1/*
2 * Copyright (c) 1987, 1993, 1994, 1995
3 *	The Regents of the University of California.  All rights reserved.
4 *
5 * Redistribution and use in source and binary forms, with or without
6 * modification, are permitted provided that the following conditions
7 * are met:
8 * 1. Redistributions of source code must retain the above copyright
9 *    notice, this list of conditions and the following disclaimer.
10 * 2. Redistributions in binary form must reproduce the above copyright
11 *    notice, this list of conditions and the following disclaimer in the
12 *    documentation and/or other materials provided with the distribution.
13 * 4. Neither the name of the University nor the names of its contributors
14 *    may be used to endorse or promote products derived from this software
15 *    without specific prior written permission.
16 *
17 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
18 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
19 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
20 * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
21 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
22 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
23 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
24 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
25 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
26 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
27 * SUCH DAMAGE.
28 */
29
30#ifndef lint
31static const char copyright[] =
32"@(#) Copyright (c) 1987, 1993, 1994, 1995\n\
33	The Regents of the University of California.  All rights reserved.\n";
34#endif
35
36#if 0
37#ifndef lint
38static char sccsid[] = "@(#)ctags.c	8.4 (Berkeley) 2/7/95";
39#endif
40#endif
41
42#include <sys/cdefs.h>
43#include <sys/types.h>
44#include <sys/wait.h>
45__FBSDID("$FreeBSD$");
46
47#include <err.h>
48#include <limits.h>
49#include <locale.h>
50#include <regex.h>
51#include <stdio.h>
52#include <stdlib.h>
53#include <string.h>
54#include <unistd.h>
55
56#include "ctags.h"
57
58/*
59 * ctags: create a tags file
60 */
61
62NODE	*head;			/* head of the sorted binary tree */
63
64				/* boolean "func" (see init()) */
65bool	_wht[256], _etk[256], _itk[256], _btk[256], _gd[256];
66
67FILE	*inf;			/* ioptr for current input file */
68FILE	*outf;			/* ioptr for tags file */
69
70long	lineftell;		/* ftell after getc( inf ) == '\n' */
71
72int	lineno;			/* line number of current line */
73int	dflag;			/* -d: non-macro defines */
74int	tflag;			/* -t: create tags for typedefs */
75int	vflag;			/* -v: vgrind style index output */
76int	wflag;			/* -w: suppress warnings */
77int	xflag;			/* -x: cxref style output */
78
79char	*curfile;		/* current input file name */
80char	searchar = '/';		/* use /.../ searches by default */
81char	lbuf[LINE_MAX];
82
83void	init(void);
84void	find_entries(char *);
85static void usage(void);
86
87int
88main(int argc, char **argv)
89{
90	static const char	*outfile = "tags";	/* output file */
91	int	aflag;				/* -a: append to tags */
92	int	uflag;				/* -u: update tags */
93	int	exit_val;			/* exit value */
94	int	step;				/* step through args */
95	int	ch;				/* getopts char */
96
97	setlocale(LC_ALL, "");
98
99	aflag = uflag = NO;
100	tflag = YES;
101	while ((ch = getopt(argc, argv, "BFTadf:tuwvx")) != -1)
102		switch(ch) {
103		case 'B':
104			searchar = '?';
105			break;
106		case 'F':
107			searchar = '/';
108			break;
109		case 'T':
110			tflag = NO;
111			break;
112		case 'a':
113			aflag++;
114			break;
115		case 'd':
116			dflag++;
117			break;
118		case 'f':
119			outfile = optarg;
120			break;
121		case 't':
122			tflag = YES;
123			break;
124		case 'u':
125			uflag++;
126			break;
127		case 'w':
128			wflag++;
129			break;
130		case 'v':
131			vflag++;
132		case 'x':
133			xflag++;
134			break;
135		case '?':
136		default:
137			usage();
138		}
139	argv += optind;
140	argc -= optind;
141	if (!argc)
142		usage();
143
144	if (!xflag)
145		setlocale(LC_COLLATE, "C");
146
147	init();
148
149	for (exit_val = step = 0; step < argc; ++step)
150		if (!(inf = fopen(argv[step], "r"))) {
151			warn("%s", argv[step]);
152			exit_val = 1;
153		}
154		else {
155			curfile = argv[step];
156			find_entries(argv[step]);
157			(void)fclose(inf);
158		}
159
160	if (head) {
161		if (xflag)
162			put_entries(head);
163		else {
164			if (uflag) {
165				FILE *oldf;
166				regex_t *regx;
167
168				if ((oldf = fopen(outfile, "r")) == NULL)
169					err(1, "opening %s", outfile);
170				if (unlink(outfile))
171					err(1, "unlinking %s", outfile);
172				if ((outf = fopen(outfile, "w")) == NULL)
173					err(1, "recreating %s", outfile);
174				if ((regx = calloc(argc, sizeof(regex_t))) == NULL)
175					err(1, "RE alloc");
176				for (step = 0; step < argc; step++) {
177					(void)strcpy(lbuf, "\t");
178					(void)strlcat(lbuf, argv[step], LINE_MAX);
179					(void)strlcat(lbuf, "\t", LINE_MAX);
180					if (regcomp(regx + step, lbuf,
181					    REG_NOSPEC))
182						warn("RE compilation failed");
183				}
184nextline:
185				while (fgets(lbuf, LINE_MAX, oldf)) {
186					for (step = 0; step < argc; step++)
187						if (regexec(regx + step,
188						    lbuf, 0, NULL, 0) == 0)
189							goto nextline;
190					fputs(lbuf, outf);
191				}
192				for (step = 0; step < argc; step++)
193					regfree(regx + step);
194				free(regx);
195				fclose(oldf);
196				fclose(outf);
197				++aflag;
198			}
199			if (!(outf = fopen(outfile, aflag ? "a" : "w")))
200				err(1, "%s", outfile);
201			put_entries(head);
202			(void)fclose(outf);
203			if (uflag) {
204				pid_t pid;
205
206				if ((pid = fork()) == -1)
207					err(1, "fork failed");
208				else if (pid == 0) {
209					execlp("sort", "sort", "-o", outfile,
210					    outfile, NULL);
211					err(1, "exec of sort failed");
212				}
213				/* Just assume the sort went OK. The old code
214				   did not do any checks either. */
215				(void)wait(NULL);
216			}
217		}
218	}
219	exit(exit_val);
220}
221
222static void
223usage(void)
224{
225	(void)fprintf(stderr, "usage: ctags [-BFTaduwvx] [-f tagsfile] file ...\n");
226	exit(1);
227}
228
229/*
230 * init --
231 *	this routine sets up the boolean pseudo-functions which work by
232 *	setting boolean flags dependent upon the corresponding character.
233 *	Every char which is NOT in that string is false with respect to
234 *	the pseudo-function.  Therefore, all of the array "_wht" is NO
235 *	by default and then the elements subscripted by the chars in
236 *	CWHITE are set to YES.  Thus, "_wht" of a char is YES if it is in
237 *	the string CWHITE, else NO.
238 */
239void
240init(void)
241{
242	int		i;
243	const unsigned char	*sp;
244
245	for (i = 0; i < 256; i++) {
246		_wht[i] = _etk[i] = _itk[i] = _btk[i] = NO;
247		_gd[i] = YES;
248	}
249#define	CWHITE	" \f\t\n"
250	for (sp = CWHITE; *sp; sp++)	/* white space chars */
251		_wht[*sp] = YES;
252#define	CTOKEN	" \t\n\"'#()[]{}=-+%*/&|^~!<>;,.:?"
253	for (sp = CTOKEN; *sp; sp++)	/* token ending chars */
254		_etk[*sp] = YES;
255#define	CINTOK	"ABCDEFGHIJKLMNOPQRSTUVWXYZ_abcdefghijklmnopqrstuvwxyz0123456789"
256	for (sp = CINTOK; *sp; sp++)	/* valid in-token chars */
257		_itk[*sp] = YES;
258#define	CBEGIN	"ABCDEFGHIJKLMNOPQRSTUVWXYZ_abcdefghijklmnopqrstuvwxyz"
259	for (sp = CBEGIN; *sp; sp++)	/* token starting chars */
260		_btk[*sp] = YES;
261#define	CNOTGD	",;"
262	for (sp = CNOTGD; *sp; sp++)	/* invalid after-function chars */
263		_gd[*sp] = NO;
264}
265
266/*
267 * find_entries --
268 *	this routine opens the specified file and calls the function
269 *	which searches the file.
270 */
271void
272find_entries(char *file)
273{
274	char	*cp;
275
276	lineno = 0;				/* should be 1 ?? KB */
277	if ((cp = strrchr(file, '.'))) {
278		if (cp[1] == 'l' && !cp[2]) {
279			int	c;
280
281			for (;;) {
282				if (GETC(==, EOF))
283					return;
284				if (!iswhite(c)) {
285					rewind(inf);
286					break;
287				}
288			}
289#define	LISPCHR	";(["
290/* lisp */		if (strchr(LISPCHR, c)) {
291				l_entries();
292				return;
293			}
294/* lex */		else {
295				/*
296				 * we search all 3 parts of a lex file
297				 * for C references.  This may be wrong.
298				 */
299				toss_yysec();
300				(void)strcpy(lbuf, "%%$");
301				pfnote("yylex", lineno);
302				rewind(inf);
303			}
304		}
305/* yacc */	else if (cp[1] == 'y' && !cp[2]) {
306			/*
307			 * we search only the 3rd part of a yacc file
308			 * for C references.  This may be wrong.
309			 */
310			toss_yysec();
311			(void)strcpy(lbuf, "%%$");
312			pfnote("yyparse", lineno);
313			y_entries();
314		}
315/* fortran */	else if ((cp[1] != 'c' && cp[1] != 'h') && !cp[2]) {
316			if (PF_funcs())
317				return;
318			rewind(inf);
319		}
320	}
321/* C */	c_entries();
322}
323