: unaligned end");
+ if (a - b < c) {
+ if (ckWARN_d(WARN_UTF8)) {
+ if (PL_op)
+ Perl_warner(aTHX_ packWARN(WARN_UTF8),
+ "%s in %s", unees, OP_DESC(PL_op));
+ else
+ Perl_warner(aTHX_ packWARN(WARN_UTF8), unees);
+ }
+ return off;
+ }
b += c;
off++;
}
while (s < send) {
UV uv = NATIVE_TO_ASCII(*s++);
if (UNI_IS_INVARIANT(uv))
- *d++ = UTF_TO_NATIVE(uv);
+ *d++ = (U8)UTF_TO_NATIVE(uv);
else {
- *d++ = UTF8_EIGHT_BIT_HI(uv);
- *d++ = UTF8_EIGHT_BIT_LO(uv);
+ *d++ = (U8)UTF8_EIGHT_BIT_HI(uv);
+ *d++ = (U8)UTF8_EIGHT_BIT_LO(uv);
}
}
*d = '\0';
UV uv = (p[0] << 8) + p[1]; /* UTF-16BE */
p += 2;
if (uv < 0x80) {
- *d++ = uv;
+ *d++ = (U8)uv;
continue;
}
if (uv < 0x800) {
- *d++ = (( uv >> 6) | 0xc0);
- *d++ = (( uv & 0x3f) | 0x80);
+ *d++ = (U8)(( uv >> 6) | 0xc0);
+ *d++ = (U8)(( uv & 0x3f) | 0x80);
continue;
}
if (uv >= 0xd800 && uv < 0xdbff) { /* surrogates */
uv = ((uv - 0xd800) << 10) + (low - 0xdc00) + 0x10000;
}
if (uv < 0x10000) {
- *d++ = (( uv >> 12) | 0xe0);
- *d++ = (((uv >> 6) & 0x3f) | 0x80);
- *d++ = (( uv & 0x3f) | 0x80);
+ *d++ = (U8)(( uv >> 12) | 0xe0);
+ *d++ = (U8)(((uv >> 6) & 0x3f) | 0x80);
+ *d++ = (U8)(( uv & 0x3f) | 0x80);
continue;
}
else {
- *d++ = (( uv >> 18) | 0xf0);
- *d++ = (((uv >> 12) & 0x3f) | 0x80);
- *d++ = (((uv >> 6) & 0x3f) | 0x80);
- *d++ = (( uv & 0x3f) | 0x80);
+ *d++ = (U8)(( uv >> 18) | 0xf0);
+ *d++ = (U8)(((uv >> 12) & 0x3f) | 0x80);
+ *d++ = (U8)(((uv >> 6) & 0x3f) | 0x80);
+ *d++ = (U8)(( uv & 0x3f) | 0x80);
continue;
}
}
Perl_is_uni_alnum(pTHX_ UV c)
{
U8 tmpbuf[UTF8_MAXLEN+1];
- uvchr_to_utf8(tmpbuf, (UV)c);
+ uvchr_to_utf8(tmpbuf, c);
return is_utf8_alnum(tmpbuf);
}
Perl_is_uni_alnumc(pTHX_ UV c)
{
U8 tmpbuf[UTF8_MAXLEN+1];
- uvchr_to_utf8(tmpbuf, (UV)c);
+ uvchr_to_utf8(tmpbuf, c);
return is_utf8_alnumc(tmpbuf);
}
Perl_is_uni_idfirst(pTHX_ UV c)
{
U8 tmpbuf[UTF8_MAXLEN+1];
- uvchr_to_utf8(tmpbuf, (UV)c);
+ uvchr_to_utf8(tmpbuf, c);
return is_utf8_idfirst(tmpbuf);
}
Perl_is_uni_alpha(pTHX_ UV c)
{
U8 tmpbuf[UTF8_MAXLEN+1];
- uvchr_to_utf8(tmpbuf, (UV)c);
+ uvchr_to_utf8(tmpbuf, c);
return is_utf8_alpha(tmpbuf);
}
Perl_is_uni_ascii(pTHX_ UV c)
{
U8 tmpbuf[UTF8_MAXLEN+1];
- uvchr_to_utf8(tmpbuf, (UV)c);
+ uvchr_to_utf8(tmpbuf, c);
return is_utf8_ascii(tmpbuf);
}
Perl_is_uni_space(pTHX_ UV c)
{
U8 tmpbuf[UTF8_MAXLEN+1];
- uvchr_to_utf8(tmpbuf, (UV)c);
+ uvchr_to_utf8(tmpbuf, c);
return is_utf8_space(tmpbuf);
}
Perl_is_uni_digit(pTHX_ UV c)
{
U8 tmpbuf[UTF8_MAXLEN+1];
- uvchr_to_utf8(tmpbuf, (UV)c);
+ uvchr_to_utf8(tmpbuf, c);
return is_utf8_digit(tmpbuf);
}
Perl_is_uni_upper(pTHX_ UV c)
{
U8 tmpbuf[UTF8_MAXLEN+1];
- uvchr_to_utf8(tmpbuf, (UV)c);
+ uvchr_to_utf8(tmpbuf, c);
return is_utf8_upper(tmpbuf);
}
Perl_is_uni_lower(pTHX_ UV c)
{
U8 tmpbuf[UTF8_MAXLEN+1];
- uvchr_to_utf8(tmpbuf, (UV)c);
+ uvchr_to_utf8(tmpbuf, c);
return is_utf8_lower(tmpbuf);
}
Perl_is_uni_cntrl(pTHX_ UV c)
{
U8 tmpbuf[UTF8_MAXLEN+1];
- uvchr_to_utf8(tmpbuf, (UV)c);
+ uvchr_to_utf8(tmpbuf, c);
return is_utf8_cntrl(tmpbuf);
}
Perl_is_uni_graph(pTHX_ UV c)
{
U8 tmpbuf[UTF8_MAXLEN+1];
- uvchr_to_utf8(tmpbuf, (UV)c);
+ uvchr_to_utf8(tmpbuf, c);
return is_utf8_graph(tmpbuf);
}
Perl_is_uni_print(pTHX_ UV c)
{
U8 tmpbuf[UTF8_MAXLEN+1];
- uvchr_to_utf8(tmpbuf, (UV)c);
+ uvchr_to_utf8(tmpbuf, c);
return is_utf8_print(tmpbuf);
}
Perl_is_uni_punct(pTHX_ UV c)
{
U8 tmpbuf[UTF8_MAXLEN+1];
- uvchr_to_utf8(tmpbuf, (UV)c);
+ uvchr_to_utf8(tmpbuf, c);
return is_utf8_punct(tmpbuf);
}
Perl_is_uni_xdigit(pTHX_ UV c)
{
U8 tmpbuf[UTF8_MAXLEN_UCLC+1];
- uvchr_to_utf8(tmpbuf, (UV)c);
+ uvchr_to_utf8(tmpbuf, c);
return is_utf8_xdigit(tmpbuf);
}
UV
Perl_to_uni_upper(pTHX_ UV c, U8* p, STRLEN *lenp)
{
- U8 tmpbuf[UTF8_MAXLEN_UCLC+1];
- uvchr_to_utf8(tmpbuf, (UV)c);
- return to_utf8_upper(tmpbuf, p, lenp);
+ uvchr_to_utf8(p, c);
+ return to_utf8_upper(p, p, lenp);
}
UV
Perl_to_uni_title(pTHX_ UV c, U8* p, STRLEN *lenp)
{
- U8 tmpbuf[UTF8_MAXLEN_UCLC+1];
- uvchr_to_utf8(tmpbuf, (UV)c);
- return to_utf8_title(tmpbuf, p, lenp);
+ uvchr_to_utf8(p, c);
+ return to_utf8_title(p, p, lenp);
}
UV
Perl_to_uni_lower(pTHX_ UV c, U8* p, STRLEN *lenp)
{
- U8 tmpbuf[UTF8_MAXLEN+1];
- uvchr_to_utf8(tmpbuf, (UV)c);
- return to_utf8_lower(tmpbuf, p, lenp);
+ uvchr_to_utf8(p, c);
+ return to_utf8_lower(p, p, lenp);
}
UV
Perl_to_uni_fold(pTHX_ UV c, U8* p, STRLEN *lenp)
{
- U8 tmpbuf[UTF8_MAXLEN+1];
- uvchr_to_utf8(tmpbuf, (UV)c);
- return to_utf8_fold(tmpbuf, p, lenp);
+ uvchr_to_utf8(p, c);
+ return to_utf8_fold(p, p, lenp);
}
/* for now these all assume no locale info available for Unicode > 255 */
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)
{
* descendant of isalnum(3), in other words, it doesn't
* contain the '_'. --jhi */
PL_utf8_alnum = swash_init("utf8", "IsWord", &PL_sv_undef, 0, 0);
- return swash_fetch(PL_utf8_alnum, p, TRUE);
+ return swash_fetch(PL_utf8_alnum, p, TRUE) != 0;
/* return *p == '_' || is_utf8_alpha(p) || is_utf8_digit(p); */
#ifdef SURPRISINGLY_SLOWER /* probably because alpha is usually true */
if (!PL_utf8_alnum)
PL_utf8_alnum = swash_init("utf8", "",
sv_2mortal(newSVpv("+utf8::IsAlpha\n+utf8::IsDigit\n005F\n",0)), 0, 0);
- return swash_fetch(PL_utf8_alnum, p, TRUE);
+ return swash_fetch(PL_utf8_alnum, p, TRUE) != 0;
#endif
}
return FALSE;
if (!PL_utf8_alnum)
PL_utf8_alnum = swash_init("utf8", "IsAlnumC", &PL_sv_undef, 0, 0);
- return swash_fetch(PL_utf8_alnum, p, TRUE);
+ return swash_fetch(PL_utf8_alnum, p, TRUE) != 0;
/* return is_utf8_alpha(p) || is_utf8_digit(p); */
#ifdef SURPRISINGLY_SLOWER /* probably because alpha is usually true */
if (!PL_utf8_alnum)
PL_utf8_alnum = swash_init("utf8", "",
sv_2mortal(newSVpv("+utf8::IsAlpha\n+utf8::IsDigit\n005F\n",0)), 0, 0);
- return swash_fetch(PL_utf8_alnum, p, TRUE);
+ return swash_fetch(PL_utf8_alnum, p, TRUE) != 0;
#endif
}
bool
-Perl_is_utf8_idfirst(pTHX_ U8 *p)
+Perl_is_utf8_idfirst(pTHX_ U8 *p) /* The naming is historical. */
{
- return *p == '_' || is_utf8_alpha(p);
+ if (*p == '_')
+ return TRUE;
+ if (!is_utf8_char(p))
+ return FALSE;
+ if (!PL_utf8_idstart) /* is_utf8_idstart would be more logical. */
+ PL_utf8_idstart = swash_init("utf8", "IdStart", &PL_sv_undef, 0, 0);
+ return swash_fetch(PL_utf8_idstart, p, TRUE) != 0;
+}
+
+bool
+Perl_is_utf8_idcont(pTHX_ U8 *p)
+{
+ if (*p == '_')
+ return TRUE;
+ if (!is_utf8_char(p))
+ return FALSE;
+ if (!PL_utf8_idcont)
+ PL_utf8_idcont = swash_init("utf8", "IdContinue", &PL_sv_undef, 0, 0);
+ return swash_fetch(PL_utf8_idcont, p, TRUE) != 0;
}
bool
return FALSE;
if (!PL_utf8_alpha)
PL_utf8_alpha = swash_init("utf8", "IsAlpha", &PL_sv_undef, 0, 0);
- return swash_fetch(PL_utf8_alpha, p, TRUE);
+ return swash_fetch(PL_utf8_alpha, p, TRUE) != 0;
}
bool
return FALSE;
if (!PL_utf8_ascii)
PL_utf8_ascii = swash_init("utf8", "IsAscii", &PL_sv_undef, 0, 0);
- return swash_fetch(PL_utf8_ascii, p, TRUE);
+ return swash_fetch(PL_utf8_ascii, p, TRUE) != 0;
}
bool
return FALSE;
if (!PL_utf8_space)
PL_utf8_space = swash_init("utf8", "IsSpacePerl", &PL_sv_undef, 0, 0);
- return swash_fetch(PL_utf8_space, p, TRUE);
+ return swash_fetch(PL_utf8_space, p, TRUE) != 0;
}
bool
return FALSE;
if (!PL_utf8_digit)
PL_utf8_digit = swash_init("utf8", "IsDigit", &PL_sv_undef, 0, 0);
- return swash_fetch(PL_utf8_digit, p, TRUE);
+ return swash_fetch(PL_utf8_digit, p, TRUE) != 0;
}
bool
return FALSE;
if (!PL_utf8_upper)
PL_utf8_upper = swash_init("utf8", "IsUpper", &PL_sv_undef, 0, 0);
- return swash_fetch(PL_utf8_upper, p, TRUE);
+ return swash_fetch(PL_utf8_upper, p, TRUE) != 0;
}
bool
return FALSE;
if (!PL_utf8_lower)
PL_utf8_lower = swash_init("utf8", "IsLower", &PL_sv_undef, 0, 0);
- return swash_fetch(PL_utf8_lower, p, TRUE);
+ return swash_fetch(PL_utf8_lower, p, TRUE) != 0;
}
bool
return FALSE;
if (!PL_utf8_cntrl)
PL_utf8_cntrl = swash_init("utf8", "IsCntrl", &PL_sv_undef, 0, 0);
- return swash_fetch(PL_utf8_cntrl, p, TRUE);
+ return swash_fetch(PL_utf8_cntrl, p, TRUE) != 0;
}
bool
return FALSE;
if (!PL_utf8_graph)
PL_utf8_graph = swash_init("utf8", "IsGraph", &PL_sv_undef, 0, 0);
- return swash_fetch(PL_utf8_graph, p, TRUE);
+ return swash_fetch(PL_utf8_graph, p, TRUE) != 0;
}
bool
return FALSE;
if (!PL_utf8_print)
PL_utf8_print = swash_init("utf8", "IsPrint", &PL_sv_undef, 0, 0);
- return swash_fetch(PL_utf8_print, p, TRUE);
+ return swash_fetch(PL_utf8_print, p, TRUE) != 0;
}
bool
return FALSE;
if (!PL_utf8_punct)
PL_utf8_punct = swash_init("utf8", "IsPunct", &PL_sv_undef, 0, 0);
- return swash_fetch(PL_utf8_punct, p, TRUE);
+ return swash_fetch(PL_utf8_punct, p, TRUE) != 0;
}
bool
return FALSE;
if (!PL_utf8_xdigit)
PL_utf8_xdigit = swash_init("utf8", "IsXDigit", &PL_sv_undef, 0, 0);
- return swash_fetch(PL_utf8_xdigit, p, TRUE);
+ return swash_fetch(PL_utf8_xdigit, p, TRUE) != 0;
}
bool
return FALSE;
if (!PL_utf8_mark)
PL_utf8_mark = swash_init("utf8", "IsM", &PL_sv_undef, 0, 0);
- return swash_fetch(PL_utf8_mark, p, TRUE);
+ return swash_fetch(PL_utf8_mark, p, TRUE) != 0;
}
/*
conversion result to. The "lenp" is a pointer to the length
of the result.
-The "swash" is a pointer to the swash to use.
+The "swashp" is a pointer to the swash to use.
-The "normal" is a string like "ToLower" which means the swash
-$utf8::ToLower, which is stored in lib/unicore/To/Lower.pl,
-and loaded by SWASHGET, using lib/utf8_heavy.pl.
+Both the special and normal mappings are stored lib/unicore/To/Foo.pl,
+and loaded by SWASHGET, using lib/utf8_heavy.pl. The special (usually,
+but not always, a multicharacter mapping), is tried first.
-The "special" is a string like "utf8::ToSpecLower", which means
-the hash %utf8::ToSpecLower, which is stored in the same file,
-lib/unicore/To/Lower.pl, and also loaded by SWASHGET. The access
-to the hash is by Perl_to_utf8_case().
+The "special" is a string like "utf8::ToSpecLower", which means the
+hash %utf8::ToSpecLower. The access to the hash is through
+Perl_to_utf8_case().
-=cut
- */
+The "normal" is a string like "ToLower" which means the swash
+%utf8::ToLower.
+
+=cut */
UV
-Perl_to_utf8_case(pTHX_ U8 *p, U8* ustrp, STRLEN *lenp, SV **swashp,char *normal, char *special)
+Perl_to_utf8_case(pTHX_ U8 *p, U8* ustrp, STRLEN *lenp, SV **swashp, char *normal, char *special)
{
- UV uv;
+ UV uv0, uv1;
+ U8 tmpbuf[UTF8_MAXLEN_FOLD+1];
+ STRLEN len = 0;
- 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 {
+ 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. */
+ uv1 = NATIVE_TO_UNI(uv0);
+ uvuni_to_utf8(tmpbuf, uv1);
+
+ if (!*swashp) /* load on-demand */
+ *swashp = swash_init("utf8", normal, &PL_sv_undef, 4, 0);
+
+ if (special) {
+ /* It might be "special" (sometimes, but not always,
+ * a multicharacter mapping) */
HV *hv;
SV *keysv;
HE *he;
-
- uv = utf8_to_uvchr(p, 0);
-
+ SV *val;
+
if ((hv = get_hv(special, FALSE)) &&
- (keysv = sv_2mortal(Perl_newSVpvf(aTHX_ "%04"UVXf, uv))) &&
- (he = hv_fetch_ent(hv, keysv, FALSE, 0))) {
- SV *val = HeVAL(he);
- char *s = SvPV(val, *lenp);
- U8 c = *(U8*)s;
- if (*lenp > 1 || UNI_IS_INVARIANT(c))
- Copy(s, ustrp, *lenp, U8);
+ (keysv = sv_2mortal(Perl_newSVpvf(aTHX_ "%04"UVXf, uv1))) &&
+ (he = hv_fetch_ent(hv, keysv, FALSE, 0)) &&
+ (val = HeVAL(he))) {
+ char *s;
+
+ s = SvPV(val, len);
+ if (len == 1)
+ len = uvuni_to_utf8(ustrp, NATIVE_TO_UNI(*(U8*)s)) - ustrp;
else {
- /* something in the 0x80..0xFF range */
- ustrp[0] = UTF8_EIGHT_BIT_HI(c);
- ustrp[1] = UTF8_EIGHT_BIT_LO(c);
- *lenp = 2;
+#ifdef EBCDIC
+ /* If we have EBCDIC we need to remap the characters
+ * since any characters in the low 256 are Unicode
+ * code points, not EBCDIC. */
+ U8 *t = (U8*)s, *tend = t + len, *d;
+
+ d = tmpbuf;
+ if (SvUTF8(val)) {
+ STRLEN tlen = 0;
+
+ while (t < tend) {
+ UV c = utf8_to_uvchr(t, &tlen);
+ if (tlen > 0) {
+ d = uvchr_to_utf8(d, UNI_TO_NATIVE(c));
+ t += tlen;
+ }
+ else
+ break;
+ }
+ }
+ else {
+ while (t < tend) {
+ d = uvchr_to_utf8(d, UNI_TO_NATIVE(*t));
+ t++;
+ }
+ }
+ len = d - tmpbuf;
+ Copy(tmpbuf, ustrp, len, U8);
+#else
+ Copy(s, ustrp, len, U8);
+#endif
}
- return 0;
}
}
- *lenp = UNISKIP(uv);
- uvuni_to_utf8(ustrp, uv);
- return uv;
+
+ if (!len && *swashp) {
+ UV uv2 = swash_fetch(*swashp, tmpbuf, TRUE);
+
+ if (uv2) {
+ /* It was "normal" (a single character mapping). */
+ UV uv3 = UNI_TO_NATIVE(uv2);
+
+ len = uvchr_to_utf8(ustrp, uv3) - ustrp;
+ }
+ }
+
+ if (!len) /* Neither: just copy. */
+ len = uvchr_to_utf8(ustrp, uv0) - ustrp;
+
+ if (lenp)
+ *lenp = len;
+
+ return len ? utf8_to_uvchr(ustrp, 0) : 0;
}
+/*
+=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)
{
SAVEI32(PL_hints);
PL_hints = 0;
save_re_context();
- if (PL_curcop == &PL_compiling)
+ if (PL_curcop == &PL_compiling) {
/* XXX ought to be handled by lex_start */
+ SAVEI32(PL_in_my);
sv_setpv(tokenbufsv, PL_tokenbuf);
+ }
errsv_save = newSVsv(ERRSV);
if (call_method("SWASHNEW", G_SCALAR))
retval = newSVsv(*PL_stack_sp--);
char* pv = SvPV(tokenbufsv, len);
Copy(pv, PL_tokenbuf, len+1, char);
- PL_curcop->op_private = PL_hints;
+ PL_curcop->op_private = (U8)(PL_hints & HINT_PRIVATE_MASK);
}
- if (!SvROK(retval) || SvTYPE(SvRV(retval)) != SVt_PVHV)
+ if (!SvROK(retval) || SvTYPE(SvRV(retval)) != SVt_PVHV) {
+ if (SvPOK(retval))
+ Perl_croak(aTHX_ "Can't find Unicode property definition \"%s\"",
+ SvPV_nolen(retval));
Perl_croak(aTHX_ "SWASHNEW didn't return an HV ref");
+ }
return retval;
}
UV c = NATIVE_TO_ASCII(*ptr);
if (!do_utf8 && !UNI_IS_INVARIANT(c)) {
- tmputf8[0] = UTF8_EIGHT_BIT_HI(c);
- tmputf8[1] = UTF8_EIGHT_BIT_LO(c);
+ tmputf8[0] = (U8)UTF8_EIGHT_BIT_HI(c);
+ tmputf8[1] = (U8)UTF8_EIGHT_BIT_LO(c);
ptr = tmputf8;
}
/* Given a UTF-X encoded char 0xAA..0xYY,0xZZ
/* 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, NULL, 0);
+ UV code_point = utf8n_to_uvuni(ptr, UTF8_MAXLEN, 0,
+ ckWARN(WARN_UTF8) ?
+ 0 : UTF8_ALLOW_ANY);
SV *errsv_save;
ENTER;
SAVETMPS;
FREETMPS;
LEAVE;
if (PL_curcop == &PL_compiling)
- PL_curcop->op_private = PL_hints;
+ PL_curcop->op_private = (U8)(PL_hints & HINT_PRIVATE_MASK);
svp = hv_store(hv, (char*)ptr, klen, retval, 0);
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", (char)(u & 0xFF));
+ 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 < (UV)(e1 - (U8*)s1)))
+ f1 = (U8*)s1 + l1;
+ if (pe2)
+ e2 = *(U8**)pe2;
+ if (e2 == 0 || (l2 && l2 < (UV)(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 */
+
+ if (!u1 || !u2)
+ natbuf[1] = 0; /* Need to terminate the buffer. */
+
+ 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] = *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] = *p2;
+ to_utf8_fold(natbuf, foldbuf2, &foldlen2);
+ }
+ q2 = foldbuf2;
+ n2 = foldlen2;
+ }
+ 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);
}
- a += la;
- b += lb;
+ 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 */
}
https://perl5.git.perl.org / perl5.git / blobdiff