enc/utf_16be.c

   1 /**********************************************************************
   2   utf_16be.c -  Oniguruma (regular expression library)
   3 **********************************************************************/
   4 /*-
   5  * Copyright (c) 2002-2008  K.Kosako  <sndgk393 AT ybb DOT ne DOT jp>
   6  * All rights reserved.
   7  *
   8  * Redistribution and use in source and binary forms, with or without
   9  * modification, are permitted provided that the following conditions
  10  * are met:
  11  * 1. Redistributions of source code must retain the above copyright
  12  *    notice, this list of conditions and the following disclaimer.
  13  * 2. Redistributions in binary form must reproduce the above copyright
  14  *    notice, this list of conditions and the following disclaimer in the
  15  *    documentation and/or other materials provided with the distribution.
  16  *
  17  * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
  18  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
  19  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
  20  * ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
  21  * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
  22  * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
  23  * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
  24  * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
  25  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
  26  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
  27  * SUCH DAMAGE.
  28  */
  29
  30 #include "regenc.h"
  31 #include "iso_8859.h"
  32
  33 #if 0
  34 static const int EncLen_UTF16[] = {
  35   2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
  36   2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
  37   2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
  38   2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
  39   2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
  40   2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
  41   2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
  42   2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
  43   2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
  44   2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
  45   2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
  46   2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
  47   2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
  48   2, 2, 2, 2, 2, 2, 2, 2, 4, 4, 4, 4, 2, 2, 2, 2,
  49   2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
  50   2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2
  51 };
  52 #endif
  53
  54 static int
  55 utf16be_mbc_enc_len(const UChar* p, const OnigUChar* e ARG_UNUSED,
  56                     OnigEncoding enc ARG_UNUSED)
  57 {
  58   int byte = p[0];
  59   if (!UTF16_IS_SURROGATE(byte)) {
  60     if (2 <= e-p)
  61       return ONIGENC_CONSTRUCT_MBCLEN_CHARFOUND(2);
  62     else
  63       return ONIGENC_CONSTRUCT_MBCLEN_NEEDMORE(1);
  64   }
  65   if (UTF16_IS_SURROGATE_FIRST(byte)) {
  66     switch (e-p) {
  67       case 1: return ONIGENC_CONSTRUCT_MBCLEN_NEEDMORE(3);
  68       case 2: return ONIGENC_CONSTRUCT_MBCLEN_NEEDMORE(2);
  69       case 3:
  70         if (UTF16_IS_SURROGATE_SECOND(p[2]))
  71           return ONIGENC_CONSTRUCT_MBCLEN_NEEDMORE(1);
  72         break;
  73       default:
  74         if (UTF16_IS_SURROGATE_SECOND(p[2]))
  75           return ONIGENC_CONSTRUCT_MBCLEN_CHARFOUND(4);
  76         break;
  77     }
  78   }
  79   return ONIGENC_CONSTRUCT_MBCLEN_INVALID();
  80 }
  81
  82 static int
  83 utf16be_is_mbc_newline(const UChar* p, const UChar* end,
  84                        OnigEncoding enc)
  85 {
  86   if (p + 1 < end) {
  87     if (*(p+1) == 0x0a && *p == 0x00)
  88       return 1;
  89 #ifdef USE_UNICODE_ALL_LINE_TERMINATORS
  90     if ((*(p+1) == 0x0b || *(p+1) == 0x0c || *(p+1) == 0x0d || *(p+1) == 0x85)
  91         && *p == 0x00)
  92       return 1;
  93     if (*p == 0x20 && (*(p+1) == 0x29 || *(p+1) == 0x28))
  94       return 1;
  95 #endif
  96   }
  97   return 0;
  98 }
  99
 100 static OnigCodePoint
 101 utf16be_mbc_to_code(const UChar* p, const UChar* end ARG_UNUSED,
 102                     OnigEncoding enc)
 103 {
 104   OnigCodePoint code;
 105
 106   if (UTF16_IS_SURROGATE_FIRST(*p)) {
 107     code = ((((p[0] << 8) + p[1]) & 0x03ff) << 10)
 108          + (((p[2] << 8) + p[3]) & 0x03ff) + 0x10000;
 109   }
 110   else {
 111     code = p[0] * 256 + p[1];
 112   }
 113   return code;
 114 }
 115
 116 static int
 117 utf16be_code_to_mbclen(OnigCodePoint code,
 118                        OnigEncoding enc)
 119 {
 120   return (code > 0xffff ? 4 : 2);
 121 }
 122
 123 static int
 124 utf16be_code_to_mbc(OnigCodePoint code, UChar *buf,
 125                     OnigEncoding enc)
 126 {
 127   UChar* p = buf;
 128
 129   if (code > 0xffff) {
 130     unsigned int high = (code >> 10) + 0xD7C0;
 131     unsigned int low = (code & 0x3FF) + 0xDC00;
 132     *p++ = (high >> 8) & 0xFF;
 133     *p++ = high & 0xFF;
 134     *p++ = (low >> 8) & 0xFF;
 135     *p++ = low & 0xFF;
 136     return 4;
 137   }
 138   else {
 139     *p++ = (UChar )((code & 0xff00) >> 8);
 140     *p++ = (UChar )(code & 0xff);
 141     return 2;
 142   }
 143 }
 144
 145 static int
 146 utf16be_mbc_case_fold(OnigCaseFoldType flag,
 147                       const UChar** pp, const UChar* end, UChar* fold,
 148                       OnigEncoding enc)
 149 {
 150   const UChar* p = *pp;
 151
 152   if (ONIGENC_IS_ASCII_CODE(*(p+1)) && *p == 0) {
 153     p++;
 154 #ifdef USE_UNICODE_CASE_FOLD_TURKISH_AZERI
 155     if ((flag & ONIGENC_CASE_FOLD_TURKISH_AZERI) != 0) {
 156       if (*p == 0x49) {
 157         *fold++ = 0x01;
 158         *fold   = 0x31;
 159         (*pp) += 2;
 160         return 2;
 161       }
 162     }
 163 #endif
 164
 165     *fold++ = 0;
 166     *fold   = ONIGENC_ASCII_CODE_TO_LOWER_CASE(*p);
 167     *pp += 2;
 168     return 2;
 169   }
 170   else
 171     return onigenc_unicode_mbc_case_fold(enc, flag,
 172                                          pp, end, fold);
 173 }
 174
 175 #if 0
 176 static int
 177 utf16be_is_mbc_ambiguous(OnigCaseFoldType flag, const UChar** pp, const UChar* end)
 178 {
 179   const UChar* p = *pp;
 180
 181   (*pp) += EncLen_UTF16[*p];
 182
 183   if (*p == 0) {
 184     int c, v;
 185
 186     p++;
 187     if (*p == SHARP_s && (flag & INTERNAL_ONIGENC_CASE_FOLD_MULTI_CHAR) != 0) {
 188       return TRUE;
 189     }
 190
 191     c = *p;
 192     v = ONIGENC_IS_UNICODE_ISO_8859_1_BIT_CTYPE(c,
 193                 (BIT_CTYPE_UPPER | BIT_CTYPE_LOWER));
 194
 195     if ((v | BIT_CTYPE_LOWER) != 0) {
 196       /* 0xaa, 0xb5, 0xba are lower case letter, but can't convert. */
 197       if (c >= 0xaa && c <= 0xba)
 198         return FALSE;
 199       else
 200         return TRUE;
 201     }
 202     return (v != 0 ? TRUE : FALSE);
 203   }
 204
 205   return FALSE;
 206 }
 207 #endif
 208
 209 static UChar*
 210 utf16be_left_adjust_char_head(const UChar* start, const UChar* s, const UChar* end,
 211                               OnigEncoding enc ARG_UNUSED)
 212 {
 213   if (s <= start) return (UChar* )s;
 214
 215   if ((s - start) % 2 == 1) {
 216     s--;
 217   }
 218
 219   if (UTF16_IS_SURROGATE_SECOND(*s) && s > start + 1)
 220     s -= 2;
 221
 222   return (UChar* )s;
 223 }
 224
 225 static int
 226 utf16be_get_case_fold_codes_by_str(OnigCaseFoldType flag,
 227                                    const OnigUChar* p, const OnigUChar* end,
 228                                    OnigCaseFoldCodeItem items[],
 229                                    OnigEncoding enc)
 230 {
 231   return onigenc_unicode_get_case_fold_codes_by_str(enc,
 232                                                     flag, p, end, items);
 233 }
 234
 235 OnigEncodingDefine(utf_16be, UTF_16BE) = {
 236   utf16be_mbc_enc_len,
 237   "UTF-16BE",   /* name */
 238   4,            /* max byte length */
 239   2,            /* min byte length */
 240   utf16be_is_mbc_newline,
 241   utf16be_mbc_to_code,
 242   utf16be_code_to_mbclen,
 243   utf16be_code_to_mbc,
 244   utf16be_mbc_case_fold,
 245   onigenc_unicode_apply_all_case_fold,
 246   utf16be_get_case_fold_codes_by_str,
 247   onigenc_unicode_property_name_to_ctype,
 248   onigenc_unicode_is_code_ctype,
 249   onigenc_utf16_32_get_ctype_code_range,
 250   utf16be_left_adjust_char_head,
 251   onigenc_always_false_is_allowed_reverse_match,
 252   onigenc_unicode_case_map,
 253   0,
 254   ONIGENC_FLAG_UNICODE,
 255 };
 256 ENC_ALIAS("UCS-2BE", "UTF-16BE")