source/include/kanji.h

   1 /*
   2    Unix SMB/Netbios implementation.
   3    Version 1.9.
   4    Kanji Extensions
   5    Copyright (C) Andrew Tridgell 1992-1998
   6
   7    This program is free software; you can redistribute it and/or modify
   8    it under the terms of the GNU General Public License as published by
   9    the Free Software Foundation; either version 2 of the License, or
  10    (at your option) any later version.
  11
  12    This program is distributed in the hope that it will be useful,
  13    but WITHOUT ANY WARRANTY; without even the implied warranty of
  14    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  15    GNU General Public License for more details.
  16
  17    You should have received a copy of the GNU General Public License
  18    along with this program; if not, write to the Free Software
  19    Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  20
  21    Adding for Japanese language by <fujita@ainix.isac.co.jp> 1994.9.5
  22      and extend coding system to EUC/SJIS/JIS/HEX at 1994.10.11
  23      and add all jis codes sequence at 1995.8.16
  24      Notes: Hexadecimal code by <ohki@gssm.otuka.tsukuba.ac.jp>
  25      and add upper/lower case conversion 1997.8.21
  26 */
  27 #ifndef _KANJI_H_
  28 #define _KANJI_H_
  29
  30 /* FOR SHIFT JIS CODE */
  31 #define is_shift_jis(c) \
  32     ((0x81 <= ((unsigned char) (c)) && ((unsigned char) (c)) <= 0x9f) \
  33      || (0xe0 <= ((unsigned char) (c)) && ((unsigned char) (c)) <= 0xef))
  34 #define is_shift_jis2(c) \
  35     (0x40 <= ((unsigned char) (c)) && ((unsigned char) (c)) <= 0xfc \
  36     && ((unsigned char) (c)) != 0x7f)
  37 #define is_kana(c) ((0xa0 <= ((unsigned char) (c)) && ((unsigned char) (c)) <= 0xdf))
  38
  39 /* case conversion */
  40 #define is_sj_upper2(c) \
  41   ((0x60 <= (unsigned char) (c)) && ((unsigned char) (c) <= 0x79))
  42 #define is_sj_lower2(c) \
  43   ((0x81 <= (unsigned char) (c)) && ((unsigned char) (c) <= 0x9A))
  44 #define sjis_alph 0x82
  45 #define is_sj_alph(c) (sjis_alph == (unsigned char) (c))
  46 #define is_sj_upper(c1, c2) (is_sj_alph (c1) && is_sj_upper2 (c2))
  47 #define is_sj_lower(c1, c2) (is_sj_alph (c1) && is_sj_lower2 (c2))
  48 #define sj_toupper2(c) \
  49     (is_sj_lower2 (c) ? ((int) ((unsigned char) (c) - 0x81 + 0x60)) : \
  50      ((int) (unsigned char) (c)))
  51 #define sj_tolower2(c) \
  52     (is_sj_upper2 (c) ? ((int) ((unsigned char) (c) - 0x60 + 0x81)) : \
  53      ((int) (unsigned char) (c)))
  54
  55 #ifdef _KANJI_C_
  56 /* FOR EUC CODE */
  57 #define euc_kana (0x8e)
  58 #define is_euc_kana(c) (((unsigned char) (c)) == euc_kana)
  59 #define is_euc(c)  (0xa0 < ((unsigned char) (c)) && ((unsigned char) (c)) < 0xff)
  60
  61 /* FOR JIS CODE */
  62 /* default jis third shift code, use for output */
  63 #ifndef JIS_KSO
  64 #define JIS_KSO 'B'
  65 #endif
  66 #ifndef JIS_KSI
  67 #define JIS_KSI 'J'
  68 #endif
  69 /* in: \E$B or \E$@ */
  70 /* out: \E(J or \E(B or \E(H */
  71 #define jis_esc (0x1b)
  72 #define jis_so (0x0e)
  73 #define jis_so1 ('$')
  74 #define jis_so2 ('B')
  75 #define jis_si (0x0f)
  76 #define jis_si1 ('(')
  77 #define jis_si2 ('J')
  78 #define is_esc(c) (((unsigned char) (c)) == jis_esc)
  79 #define is_so1(c) (((unsigned char) (c)) == jis_so1)
  80 #define is_so2(c) (((unsigned char) (c)) == jis_so2 || ((unsigned char) (c)) == '@')
  81 #define is_si1(c) (((unsigned char) (c)) == jis_si1)
  82 #define is_si2(c) (((unsigned char) (c)) == jis_si2 || ((unsigned char) (c)) == 'B' \
  83     || ((unsigned char) (c)) == 'H')
  84 #define is_so(c) (((unsigned char) (c)) == jis_so)
  85 #define is_si(c) (((unsigned char) (c)) == jis_si)
  86 #define junet_kana1 ('(')
  87 #define junet_kana2 ('I')
  88 #define is_juk1(c) (((unsigned char) (c)) == junet_kana1)
  89 #define is_juk2(c) (((unsigned char) (c)) == junet_kana2)
  90
  91 #define _KJ_ROMAN (0)
  92 #define _KJ_KANJI (1)
  93 #define _KJ_KANA (2)
  94
  95 /* FOR HEX */
  96 #define HEXTAG ':'
  97 #define hex2bin(x)                                                    \
  98     ( ((int) '0' <= ((int) (x)) && ((int) (x)) <= (int)'9')?          \
  99         (((int) (x))-(int)'0'):                                       \
 100       ((int) 'a'<= ((int) (x)) && ((int) (x))<= (int) 'f')?           \
 101         (((int) (x)) - (int)'a'+10):                                  \
 102       (((int) (x)) - (int)'A'+10) )
 103 #define bin2hex(x)                                                    \
 104     ( (((int) (x)) >= 10)? (((int) (x))-10 + (int) 'a'): (((int) (x)) + (int) '0') )
 105
 106 /* For Hangul (Korean - code page 949). */
 107 #define is_hangul(c) ((0x81 <= ((unsigned char) (c)) && ((unsigned char) (c)) <= 0xfd))
 108
 109 /* For traditional Chinese (known as Big5 encoding - code page 950). */
 110 #define is_big5_c1(c) ((0xa1 <= ((unsigned char) (c)) && ((unsigned char) (c)) <= 0xf9))
 111
 112 /* For simplified Chinese (code page - 936). */
 113 #define is_simpch_c1(c) ((0xa1 <= ((unsigned char) (c)) && ((unsigned char) (c)) <= 0xf7))
 114
 115 #else /* not _KANJI_C_ */
 116
 117 /*
 118  * The following is needed for AIX systems that have
 119  * their own #defines for strchr, strrchr, strstr
 120  * and strtok.
 121  */
 122
 123 #ifdef strchr
 124 #undef strchr
 125 #endif /* strchr */
 126
 127 #ifdef strrchr
 128 #undef strrchr
 129 #endif /* strrchr */
 130
 131 #ifdef strstr
 132 #undef strstr
 133 #endif /* strstr */
 134
 135 #ifdef strtok
 136 #undef strtok
 137 #endif /* strtok */
 138
 139 /* Ensure we use our definitions in all other files than kanji.c. */
 140
 141 /* Function pointers we will replace. */
 142 extern char *(*multibyte_strchr)(char *s, int c);
 143 extern char *(*multibyte_strrchr)(char *s, int c);
 144 extern char *(*multibyte_strstr)(char *s1, char *s2);
 145 extern char *(*multibyte_strtok)(char *s1, char *s2);
 146 extern char *(*_dos_to_unix)(char *str, BOOL overwrite);
 147 extern char *(*_unix_to_dos)(char *str, BOOL overwrite);
 148 extern BOOL (*is_multibyte_char)(char c);
 149 extern int (*_skip_multibyte_char)(char c);
 150
 151 #define strchr(s1, c) ((*multibyte_strchr)((s1), (c)))
 152 #define strrchr(s1, c) ((*multibyte_strrchr)((s1), (c)))
 153 #define strstr(s1, s2) ((*multibyte_strstr)((s1), (s2)))
 154 #define strtok(s1, s2) ((*multibyte_strtok)((s1), (s2)))
 155 #define dos_to_unix(x,y) ((*_dos_to_unix)((x), (y)))
 156 #define unix_to_dos(x,y) ((*_unix_to_dos)((x), (y)))
 157 #define skip_multibyte_char(c) ((*_skip_multibyte_char)((c)))
 158
 159 #endif /* _KANJI_C_ */
 160
 161 #define UNKNOWN_CODE (-1)
 162 #define SJIS_CODE (0)
 163 #define EUC_CODE (1)
 164 #define JIS7_CODE (2)
 165 #define JIS8_CODE (3)
 166 #define JUNET_CODE (4)
 167 #define HEX_CODE (5)
 168 #define CAP_CODE (6)
 169 #define DOSV_CODE SJIS_CODE
 170
 171 #endif /* _KANJI_H_ */