• Main Page
  • Modules
  • Data Structures
  • Files
  • File List
  • Globals

enc/utf_32be.c

Go to the documentation of this file.
00001 /**********************************************************************
00002   utf_32be.c -  Oniguruma (regular expression library)
00003 **********************************************************************/
00004 /*-
00005  * Copyright (c) 2002-2007  K.Kosako  <sndgk393 AT ybb DOT ne DOT jp>
00006  * All rights reserved.
00007  *
00008  * Redistribution and use in source and binary forms, with or without
00009  * modification, are permitted provided that the following conditions
00010  * are met:
00011  * 1. Redistributions of source code must retain the above copyright
00012  *    notice, this list of conditions and the following disclaimer.
00013  * 2. Redistributions in binary form must reproduce the above copyright
00014  *    notice, this list of conditions and the following disclaimer in the
00015  *    documentation and/or other materials provided with the distribution.
00016  *
00017  * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
00018  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
00019  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
00020  * ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
00021  * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
00022  * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
00023  * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
00024  * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
00025  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
00026  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
00027  * SUCH DAMAGE.
00028  */
00029 
00030 #include "regenc.h"
00031 
00032 static int
00033 utf32be_mbc_enc_len(const UChar* p ARG_UNUSED, const OnigUChar* e ARG_UNUSED,
00034                     OnigEncoding enc ARG_UNUSED)
00035 {
00036   return 4;
00037 }
00038 
00039 static int
00040 utf32be_is_mbc_newline(const UChar* p, const UChar* end,
00041                        OnigEncoding enc ARG_UNUSED)
00042 {
00043   if (p + 3 < end) {
00044     if (*(p+3) == 0x0a && *(p+2) == 0 && *(p+1) == 0 && *p == 0)
00045       return 1;
00046 #ifdef USE_UNICODE_ALL_LINE_TERMINATORS
00047     if ((
00048 #ifndef USE_CRNL_AS_LINE_TERMINATOR
00049          *(p+3) == 0x0d ||
00050 #endif
00051          *(p+3) == 0x85)
00052         && *(p+2) == 0 && *(p+1) == 0 && *p == 0x00)
00053       return 1;
00054     if (*(p+2) == 0x20 && (*(p+3) == 0x29 || *(p+3) == 0x28)
00055         && *(p+1) == 0 && *p == 0)
00056       return 1;
00057 #endif
00058   }
00059   return 0;
00060 }
00061 
00062 static OnigCodePoint
00063 utf32be_mbc_to_code(const UChar* p, const UChar* end ARG_UNUSED,
00064                     OnigEncoding enc ARG_UNUSED)
00065 {
00066   return (OnigCodePoint )(((p[0] * 256 + p[1]) * 256 + p[2]) * 256 + p[3]);
00067 }
00068 
00069 static int
00070 utf32be_code_to_mbclen(OnigCodePoint code ARG_UNUSED,
00071                        OnigEncoding enc ARG_UNUSED)
00072 {
00073   return 4;
00074 }
00075 
00076 static int
00077 utf32be_code_to_mbc(OnigCodePoint code, UChar *buf,
00078                     OnigEncoding enc ARG_UNUSED)
00079 {
00080   UChar* p = buf;
00081 
00082   *p++ = (UChar )((code & 0xff000000) >>24);
00083   *p++ = (UChar )((code & 0xff0000)   >>16);
00084   *p++ = (UChar )((code & 0xff00)     >> 8);
00085   *p++ = (UChar ) (code & 0xff);
00086   return 4;
00087 }
00088 
00089 static int
00090 utf32be_mbc_case_fold(OnigCaseFoldType flag,
00091                       const UChar** pp, const UChar* end, UChar* fold,
00092                       OnigEncoding enc)
00093 {
00094   const UChar* p = *pp;
00095 
00096   if (ONIGENC_IS_ASCII_CODE(*(p+3)) && *(p+2) == 0 && *(p+1) == 0 && *p == 0) {
00097     *fold++ = 0;
00098     *fold++ = 0;
00099 
00100 #ifdef USE_UNICODE_CASE_FOLD_TURKISH_AZERI
00101     if ((flag & ONIGENC_CASE_FOLD_TURKISH_AZERI) != 0) {
00102       if (*(p+3) == 0x49) {
00103         *fold++ = 0x01;
00104         *fold   = 0x31;
00105         (*pp) += 4;
00106         return 4;
00107       }
00108     }
00109 #endif
00110 
00111     *fold++ = 0;
00112     *fold   = ONIGENC_ASCII_CODE_TO_LOWER_CASE(*(p+3));
00113     *pp += 4;
00114     return 4;
00115   }
00116   else
00117     return onigenc_unicode_mbc_case_fold(enc, flag, pp,
00118                                          end, fold);
00119 }
00120 
00121 #if 0
00122 static int
00123 utf32be_is_mbc_ambiguous(OnigCaseFoldType flag, const UChar** pp, const UChar* end)
00124 {
00125   const UChar* p = *pp;
00126 
00127   (*pp) += 4;
00128 
00129   if (*(p+2) == 0 && *(p+1) == 0 && *p == 0) {
00130     int c, v;
00131 
00132     p += 3;
00133     if (*p == 0xdf && (flag & INTERNAL_ONIGENC_CASE_FOLD_MULTI_CHAR) != 0) {
00134       return TRUE;
00135     }
00136 
00137     c = *p;
00138     v = ONIGENC_IS_UNICODE_ISO_8859_1_BIT_CTYPE(c,
00139                        (BIT_CTYPE_UPPER | BIT_CTYPE_LOWER));
00140     if ((v | BIT_CTYPE_LOWER) != 0) {
00141       /* 0xaa, 0xb5, 0xba are lower case letter, but can't convert. */
00142       if (c >= 0xaa && c <= 0xba)
00143         return FALSE;
00144       else
00145         return TRUE;
00146     }
00147     return (v != 0 ? TRUE : FALSE);
00148   }
00149 
00150   return FALSE;
00151 }
00152 #endif
00153 
00154 static UChar*
00155 utf32be_left_adjust_char_head(const UChar* start, const UChar* s, const UChar* end,
00156                               OnigEncoding enc ARG_UNUSED)
00157 {
00158   int rem;
00159 
00160   if (s <= start) return (UChar* )s;
00161 
00162   rem = (s - start) % 4;
00163   return (UChar* )(s - rem);
00164 }
00165 
00166 static int
00167 utf32be_get_case_fold_codes_by_str(OnigCaseFoldType flag,
00168                                    const OnigUChar* p, const OnigUChar* end,
00169                                    OnigCaseFoldCodeItem items[],
00170                                    OnigEncoding enc)
00171 {
00172   return onigenc_unicode_get_case_fold_codes_by_str(enc,
00173                                                     flag, p, end, items);
00174 }
00175 
00176 OnigEncodingDefine(utf_32be, UTF_32BE) = {
00177   utf32be_mbc_enc_len,
00178   "UTF-32BE",   /* name */
00179   4,            /* max byte length */
00180   4,            /* min byte length */
00181   utf32be_is_mbc_newline,
00182   utf32be_mbc_to_code,
00183   utf32be_code_to_mbclen,
00184   utf32be_code_to_mbc,
00185   utf32be_mbc_case_fold,
00186   onigenc_unicode_apply_all_case_fold,
00187   utf32be_get_case_fold_codes_by_str,
00188   onigenc_unicode_property_name_to_ctype,
00189   onigenc_unicode_is_code_ctype,
00190   onigenc_utf16_32_get_ctype_code_range,
00191   utf32be_left_adjust_char_head,
00192   onigenc_always_false_is_allowed_reverse_match
00193 };
00194 ENC_ALIAS("UCS-4BE", "UTF-32BE")
00195 
00196 

Generated on Thu Sep 8 2011 03:50:27 for Ruby by  doxygen 1.7.1