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
353
354
355
356
357
358
359
360
361
362
363
364
365
|
/* $OpenBSD: nl.c,v 1.3 2014/05/20 01:25:23 guenther Exp $ */
/* $NetBSD: nl.c,v 1.11 2011/08/16 12:00:46 christos Exp $ */
/*-
* Copyright (c) 1999 The NetBSD Foundation, Inc.
* All rights reserved.
*
* This code is derived from software contributed to The NetBSD Foundation
* by Klaus Klein.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
*
* THIS SOFTWARE IS PROVIDED BY THE NETBSD FOUNDATION, INC. AND CONTRIBUTORS
* ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
* TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
* PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE FOUNDATION OR CONTRIBUTORS
* BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
* CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
* SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
* INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
* CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
* ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
* POSSIBILITY OF SUCH DAMAGE.
*/
#include <sys/cdefs.h>
#include <err.h>
#include <errno.h>
#include <limits.h>
#include <locale.h>
#include <regex.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
#include <wchar.h>
typedef enum {
number_all, /* number all lines */
number_nonempty, /* number non-empty lines */
number_none, /* no line numbering */
number_regex /* number lines matching regular expression */
} numbering_type;
struct numbering_property {
const char * const name; /* for diagnostics */
numbering_type type; /* numbering type */
regex_t expr; /* for type == number_regex */
};
/* line numbering formats */
#define FORMAT_LN "%-*d" /* left justified, leading zeros suppressed */
#define FORMAT_RN "%*d" /* right justified, leading zeros suppressed */
#define FORMAT_RZ "%0*d" /* right justified, leading zeros kept */
#define FOOTER 0
#define BODY 1
#define HEADER 2
#define NP_LAST HEADER
static struct numbering_property numbering_properties[NP_LAST + 1] = {
{ "footer", number_none, { 0, 0, 0, 0 } },
{ "body", number_nonempty, { 0, 0, 0, 0 } },
{ "header", number_none, { 0, 0, 0, 0 } },
};
void filter(void);
void parse_numbering(const char *, int);
__dead void usage(void);
/*
* Delimiter characters that indicate the start of a logical page section.
*/
static char delim[2 * MB_LEN_MAX];
static int delimlen;
/*
* Configurable parameters.
*/
/* line numbering format */
static const char *format = FORMAT_RN;
/* increment value used to number logical page lines */
static int incr = 1;
/* number of adjacent blank lines to be considered (and numbered) as one */
static unsigned int nblank = 1;
/* whether to restart numbering at logical page delimiters */
static int restart = 1;
/* characters used in separating the line number and the corrsp. text line */
static const char *sep = "\t";
/* initial value used to number logical page lines */
static int startnum = 1;
/* number of characters to be used for the line number */
/* should be unsigned but required signed by `*' precision conversion */
static int width = 6;
int
main(int argc, char *argv[])
{
int c;
size_t clen;
char delim1[MB_LEN_MAX] = { '\\' }, delim2[MB_LEN_MAX] = { ':' };
size_t delim1len = 1, delim2len = 1;
const char *errstr;
(void)setlocale(LC_ALL, "");
while ((c = getopt(argc, argv, "pb:d:f:h:i:l:n:s:v:w:")) != -1) {
switch (c) {
case 'p':
restart = 0;
break;
case 'b':
parse_numbering(optarg, BODY);
break;
case 'd':
clen = mbrlen(optarg, MB_CUR_MAX, NULL);
if (clen == (size_t)-1 || clen == (size_t)-2)
errc(EXIT_FAILURE, EILSEQ, NULL);
if (clen != 0) {
memcpy(delim1, optarg, delim1len = clen);
clen = mbrlen(optarg + delim1len,
MB_CUR_MAX, NULL);
if (clen == (size_t)-1 || clen == (size_t)-2)
errc(EXIT_FAILURE, EILSEQ, NULL);
if (clen != 0) {
memcpy(delim2, optarg + delim1len,
delim2len = clen);
if (optarg[delim1len + clen] != '\0') {
errx(EXIT_FAILURE,
"invalid delimiter: %s",
optarg);
}
}
}
break;
case 'f':
parse_numbering(optarg, FOOTER);
break;
case 'h':
parse_numbering(optarg, HEADER);
break;
case 'i':
incr = strtonum(optarg, INT_MIN, INT_MAX, &errstr);
if (errstr)
errx(EXIT_FAILURE, "increment value is %s: %s",
errstr, optarg);
break;
case 'l':
nblank = strtonum(optarg, 0, UINT_MAX, &errstr);
if (errstr)
errx(EXIT_FAILURE,
"blank line value is %s: %s",
errstr, optarg);
break;
case 'n':
if (strcmp(optarg, "ln") == 0) {
format = FORMAT_LN;
} else if (strcmp(optarg, "rn") == 0) {
format = FORMAT_RN;
} else if (strcmp(optarg, "rz") == 0) {
format = FORMAT_RZ;
} else
errx(EXIT_FAILURE,
"illegal format -- %s", optarg);
break;
case 's':
sep = optarg;
break;
case 'v':
startnum = strtonum(optarg, INT_MIN, INT_MAX, &errstr);
if (errstr)
errx(EXIT_FAILURE,
"initial logical page value is %s: %s",
errstr, optarg);
break;
case 'w':
width = strtonum(optarg, 1, INT_MAX, &errstr);
if (errstr)
errx(EXIT_FAILURE, "width is %s: %s", errstr,
optarg);
break;
case '?':
default:
usage();
/* NOTREACHED */
}
}
argc -= optind;
argv += optind;
switch (argc) {
case 0:
break;
case 1:
if (strcmp(argv[0], "-") != 0 &&
freopen(argv[0], "r", stdin) == NULL)
err(EXIT_FAILURE, "%s", argv[0]);
break;
default:
usage();
/* NOTREACHED */
}
/* Generate the delimiter sequence */
memcpy(delim, delim1, delim1len);
memcpy(delim + delim1len, delim2, delim2len);
delimlen = delim1len + delim2len;
/* Do the work. */
filter();
exit(EXIT_SUCCESS);
}
void
filter(void)
{
char *buffer;
size_t buffersize;
ssize_t linelen;
int line; /* logical line number */
int section; /* logical page section */
unsigned int adjblank; /* adjacent blank lines */
int donumber = 0, idx;
adjblank = 0;
line = startnum;
section = BODY;
buffer = NULL;
buffersize = 0;
while ((linelen = getline(&buffer, &buffersize, stdin)) > 0) {
for (idx = FOOTER; idx <= NP_LAST; idx++) {
/* Does it look like a delimiter? */
if (delimlen * (idx + 1) > linelen)
break;
if (memcmp(buffer + delimlen * idx, delim,
delimlen) != 0)
break;
/* Was this the whole line? */
if (buffer[delimlen * (idx + 1)] == '\n') {
section = idx;
adjblank = 0;
if (restart)
line = startnum;
goto nextline;
}
}
switch (numbering_properties[section].type) {
case number_all:
/*
* Doing this for number_all only is disputable, but
* the standard expresses an explicit dependency on
* `-b a' etc.
*/
if (buffer[0] == '\n' && ++adjblank < nblank)
donumber = 0;
else
donumber = 1, adjblank = 0;
break;
case number_nonempty:
donumber = (buffer[0] != '\n');
break;
case number_none:
donumber = 0;
break;
case number_regex:
donumber =
(regexec(&numbering_properties[section].expr,
buffer, 0, NULL, 0) == 0);
break;
}
if (donumber) {
(void)printf(format, width, line);
line += incr;
(void)fputs(sep, stdout);
} else {
(void)printf("%*s", width, "");
}
(void)fwrite(buffer, linelen, 1, stdout);
if (ferror(stdout))
err(EXIT_FAILURE, "output error");
nextline:
;
}
if (ferror(stdin))
err(EXIT_FAILURE, "input error");
free(buffer);
}
/*
* Various support functions.
*/
void
parse_numbering(const char *argstr, int section)
{
int error;
char errorbuf[NL_TEXTMAX];
switch (argstr[0]) {
case 'a':
numbering_properties[section].type = number_all;
break;
case 'n':
numbering_properties[section].type = number_none;
break;
case 't':
numbering_properties[section].type = number_nonempty;
break;
case 'p':
/* If there was a previous expression, throw it away. */
if (numbering_properties[section].type == number_regex)
regfree(&numbering_properties[section].expr);
else
numbering_properties[section].type = number_regex;
/* Compile/validate the supplied regular expression. */
if ((error = regcomp(&numbering_properties[section].expr,
&argstr[1], REG_NEWLINE|REG_NOSUB)) != 0) {
(void)regerror(error,
&numbering_properties[section].expr,
errorbuf, sizeof(errorbuf));
errx(EXIT_FAILURE,
"%s expr: %s -- %s",
numbering_properties[section].name, errorbuf,
&argstr[1]);
}
break;
default:
errx(EXIT_FAILURE,
"illegal %s line numbering type -- %s",
numbering_properties[section].name, argstr);
}
}
__dead void
usage(void)
{
(void)fprintf(stderr, "usage: %s [-p] [-b type] [-d delim] [-f type] "
"[-h type] [-i incr] [-l num]\n\t[-n format] [-s sep] "
"[-v startnum] [-w width] [file]\n", getprogname());
exit(EXIT_FAILURE);
}
|