/* utf8.c
*
- * Copyright (C) 2000, 2001, 2002, 2003, 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.
#define PERL_IN_UTF8_C
#include "perl.h"
-static char unees[] = "Malformed UTF-8 character (unexpected end of string)";
+static const char unees[] =
+ "Malformed UTF-8 character (unexpected end of string)";
/*
=head1 Unicode Support
+This file contains various utility functions for manipulating UTF8-encoded
+strings. For the uninitiated, this is a method of representing arbitrary
+Unicode characters as a variable number of bytes, in such a way that
+characters in the ASCII range are unmodified, and a zero byte never appears
+within non-zero characters.
+
=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,
#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.
+This is the "slow" version as opposed to the "fast" version which is
+the "unrolled" IS_UTF8_CHAR(). E.g. for t/uni/class.t the speed
+difference is a factor of 2 to 3. For lengths (UTF8SKIP(s)) of four
+or less you should use the IS_UTF8_CHAR(), for lengths of five or more
+you should use the _slow(). In practice this means that the _slow()
+will be used very rarely, since the maximum Unicode code point (as of
+Unicode 4.1) is U+10FFFF, which encodes in UTF-8 to four bytes. Only
+the "Perl extended UTF-8" (the infamous 'v-strings') will encode into
+five bytes or more.
+
=cut */
-STRLEN
-Perl_is_utf8_char(pTHX_ U8 *s)
+STATIC STRLEN
+S_is_utf8_char_slow(pTHX_ const U8 *s, const STRLEN len)
{
U8 u = *s;
- STRLEN slen, len;
+ STRLEN slen;
UV uv, ouv;
if (UTF8_IS_INVARIANT(u))
if (!UTF8_IS_START(u))
return 0;
- len = UTF8SKIP(s);
-
if (len < 2 || !UTF8_IS_CONTINUATION(s[1]))
return 0;
slen = len - 1;
s++;
+#ifdef EBCDIC
+ u = NATIVE_TO_UTF(u);
+#endif
u &= UTF_START_MASK(len);
uv = u;
ouv = uv;
}
/*
-=for apidoc A|bool|is_utf8_string|U8 *s|STRLEN len
+=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
+UTF-8 character. The actual number of bytes in the UTF-8 character
+will be returned if it is valid, otherwise 0.
+
+=cut */
+STRLEN
+Perl_is_utf8_char(pTHX_ const U8 *s)
+{
+ const STRLEN len = UTF8SKIP(s);
+#ifdef IS_UTF8_CHAR
+ if (IS_UTF8_CHAR_FAST(len))
+ return IS_UTF8_CHAR(s, len) ? len : 0;
+#endif /* #ifdef IS_UTF8_CHAR */
+ return is_utf8_char_slow(s, 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
not mean 'a string that contains code points above 0x7F encoded in UTF-8'
because a valid ASCII string is a valid UTF-8 string.
+See also is_utf8_string_loclen() and is_utf8_string_loc().
+
=cut
*/
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;
- STRLEN c;
+ const U8* x = s;
+ const U8* send;
if (!len)
- len = strlen((char *)s);
+ len = strlen((const char *)s);
send = s + len;
while (x < send) {
+ STRLEN c;
/* Inline the easy bits of is_utf8_char() here for speed... */
if (UTF8_IS_INVARIANT(*x))
c = 1;
else if (!UTF8_IS_START(*x))
- return FALSE;
+ goto out;
else {
/* ... and call is_utf8_char() only if really needed. */
- c = is_utf8_char(x);
+#ifdef IS_UTF8_CHAR
+ c = UTF8SKIP(x);
+ if (IS_UTF8_CHAR_FAST(c)) {
+ if (!IS_UTF8_CHAR(x, c))
+ goto out;
+ } else if (!is_utf8_char_slow(x, c))
+ goto out;
+#else
+ c = is_utf8_char(x);
+#endif /* #ifdef IS_UTF8_CHAR */
if (!c)
- return FALSE;
+ goto out;
}
x += c;
}
+
+ out:
if (x != send)
return FALSE;
}
/*
-=for apidoc A|bool|is_utf8_string_loc|U8 *s|STRLEN len|U8 **p
+Implemented as a macro in utf8.h
+
+=for apidoc A|bool|is_utf8_string_loc|const U8 *s|STRLEN len|const U8 **ep
+
+Like is_utf8_string() but stores the location of the failure (in the
+case of "utf8ness failure") or the location s+len (in the case of
+"utf8ness success") in the C<ep>.
+
+See also is_utf8_string_loclen() and is_utf8_string().
+
+=for apidoc A|bool|is_utf8_string_loclen|const U8 *s|STRLEN len|const U8 **ep|const STRLEN *el
+
+Like is_utf8_string() but stores the location of the failure (in the
+case of "utf8ness failure") or the location s+len (in the case of
+"utf8ness success") in the C<ep>, and the number of UTF-8
+encoded characters in the C<el>.
-Like is_ut8_string but store the location of the failure in
-the last argument.
+See also is_utf8_string_loc() and is_utf8_string().
=cut
*/
bool
-Perl_is_utf8_string_loc(pTHX_ U8 *s, STRLEN len, U8 **p)
+Perl_is_utf8_string_loclen(pTHX_ const U8 *s, STRLEN len, const U8 **ep, STRLEN *el)
{
- U8* x = s;
- U8* send;
+ const U8* x = s;
+ const U8* send;
STRLEN c;
if (!len)
- len = strlen((char *)s);
+ len = strlen((const char *)s);
send = s + len;
+ if (el)
+ *el = 0;
while (x < send) {
/* Inline the easy bits of is_utf8_char() here for speed... */
if (UTF8_IS_INVARIANT(*x))
- c = 1;
- else if (!UTF8_IS_START(*x)) {
- if (p)
- *p = x;
- return FALSE;
- }
+ c = 1;
+ else if (!UTF8_IS_START(*x))
+ goto out;
else {
- /* ... and call is_utf8_char() only if really needed. */
- c = is_utf8_char(x);
- if (!c) {
- if (p)
- *p = x;
- return FALSE;
- }
+ /* ... and call is_utf8_char() only if really needed. */
+#ifdef IS_UTF8_CHAR
+ c = UTF8SKIP(x);
+ if (IS_UTF8_CHAR_FAST(c)) {
+ if (!IS_UTF8_CHAR(x, c))
+ c = 0;
+ } else
+ c = is_utf8_char_slow(x, c);
+#else
+ c = is_utf8_char(x);
+#endif /* #ifdef IS_UTF8_CHAR */
+ if (!c)
+ goto out;
}
- x += c;
+ x += c;
+ if (el)
+ (*el)++;
}
- if (x != send) {
- if (p)
- *p = x;
+
+ out:
+ if (ep)
+ *ep = x;
+ if (x != send)
return FALSE;
- }
return TRUE;
}
/*
-=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;
if (!(uv > ouv)) {
/* These cannot be allowed. */
if (uv == ouv) {
- if (!(flags & UTF8_ALLOW_LONG)) {
+ if (expectlen != 13 && !(flags & UTF8_ALLOW_LONG)) {
warning = UTF8_WARN_LONG;
goto malformed;
}
}
if (dowarn) {
- SV* sv = sv_2mortal(newSVpv("Malformed UTF-8 character ", 0));
+ SV* const sv = sv_2mortal(newSVpv("Malformed UTF-8 character ", 0));
switch (warning) {
case 0: /* Intentionally empty. */ break;
case UTF8_WARN_EMPTY:
- Perl_sv_catpvf(aTHX_ sv, "(empty string)");
+ Perl_sv_catpv(aTHX_ sv, "(empty string)");
break;
case UTF8_WARN_CONTINUATION:
Perl_sv_catpvf(aTHX_ sv, "(unexpected continuation byte 0x%02"UVxf", with no preceding start byte)", 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
+ else {
+ const int len = (int)(s-s0);
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);
-
+ (UV)s[1], len, len > 1 ? "s" : "", startbyte, (int)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, after start byte 0x%02"UVxf")",
- curlen, curlen == 1 ? "" : "s", expectlen, startbyte);
+ (int)curlen, curlen == 1 ? "" : "s", (int)expectlen, startbyte);
expectlen = curlen; /* distance for caller to skip */
break;
case UTF8_WARN_OVERFLOW:
break;
case UTF8_WARN_LONG:
Perl_sv_catpvf(aTHX_ sv, "(%d byte%s, need %d, after start byte 0x%02"UVxf")",
- expectlen, expectlen == 1 ? "": "s", UNISKIP(uv), startbyte);
+ (int)expectlen, expectlen == 1 ? "": "s", UNISKIP(uv), startbyte);
break;
case UTF8_WARN_FFFF:
Perl_sv_catpvf(aTHX_ sv, "(character 0x%04"UVxf")", uv);
break;
default:
- Perl_sv_catpvf(aTHX_ sv, "(unknown reason)");
+ Perl_sv_catpv(aTHX_ sv, "(unknown reason)");
break;
}
if (warning) {
- char *s = SvPVX(sv);
+ const char * const s = SvPVX_const(sv);
if (PL_op)
Perl_warner(aTHX_ packWARN(WARN_UTF8),
}
/*
-=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_MAXLEN, 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_MAXLEN, retlen,
+ return Perl_utf8n_to_uvuni(aTHX_ s, UTF8_MAXBYTES, retlen,
ckWARN(WARN_UTF8) ? 0 : UTF8_ALLOW_ANY);
}
/*
-=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;
* the bitops (especially ~) can create illegal UTF-8.
* In other words: in Perl UTF-8 is not just for Unicode. */
- 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;
- }
+ if (e < s)
+ goto warn_and_return;
while (s < e) {
- U8 t = UTF8SKIP(s);
-
+ const U8 t = UTF8SKIP(s);
if (e - s < t) {
+ warn_and_return:
if (ckWARN_d(WARN_UTF8)) {
if (PL_op)
Perl_warner(aTHX_ packWARN(WARN_UTF8),
- unees, OP_DESC(PL_op));
+ "%s in %s", unees, OP_DESC(PL_op));
else
Perl_warner(aTHX_ packWARN(WARN_UTF8), unees);
}
}
/*
-=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);
-
- 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;
- }
+ const U8 c = UTF8SKIP(a);
+ if (b - a < c)
+ goto warn_and_return;
a += c;
off--;
}
}
else {
while (b < a) {
- U8 c = UTF8SKIP(b);
+ const U8 c = UTF8SKIP(b);
if (a - b < c) {
+ warn_and_return:
if (ckWARN_d(WARN_UTF8)) {
if (PL_op)
Perl_warner(aTHX_ packWARN(WARN_UTF8),
*/
U8 *
-Perl_utf8_hop(pTHX_ U8 *s, I32 off)
+Perl_utf8_hop(pTHX_ const U8 *s, I32 off)
{
/* Note: cannot use UTF8_IS_...() too eagerly here since e.g
* the bitops (especially ~) can create illegal UTF-8.
s--;
}
}
- return s;
+ return (U8 *)s;
}
/*
}
/*
-=for apidoc A|U8 *|bytes_from_utf8|U8 *s|STRLEN *len|bool *is_utf8
+=for apidoc A|U8 *|bytes_from_utf8|const 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
*/
U8 *
-Perl_bytes_from_utf8(pTHX_ U8 *s, STRLEN *len, bool *is_utf8)
+Perl_bytes_from_utf8(pTHX_ const U8 *s, STRLEN *len, bool *is_utf8)
{
U8 *d;
- U8 *start = s;
- U8 *send;
+ const U8 *start = s;
+ const U8 *send;
I32 count = 0;
if (!*is_utf8)
- return start;
+ return (U8 *)start;
/* ensure valid UTF-8 and chars < 256 before converting string */
for (send = s + *len; s < send;) {
- U8 c = *s++;
+ U8 c = *s++;
if (!UTF8_IS_INVARIANT(c)) {
if (UTF8_IS_DOWNGRADEABLE_START(c) && s < send &&
(c = *s++) && UTF8_IS_CONTINUATION(c))
count++;
else
- return start;
+ return (U8 *)start;
}
}
*is_utf8 = 0;
- Newz(801, d, (*len) - count + 1, U8);
+ Newxz(d, (*len) - count + 1, U8);
s = start; start = d;
while (s < send) {
U8 c = *s++;
}
*d = '\0';
*len = d - start;
- return start;
+ return (U8 *)start;
}
/*
-=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);
+ Newxz(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 {
U8* pend;
U8* dstart = d;
+ if (bytelen == 1 && p[0] == 0) { /* Be understanding. */
+ d[0] = 0;
+ *newlen = 1;
+ return d;
+ }
+
if (bytelen & 1)
- Perl_croak(aTHX_ "panic: utf16_to_utf8: odd bytelen");
+ Perl_croak(aTHX_ "panic: utf16_to_utf8: odd bytelen %"UVf, (UV)bytelen);
pend = p + bytelen;
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);
}
bool
-Perl_is_utf8_alnum(pTHX_ U8 *p)
+S_is_utf8_common(pTHX_ const U8 *const p, SV **swash,
+ const char *const swashname)
{
if (!is_utf8_char(p))
return FALSE;
- if (!PL_utf8_alnum)
- /* NOTE: "IsWord", not "IsAlnum", since Alnum is a true
- * 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) != 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) != 0;
-#endif
+ if (!*swash)
+ *swash = swash_init("utf8", swashname, &PL_sv_undef, 0, 0);
+ return swash_fetch(*swash, p, TRUE) != 0;
}
bool
-Perl_is_utf8_alnumc(pTHX_ U8 *p)
+Perl_is_utf8_alnum(pTHX_ const U8 *p)
{
- if (!is_utf8_char(p))
- 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) != 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) != 0;
-#endif
+ /* NOTE: "IsWord", not "IsAlnum", since Alnum is a true
+ * descendant of isalnum(3), in other words, it doesn't
+ * contain the '_'. --jhi */
+ return S_is_utf8_common(aTHX_ p, &PL_utf8_alnum, "IsWord");
+}
+
+bool
+Perl_is_utf8_alnumc(pTHX_ const U8 *p)
+{
+ return S_is_utf8_common(aTHX_ p, &PL_utf8_alnumc, "IsAlnumC");
}
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;
- 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;
+ /* is_utf8_idstart would be more logical. */
+ return S_is_utf8_common(aTHX_ p, &PL_utf8_idstart, "IdStart");
}
bool
-Perl_is_utf8_idcont(pTHX_ U8 *p)
+Perl_is_utf8_idcont(pTHX_ const 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;
+ return S_is_utf8_common(aTHX_ p, &PL_utf8_idcont, "IdContinue");
}
bool
-Perl_is_utf8_alpha(pTHX_ U8 *p)
+Perl_is_utf8_alpha(pTHX_ const U8 *p)
{
- if (!is_utf8_char(p))
- 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) != 0;
+ return S_is_utf8_common(aTHX_ p, &PL_utf8_alpha, "IsAlpha");
}
bool
-Perl_is_utf8_ascii(pTHX_ U8 *p)
+Perl_is_utf8_ascii(pTHX_ const U8 *p)
{
- if (!is_utf8_char(p))
- 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) != 0;
+ return S_is_utf8_common(aTHX_ p, &PL_utf8_ascii, "IsAscii");
}
bool
-Perl_is_utf8_space(pTHX_ U8 *p)
+Perl_is_utf8_space(pTHX_ const U8 *p)
{
- if (!is_utf8_char(p))
- 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) != 0;
+ return S_is_utf8_common(aTHX_ p, &PL_utf8_space, "IsSpacePerl");
}
bool
-Perl_is_utf8_digit(pTHX_ U8 *p)
+Perl_is_utf8_digit(pTHX_ const U8 *p)
{
- if (!is_utf8_char(p))
- 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) != 0;
+ return S_is_utf8_common(aTHX_ p, &PL_utf8_digit, "IsDigit");
}
bool
-Perl_is_utf8_upper(pTHX_ U8 *p)
+Perl_is_utf8_upper(pTHX_ const U8 *p)
{
- if (!is_utf8_char(p))
- return FALSE;
- if (!PL_utf8_upper)
- PL_utf8_upper = swash_init("utf8", "IsUppercase", &PL_sv_undef, 0, 0);
- return swash_fetch(PL_utf8_upper, p, TRUE) != 0;
+ return S_is_utf8_common(aTHX_ p, &PL_utf8_upper, "IsUppercase");
}
bool
-Perl_is_utf8_lower(pTHX_ U8 *p)
+Perl_is_utf8_lower(pTHX_ const U8 *p)
{
- if (!is_utf8_char(p))
- return FALSE;
- if (!PL_utf8_lower)
- PL_utf8_lower = swash_init("utf8", "IsLowercase", &PL_sv_undef, 0, 0);
- return swash_fetch(PL_utf8_lower, p, TRUE) != 0;
+ return S_is_utf8_common(aTHX_ p, &PL_utf8_lower, "IsLowercase");
}
bool
-Perl_is_utf8_cntrl(pTHX_ U8 *p)
+Perl_is_utf8_cntrl(pTHX_ const U8 *p)
{
- if (!is_utf8_char(p))
- 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) != 0;
+ return S_is_utf8_common(aTHX_ p, &PL_utf8_cntrl, "IsCntrl");
}
bool
-Perl_is_utf8_graph(pTHX_ U8 *p)
+Perl_is_utf8_graph(pTHX_ const U8 *p)
{
- if (!is_utf8_char(p))
- 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) != 0;
+ return S_is_utf8_common(aTHX_ p, &PL_utf8_graph, "IsGraph");
}
bool
-Perl_is_utf8_print(pTHX_ U8 *p)
+Perl_is_utf8_print(pTHX_ const U8 *p)
{
- if (!is_utf8_char(p))
- 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) != 0;
+ return S_is_utf8_common(aTHX_ p, &PL_utf8_print, "IsPrint");
}
bool
-Perl_is_utf8_punct(pTHX_ U8 *p)
+Perl_is_utf8_punct(pTHX_ const U8 *p)
{
- if (!is_utf8_char(p))
- 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) != 0;
+ return S_is_utf8_common(aTHX_ p, &PL_utf8_punct, "IsPunct");
}
bool
-Perl_is_utf8_xdigit(pTHX_ U8 *p)
+Perl_is_utf8_xdigit(pTHX_ const U8 *p)
{
- if (!is_utf8_char(p))
- 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) != 0;
+ return S_is_utf8_common(aTHX_ p, &PL_utf8_xdigit, "Isxdigit");
}
bool
-Perl_is_utf8_mark(pTHX_ U8 *p)
+Perl_is_utf8_mark(pTHX_ const U8 *p)
{
- if (!is_utf8_char(p))
- 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) != 0;
+ return S_is_utf8_common(aTHX_ p, &PL_utf8_mark, "IsM");
}
/*
=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, const char *normal, const 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);
+ const UV uv0 = utf8_to_uvchr(p, NULL);
/* 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);
+ const UV 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) {
+ /* The 0xDF is the only special casing Unicode code point below 0x100. */
+ if (special && (uv1 == 0xDF || uv1 > 0xFF)) {
/* It might be "special" (sometimes, but not always,
* a multicharacter mapping) */
HV *hv;
- SV *keysv;
- HE *he;
- SV *val;
-
- if ((hv = get_hv(special, FALSE)) &&
- (keysv = sv_2mortal(Perl_newSVpvf(aTHX_ "%04"UVXf, uv1))) &&
- (he = hv_fetch_ent(hv, keysv, FALSE, 0)) &&
- (val = HeVAL(he))) {
- char *s;
+ SV **svp;
- s = SvPV(val, len);
+ if ((hv = get_hv(special, FALSE)) &&
+ (svp = hv_fetch(hv, (const char*)tmpbuf, UNISKIP(uv1), FALSE)) &&
+ (*svp)) {
+ const char *s;
+
+ s = SvPV_const(*svp, len);
if (len == 1)
len = uvuni_to_utf8(ustrp, NATIVE_TO_UNI(*(U8*)s)) - ustrp;
else {
U8 *t = (U8*)s, *tend = t + len, *d;
d = tmpbuf;
- if (SvUTF8(val)) {
+ if (SvUTF8(*svp)) {
STRLEN tlen = 0;
while (t < tend) {
}
/*
-=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
-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.)
=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
-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.)
=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
-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.)
=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
-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).
=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)
{
+ dVAR;
SV* retval;
- SV* tokenbufsv = sv_2mortal(NEWSV(0,0));
+ SV* const tokenbufsv = sv_newmortal();
dSP;
- HV *stash = gv_stashpvn(pkg, strlen(pkg), FALSE);
+ const size_t pkg_len = strlen(pkg);
+ const size_t name_len = strlen(name);
+ HV * const stash = gv_stashpvn(pkg, pkg_len, FALSE);
SV* errsv_save;
+ PUSHSTACKi(PERLSI_MAGIC);
+ ENTER;
+ SAVEI32(PL_hints);
+ PL_hints = 0;
+ save_re_context();
if (!gv_fetchmeth(stash, "SWASHNEW", 8, -1)) { /* demand load utf8 */
ENTER;
errsv_save = newSVsv(ERRSV);
- Perl_load_module(aTHX_ PERL_LOADMOD_NOIMPORT, newSVpv(pkg,0), Nullsv);
+ Perl_load_module(aTHX_ PERL_LOADMOD_NOIMPORT, newSVpvn(pkg,pkg_len),
+ Nullsv);
if (!SvTRUE(ERRSV))
sv_setsv(ERRSV, errsv_save);
SvREFCNT_dec(errsv_save);
LEAVE;
}
SPAGAIN;
- PUSHSTACKi(PERLSI_MAGIC);
PUSHMARK(SP);
EXTEND(SP,5);
- PUSHs(sv_2mortal(newSVpvn(pkg, strlen(pkg))));
- PUSHs(sv_2mortal(newSVpvn(name, strlen(name))));
+ PUSHs(sv_2mortal(newSVpvn(pkg, pkg_len)));
+ PUSHs(sv_2mortal(newSVpvn(name, name_len)));
PUSHs(listsv);
PUSHs(sv_2mortal(newSViv(minbits)));
PUSHs(sv_2mortal(newSViv(none)));
PUTBACK;
- ENTER;
- SAVEI32(PL_hints);
- PL_hints = 0;
- save_re_context();
if (IN_PERL_COMPILETIME) {
/* XXX ought to be handled by lex_start */
SAVEI32(PL_in_my);
POPSTACK;
if (IN_PERL_COMPILETIME) {
STRLEN len;
- char* pv = SvPV(tokenbufsv, len);
+ const char* const pv = SvPV_const(tokenbufsv, len);
Copy(pv, PL_tokenbuf, len+1, char);
PL_curcop->op_private = (U8)(PL_hints & HINT_PRIVATE_MASK);
* 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);
+ dVAR;
+ HV* const hv = (HV*)SvRV(sv);
U32 klen;
U32 off;
STRLEN slen;
STRLEN needents;
- U8 *tmps = NULL;
+ const U8 *tmps = NULL;
U32 bit;
SV *retval;
U8 tmputf8[2];
}
else {
/* Try our second-level swatch cache, kept in a hash. */
- SV** svp = hv_fetch(hv, (char*)ptr, klen, FALSE);
+ SV** svp = hv_fetch(hv, (const char*)ptr, klen, FALSE);
/* If not cached, generate it via utf8::SWASHGET */
- if (!svp || !SvPOK(*svp) || !(tmps = (U8*)SvPV(*svp, slen))) {
+ if (!svp || !SvPOK(*svp) || !(tmps = (const U8*)SvPV_const(*svp, slen))) {
dSP;
/* 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,
+ const UV code_point = utf8n_to_uvuni(ptr, UTF8_MAXBYTES, 0,
ckWARN(WARN_UTF8) ?
0 : UTF8_ALLOW_ANY);
SV *errsv_save;
if (IN_PERL_COMPILETIME)
PL_curcop->op_private = (U8)(PL_hints & HINT_PRIVATE_MASK);
- svp = hv_store(hv, (char*)ptr, klen, retval, 0);
+ svp = hv_store(hv, (const char *)ptr, klen, retval, 0);
if (!svp || !(tmps = (U8*)SvPV(*svp, slen)) || (slen << 3) < needents)
Perl_croak(aTHX_ "SWASHGET didn't return result of proper length");
PL_last_swash_hv = hv;
PL_last_swash_klen = klen;
- PL_last_swash_tmps = tmps;
+ /* FIXME change interpvar.h? */
+ PL_last_swash_tmps = (U8 *) tmps;
PL_last_swash_slen = slen;
if (klen)
Copy(ptr, PL_last_swash_key, klen, U8);
return 0;
}
-
/*
=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,
}
/*
-=for apidoc A|UV|utf8n_to_uvchr|U8 *s|STRLEN curlen|STRLEN *retlen|U32 flags
+=for apidoc A|UV|utf8n_to_uvchr|U8 *s|STRLEN curlen|STRLEN *retlen|U32
+flags
-Returns the native character value of the first character in the string C<s>
+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
length, in bytes, of that character.
*/
#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);
+ const UV uv = Perl_utf8n_to_uvuni(aTHX_ s, curlen, retlen, flags);
return UNI_TO_NATIVE(uv);
}
=cut */
char *
-Perl_pv_uni_display(pTHX_ SV *dsv, U8 *spv, STRLEN len, STRLEN pvlim, UV flags)
+Perl_pv_uni_display(pTHX_ SV *dsv, const U8 *spv, STRLEN len, STRLEN pvlim, UV flags)
{
int truncated = 0;
- char *s, *e;
+ const char *s, *e;
sv_setpvn(dsv, "", 0);
- for (s = (char *)spv, e = s + len; s < e; s += UTF8SKIP(s)) {
+ for (s = (const char *)spv, e = s + len; s < e; s += UTF8SKIP(s)) {
UV u;
- bool ok = FALSE;
+ /* This serves double duty as a flag and a character to print after
+ a \ when flags & UNI_DISPLAY_BACKSLASH is true.
+ */
+ char ok = 0;
if (pvlim && SvCUR(dsv) >= pvlim) {
truncated++;
}
u = utf8_to_uvchr((U8*)s, 0);
if (u < 256) {
+ const unsigned char c = (unsigned char)u & 0xFF;
if (!ok && (flags & UNI_DISPLAY_BACKSLASH)) {
- switch (u & 0xFF) {
+ switch (c) {
case '\n':
- Perl_sv_catpvf(aTHX_ dsv, "\\n"); ok = TRUE; break;
+ ok = 'n'; break;
case '\r':
- Perl_sv_catpvf(aTHX_ dsv, "\\r"); ok = TRUE; break;
+ ok = 'r'; break;
case '\t':
- Perl_sv_catpvf(aTHX_ dsv, "\\t"); ok = TRUE; break;
+ ok = 't'; break;
case '\f':
- Perl_sv_catpvf(aTHX_ dsv, "\\f"); ok = TRUE; break;
+ ok = 'f'; break;
case '\a':
- Perl_sv_catpvf(aTHX_ dsv, "\\a"); ok = TRUE; break;
+ ok = 'a'; break;
case '\\':
- Perl_sv_catpvf(aTHX_ dsv, "\\\\" ); ok = TRUE; break;
+ ok = '\\'; break;
default: break;
}
+ if (ok) {
+ Perl_sv_catpvf(aTHX_ dsv, "\\%c", ok);
+ }
}
/* 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 && (flags & UNI_DISPLAY_ISPRINT) && isPRINT(c)) {
+ Perl_sv_catpvf(aTHX_ dsv, "%c", c);
+ ok = 1;
}
}
if (!ok)
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, (const U8*)SvPVX_const(ssv),
+ SvCUR(ssv), pvlim, flags);
}
/*
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
+circumstances. 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
I32
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;
+ register const U8 *p1 = (const U8*)s1;
+ register const U8 *p2 = (const U8*)s2;
+ register const U8 *f1 = 0, *f2 = 0;
+ register U8 *e1 = 0, *q1 = 0;
+ register U8 *e2 = 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;
if (pe1)
e1 = *(U8**)pe1;
- if (e1 == 0 || (l1 && l1 < (UV)(e1 - (U8*)s1)))
- f1 = (U8*)s1 + l1;
+ if (e1 == 0 || (l1 && l1 < (UV)(e1 - (const U8*)s1)))
+ f1 = (const U8*)s1 + l1;
if (pe2)
e2 = *(U8**)pe2;
- if (e2 == 0 || (l2 && l2 < (UV)(e2 - (U8*)s2)))
- f2 = (U8*)s2 + l2;
+ if (e2 == 0 || (l2 && l2 < (UV)(e2 - (const U8*)s2)))
+ f2 = (const 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)
to_utf8_fold(p1, foldbuf1, &foldlen1);
else {
- natbuf[0] = *p1;
+ uvuni_to_utf8(natbuf, (UV) NATIVE_TO_UNI(((UV)*p1)));
to_utf8_fold(natbuf, foldbuf1, &foldlen1);
}
q1 = foldbuf1;
if (u2)
to_utf8_fold(p2, foldbuf2, &foldlen2);
else {
- natbuf[0] = *p2;
+ uvuni_to_utf8(natbuf, (UV) NATIVE_TO_UNI(((UV)*p2)));
to_utf8_fold(natbuf, foldbuf2, &foldlen2);
}
q2 = foldbuf2;
return match ? 0 : 1; /* 0 match, 1 mismatch */
}
+/*
+ * Local variables:
+ * c-indentation-style: bsd
+ * c-basic-offset: 4
+ * indent-tabs-mode: t
+ * End:
+ *
+ * ex: set ts=8 sts=4 sw=4 noet:
+ */
https://perl5.git.perl.org / perl5.git / blobdiff