xref: /freebsd/usr.bin/ctags/ctags.c (revision 42249ef2)
1 /*-
2  * SPDX-License-Identifier: BSD-3-Clause
3  *
4  * Copyright (c) 1987, 1993, 1994, 1995
5  *	The Regents of the University of California.  All rights reserved.
6  *
7  * Redistribution and use in source and binary forms, with or without
8  * modification, are permitted provided that the following conditions
9  * are met:
10  * 1. Redistributions of source code must retain the above copyright
11  *    notice, this list of conditions and the following disclaimer.
12  * 2. Redistributions in binary form must reproduce the above copyright
13  *    notice, this list of conditions and the following disclaimer in the
14  *    documentation and/or other materials provided with the distribution.
15  * 3. Neither the name of the University nor the names of its contributors
16  *    may be used to endorse or promote products derived from this software
17  *    without specific prior written permission.
18  *
19  * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
20  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
21  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
22  * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
23  * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
24  * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
25  * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
26  * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
27  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
28  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
29  * SUCH DAMAGE.
30  */
31 
32 #ifndef lint
33 static const char copyright[] =
34 "@(#) Copyright (c) 1987, 1993, 1994, 1995\n\
35 	The Regents of the University of California.  All rights reserved.\n";
36 #endif
37 
38 #if 0
39 #ifndef lint
40 static char sccsid[] = "@(#)ctags.c	8.4 (Berkeley) 2/7/95";
41 #endif
42 #endif
43 
44 #include <sys/cdefs.h>
45 #include <sys/types.h>
46 #include <sys/wait.h>
47 __FBSDID("$FreeBSD$");
48 
49 #include <err.h>
50 #include <limits.h>
51 #include <locale.h>
52 #include <regex.h>
53 #include <stdio.h>
54 #include <stdlib.h>
55 #include <string.h>
56 #include <unistd.h>
57 
58 #include "ctags.h"
59 
60 /*
61  * ctags: create a tags file
62  */
63 
64 NODE	*head;			/* head of the sorted binary tree */
65 
66 				/* boolean "func" (see init()) */
67 bool	_wht[256], _etk[256], _itk[256], _btk[256], _gd[256];
68 
69 FILE	*inf;			/* ioptr for current input file */
70 FILE	*outf;			/* ioptr for tags file */
71 
72 long	lineftell;		/* ftell after getc( inf ) == '\n' */
73 
74 int	lineno;			/* line number of current line */
75 int	dflag;			/* -d: non-macro defines */
76 int	tflag;			/* -t: create tags for typedefs */
77 int	vflag;			/* -v: vgrind style index output */
78 int	wflag;			/* -w: suppress warnings */
79 int	xflag;			/* -x: cxref style output */
80 
81 char	*curfile;		/* current input file name */
82 char	searchar = '/';		/* use /.../ searches by default */
83 char	lbuf[LINE_MAX];
84 
85 void	init(void);
86 void	find_entries(char *);
87 static void usage(void);
88 
89 int
90 main(int argc, char **argv)
91 {
92 	static const char	*outfile = "tags";	/* output file */
93 	int	aflag;				/* -a: append to tags */
94 	int	uflag;				/* -u: update tags */
95 	int	exit_val;			/* exit value */
96 	int	step;				/* step through args */
97 	int	ch;				/* getopts char */
98 
99 	setlocale(LC_ALL, "");
100 
101 	aflag = uflag = NO;
102 	tflag = YES;
103 	while ((ch = getopt(argc, argv, "BFTadf:tuwvx")) != -1)
104 		switch(ch) {
105 		case 'B':
106 			searchar = '?';
107 			break;
108 		case 'F':
109 			searchar = '/';
110 			break;
111 		case 'T':
112 			tflag = NO;
113 			break;
114 		case 'a':
115 			aflag++;
116 			break;
117 		case 'd':
118 			dflag++;
119 			break;
120 		case 'f':
121 			outfile = optarg;
122 			break;
123 		case 't':
124 			tflag = YES;
125 			break;
126 		case 'u':
127 			uflag++;
128 			break;
129 		case 'w':
130 			wflag++;
131 			break;
132 		case 'v':
133 			vflag++;
134 		case 'x':
135 			xflag++;
136 			break;
137 		case '?':
138 		default:
139 			usage();
140 		}
141 	argv += optind;
142 	argc -= optind;
143 	if (!argc)
144 		usage();
145 
146 	if (!xflag)
147 		setlocale(LC_COLLATE, "C");
148 
149 	init();
150 
151 	for (exit_val = step = 0; step < argc; ++step)
152 		if (!(inf = fopen(argv[step], "r"))) {
153 			warn("%s", argv[step]);
154 			exit_val = 1;
155 		}
156 		else {
157 			curfile = argv[step];
158 			find_entries(argv[step]);
159 			(void)fclose(inf);
160 		}
161 
162 	if (head) {
163 		if (xflag)
164 			put_entries(head);
165 		else {
166 			if (uflag) {
167 				FILE *oldf;
168 				regex_t *regx;
169 
170 				if ((oldf = fopen(outfile, "r")) == NULL)
171 					err(1, "opening %s", outfile);
172 				if (unlink(outfile))
173 					err(1, "unlinking %s", outfile);
174 				if ((outf = fopen(outfile, "w")) == NULL)
175 					err(1, "recreating %s", outfile);
176 				if ((regx = calloc(argc, sizeof(regex_t))) == NULL)
177 					err(1, "RE alloc");
178 				for (step = 0; step < argc; step++) {
179 					(void)strcpy(lbuf, "\t");
180 					(void)strlcat(lbuf, argv[step], LINE_MAX);
181 					(void)strlcat(lbuf, "\t", LINE_MAX);
182 					if (regcomp(regx + step, lbuf,
183 					    REG_NOSPEC))
184 						warn("RE compilation failed");
185 				}
186 nextline:
187 				while (fgets(lbuf, LINE_MAX, oldf)) {
188 					for (step = 0; step < argc; step++)
189 						if (regexec(regx + step,
190 						    lbuf, 0, NULL, 0) == 0)
191 							goto nextline;
192 					fputs(lbuf, outf);
193 				}
194 				for (step = 0; step < argc; step++)
195 					regfree(regx + step);
196 				free(regx);
197 				fclose(oldf);
198 				fclose(outf);
199 				++aflag;
200 			}
201 			if (!(outf = fopen(outfile, aflag ? "a" : "w")))
202 				err(1, "%s", outfile);
203 			put_entries(head);
204 			(void)fclose(outf);
205 			if (uflag) {
206 				pid_t pid;
207 
208 				if ((pid = fork()) == -1)
209 					err(1, "fork failed");
210 				else if (pid == 0) {
211 					execlp("sort", "sort", "-o", outfile,
212 					    outfile, NULL);
213 					err(1, "exec of sort failed");
214 				}
215 				/* Just assume the sort went OK. The old code
216 				   did not do any checks either. */
217 				(void)wait(NULL);
218 			}
219 		}
220 	}
221 	exit(exit_val);
222 }
223 
224 static void
225 usage(void)
226 {
227 	(void)fprintf(stderr, "usage: ctags [-BFTaduwvx] [-f tagsfile] file ...\n");
228 	exit(1);
229 }
230 
231 /*
232  * init --
233  *	this routine sets up the boolean pseudo-functions which work by
234  *	setting boolean flags dependent upon the corresponding character.
235  *	Every char which is NOT in that string is false with respect to
236  *	the pseudo-function.  Therefore, all of the array "_wht" is NO
237  *	by default and then the elements subscripted by the chars in
238  *	CWHITE are set to YES.  Thus, "_wht" of a char is YES if it is in
239  *	the string CWHITE, else NO.
240  */
241 void
242 init(void)
243 {
244 	int		i;
245 	const unsigned char	*sp;
246 
247 	for (i = 0; i < 256; i++) {
248 		_wht[i] = _etk[i] = _itk[i] = _btk[i] = NO;
249 		_gd[i] = YES;
250 	}
251 #define	CWHITE	" \f\t\n"
252 	for (sp = CWHITE; *sp; sp++)	/* white space chars */
253 		_wht[*sp] = YES;
254 #define	CTOKEN	" \t\n\"'#()[]{}=-+%*/&|^~!<>;,.:?"
255 	for (sp = CTOKEN; *sp; sp++)	/* token ending chars */
256 		_etk[*sp] = YES;
257 #define	CINTOK	"ABCDEFGHIJKLMNOPQRSTUVWXYZ_abcdefghijklmnopqrstuvwxyz0123456789"
258 	for (sp = CINTOK; *sp; sp++)	/* valid in-token chars */
259 		_itk[*sp] = YES;
260 #define	CBEGIN	"ABCDEFGHIJKLMNOPQRSTUVWXYZ_abcdefghijklmnopqrstuvwxyz"
261 	for (sp = CBEGIN; *sp; sp++)	/* token starting chars */
262 		_btk[*sp] = YES;
263 #define	CNOTGD	",;"
264 	for (sp = CNOTGD; *sp; sp++)	/* invalid after-function chars */
265 		_gd[*sp] = NO;
266 }
267 
268 /*
269  * find_entries --
270  *	this routine opens the specified file and calls the function
271  *	which searches the file.
272  */
273 void
274 find_entries(char *file)
275 {
276 	char	*cp;
277 
278 	lineno = 0;				/* should be 1 ?? KB */
279 	if ((cp = strrchr(file, '.'))) {
280 		if (cp[1] == 'l' && !cp[2]) {
281 			int	c;
282 
283 			for (;;) {
284 				if (GETC(==, EOF))
285 					return;
286 				if (!iswhite(c)) {
287 					rewind(inf);
288 					break;
289 				}
290 			}
291 #define	LISPCHR	";(["
292 /* lisp */		if (strchr(LISPCHR, c)) {
293 				l_entries();
294 				return;
295 			}
296 /* lex */		else {
297 				/*
298 				 * we search all 3 parts of a lex file
299 				 * for C references.  This may be wrong.
300 				 */
301 				toss_yysec();
302 				(void)strcpy(lbuf, "%%$");
303 				pfnote("yylex", lineno);
304 				rewind(inf);
305 			}
306 		}
307 /* yacc */	else if (cp[1] == 'y' && !cp[2]) {
308 			/*
309 			 * we search only the 3rd part of a yacc file
310 			 * for C references.  This may be wrong.
311 			 */
312 			toss_yysec();
313 			(void)strcpy(lbuf, "%%$");
314 			pfnote("yyparse", lineno);
315 			y_entries();
316 		}
317 /* fortran */	else if ((cp[1] != 'c' && cp[1] != 'h') && !cp[2]) {
318 			if (PF_funcs())
319 				return;
320 			rewind(inf);
321 		}
322 	}
323 /* C */	c_entries();
324 }
325