mirror of
https://github.com/ruby/ruby.git
synced 2022-11-09 12:17:21 -05:00
* enc/utf_{16,32}{be,le}.c: renamed to match with encoding names.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@14948 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
This commit is contained in:
nobu
parent
ecf8b1c807
commit
aab064f0dc
4 changed files with 869 additions and 0 deletions
239
enc/utf_16be.c
Normal file
239
enc/utf_16be.c
Normal file
|
|
@ -0,0 +1,239 @@
|
|||
/**********************************************************************
|
||||
utf_16be.c - Oniguruma (regular expression library)
|
||||
**********************************************************************/
|
||||
/*-
|
||||
* Copyright (c) 2002-2007 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"
|
||||
|
||||
OnigEncodingDeclare(UTF_16BE);
|
||||
|
||||
#define UTF16_IS_SURROGATE_FIRST(c) (c >= 0xd8 && c <= 0xdb)
|
||||
#define UTF16_IS_SURROGATE_SECOND(c) (c >= 0xdc && c <= 0xdf)
|
||||
|
||||
static const int EncLen_UTF16[] = {
|
||||
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
|
||||
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
|
||||
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
|
||||
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
|
||||
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
|
||||
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
|
||||
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
|
||||
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
|
||||
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
|
||||
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
|
||||
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
|
||||
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
|
||||
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
|
||||
2, 2, 2, 2, 2, 2, 2, 2, 4, 4, 4, 4, 2, 2, 2, 2,
|
||||
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
|
||||
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2
|
||||
};
|
||||
|
||||
static int
|
||||
utf16be_mbc_enc_len(const UChar* p, const OnigUChar* e ARG_UNUSED,
|
||||
struct OnigEncodingTypeST* enc ARG_UNUSED)
|
||||
{
|
||||
return EncLen_UTF16[*p];
|
||||
}
|
||||
|
||||
static int
|
||||
utf16be_is_mbc_newline(const UChar* p, const UChar* end,
|
||||
struct OnigEncodingTypeST* enc ARG_UNUSED)
|
||||
{
|
||||
if (p + 1 < end) {
|
||||
if (*(p+1) == 0x0a && *p == 0x00)
|
||||
return 1;
|
||||
#ifdef USE_UNICODE_ALL_LINE_TERMINATORS
|
||||
if ((
|
||||
#ifndef USE_CRNL_AS_LINE_TERMINATOR
|
||||
*(p+1) == 0x0d ||
|
||||
#endif
|
||||
*(p+1) == 0x85) && *p == 0x00)
|
||||
return 1;
|
||||
if (*p == 0x20 && (*(p+1) == 0x29 || *(p+1) == 0x28))
|
||||
return 1;
|
||||
#endif
|
||||
}
|
||||
return 0;
|
||||
}
|
||||
|
||||
static OnigCodePoint
|
||||
utf16be_mbc_to_code(const UChar* p, const UChar* end ARG_UNUSED,
|
||||
struct OnigEncodingTypeST* enc ARG_UNUSED)
|
||||
{
|
||||
OnigCodePoint code;
|
||||
|
||||
if (UTF16_IS_SURROGATE_FIRST(*p)) {
|
||||
code = ((((p[0] - 0xd8) << 2) + ((p[1] & 0xc0) >> 6) + 1) << 16)
|
||||
+ ((((p[1] & 0x3f) << 2) + (p[2] - 0xdc)) << 8)
|
||||
+ p[3];
|
||||
}
|
||||
else {
|
||||
code = p[0] * 256 + p[1];
|
||||
}
|
||||
return code;
|
||||
}
|
||||
|
||||
static int
|
||||
utf16be_code_to_mbclen(OnigCodePoint code,
|
||||
struct OnigEncodingTypeST* enc ARG_UNUSED)
|
||||
{
|
||||
return (code > 0xffff ? 4 : 2);
|
||||
}
|
||||
|
||||
static int
|
||||
utf16be_code_to_mbc(OnigCodePoint code, UChar *buf,
|
||||
struct OnigEncodingTypeST* enc ARG_UNUSED)
|
||||
{
|
||||
UChar* p = buf;
|
||||
|
||||
if (code > 0xffff) {
|
||||
unsigned int plane, high;
|
||||
|
||||
plane = code >> 16;
|
||||
*p++ = (plane >> 2) + 0xd8;
|
||||
high = (code & 0xff00) >> 8;
|
||||
*p++ = ((plane & 0x03) << 6) + (high >> 2);
|
||||
*p++ = (high & 0x02) + 0xdc;
|
||||
*p = (UChar )(code & 0xff);
|
||||
return 4;
|
||||
}
|
||||
else {
|
||||
*p++ = (UChar )((code & 0xff00) >> 8);
|
||||
*p++ = (UChar )(code & 0xff);
|
||||
return 2;
|
||||
}
|
||||
}
|
||||
|
||||
static int
|
||||
utf16be_mbc_case_fold(OnigCaseFoldType flag,
|
||||
const UChar** pp, const UChar* end, UChar* fold,
|
||||
struct OnigEncodingTypeST* enc ARG_UNUSED)
|
||||
{
|
||||
const UChar* p = *pp;
|
||||
|
||||
if (ONIGENC_IS_ASCII_CODE(*(p+1)) && *p == 0) {
|
||||
p++;
|
||||
#ifdef USE_UNICODE_CASE_FOLD_TURKISH_AZERI
|
||||
if ((flag & ONIGENC_CASE_FOLD_TURKISH_AZERI) != 0) {
|
||||
if (*p == 0x49) {
|
||||
*fold++ = 0x01;
|
||||
*fold = 0x31;
|
||||
(*pp) += 2;
|
||||
return 2;
|
||||
}
|
||||
}
|
||||
#endif
|
||||
|
||||
*fold++ = 0;
|
||||
*fold = ONIGENC_ASCII_CODE_TO_LOWER_CASE(*p);
|
||||
*pp += 2;
|
||||
return 2;
|
||||
}
|
||||
else
|
||||
return onigenc_unicode_mbc_case_fold(&OnigEncodingName(UTF_16BE), flag,
|
||||
pp, end, fold);
|
||||
}
|
||||
|
||||
#if 0
|
||||
static int
|
||||
utf16be_is_mbc_ambiguous(OnigCaseFoldType flag, const UChar** pp, const UChar* end)
|
||||
{
|
||||
const UChar* p = *pp;
|
||||
|
||||
(*pp) += EncLen_UTF16[*p];
|
||||
|
||||
if (*p == 0) {
|
||||
int c, v;
|
||||
|
||||
p++;
|
||||
if (*p == 0xdf && (flag & INTERNAL_ONIGENC_CASE_FOLD_MULTI_CHAR) != 0) {
|
||||
return TRUE;
|
||||
}
|
||||
|
||||
c = *p;
|
||||
v = ONIGENC_IS_UNICODE_ISO_8859_1_BIT_CTYPE(c,
|
||||
(BIT_CTYPE_UPPER | BIT_CTYPE_LOWER));
|
||||
|
||||
if ((v | BIT_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;
|
||||
}
|
||||
#endif
|
||||
|
||||
static UChar*
|
||||
utf16be_left_adjust_char_head(const UChar* start, const UChar* s,
|
||||
struct OnigEncodingTypeST* enc ARG_UNUSED)
|
||||
{
|
||||
if (s <= start) return (UChar* )s;
|
||||
|
||||
if ((s - start) % 2 == 1) {
|
||||
s--;
|
||||
}
|
||||
|
||||
if (UTF16_IS_SURROGATE_SECOND(*s) && s > start + 1)
|
||||
s -= 2;
|
||||
|
||||
return (UChar* )s;
|
||||
}
|
||||
|
||||
static int
|
||||
utf16be_get_case_fold_codes_by_str(OnigCaseFoldType flag,
|
||||
const OnigUChar* p, const OnigUChar* end,
|
||||
OnigCaseFoldCodeItem items[],
|
||||
struct OnigEncodingTypeST* enc ARG_UNUSED)
|
||||
{
|
||||
return onigenc_unicode_get_case_fold_codes_by_str(&OnigEncodingName(UTF_16BE),
|
||||
flag, p, end, items);
|
||||
}
|
||||
|
||||
OnigEncodingDefine(utf_16be, UTF_16BE) = {
|
||||
utf16be_mbc_enc_len,
|
||||
"UTF-16BE", /* name */
|
||||
4, /* max byte length */
|
||||
2, /* min byte length */
|
||||
utf16be_is_mbc_newline,
|
||||
utf16be_mbc_to_code,
|
||||
utf16be_code_to_mbclen,
|
||||
utf16be_code_to_mbc,
|
||||
utf16be_mbc_case_fold,
|
||||
onigenc_unicode_apply_all_case_fold,
|
||||
utf16be_get_case_fold_codes_by_str,
|
||||
onigenc_unicode_property_name_to_ctype,
|
||||
onigenc_unicode_is_code_ctype,
|
||||
onigenc_utf16_32_get_ctype_code_range,
|
||||
utf16be_left_adjust_char_head,
|
||||
onigenc_always_false_is_allowed_reverse_match
|
||||
};
|
||||
240
enc/utf_16le.c
Normal file
240
enc/utf_16le.c
Normal file
|
|
@ -0,0 +1,240 @@
|
|||
/**********************************************************************
|
||||
utf_16le.c - Oniguruma (regular expression library)
|
||||
**********************************************************************/
|
||||
/*-
|
||||
* Copyright (c) 2002-2007 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"
|
||||
|
||||
OnigEncodingDeclare(UTF_16LE);
|
||||
|
||||
#define UTF16_IS_SURROGATE_FIRST(c) (c >= 0xd8 && c <= 0xdb)
|
||||
#define UTF16_IS_SURROGATE_SECOND(c) (c >= 0xdc && c <= 0xdf)
|
||||
|
||||
static const int EncLen_UTF16[] = {
|
||||
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
|
||||
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
|
||||
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
|
||||
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
|
||||
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
|
||||
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
|
||||
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
|
||||
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
|
||||
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
|
||||
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
|
||||
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
|
||||
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
|
||||
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
|
||||
2, 2, 2, 2, 2, 2, 2, 2, 4, 4, 4, 4, 2, 2, 2, 2,
|
||||
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
|
||||
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2
|
||||
};
|
||||
|
||||
static int
|
||||
utf16le_mbc_enc_len(const UChar* p, const OnigUChar* e ARG_UNUSED,
|
||||
struct OnigEncodingTypeST* enc ARG_UNUSED)
|
||||
{
|
||||
return EncLen_UTF16[*(p+1)];
|
||||
}
|
||||
|
||||
static int
|
||||
utf16le_is_mbc_newline(const UChar* p, const UChar* end,
|
||||
struct OnigEncodingTypeST* enc ARG_UNUSED)
|
||||
{
|
||||
if (p + 1 < end) {
|
||||
if (*p == 0x0a && *(p+1) == 0x00)
|
||||
return 1;
|
||||
#ifdef USE_UNICODE_ALL_LINE_TERMINATORS
|
||||
if ((
|
||||
#ifndef USE_CRNL_AS_LINE_TERMINATOR
|
||||
*p == 0x0d ||
|
||||
#endif
|
||||
*p == 0x85) && *(p+1) == 0x00)
|
||||
return 1;
|
||||
if (*(p+1) == 0x20 && (*p == 0x29 || *p == 0x28))
|
||||
return 1;
|
||||
#endif
|
||||
}
|
||||
return 0;
|
||||
}
|
||||
|
||||
static OnigCodePoint
|
||||
utf16le_mbc_to_code(const UChar* p, const UChar* end ARG_UNUSED,
|
||||
struct OnigEncodingTypeST* enc ARG_UNUSED)
|
||||
{
|
||||
OnigCodePoint code;
|
||||
UChar c0 = *p;
|
||||
UChar c1 = *(p+1);
|
||||
|
||||
if (UTF16_IS_SURROGATE_FIRST(c1)) {
|
||||
code = ((((c1 - 0xd8) << 2) + ((c0 & 0xc0) >> 6) + 1) << 16)
|
||||
+ ((((c0 & 0x3f) << 2) + (p[3] - 0xdc)) << 8)
|
||||
+ p[2];
|
||||
}
|
||||
else {
|
||||
code = c1 * 256 + p[0];
|
||||
}
|
||||
return code;
|
||||
}
|
||||
|
||||
static int
|
||||
utf16le_code_to_mbclen(OnigCodePoint code,
|
||||
struct OnigEncodingTypeST* enc ARG_UNUSED)
|
||||
{
|
||||
return (code > 0xffff ? 4 : 2);
|
||||
}
|
||||
|
||||
static int
|
||||
utf16le_code_to_mbc(OnigCodePoint code, UChar *buf,
|
||||
struct OnigEncodingTypeST* enc ARG_UNUSED)
|
||||
{
|
||||
UChar* p = buf;
|
||||
|
||||
if (code > 0xffff) {
|
||||
unsigned int plane, high;
|
||||
|
||||
plane = code >> 16;
|
||||
high = (code & 0xff00) >> 8;
|
||||
|
||||
*p++ = ((plane & 0x03) << 6) + (high >> 2);
|
||||
*p++ = (plane >> 2) + 0xd8;
|
||||
*p++ = (UChar )(code & 0xff);
|
||||
*p = (high & 0x02) + 0xdc;
|
||||
return 4;
|
||||
}
|
||||
else {
|
||||
*p++ = (UChar )(code & 0xff);
|
||||
*p++ = (UChar )((code & 0xff00) >> 8);
|
||||
return 2;
|
||||
}
|
||||
}
|
||||
|
||||
static int
|
||||
utf16le_mbc_case_fold(OnigCaseFoldType flag,
|
||||
const UChar** pp, const UChar* end, UChar* fold,
|
||||
struct OnigEncodingTypeST* enc ARG_UNUSED)
|
||||
{
|
||||
const UChar* p = *pp;
|
||||
|
||||
if (ONIGENC_IS_ASCII_CODE(*p) && *(p+1) == 0) {
|
||||
#ifdef USE_UNICODE_CASE_FOLD_TURKISH_AZERI
|
||||
if ((flag & ONIGENC_CASE_FOLD_TURKISH_AZERI) != 0) {
|
||||
if (*p == 0x49) {
|
||||
*fold++ = 0x31;
|
||||
*fold = 0x01;
|
||||
(*pp) += 2;
|
||||
return 2;
|
||||
}
|
||||
}
|
||||
#endif
|
||||
|
||||
*fold++ = ONIGENC_ASCII_CODE_TO_LOWER_CASE(*p);
|
||||
*fold = 0;
|
||||
*pp += 2;
|
||||
return 2;
|
||||
}
|
||||
else
|
||||
return onigenc_unicode_mbc_case_fold(&OnigEncodingName(UTF_16LE), flag, pp,
|
||||
end, fold);
|
||||
}
|
||||
|
||||
#if 0
|
||||
static int
|
||||
utf16le_is_mbc_ambiguous(OnigCaseFoldType flag, const UChar** pp,
|
||||
const UChar* end)
|
||||
{
|
||||
const UChar* p = *pp;
|
||||
|
||||
(*pp) += EncLen_UTF16[*(p+1)];
|
||||
|
||||
if (*(p+1) == 0) {
|
||||
int c, v;
|
||||
|
||||
if (*p == 0xdf && (flag & INTERNAL_ONIGENC_CASE_FOLD_MULTI_CHAR) != 0) {
|
||||
return TRUE;
|
||||
}
|
||||
|
||||
c = *p;
|
||||
v = ONIGENC_IS_UNICODE_ISO_8859_1_BIT_CTYPE(c,
|
||||
(BIT_CTYPE_UPPER | BIT_CTYPE_LOWER));
|
||||
if ((v | BIT_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;
|
||||
}
|
||||
#endif
|
||||
|
||||
static UChar*
|
||||
utf16le_left_adjust_char_head(const UChar* start, const UChar* s,
|
||||
struct OnigEncodingTypeST* enc ARG_UNUSED)
|
||||
{
|
||||
if (s <= start) return (UChar* )s;
|
||||
|
||||
if ((s - start) % 2 == 1) {
|
||||
s--;
|
||||
}
|
||||
|
||||
if (UTF16_IS_SURROGATE_SECOND(*(s+1)) && s > start + 1)
|
||||
s -= 2;
|
||||
|
||||
return (UChar* )s;
|
||||
}
|
||||
|
||||
static int
|
||||
utf16le_get_case_fold_codes_by_str(OnigCaseFoldType flag,
|
||||
const OnigUChar* p, const OnigUChar* end,
|
||||
OnigCaseFoldCodeItem items[],
|
||||
struct OnigEncodingTypeST* enc ARG_UNUSED)
|
||||
{
|
||||
return onigenc_unicode_get_case_fold_codes_by_str(&OnigEncodingName(UTF_16LE),
|
||||
flag, p, end, items);
|
||||
}
|
||||
|
||||
OnigEncodingDefine(utf_16le, UTF_16LE) = {
|
||||
utf16le_mbc_enc_len,
|
||||
"UTF-16LE", /* name */
|
||||
4, /* max byte length */
|
||||
2, /* min byte length */
|
||||
utf16le_is_mbc_newline,
|
||||
utf16le_mbc_to_code,
|
||||
utf16le_code_to_mbclen,
|
||||
utf16le_code_to_mbc,
|
||||
utf16le_mbc_case_fold,
|
||||
onigenc_unicode_apply_all_case_fold,
|
||||
utf16le_get_case_fold_codes_by_str,
|
||||
onigenc_unicode_property_name_to_ctype,
|
||||
onigenc_unicode_is_code_ctype,
|
||||
onigenc_utf16_32_get_ctype_code_range,
|
||||
utf16le_left_adjust_char_head,
|
||||
onigenc_always_false_is_allowed_reverse_match
|
||||
};
|
||||
195
enc/utf_32be.c
Normal file
195
enc/utf_32be.c
Normal file
|
|
@ -0,0 +1,195 @@
|
|||
/**********************************************************************
|
||||
utf_32be.c - Oniguruma (regular expression library)
|
||||
**********************************************************************/
|
||||
/*-
|
||||
* Copyright (c) 2002-2007 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"
|
||||
|
||||
OnigEncodingDeclare(UTF_32BE);
|
||||
|
||||
static int
|
||||
utf32be_mbc_enc_len(const UChar* p ARG_UNUSED, const OnigUChar* e ARG_UNUSED,
|
||||
struct OnigEncodingTypeST* enc ARG_UNUSED)
|
||||
{
|
||||
return 4;
|
||||
}
|
||||
|
||||
static int
|
||||
utf32be_is_mbc_newline(const UChar* p, const UChar* end,
|
||||
struct OnigEncodingTypeST* enc ARG_UNUSED)
|
||||
{
|
||||
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 ((
|
||||
#ifndef USE_CRNL_AS_LINE_TERMINATOR
|
||||
*(p+3) == 0x0d ||
|
||||
#endif
|
||||
*(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 ARG_UNUSED,
|
||||
struct OnigEncodingTypeST* enc ARG_UNUSED)
|
||||
{
|
||||
return (OnigCodePoint )(((p[0] * 256 + p[1]) * 256 + p[2]) * 256 + p[3]);
|
||||
}
|
||||
|
||||
static int
|
||||
utf32be_code_to_mbclen(OnigCodePoint code ARG_UNUSED,
|
||||
struct OnigEncodingTypeST* enc ARG_UNUSED)
|
||||
{
|
||||
return 4;
|
||||
}
|
||||
|
||||
static int
|
||||
utf32be_code_to_mbc(OnigCodePoint code, UChar *buf,
|
||||
struct OnigEncodingTypeST* enc ARG_UNUSED)
|
||||
{
|
||||
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_case_fold(OnigCaseFoldType flag,
|
||||
const UChar** pp, const UChar* end, UChar* fold,
|
||||
struct OnigEncodingTypeST* enc ARG_UNUSED)
|
||||
{
|
||||
const UChar* p = *pp;
|
||||
|
||||
if (ONIGENC_IS_ASCII_CODE(*(p+3)) && *(p+2) == 0 && *(p+1) == 0 && *p == 0) {
|
||||
*fold++ = 0;
|
||||
*fold++ = 0;
|
||||
|
||||
#ifdef USE_UNICODE_CASE_FOLD_TURKISH_AZERI
|
||||
if ((flag & ONIGENC_CASE_FOLD_TURKISH_AZERI) != 0) {
|
||||
if (*(p+3) == 0x49) {
|
||||
*fold++ = 0x01;
|
||||
*fold = 0x31;
|
||||
(*pp) += 4;
|
||||
return 4;
|
||||
}
|
||||
}
|
||||
#endif
|
||||
|
||||
*fold++ = 0;
|
||||
*fold = ONIGENC_ASCII_CODE_TO_LOWER_CASE(*(p+3));
|
||||
*pp += 4;
|
||||
return 4;
|
||||
}
|
||||
else
|
||||
return onigenc_unicode_mbc_case_fold(&OnigEncodingName(UTF_32BE), flag, pp,
|
||||
end, fold);
|
||||
}
|
||||
|
||||
#if 0
|
||||
static int
|
||||
utf32be_is_mbc_ambiguous(OnigCaseFoldType 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 (*p == 0xdf && (flag & INTERNAL_ONIGENC_CASE_FOLD_MULTI_CHAR) != 0) {
|
||||
return TRUE;
|
||||
}
|
||||
|
||||
c = *p;
|
||||
v = ONIGENC_IS_UNICODE_ISO_8859_1_BIT_CTYPE(c,
|
||||
(BIT_CTYPE_UPPER | BIT_CTYPE_LOWER));
|
||||
if ((v | BIT_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;
|
||||
}
|
||||
#endif
|
||||
|
||||
static UChar*
|
||||
utf32be_left_adjust_char_head(const UChar* start, const UChar* s,
|
||||
struct OnigEncodingTypeST* enc ARG_UNUSED)
|
||||
{
|
||||
int rem;
|
||||
|
||||
if (s <= start) return (UChar* )s;
|
||||
|
||||
rem = (s - start) % 4;
|
||||
return (UChar* )(s - rem);
|
||||
}
|
||||
|
||||
static int
|
||||
utf32be_get_case_fold_codes_by_str(OnigCaseFoldType flag,
|
||||
const OnigUChar* p, const OnigUChar* end,
|
||||
OnigCaseFoldCodeItem items[],
|
||||
struct OnigEncodingTypeST* enc ARG_UNUSED)
|
||||
{
|
||||
return onigenc_unicode_get_case_fold_codes_by_str(&OnigEncodingName(UTF_32BE),
|
||||
flag, p, end, items);
|
||||
}
|
||||
|
||||
OnigEncodingDefine(utf_32be, UTF_32BE) = {
|
||||
utf32be_mbc_enc_len,
|
||||
"UTF-32BE", /* name */
|
||||
4, /* max byte length */
|
||||
4, /* min byte length */
|
||||
utf32be_is_mbc_newline,
|
||||
utf32be_mbc_to_code,
|
||||
utf32be_code_to_mbclen,
|
||||
utf32be_code_to_mbc,
|
||||
utf32be_mbc_case_fold,
|
||||
onigenc_unicode_apply_all_case_fold,
|
||||
utf32be_get_case_fold_codes_by_str,
|
||||
onigenc_unicode_property_name_to_ctype,
|
||||
onigenc_unicode_is_code_ctype,
|
||||
onigenc_utf16_32_get_ctype_code_range,
|
||||
utf32be_left_adjust_char_head,
|
||||
onigenc_always_false_is_allowed_reverse_match
|
||||
};
|
||||
195
enc/utf_32le.c
Normal file
195
enc/utf_32le.c
Normal file
|
|
@ -0,0 +1,195 @@
|
|||
/**********************************************************************
|
||||
utf_32le.c - Oniguruma (regular expression library)
|
||||
**********************************************************************/
|
||||
/*-
|
||||
* Copyright (c) 2002-2007 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"
|
||||
|
||||
OnigEncodingDeclare(UTF_32LE);
|
||||
|
||||
static int
|
||||
utf32le_mbc_enc_len(const UChar* p ARG_UNUSED, const OnigUChar* e ARG_UNUSED,
|
||||
struct OnigEncodingTypeST* enc ARG_UNUSED)
|
||||
{
|
||||
return 4;
|
||||
}
|
||||
|
||||
static int
|
||||
utf32le_is_mbc_newline(const UChar* p, const UChar* end,
|
||||
struct OnigEncodingTypeST* enc ARG_UNUSED)
|
||||
{
|
||||
if (p + 3 < end) {
|
||||
if (*p == 0x0a && *(p+1) == 0 && *(p+2) == 0 && *(p+3) == 0)
|
||||
return 1;
|
||||
#ifdef USE_UNICODE_ALL_LINE_TERMINATORS
|
||||
if ((
|
||||
#ifndef USE_CRNL_AS_LINE_TERMINATOR
|
||||
*p == 0x0d ||
|
||||
#endif
|
||||
*p == 0x85)
|
||||
&& *(p+1) == 0x00 && (p+2) == 0x00 && *(p+3) == 0x00)
|
||||
return 1;
|
||||
if (*(p+1) == 0x20 && (*p == 0x29 || *p == 0x28)
|
||||
&& *(p+2) == 0x00 && *(p+3) == 0x00)
|
||||
return 1;
|
||||
#endif
|
||||
}
|
||||
return 0;
|
||||
}
|
||||
|
||||
static OnigCodePoint
|
||||
utf32le_mbc_to_code(const UChar* p, const UChar* end ARG_UNUSED,
|
||||
struct OnigEncodingTypeST* enc ARG_UNUSED)
|
||||
{
|
||||
return (OnigCodePoint )(((p[3] * 256 + p[2]) * 256 + p[1]) * 256 + p[0]);
|
||||
}
|
||||
|
||||
static int
|
||||
utf32le_code_to_mbclen(OnigCodePoint code ARG_UNUSED,
|
||||
struct OnigEncodingTypeST* enc ARG_UNUSED)
|
||||
{
|
||||
return 4;
|
||||
}
|
||||
|
||||
static int
|
||||
utf32le_code_to_mbc(OnigCodePoint code, UChar *buf,
|
||||
struct OnigEncodingTypeST* enc ARG_UNUSED)
|
||||
{
|
||||
UChar* p = buf;
|
||||
|
||||
*p++ = (UChar ) (code & 0xff);
|
||||
*p++ = (UChar )((code & 0xff00) >> 8);
|
||||
*p++ = (UChar )((code & 0xff0000) >>16);
|
||||
*p++ = (UChar )((code & 0xff000000) >>24);
|
||||
return 4;
|
||||
}
|
||||
|
||||
static int
|
||||
utf32le_mbc_case_fold(OnigCaseFoldType flag,
|
||||
const UChar** pp, const UChar* end, UChar* fold,
|
||||
struct OnigEncodingTypeST* enc ARG_UNUSED)
|
||||
{
|
||||
const UChar* p = *pp;
|
||||
|
||||
if (ONIGENC_IS_ASCII_CODE(*p) && *(p+1) == 0 && *(p+2) == 0 && *(p+3) == 0) {
|
||||
#ifdef USE_UNICODE_CASE_FOLD_TURKISH_AZERI
|
||||
if ((flag & ONIGENC_CASE_FOLD_TURKISH_AZERI) != 0) {
|
||||
if (*p == 0x49) {
|
||||
*fold++ = 0x31;
|
||||
*fold++ = 0x01;
|
||||
}
|
||||
}
|
||||
else {
|
||||
#endif
|
||||
*fold++ = ONIGENC_ASCII_CODE_TO_LOWER_CASE(*p);
|
||||
*fold++ = 0;
|
||||
#ifdef USE_UNICODE_CASE_FOLD_TURKISH_AZERI
|
||||
}
|
||||
#endif
|
||||
|
||||
*fold++ = 0;
|
||||
*fold = 0;
|
||||
*pp += 4;
|
||||
return 4;
|
||||
}
|
||||
else
|
||||
return onigenc_unicode_mbc_case_fold(&OnigEncodingName(UTF_32LE), flag, pp,
|
||||
end, fold);
|
||||
}
|
||||
|
||||
#if 0
|
||||
static int
|
||||
utf32le_is_mbc_ambiguous(OnigCaseFoldType flag, const UChar** pp, const UChar* end)
|
||||
{
|
||||
const UChar* p = *pp;
|
||||
|
||||
(*pp) += 4;
|
||||
|
||||
if (*(p+1) == 0 && *(p+2) == 0 && *(p+3) == 0) {
|
||||
int c, v;
|
||||
|
||||
if (*p == 0xdf && (flag & INTERNAL_ONIGENC_CASE_FOLD_MULTI_CHAR) != 0) {
|
||||
return TRUE;
|
||||
}
|
||||
|
||||
c = *p;
|
||||
v = ONIGENC_IS_UNICODE_ISO_8859_1_BIT_CTYPE(c,
|
||||
(BIT_CTYPE_UPPER | BIT_CTYPE_LOWER));
|
||||
if ((v | BIT_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;
|
||||
}
|
||||
#endif
|
||||
|
||||
static UChar*
|
||||
utf32le_left_adjust_char_head(const UChar* start, const UChar* s,
|
||||
struct OnigEncodingTypeST* enc ARG_UNUSED)
|
||||
{
|
||||
int rem;
|
||||
|
||||
if (s <= start) return (UChar* )s;
|
||||
|
||||
rem = (s - start) % 4;
|
||||
return (UChar* )(s - rem);
|
||||
}
|
||||
|
||||
static int
|
||||
utf32le_get_case_fold_codes_by_str(OnigCaseFoldType flag,
|
||||
const OnigUChar* p, const OnigUChar* end,
|
||||
OnigCaseFoldCodeItem items[],
|
||||
struct OnigEncodingTypeST* enc ARG_UNUSED)
|
||||
{
|
||||
return onigenc_unicode_get_case_fold_codes_by_str(&OnigEncodingName(UTF_32LE),
|
||||
flag, p, end, items);
|
||||
}
|
||||
|
||||
OnigEncodingDefine(utf_32le, UTF_32LE) = {
|
||||
utf32le_mbc_enc_len,
|
||||
"UTF-32LE", /* name */
|
||||
4, /* max byte length */
|
||||
4, /* min byte length */
|
||||
utf32le_is_mbc_newline,
|
||||
utf32le_mbc_to_code,
|
||||
utf32le_code_to_mbclen,
|
||||
utf32le_code_to_mbc,
|
||||
utf32le_mbc_case_fold,
|
||||
onigenc_unicode_apply_all_case_fold,
|
||||
utf32le_get_case_fold_codes_by_str,
|
||||
onigenc_unicode_property_name_to_ctype,
|
||||
onigenc_unicode_is_code_ctype,
|
||||
onigenc_utf16_32_get_ctype_code_range,
|
||||
utf32le_left_adjust_char_head,
|
||||
onigenc_always_false_is_allowed_reverse_match
|
||||
};
|
||||
Loading…
Reference in a new issue