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
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
/* $Id$ */
/**************************************************************************
* chars.c *
* *
* Copyright (C) 2005 Chris Allegretta *
* This program is free software; you can redistribute it and/or modify *
* it under the terms of the GNU General Public License as published by *
* the Free Software Foundation; either version 2, or (at your option) *
* any later version. *
* *
* This program is distributed in the hope that it will be useful, *
* but WITHOUT ANY WARRANTY; without even the implied warranty of *
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the *
* GNU General Public License for more details. *
* *
* You should have received a copy of the GNU General Public License *
* along with this program; if not, write to the Free Software *
* Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. *
* *
**************************************************************************/
#ifdef HAVE_CONFIG_H
#include <config.h>
#endif
#include <stdlib.h>
#include <ctype.h>
#include <assert.h>
#include "proto.h"
#include "nano.h"
#if defined(HAVE_WCHAR_H) && defined(NANO_WIDE)
#include <wchar.h>
#endif
#if defined(HAVE_WCTYPE_H) && defined(NANO_WIDE)
#include <wctype.h>
#endif
/* This function is equivalent to isblank(). */
bool is_blank_char(unsigned char c)
{
return
#ifdef HAVE_ISBLANK
isblank(c)
#else
isspace(c) && (c == '\t' || !is_cntrl_char(c))
#endif
;
}
/* This function is equivalent to isblank() for multibyte characters. */
bool is_blank_mbchar(const char *c)
{
assert(c != NULL);
#ifdef NANO_WIDE
if (!ISSET(NO_UTF8)) {
wchar_t wc;
int c_mb_len = mbtowc(&wc, c, MB_CUR_MAX);
if (c_mb_len <= 0) {
mbtowc(NULL, NULL, 0);
wc = (unsigned char)*c;
}
return is_blank_wchar(wc);
} else
#endif
return is_blank_char((unsigned char)*c);
}
#ifdef NANO_WIDE
/* This function is equivalent to isblank() for wide characters. */
bool is_blank_wchar(wchar_t wc)
{
return
#ifdef HAVE_ISWBLANK
iswblank(wc)
#else
iswspace(wc) && (wc == '\t' || !is_cntrl_wchar(wc))
#endif
;
}
#endif
/* This function is equivalent to iscntrl(), except in that it also
* handles control characters with their high bits set. */
bool is_cntrl_char(unsigned char c)
{
return (c < 32) || (127 <= c && c < 160);
}
/* This function is equivalent to iscntrl() for multibyte characters,
* except in that it also handles multibyte control characters with
* their high bits set. */
bool is_cntrl_mbchar(const char *c)
{
assert(c != NULL);
#ifdef NANO_WIDE
if (!ISSET(NO_UTF8)) {
wchar_t wc;
int c_mb_len = mbtowc(&wc, c, MB_CUR_MAX);
if (c_mb_len <= 0) {
mbtowc(NULL, NULL, 0);
wc = (unsigned char)*c;
}
return is_cntrl_wchar(wc);
} else
#endif
return is_cntrl_char((unsigned char)*c);
}
#ifdef NANO_WIDE
/* This function is equivalent to iscntrl() for wide characters, except
* in that it also handles wide control characters with their high bits
* set. */
bool is_cntrl_wchar(wchar_t wc)
{
return (0 <= wc && wc < 32) || (127 <= wc && wc < 160);
}
#endif
/* c is a control character. It displays as ^@, ^?, or ^[ch] where ch
* is c + 64. We return that character. */
unsigned char control_rep(unsigned char c)
{
/* Treat newlines embedded in a line as encoded nulls. */
if (c == '\n')
return '@';
else if (c == NANO_CONTROL_8)
return '?';
else
return c + 64;
}
/* c is a multibyte control character. It displays as ^@, ^?, or ^[ch]
* where ch is c + 64. We return that multibyte character. */
char *control_mbrep(const char *c, char *crep, int *crep_len)
{
assert(c != NULL);
#ifdef NANO_WIDE
if (!ISSET(NO_UTF8)) {
wchar_t wc, wcrep;
int c_mb_len = mbtowc(&wc, c, MB_CUR_MAX), crep_mb_len;
if (c_mb_len <= 0) {
mbtowc(NULL, NULL, 0);
wc = *c;
}
wcrep = control_wrep(wc);
crep_mb_len = wctomb(crep, wcrep);
if (crep_mb_len <= 0) {
wctomb(NULL, 0);
crep_mb_len = 0;
}
*crep_len = crep_mb_len;
return crep;
} else {
#endif
*crep_len = 1;
crep[0] = control_rep((unsigned char)*c);
return crep;
#ifdef NANO_WIDE
}
#endif
}
#ifdef NANO_WIDE
/* c is a wide control character. It displays as ^@, ^?, or ^[ch] where
* ch is c + 64. We return that wide character. */
wchar_t control_wrep(wchar_t wc)
{
/* Treat newlines embedded in a line as encoded nulls. */
if (wc == '\n')
return '@';
else if (wc == NANO_CONTROL_8)
return '?';
else
return wc + 64;
}
#endif
/* This function is equivalent to wcwidth() for multibyte characters. */
int mbwidth(const char *c)
{
assert(c != NULL);
#ifdef NANO_WIDE
if (!ISSET(NO_UTF8)) {
wchar_t wc;
int c_mb_len = mbtowc(&wc, c, MB_CUR_MAX), width;
if (c_mb_len <= 0) {
mbtowc(NULL, NULL, 0);
wc = (unsigned char)*c;
}
width = wcwidth(wc);
if (width == -1)
width++;
return width;
} else
#endif
return 1;
}
/* Return the maximum width in bytes of a multibyte character. */
int mb_cur_max(void)
{
#ifdef NANO_WIDE
if (!ISSET(NO_UTF8))
return MB_CUR_MAX;
else
#endif
return 1;
}
/* Convert the value in chr to a multibyte character with the same
* wide character value as chr. Return the multibyte character and its
* length. */
char *make_mbchar(unsigned int chr, char *chr_mb, int *chr_mb_len)
{
#ifdef NANO_WIDE
if (!ISSET(NO_UTF8)) {
*chr_mb_len = wctomb(chr_mb, chr);
if (*chr_mb_len <= 0) {
mbtowc(NULL, NULL, 0);
*chr_mb_len = 1;
chr_mb[0] = (unsigned char)chr;
}
} else {
#endif
*chr_mb_len = 1;
chr_mb[0] = (unsigned char)chr;
#ifdef NANO_WIDE
}
#endif
return chr_mb;
}
/* Parse a multibyte character from buf. Return the number of bytes
* used. If chr isn't NULL, store the multibyte character in it. If
* bad_chr isn't NULL, set it to TRUE if we have a null byte or a bad
* multibyte character. If col isn't NULL, store the new display width
* in it. If *str is '\t', we expect col to have the current display
* width. */
int parse_mbchar(const char *buf, char *chr
#ifdef NANO_WIDE
, bool *bad_chr
#endif
, size_t *col)
{
int buf_mb_len;
assert(buf != NULL);
#ifdef NANO_WIDE
if (bad_chr != NULL)
*bad_chr = FALSE;
if (!ISSET(NO_UTF8)) {
/* Get the number of bytes in the multibyte character. */
buf_mb_len = mblen(buf, MB_CUR_MAX);
/* If buf contains a null byte or an invalid multibyte
* character, interpret buf's first byte and set bad_chr to
* TRUE. */
if (buf_mb_len <= 0) {
mblen(NULL, 0);
buf_mb_len = 1;
if (bad_chr != NULL)
*bad_chr = TRUE;
}
/* Save the multibyte character in chr. */
if (chr != NULL) {
int i;
for (i = 0; i < buf_mb_len; i++)
chr[i] = buf[i];
}
/* Save the column width of the wide character in col. */
if (col != NULL) {
/* If we have a tab, get its width in columns using the
* current value of col. */
if (*buf == '\t')
*col += tabsize - *col % tabsize;
/* If we have a control character, get its width using one
* column for the "^" that will be displayed in front of it,
* and the width in columns of its visible equivalent as
* returned by control_rep(). */
else if (is_cntrl_mbchar(buf)) {
char *ctrl_buf_mb = charalloc(mb_cur_max());
int ctrl_buf_mb_len;
(*col)++;
ctrl_buf_mb = control_mbrep(buf, ctrl_buf_mb,
&ctrl_buf_mb_len);
*col += mbwidth(ctrl_buf_mb);
free(ctrl_buf_mb);
/* If we have a normal character, get its width in columns
* normally. */
} else
*col += mbwidth(buf);
}
} else {
#endif
/* Get the number of bytes in the byte character. */
buf_mb_len = 1;
/* Save the byte character in chr. */
if (chr != NULL)
*chr = *buf;
if (col != NULL) {
/* If we have a tab, get its width in columns using the
* current value of col. */
if (*buf == '\t')
*col += tabsize - *col % tabsize;
/* If we have a control character, it's two columns wide:
* one column for the "^" that will be displayed in front of
* it, and one column for its visible equivalent as returned
* by control_rep(). */
else if (is_cntrl_char((unsigned char)*buf))
*col += 2;
/* If we have a normal character, it's one column wide. */
else
(*col)++;
}
#ifdef NANO_WIDE
}
#endif
return buf_mb_len;
}