1 | /* |
---|
2 | File CKCXLA.H |
---|
3 | |
---|
4 | System-independent character-set translation header file for C-Kermit. |
---|
5 | */ |
---|
6 | |
---|
7 | /* |
---|
8 | Author: Frank da Cruz <fdc@columbia.edu>, |
---|
9 | The Kermit Project - Columbia University, New York City. |
---|
10 | |
---|
11 | Copyright (C) 1985, 2002, |
---|
12 | Trustees of Columbia University in the City of New York. |
---|
13 | All rights reserved. See the C-Kermit COPYING.TXT file or the |
---|
14 | copyright text in the ckcmai.c module for disclaimer and permissions. |
---|
15 | */ |
---|
16 | /* |
---|
17 | NOTE: |
---|
18 | ISO 204 is Latin-1 + Euro. |
---|
19 | ISO 205 is Latin-4 + Euro. |
---|
20 | ISO 206 is Latin-7 + Euro. |
---|
21 | */ |
---|
22 | #ifndef CKCXLA_H /* Guard against multiple inclusion */ |
---|
23 | #define CKCXLA_H |
---|
24 | |
---|
25 | #ifndef KANJI /* Systems supporting Kanji */ |
---|
26 | #ifdef OS2 |
---|
27 | #define KANJI |
---|
28 | #endif /* OS2 */ |
---|
29 | #endif /* KANJI */ |
---|
30 | |
---|
31 | #ifdef NOKANJI /* Except if NOKANJI is defined. */ |
---|
32 | #ifdef KANJI |
---|
33 | #undef KANJI |
---|
34 | #endif /* KANJI */ |
---|
35 | #endif /* NOKANJI */ |
---|
36 | |
---|
37 | #ifndef NOUNICODE |
---|
38 | #ifndef UNICODE /* Unicode support */ |
---|
39 | #ifdef OS2ORUNIX /* Only for K95, UNIX, VMS,... */ |
---|
40 | #define UNICODE |
---|
41 | #else |
---|
42 | #ifdef VMS |
---|
43 | #define UNICODE |
---|
44 | #endif /* VMS */ |
---|
45 | #endif /* OS2ORUNIX */ |
---|
46 | #endif /* UNICODE */ |
---|
47 | #endif /* NOUNICODE */ |
---|
48 | |
---|
49 | #define XLA_NONE 0 /* Translation types - none */ |
---|
50 | #define XLA_BYTE 1 /* Byte-for-byte */ |
---|
51 | #define XLA_JAPAN 2 /* Japanese */ |
---|
52 | #define XLA_UNICODE 3 /* Unicode */ |
---|
53 | |
---|
54 | #ifndef UNIORKANJI /* Unicode OR Kanji */ |
---|
55 | #ifdef UNICODE /* i.e. some support for */ |
---|
56 | #define UNIORKANJI /* multibyte character sets */ |
---|
57 | #endif /* UNICODE */ |
---|
58 | #ifdef KANJI |
---|
59 | #define UNIORKANJI |
---|
60 | #endif /* KANJI */ |
---|
61 | #endif /* UNIORKANJI */ |
---|
62 | /* |
---|
63 | Disable all support for all classes of character sets |
---|
64 | if NOCSETS is defined. |
---|
65 | */ |
---|
66 | #ifdef NOCSETS |
---|
67 | |
---|
68 | #ifdef CKOUNI |
---|
69 | #undef CKOUNI |
---|
70 | #endif /* CKOUNI */ |
---|
71 | #ifdef KANJI |
---|
72 | #undef KANJI |
---|
73 | #endif /* KANJI */ |
---|
74 | #ifdef CYRILLIC |
---|
75 | #undef CYRILLIC |
---|
76 | #endif /* CYRILLIC */ |
---|
77 | #ifdef LATIN2 |
---|
78 | #undef LATIN2 |
---|
79 | #endif /* LATIN2 */ |
---|
80 | #ifdef HEBREW |
---|
81 | #undef HEBREW |
---|
82 | #endif /* HEBREW */ |
---|
83 | #ifdef UNICODE |
---|
84 | #undef UNICODE |
---|
85 | #endif /* UNICODE */ |
---|
86 | |
---|
87 | #else /* Not NOCSETS - Rest of this file... */ |
---|
88 | |
---|
89 | #ifdef NOUNICODE /* Unicode */ |
---|
90 | #ifdef UNICODE |
---|
91 | #undef UNICODE |
---|
92 | #endif /* UNICODE */ |
---|
93 | #endif /* NOUNICODE */ |
---|
94 | |
---|
95 | #ifdef UNICODE |
---|
96 | #ifdef OS2 |
---|
97 | #ifndef CKOUNI |
---|
98 | #define CKOUNI /* Special Unicode features for K95 */ |
---|
99 | #endif /* CKOUNI */ |
---|
100 | #endif /* OS2 */ |
---|
101 | #endif /* UNICODE */ |
---|
102 | |
---|
103 | #ifndef OS2 |
---|
104 | #ifdef CKOUNI |
---|
105 | #undef CKOUNI |
---|
106 | #endif /* CKOUNI */ |
---|
107 | #endif /* OS2 */ |
---|
108 | |
---|
109 | #ifndef NOLATIN2 /* If they didn't say "no Latin-2" */ |
---|
110 | #ifndef LATIN2 /* Then if LATIN2 isn't already */ |
---|
111 | #define LATIN2 /* defined, define it. */ |
---|
112 | #endif /* LATIN2 */ |
---|
113 | #endif /* NOLATIN2 */ |
---|
114 | |
---|
115 | #ifdef NOCYRILLIC /* (spelling variant...) */ |
---|
116 | #ifndef NOCYRIL |
---|
117 | #define NOCYRIL |
---|
118 | #endif /* NOCYRIL */ |
---|
119 | #endif /* NOCYRILLIC */ |
---|
120 | |
---|
121 | #ifndef NOCYRIL /* If they didn't say "no Cyrillic" */ |
---|
122 | #ifndef CYRILLIC /* Then if CYRILLIC isn't already */ |
---|
123 | #define CYRILLIC /* defined, define it. */ |
---|
124 | #endif /* CYRILLIC */ |
---|
125 | #endif /* NOCYRIL */ |
---|
126 | |
---|
127 | #ifndef NOHEBREW /* If they didn't say "no Hebrew" */ |
---|
128 | #ifndef HEBREW /* Then if HEBREW isn't already */ |
---|
129 | #define HEBREW /* defined, define it. */ |
---|
130 | #endif /* HEBREW */ |
---|
131 | #endif /* NOHEBREW */ |
---|
132 | |
---|
133 | #ifndef NOGREEK /* If not no Greek */ |
---|
134 | #ifndef GREEK /* then if GREEK isn't already */ |
---|
135 | #define GREEK /* defined, define it. */ |
---|
136 | #endif /* GREEK */ |
---|
137 | #endif /* NOGREEK */ |
---|
138 | |
---|
139 | #ifndef NOKANJI /* If not no Kanji */ |
---|
140 | #ifndef KANJI /* then if KANJI isn't already */ |
---|
141 | #define KANJI /* defined, define it. */ |
---|
142 | #endif /* KANJI */ |
---|
143 | #endif /* NOKANJI */ |
---|
144 | |
---|
145 | /* File ckcxla.h -- Character-set-related definitions, system independent */ |
---|
146 | |
---|
147 | /* Codes for Kermit Transfer Syntax Level (obsolete) */ |
---|
148 | |
---|
149 | #define TS_L0 0 /* Level 0 (Transparent) */ |
---|
150 | #define TS_L1 1 /* Level 1 (one standard character set) */ |
---|
151 | #define TS_L2 2 /* Level 2 (multiple character sets in same file) */ |
---|
152 | |
---|
153 | #define UNK 63 /* Symbol to use for unknown character (63 = ?) */ |
---|
154 | |
---|
155 | /* |
---|
156 | Codes for the base alphabet of a given character set. |
---|
157 | These are assigned in roughly ISO 8859 order. |
---|
158 | (Each is assumed to include ASCII/Roman.) |
---|
159 | */ |
---|
160 | #define AL_UNIV 0 /* Universal (like ISO 10646) */ |
---|
161 | #define AL_ROMAN 1 /* Roman (Latin) alphabet */ |
---|
162 | #define AL_CYRIL 2 /* Cyrillic alphabet */ |
---|
163 | #define AL_ARABIC 3 /* Arabic */ |
---|
164 | #define AL_GREEK 4 /* Greek */ |
---|
165 | #define AL_HEBREW 5 /* Hebrew */ |
---|
166 | #define AL_KANA 6 /* Japanese Katakana */ |
---|
167 | #define AL_JAPAN 7 /* Japanese Katakana+Kanji ideograms */ |
---|
168 | #define AL_HAN 8 /* Chinese/Japanese/Korean ideograms */ |
---|
169 | #define AL_INDIA 9 /* Indian scripts (ISCII) */ |
---|
170 | #define AL_VIET 10 /* Vietnamese (VISCII) */ |
---|
171 | /* Add more here... */ |
---|
172 | #define AL_UNK 999 /* Unknown (transparent) */ |
---|
173 | |
---|
174 | /* Codes for languages */ |
---|
175 | /* |
---|
176 | NOTE: It would perhaps be better to use ISO 639-1988 2-letter "Codes for |
---|
177 | Representation of Names of Languages" here, shown in the comments below. |
---|
178 | */ |
---|
179 | #define L_ASCII 0 /* EN ASCII, English */ |
---|
180 | #define L_USASCII 0 /* EN ASCII, English */ |
---|
181 | #define L_DUTCH 1 /* NL Dutch */ |
---|
182 | #define L_FINNISH 2 /* FI Finnish */ |
---|
183 | #define L_FRENCH 3 /* FR French */ |
---|
184 | #define L_GERMAN 4 /* DE German */ |
---|
185 | #define L_HUNGARIAN 5 /* HU Hungarian */ |
---|
186 | #define L_ITALIAN 6 /* IT Italian */ |
---|
187 | #define L_NORWEGIAN 7 /* NO Norwegian */ |
---|
188 | #define L_PORTUGUESE 8 /* PT Portuguese */ |
---|
189 | #define L_SPANISH 9 /* ES Spanish */ |
---|
190 | #define L_SWEDISH 10 /* SV Swedish */ |
---|
191 | #define L_SWISS 11 /* RM Swiss (Rhaeto-Romance) */ |
---|
192 | #define L_DANISH 12 /* DA Danish */ |
---|
193 | #define L_ICELANDIC 13 /* IS Icelandic */ |
---|
194 | #define L_RUSSIAN 14 /* RU Russian */ |
---|
195 | #define L_JAPANESE 15 /* JA Japanese */ |
---|
196 | #define L_HEBREW 16 /* IW Hebrew */ |
---|
197 | #define L_GREEK 17 /* Greek */ |
---|
198 | |
---|
199 | #define MAXLANG 17 /* Number of languages */ |
---|
200 | |
---|
201 | /* |
---|
202 | File character-sets are defined in the system-specific ck?xla.h file, |
---|
203 | except for the following ones, which must be available to all versions: |
---|
204 | */ |
---|
205 | #define FC_TRANSP 254 /* Transparent */ |
---|
206 | #define FC_UNDEF 255 /* Undefined */ |
---|
207 | /* |
---|
208 | Designators for Kermit's transfer character sets. These are all standard |
---|
209 | sets, or based on them. Symbols must be unique in the first 8 characters, |
---|
210 | because some C preprocessors have this limit. |
---|
211 | */ |
---|
212 | /* LIST1 */ |
---|
213 | #define TC_TRANSP 0 /* Transparent, no character translation */ |
---|
214 | #define TC_USASCII 1 /* ISO 646 IRV / US 7-bit ASCII */ |
---|
215 | #define TC_1LATIN 2 /* ISO 8859-1, Latin Alphabet 1 */ |
---|
216 | #define TC_2LATIN 3 /* ISO 8859-2, Latin Alphabet 2 */ |
---|
217 | #define TC_CYRILL 4 /* ISO 8859-5, Latin/Cyrillic */ |
---|
218 | #define TC_JEUC 5 /* Japanese EUC = JIS 0201+0202+0208 */ |
---|
219 | #define TC_HEBREW 6 /* ISO 8859-8, Latin/Hebrew */ |
---|
220 | #define TC_GREEK 7 /* ISO 8859-7, Latin/Greek */ |
---|
221 | #define TC_9LATIN 8 /* ISO 8859-15 Latin Alphabet 9 (with Euro) */ |
---|
222 | #define TC_UCS2 9 /* ISO 10646 / Unicode UCS-2 */ |
---|
223 | #define TC_UTF8 10 /* ISO 10646 / Unicode UTF-8 */ |
---|
224 | |
---|
225 | #define MAXTCSETS 10 /* Highest Transfer Character Set Number */ |
---|
226 | |
---|
227 | #ifdef COMMENT |
---|
228 | /* |
---|
229 | Not used and probably won't be due to ISO-10646 / Unicode. |
---|
230 | */ |
---|
231 | #define TC_3LATIN 11 /* ISO 8859-3, Latin-3 */ |
---|
232 | #define TC_4LATIN 12 /* ISO 8859-4, Latin-4 */ |
---|
233 | #define TC_5LATIN 13 /* ISO 8859-9, Latin-5 */ |
---|
234 | #define TC_ARABIC 14 /* ISO-8859-6, Latin/Arabic */ |
---|
235 | #define TC_JIS208 15 /* Japanese JIS X 0208 multibyte set */ |
---|
236 | #define TC_CHINES 16 /* Chinese Standard GB 2312-80 */ |
---|
237 | #define TC_KOREAN 17 /* Korean KS C 5601-1987 */ |
---|
238 | #define TC_ISCII 18 /* Indian standard code for ii... */ |
---|
239 | #define TC_VSCII 19 /* Vietnam standard code for ii... */ |
---|
240 | /* etc... */ |
---|
241 | #endif /* COMMENT */ |
---|
242 | |
---|
243 | /* Structure for character-set information */ |
---|
244 | |
---|
245 | struct csinfo { |
---|
246 | char *name; /* Descriptive name of character set */ |
---|
247 | int size; /* Size (e.g. 128, 256, 16384) */ |
---|
248 | int code; /* Like TC_1LATIN, etc. */ |
---|
249 | char *designator; /* Designator, like I2/100 = Latin-1 */ |
---|
250 | int alphabet; /* Base alphabet */ |
---|
251 | char *keyword; /* Keyword for this character-set */ |
---|
252 | }; |
---|
253 | |
---|
254 | /* Structure for language information */ |
---|
255 | |
---|
256 | struct langinfo { |
---|
257 | int id; /* Language ID code (L_whatever) */ |
---|
258 | int fc; /* File character set to use */ |
---|
259 | int tc; /* Transfer character set to use */ |
---|
260 | char *description; /* Description of language */ |
---|
261 | }; |
---|
262 | |
---|
263 | /* Now take in the system-specific definitions */ |
---|
264 | |
---|
265 | #ifdef UNIX |
---|
266 | #include "ckuxla.h" |
---|
267 | #endif /* UNIX */ |
---|
268 | |
---|
269 | #ifdef OSK /* OS-9 */ |
---|
270 | #include "ckuxla.h" |
---|
271 | #endif /* OS-9 */ |
---|
272 | |
---|
273 | #ifdef VMS /* VAX/VMS */ |
---|
274 | #include "ckuxla.h" |
---|
275 | #endif /* VMS */ |
---|
276 | |
---|
277 | #ifdef GEMDOS /* Atari ST */ |
---|
278 | #include "ckuxla.h" |
---|
279 | #endif /* GEMDOS */ |
---|
280 | |
---|
281 | #ifdef MAC /* Macintosh */ |
---|
282 | #include "ckmxla.h" |
---|
283 | #endif /* MAC */ |
---|
284 | |
---|
285 | #ifdef OS2 /* OS/2 */ |
---|
286 | #include "ckuxla.h" /* Uses big UNIX version */ |
---|
287 | #endif /* OS2 */ |
---|
288 | |
---|
289 | #ifdef AMIGA /* Commodore Amiga */ |
---|
290 | #include "ckuxla.h" |
---|
291 | #endif /* AMIGA */ |
---|
292 | |
---|
293 | #ifdef datageneral /* Data General MV AOS/VS */ |
---|
294 | #include "ckuxla.h" |
---|
295 | #endif /* datageneral */ |
---|
296 | |
---|
297 | #ifdef STRATUS /* Stratus Computer, Inc. VOS */ |
---|
298 | #include "ckuxla.h" |
---|
299 | #endif /* STRATUS */ |
---|
300 | |
---|
301 | #ifdef UNICODE |
---|
302 | #include "ckcuni.h" /* Unicode */ |
---|
303 | #endif /* UNICODE */ |
---|
304 | |
---|
305 | #ifdef KANJI |
---|
306 | #define UNKSJIS 0x817f |
---|
307 | _PROTOTYP(USHORT eu_to_sj, (USHORT) ); /* EUC-JP to Shift-JIS */ |
---|
308 | _PROTOTYP(USHORT sj_to_eu, (USHORT) ); /* Shift-JIS to EUC-JP */ |
---|
309 | _PROTOTYP( int xkanjf, (void) ); |
---|
310 | _PROTOTYP( int xkanji, (int, int (*)(char)) ); |
---|
311 | _PROTOTYP( int xkanjz, (int (*)(char) ) ); |
---|
312 | _PROTOTYP( int zkanjf, (void) ); |
---|
313 | _PROTOTYP( int zkanji, (int (*)(void)) ); /* Kanji function prototypes */ |
---|
314 | _PROTOTYP( int zkanjz, (void) ); |
---|
315 | _PROTOTYP(VOID j7init, ( void ) ); /* Initialize JIS-7 parser */ |
---|
316 | _PROTOTYP(int getj7, ( void ) ); /* Get next JIS-7 character */ |
---|
317 | #endif /* KANJI */ |
---|
318 | |
---|
319 | #ifndef MAC |
---|
320 | #ifndef NOLOCAL |
---|
321 | _PROTOTYP( int cs_size, (int) ); |
---|
322 | _PROTOTYP( int cs_is_std, (int) ); |
---|
323 | _PROTOTYP( int cs_is_nrc, (int) ); |
---|
324 | _PROTOTYP( VOID setremcharset, (int, int) ); |
---|
325 | _PROTOTYP( VOID setlclcharset, (int) ); |
---|
326 | #endif /* NOLOCAL */ |
---|
327 | #endif /* MAC */ |
---|
328 | |
---|
329 | _PROTOTYP(VOID setxlatype, (int, int)); |
---|
330 | |
---|
331 | #endif /* NOCSETS */ |
---|
332 | #endif /* CKCXLA_H */ |
---|
333 | |
---|
334 | /* End of ckcxla.h */ |
---|