-
Notifications
You must be signed in to change notification settings - Fork 1
/
charsubst.c
288 lines (268 loc) · 6.39 KB
/
charsubst.c
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
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
/* charsubst.c
* vi: set sw=4 ts=8 ai sm noet :
*/
/*
* Permission is hereby granted to copy, reproduce, redistribute or otherwise
* use this software as long as: there is no monetary profit gained
* specifically from the use or reproduction of this software, it is not
* sold, rented, traded or otherwise marketed, and this copyright notice is
* included prominently in any copy made.
*
* The authors make no claims as to the fitness or correctness of this software
* for any use whatsoever, and it is provided as is. Any use of this software
* is at the user's own risk.
*/
#include "EXTERN.h"
#include "common.h"
#include "search.h"
#include "artstate.h"
#include "util2.h"
#include "utf.h"
#include "INTERN.h"
#include "charsubst.h"
#include "charsubst.ih"
#ifdef CHARSUBST
/* TeX encoding table - gives ISO char for "x (x=32..127) */
static Uchar textbl[96] = {
0, 0,'"', 0, 0, 0, 0,'"', 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0,196, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,214,
0, 0, 0, 0, 0,220, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
'"',228, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,246,
0, 0, 0,223, 0,252, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
};
static char texchar = '\0';
int
putsubstchar(c, limit, outputok)
int c;
int limit;
bool_int outputok;
{
Uchar d, oc[2], nc[5];
int t, i = 0;
switch (*charsubst) {
case 'm':
t = 1;
goto doconvert;
case 'a':
t = 2;
/* FALL THROUGH */
doconvert:
oc[0] = (Uchar)c;
oc[1] = '\0';
if ((i = Latin1toASCII(nc, oc, sizeof nc, t)) <= limit) {
if (outputok) {
for (t = 0; t < i; t++)
putchar((char)nc[t]);
}
}
else
i = -1;
break;
case 't':
if (c == '\\' || c == '"') {
if (texchar && (c == '\\' || texchar != '\\')) {
if (outputok)
putchar(texchar);
i++;
}
texchar = (char)c;
break;
}
else if (texchar == '\\') {
if (outputok)
putchar('\\');
if (limit == 1) {
i = -2;
break;
}
i++;
}
else if (texchar == '"') {
if (c < 32 || c > 128)
d = '\0';
else
d = textbl[c-32];
texchar = '\0';
if (d)
c = d;
else {
if (outputok)
putchar('"');
if (limit == 1) {
i = -2;
break;
}
i++;
}
}
/* FALL THROUGH */
default:
if (outputok)
putchar(c);
i++;
break;
}
return i;
}
char*
current_charsubst()
{
#ifdef USE_UTF_HACK
static char show[50];
const char* ics = input_charset_name();
const char* ocs = output_charset_name();
int maxlen = (sizeof show - 5)/2;
if (strcmp(ics, ocs) == 0)
sprintf(show, "[%.*s]", maxlen, ics, maxlen, ocs);
else
sprintf(show, "[%.*s->%.*s]", maxlen, ics, maxlen, ocs);
#else /*!USE_UTF_HACK */
static char* show;
switch (*charsubst) {
case 'm':
#ifdef VERBOSE
IF(verbose)
show = "[ISO->USmono] ";
ELSE
#endif
#ifdef TERSE
show = "[M] ";
#endif
break;
case 'a':
#ifdef VERBOSE
IF(verbose)
show = "[ISO->US] ";
ELSE
#endif
#ifdef TERSE
show = "[U] ";
#endif
break;
case 't':
#ifdef VERBOSE
IF(verbose)
show = "[TeX->ISO] ";
ELSE
#endif
#ifdef TERSE
show = "[T] ";
#endif
break;
default:
show = nullstr;
break;
}
#endif
return show;
}
int
strcharsubst(outb, inb, limit, subst)
char* outb;
char* inb;
int limit;
char_int subst;
{
char* s;
int len;
switch (subst) {
case 'm':
return Latin1toASCII((Uchar*)outb, (Uchar*)inb, limit, 1);
case 'a':
return Latin1toASCII((Uchar*)outb, (Uchar*)inb, limit, 2);
default:
if ((s = index(inb,'\n')) != NULL && s - inb + 1 < limit) {
len = s - inb + 1;
limit = len + 1;
}
else
len = strlen(inb);
safecpy(outb, inb, limit);
return len;
}
}
/* The following is an adapted version of iso2asc by Markus Kuhn,
University of Erlangen, Germany <[email protected]>
*/
#define ISO_TABLES 2 /* originally: 7 */
/* Conversion tables for displaying the G1 set (0xa0-0xff) of
ISO Latin 1 (ISO 8859-1) with 7-bit ASCII characters.
Version 1.2 -- error corrections are welcome
Table Purpose
0 universal table for many languages
1 single-spacing universal table
2 table for Danish, Dutch, German, Norwegian and Swedish
3 table for Danish, Finnish, Norwegian and Swedish using
the appropriate ISO 646 variant.
4 table with RFC 1345 codes in brackets
5 table for printers that allow overstriking with backspace
Markus Kuhn <[email protected]> */
/* In this version, I have taken out all tables except 1 and 2 -ot */
#define SUB NULL /* used if no reasonable ASCII string is possible */
static char* iso2asc[ISO_TABLES][96] = {
{
" ","!","c",SUB,SUB,"Y","|",SUB,"\"","c","a","<","-","-","R","-",
" ",SUB,"2","3","'","u","P",".",",","1","o",">",SUB,SUB,SUB,"?",
"A","A","A","A","A","A","A","C","E","E","E","E","I","I","I","I",
"D","N","O","O","O","O","O","x","O","U","U","U","U","Y","T","s",
"a","a","a","a","a","a","a","c","e","e","e","e","i","i","i","i",
"d","n","o","o","o","o","o",":","o","u","u","u","u","y","t","y"
},{
" ","!","c",SUB,SUB,"Y","|",SUB,"\"","(c)","a","<<","-","-","(R)","-",
" ","+/-","2","3","'","u","P",".",",","1","o",">>"," 1/4"," 1/2"," 3/4","?",
"A","A","A","A","Ae","Aa","AE","C","E","E","E","E","I","I","I","I",
"D","N","O","O","O","O","Oe","x","Oe","U","U","U","Ue","Y","Th","ss",
"a","a","a","a","ae","aa","ae","c","e","e","e","e","i","i","i","i",
"d","n","o","o","o","o","oe",":","oe","u","u","u","ue","y","th","ij"
}
};
/*
* Transform an 8-bit ISO Latin 1 string iso into a 7-bit ASCII string asc
* readable on old terminals using conversion table t.
*
* worst case: strlen(iso) == 4*strlen(asc)
*/
static int
Latin1toASCII(asc, iso, limit, t)
Uchar* asc;
Uchar* iso;
int limit;
int t;
{
Uchar* s = asc;
char* p;
char** tab;
if (iso == NULL || asc == NULL || limit <= 0)
return 0;
if (limit == 1)
goto done;
t--; /* offset correction -ot */
tab = iso2asc[t] - 0xa0;
while (*iso) {
if (*iso > 0x9f) {
p = tab[*iso++];
if (p) {
while (*p) {
*s++ = *p++;
if (!--limit)
goto done;
}
}
}
else {
if (*iso < 0x80)
*s++ = *iso++;
else {
*s++ = ' ';
iso++;
}
if (!--limit)
break;
}
}
done:
*s = '\0';
return s - asc;
}
#endif