enc/utf_16le.c

   1 /**********************************************************************
   2   utf_16le.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 utf16le_mbc_enc_len(const UChar* p, const OnigUChar* e,
  56                     OnigEncoding enc ARG_UNUSED)
  57 {
  58   int len = (int)(e - p);
  59   UChar byte;
  60   if (len < 2)
  61     return ONIGENC_CONSTRUCT_MBCLEN_NEEDMORE(1);
  62   byte = p[1];
  63   if (!UTF16_IS_SURROGATE(byte)) {
  64     return ONIGENC_CONSTRUCT_MBCLEN_CHARFOUND(2);
  65   }
  66   if (UTF16_IS_SURROGATE_FIRST(byte)) {
  67     if (len < 4)
  68       return ONIGENC_CONSTRUCT_MBCLEN_NEEDMORE(4-len);
  69     if (UTF16_IS_SURROGATE_SECOND(p[3]))
  70       return ONIGENC_CONSTRUCT_MBCLEN_CHARFOUND(4);
  71   }
  72   return ONIGENC_CONSTRUCT_MBCLEN_INVALID();
  73 }
  74
  75 static int
  76 utf16le_is_mbc_newline(const UChar* p, const UChar* end,
  77                        OnigEncoding enc ARG_UNUSED)
  78 {
  79   if (p + 1 < end) {
  80     if (*p == 0x0a && *(p+1) == 0x00)
  81       return 1;
  82 #ifdef USE_UNICODE_ALL_LINE_TERMINATORS
  83     if ((*p == 0x0b || *p == 0x0c || *p == 0x0d || *p == 0x85)
  84         && *(p+1) == 0x00)
  85       return 1;
  86     if (*(p+1) == 0x20 && (*p == 0x29 || *p == 0x28))
  87       return 1;
  88 #endif
  89   }
  90   return 0;
  91 }
  92
  93 static OnigCodePoint
  94 utf16le_mbc_to_code(const UChar* p, const UChar* end ARG_UNUSED,
  95                     OnigEncoding enc ARG_UNUSED)
  96 {
  97   OnigCodePoint code;
  98   UChar c0 = *p;
  99   UChar c1 = *(p+1);
 100
 101   if (UTF16_IS_SURROGATE_FIRST(c1)) {
 102     code = ((((c1 << 8) + c0) & 0x03ff) << 10)
 103          + (((p[3] << 8) + p[2]) & 0x03ff) + 0x10000;
 104   }
 105   else {
 106     code = c1 * 256 + p[0];
 107   }
 108   return code;
 109 }
 110
 111 static int
 112 utf16le_code_to_mbclen(OnigCodePoint code,
 113                        OnigEncoding enc ARG_UNUSED)
 114 {
 115   return (code > 0xffff ? 4 : 2);
 116 }
 117
 118 static int
 119 utf16le_code_to_mbc(OnigCodePoint code, UChar *buf,
 120                     OnigEncoding enc ARG_UNUSED)
 121 {
 122   UChar* p = buf;
 123
 124   if (code > 0xffff) {
 125     unsigned int high = (code >> 10) + 0xD7C0;
 126     unsigned int low = (code & 0x3FF) + 0xDC00;
 127     *p++ = high & 0xFF;
 128     *p++ = (high >> 8) & 0xFF;
 129     *p++ = low & 0xFF;
 130     *p++ = (low >> 8) & 0xFF;
 131     return 4;
 132   }
 133   else {
 134     *p++ = (UChar )(code & 0xff);
 135     *p++ = (UChar )((code & 0xff00) >> 8);
 136     return 2;
 137   }
 138 }
 139
 140 static int
 141 utf16le_mbc_case_fold(OnigCaseFoldType flag,
 142                       const UChar** pp, const UChar* end, UChar* fold,
 143                       OnigEncoding enc)
 144 {
 145   const UChar* p = *pp;
 146
 147   if (ONIGENC_IS_ASCII_CODE(*p) && *(p+1) == 0) {
 148 #ifdef USE_UNICODE_CASE_FOLD_TURKISH_AZERI
 149     if ((flag & ONIGENC_CASE_FOLD_TURKISH_AZERI) != 0) {
 150       if (*p == 0x49) {
 151         *fold++ = 0x31;
 152         *fold   = 0x01;
 153         (*pp) += 2;
 154         return 2;
 155       }
 156     }
 157 #endif
 158
 159     *fold++ = ONIGENC_ASCII_CODE_TO_LOWER_CASE(*p);
 160     *fold   = 0;
 161     *pp += 2;
 162     return 2;
 163   }
 164   else
 165     return onigenc_unicode_mbc_case_fold(enc, flag, pp,
 166                                          end, fold);
 167 }
 168
 169 #if 0
 170 static int
 171 utf16le_is_mbc_ambiguous(OnigCaseFoldType flag, const UChar** pp,
 172                          const UChar* end)
 173 {
 174   const UChar* p = *pp;
 175
 176   (*pp) += EncLen_UTF16[*(p+1)];
 177
 178   if (*(p+1) == 0) {
 179     int c, v;
 180
 181     if (*p == SHARP_s && (flag & INTERNAL_ONIGENC_CASE_FOLD_MULTI_CHAR) != 0) {
 182       return TRUE;
 183     }
 184
 185     c = *p;
 186     v = ONIGENC_IS_UNICODE_ISO_8859_1_BIT_CTYPE(c,
 187                        (BIT_CTYPE_UPPER | BIT_CTYPE_LOWER));
 188     if ((v | BIT_CTYPE_LOWER) != 0) {
 189       /* 0xaa, 0xb5, 0xba are lower case letter, but can't convert. */
 190       if (c >= 0xaa && c <= 0xba)
 191         return FALSE;
 192       else
 193         return TRUE;
 194     }
 195     return (v != 0 ? TRUE : FALSE);
 196   }
 197
 198   return FALSE;
 199 }
 200 #endif
 201
 202 static UChar*
 203 utf16le_left_adjust_char_head(const UChar* start, const UChar* s, const UChar* end,
 204                               OnigEncoding enc ARG_UNUSED)
 205 {
 206   if (s <= start) return (UChar* )s;
 207
 208   if ((s - start) % 2 == 1) {
 209     s--;
 210   }
 211
 212   if (UTF16_IS_SURROGATE_SECOND(*(s+1)) && s > start + 1)
 213     s -= 2;
 214
 215   return (UChar* )s;
 216 }
 217
 218 static int
 219 utf16le_get_case_fold_codes_by_str(OnigCaseFoldType flag,
 220                                    const OnigUChar* p, const OnigUChar* end,
 221                                    OnigCaseFoldCodeItem items[],
 222                                    OnigEncoding enc)
 223 {
 224   return onigenc_unicode_get_case_fold_codes_by_str(enc,
 225                                                     flag, p, end, items);
 226 }
 227
 228 OnigEncodingDefine(utf_16le, UTF_16LE) = {
 229   utf16le_mbc_enc_len,
 230   "UTF-16LE",   /* name */
 231   4,            /* max byte length */
 232   2,            /* min byte length */
 233   utf16le_is_mbc_newline,
 234   utf16le_mbc_to_code,
 235   utf16le_code_to_mbclen,
 236   utf16le_code_to_mbc,
 237   utf16le_mbc_case_fold,
 238   onigenc_unicode_apply_all_case_fold,
 239   utf16le_get_case_fold_codes_by_str,
 240   onigenc_unicode_property_name_to_ctype,
 241   onigenc_unicode_is_code_ctype,
 242   onigenc_utf16_32_get_ctype_code_range,
 243   utf16le_left_adjust_char_head,
 244   onigenc_always_false_is_allowed_reverse_match,
 245   onigenc_unicode_case_map,
 246   0,
 247   ONIGENC_FLAG_UNICODE,
 248 };