mirror of
https://github.com/php/php-src.git
synced 2024-10-21 00:12:34 +00:00
188 lines
5.4 KiB
C
Executable File
188 lines
5.4 KiB
C
Executable File
/**********************************************************************
|
|
utf32_be.c - Oniguruma (regular expression library)
|
|
**********************************************************************/
|
|
/*-
|
|
* Copyright (c) 2002-2006 K.Kosako <sndgk393 AT ybb DOT ne DOT jp>
|
|
* All rights reserved.
|
|
*
|
|
* Redistribution and use in source and binary forms, with or without
|
|
* modification, are permitted provided that the following conditions
|
|
* are met:
|
|
* 1. Redistributions of source code must retain the above copyright
|
|
* notice, this list of conditions and the following disclaimer.
|
|
* 2. Redistributions in binary form must reproduce the above copyright
|
|
* notice, this list of conditions and the following disclaimer in the
|
|
* documentation and/or other materials provided with the distribution.
|
|
*
|
|
* THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
|
|
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
|
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
|
|
* ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
|
|
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
|
|
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
|
|
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
|
|
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
|
|
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
|
|
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
|
|
* SUCH DAMAGE.
|
|
*/
|
|
|
|
#include "regenc.h"
|
|
|
|
static int
|
|
utf32be_mbc_enc_len(const UChar* p)
|
|
{
|
|
return 4;
|
|
}
|
|
|
|
static int
|
|
utf32be_is_mbc_newline(const UChar* p, const UChar* end)
|
|
{
|
|
if (p + 3 < end) {
|
|
if (*(p+3) == 0x0a && *(p+2) == 0 && *(p+1) == 0 && *p == 0)
|
|
return 1;
|
|
#ifdef USE_UNICODE_ALL_LINE_TERMINATORS
|
|
if ((*(p+3) == 0x0d || *(p+3) == 0x85)
|
|
&& *(p+2) == 0 && *(p+1) == 0 && *p == 0x00)
|
|
return 1;
|
|
if (*(p+2) == 0x20 && (*(p+3) == 0x29 || *(p+3) == 0x28)
|
|
&& *(p+1) == 0 && *p == 0)
|
|
return 1;
|
|
#endif
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
static OnigCodePoint
|
|
utf32be_mbc_to_code(const UChar* p, const UChar* end)
|
|
{
|
|
return (OnigCodePoint )(((p[0] * 256 + p[1]) * 256 + p[2]) * 256 + p[3]);
|
|
}
|
|
|
|
static int
|
|
utf32be_code_to_mbclen(OnigCodePoint code)
|
|
{
|
|
return 4;
|
|
}
|
|
|
|
static int
|
|
utf32be_code_to_mbc(OnigCodePoint code, UChar *buf)
|
|
{
|
|
UChar* p = buf;
|
|
|
|
*p++ = (UChar )((code & 0xff000000) >>24);
|
|
*p++ = (UChar )((code & 0xff0000) >>16);
|
|
*p++ = (UChar )((code & 0xff00) >> 8);
|
|
*p++ = (UChar ) (code & 0xff);
|
|
return 4;
|
|
}
|
|
|
|
static int
|
|
utf32be_mbc_to_normalize(OnigAmbigType flag, const UChar** pp, const UChar* end,
|
|
UChar* lower)
|
|
{
|
|
const UChar* p = *pp;
|
|
|
|
if (*(p+2) == 0 && *(p+1) == 0 && *p == 0) {
|
|
p += 3;
|
|
*lower++ = '\0';
|
|
*lower++ = '\0';
|
|
*lower++ = '\0';
|
|
if (((flag & ONIGENC_AMBIGUOUS_MATCH_ASCII_CASE) != 0 &&
|
|
ONIGENC_IS_MBC_ASCII(p)) ||
|
|
((flag & ONIGENC_AMBIGUOUS_MATCH_NONASCII_CASE) != 0 &&
|
|
!ONIGENC_IS_MBC_ASCII(p))) {
|
|
*lower = ONIGENC_ISO_8859_1_TO_LOWER_CASE(*p);
|
|
}
|
|
else {
|
|
*lower = *p;
|
|
}
|
|
|
|
(*pp) += 4;
|
|
return 4; /* return byte length of converted char to lower */
|
|
}
|
|
else {
|
|
int len = 4;
|
|
if (lower != p) {
|
|
int i;
|
|
for (i = 0; i < len; i++) {
|
|
*lower++ = *p++;
|
|
}
|
|
}
|
|
(*pp) += len;
|
|
return len; /* return byte length of converted char to lower */
|
|
}
|
|
}
|
|
|
|
static int
|
|
utf32be_is_mbc_ambiguous(OnigAmbigType flag, const UChar** pp, const UChar* end)
|
|
{
|
|
const UChar* p = *pp;
|
|
|
|
(*pp) += 4;
|
|
|
|
if (*(p+2) == 0 && *(p+1) == 0 && *p == 0) {
|
|
int c, v;
|
|
|
|
p += 3;
|
|
if (((flag & ONIGENC_AMBIGUOUS_MATCH_ASCII_CASE) != 0 &&
|
|
ONIGENC_IS_MBC_ASCII(p)) ||
|
|
((flag & ONIGENC_AMBIGUOUS_MATCH_NONASCII_CASE) != 0 &&
|
|
!ONIGENC_IS_MBC_ASCII(p))) {
|
|
c = *p;
|
|
v = ONIGENC_IS_UNICODE_ISO_8859_1_CTYPE(c,
|
|
(ONIGENC_CTYPE_UPPER | ONIGENC_CTYPE_LOWER));
|
|
if ((v | ONIGENC_CTYPE_LOWER) != 0) {
|
|
/* 0xaa, 0xb5, 0xba are lower case letter, but can't convert. */
|
|
if (c >= 0xaa && c <= 0xba)
|
|
return FALSE;
|
|
else
|
|
return TRUE;
|
|
}
|
|
return (v != 0 ? TRUE : FALSE);
|
|
}
|
|
}
|
|
|
|
return FALSE;
|
|
}
|
|
|
|
static UChar*
|
|
utf32be_left_adjust_char_head(const UChar* start, const UChar* s)
|
|
{
|
|
int rem;
|
|
|
|
if (s <= start) return (UChar* )s;
|
|
|
|
rem = (s - start) % 4;
|
|
return (UChar* )(s - rem);
|
|
}
|
|
|
|
OnigEncodingType OnigEncodingUTF32_BE = {
|
|
utf32be_mbc_enc_len,
|
|
"UTF-32BE", /* name */
|
|
4, /* max byte length */
|
|
4, /* min byte length */
|
|
(ONIGENC_AMBIGUOUS_MATCH_ASCII_CASE |
|
|
ONIGENC_AMBIGUOUS_MATCH_NONASCII_CASE ),
|
|
{
|
|
(OnigCodePoint )'\\' /* esc */
|
|
, (OnigCodePoint )ONIG_INEFFECTIVE_META_CHAR /* anychar '.' */
|
|
, (OnigCodePoint )ONIG_INEFFECTIVE_META_CHAR /* anytime '*' */
|
|
, (OnigCodePoint )ONIG_INEFFECTIVE_META_CHAR /* zero or one time '?' */
|
|
, (OnigCodePoint )ONIG_INEFFECTIVE_META_CHAR /* one or more time '+' */
|
|
, (OnigCodePoint )ONIG_INEFFECTIVE_META_CHAR /* anychar anytime */
|
|
},
|
|
utf32be_is_mbc_newline,
|
|
utf32be_mbc_to_code,
|
|
utf32be_code_to_mbclen,
|
|
utf32be_code_to_mbc,
|
|
utf32be_mbc_to_normalize,
|
|
utf32be_is_mbc_ambiguous,
|
|
onigenc_iso_8859_1_get_all_pair_ambig_codes,
|
|
onigenc_ess_tsett_get_all_comp_ambig_codes,
|
|
onigenc_unicode_is_code_ctype,
|
|
onigenc_unicode_get_ctype_code_range,
|
|
utf32be_left_adjust_char_head,
|
|
onigenc_always_false_is_allowed_reverse_match
|
|
};
|