1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
|
#ifndef __KANAID_H__ /* file wrapper */
#define __KANAID_H__
/*
* Jeffrey Friedl
* Omron Corporation ʳ
* Nagaokakyoshi, Japan 617Ĺ
*
* jfriedl@nff.ncl.omron.co.jp
*
* This work is placed under the terms of the GNU General Purpose License
* (the "GNU Copyleft").
*
* Oct 1993
*
* Routines (a'la ctype) to give info about EUC kana characters.
* Given the two-byte character as the two bytes HI and LO:
* IS_KATAKANA(HI, LO) -- true if character is katakana
* IS_HIRAGANA(HI, LO) -- true if character is hiragana
* IS_KANA(HI, LO) -- true if either of the above.
* IS_DASH(HI, LO) -- true if the character֡(which isn't kana)
*
* KANA_ID(HI, LO) -- VALID ONLY IF IS_KANA(HI,LO) IS TRUE,
* returns the KID_* codes defined below which
* describe the character.
*
* Warning: these are macros so arguments shouldn't have side effects.
*/
#define kanaid_version 100 /* 1.00 */
/*
* Flags returned by KANA_ID(Highbyte, Lowbyte) have the following bits set
*/
#define KID_A 0x00000001 /* */
#define KID_I 0x00000002 /* */
#define KID_U 0x00000004 /* */
#define KID_E 0x00000008 /* */
#define KID_O 0x00000010 /* */
/* mask to nab the volwel sound */
#define KID_VSOUND (KID_A|KID_I|KID_U|KID_E|KID_O)
#define KID_K 0x00000020 /* */
#define KID_G 0x00000040 /* */
#define KID_S 0x00000080 /* */
#define KID_Z 0x00000100 /* */
#define KID_T 0x00000200 /* ġơ */
#define KID_D 0x00000400 /* ¡šǡ */
#define KID_N 0x00000800 /* ʡˡ̡͡ */
#define KID_H 0x00001000 /* ϡҡաء */
#define KID_B 0x00002000 /* Сӡ֡١ */
#define KID_P 0x00004000 /* ѡԡסڡ */
#define KID_M 0x00008000 /* ޡߡࡢᡢ */
#define KID_Y 0x00010000 /* 䡢桢 */
#define KID_R 0x00020000 /* 顢ꡢ롢졢 */
#define KID_W 0x00040000 /* */
#define KID_n 0x00100000 /* */
/* mask to nab the consonant sound */
#define KID_CSOUND (KID_K|KID_G|KID_S|KID_Z|KID_T|KID_D|KID_N| \
KID_H|KID_B|KID_P|KID_M|KID_Y|KID_R|KID_W|KID_n)
#define KID_o 0x00080000 /* */
#define KID_SMALL 0x00200000 /* If small, as in ,,, etc. */
#define KID_VOWEL 0x00400000 /* If a raw vowel []. */
#define KID_KATAONLY 0x00800000 /* If char found only in katakana */
#define KID_ARCHAIC 0x01000000 /* If archaic */
#define KID_DUAL 0x02000000 /* For [ , , , ] */
/***********************************************************************/
/***********************************************************************/
#define KID_HIRA_HI 0244 /* high byte for hiragana EUC */
#define KID_KATA_HI 0245 /* high byte for katakana EUC */
/* true if the High/Low pair is the EUC ֡ */
#define IS_DASH(HighByte, LowByte) ((HighByte) == 0241 && (LowByte)== 0274)
#define _KID_START 161 /* the Low byte associated with _KID[0] */
#define _KID_END 246 /* the Low byte associated with end of _KID[] */
/* True if the bytes represent a katakana character (except dash) */
#define IS_KATAKANA(HighByte, LowByte) ((HighByte) == KID_KATA_HI && \
(LowByte) >= _KID_START && \
(LowByte) <= _KID_END)
/* True if the bytes represent a hiragana character */
#define IS_HIRAGANA(HighByte,LowByte) ((HighByte) == KID_HIRA_HI && \
(LowByte) >= _KID_START && \
(LowByte) <= _KID_END)
/* True if either katakana or hiragana */
#define IS_KANA(H,L) (IS_KATAKANA(H,L) || IS_HIRAGANA(H,L))
/*
* Returns the Kana ID for the given character.
*
* --> only valid if IS_KANA() or IS_HIRAGANA or IS_KATAKANA is true! <--
*
*/
#define KANA_ID(HighByte, LowByte) (_KID[(LowByte)-_KID_START])
extern unsigned long _KID[]; /* in kanaid.c */
#endif /* file wrapper */
|
