1/*	$NetBSD: fparseln.c,v 1.7 2007/03/08 19:57:53 drochner Exp $	*/
2
3/*-
4 * SPDX-License-Identifier: BSD-4-Clause
5 *
6 * Copyright (c) 1997 Christos Zoulas.  All rights reserved.
7 *
8 * Redistribution and use in source and binary forms, with or without
9 * modification, are permitted provided that the following conditions
10 * are met:
11 * 1. Redistributions of source code must retain the above copyright
12 *    notice, this list of conditions and the following disclaimer.
13 * 2. Redistributions in binary form must reproduce the above copyright
14 *    notice, this list of conditions and the following disclaimer in the
15 *    documentation and/or other materials provided with the distribution.
16 * 3. All advertising materials mentioning features or use of this software
17 *    must display the following acknowledgement:
18 *	This product includes software developed by Christos Zoulas.
19 * 4. The name of the author may not be used to endorse or promote products
20 *    derived from this software without specific prior written permission.
21 *
22 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR
23 * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
24 * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
25 * IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT,
26 * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
27 * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
28 * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
29 * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
30 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
31 * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
32 */
33
34#include <sys/cdefs.h>
35__FBSDID("$FreeBSD$");
36
37#include <sys/types.h>
38#include <assert.h>
39#include <errno.h>
40#include <stdio.h>
41#include <string.h>
42#include <stdlib.h>
43#include <libutil.h>
44
45static int isescaped(const char *, const char *, int);
46
47/* isescaped():
48 *	Return true if the character in *p that belongs to a string
49 *	that starts in *sp, is escaped by the escape character esc.
50 */
51static int
52isescaped(const char *sp, const char *p, int esc)
53{
54	const char     *cp;
55	size_t		ne;
56
57#if 0
58	_DIAGASSERT(sp != NULL);
59	_DIAGASSERT(p != NULL);
60#endif
61
62	/* No escape character */
63	if (esc == '\0')
64		return 0;
65
66	/* Count the number of escape characters that precede ours */
67	for (ne = 0, cp = p; --cp >= sp && *cp == esc; ne++)
68		continue;
69
70	/* Return true if odd number of escape characters */
71	return (ne & 1) != 0;
72}
73
74
75/* fparseln():
76 *	Read a line from a file parsing continuations ending in \
77 *	and eliminating trailing newlines, or comments starting with
78 *	the comment char.
79 */
80char *
81fparseln(FILE *fp, size_t *size, size_t *lineno, const char str[3], int flags)
82{
83	static const char dstr[3] = { '\\', '\\', '#' };
84
85	size_t	s, len;
86	char   *buf;
87	char   *ptr, *cp;
88	int	cnt;
89	char	esc, con, nl, com;
90
91#if 0
92	_DIAGASSERT(fp != NULL);
93#endif
94
95	len = 0;
96	buf = NULL;
97	cnt = 1;
98
99	if (str == NULL)
100		str = dstr;
101
102	esc = str[0];
103	con = str[1];
104	com = str[2];
105	/*
106	 * XXX: it would be cool to be able to specify the newline character,
107	 * but unfortunately, fgetln does not let us
108	 */
109	nl  = '\n';
110
111	while (cnt) {
112		cnt = 0;
113
114		if (lineno)
115			(*lineno)++;
116
117		if ((ptr = fgetln(fp, &s)) == NULL)
118			break;
119
120		if (s && com) {		/* Check and eliminate comments */
121			for (cp = ptr; cp < ptr + s; cp++)
122				if (*cp == com && !isescaped(ptr, cp, esc)) {
123					s = cp - ptr;
124					cnt = s == 0 && buf == NULL;
125					break;
126				}
127		}
128
129		if (s && nl) { 		/* Check and eliminate newlines */
130			cp = &ptr[s - 1];
131
132			if (*cp == nl)
133				s--;	/* forget newline */
134		}
135
136		if (s && con) {		/* Check and eliminate continuations */
137			cp = &ptr[s - 1];
138
139			if (*cp == con && !isescaped(ptr, cp, esc)) {
140				s--;	/* forget continuation char */
141				cnt = 1;
142			}
143		}
144
145		if (s == 0) {
146			/*
147			 * nothing to add, skip realloc except in case
148			 * we need a minimal buf to return an empty line
149			 */
150			if (cnt || buf != NULL)
151				continue;
152		}
153
154		if ((cp = realloc(buf, len + s + 1)) == NULL) {
155			free(buf);
156			return NULL;
157		}
158		buf = cp;
159
160		(void) memcpy(buf + len, ptr, s);
161		len += s;
162		buf[len] = '\0';
163	}
164
165	if ((flags & FPARSELN_UNESCALL) != 0 && esc && buf != NULL &&
166	    strchr(buf, esc) != NULL) {
167		ptr = cp = buf;
168		while (cp[0] != '\0') {
169			int skipesc;
170
171			while (cp[0] != '\0' && cp[0] != esc)
172				*ptr++ = *cp++;
173			if (cp[0] == '\0' || cp[1] == '\0')
174				break;
175
176			skipesc = 0;
177			if (cp[1] == com)
178				skipesc += (flags & FPARSELN_UNESCCOMM);
179			if (cp[1] == con)
180				skipesc += (flags & FPARSELN_UNESCCONT);
181			if (cp[1] == esc)
182				skipesc += (flags & FPARSELN_UNESCESC);
183			if (cp[1] != com && cp[1] != con && cp[1] != esc)
184				skipesc = (flags & FPARSELN_UNESCREST);
185
186			if (skipesc)
187				cp++;
188			else
189				*ptr++ = *cp++;
190			*ptr++ = *cp++;
191		}
192		*ptr = '\0';
193		len = strlen(buf);
194	}
195
196	if (size)
197		*size = len;
198	return buf;
199}
200
201#ifdef TEST
202
203int
204main(int argc, char *argv[])
205{
206	char   *ptr;
207	size_t	size, line;
208
209	line = 0;
210	while ((ptr = fparseln(stdin, &size, &line, NULL,
211	    FPARSELN_UNESCALL)) != NULL)
212		printf("line %d (%d) |%s|\n", line, size, ptr);
213	return 0;
214}
215
216/*
217
218# This is a test
219line 1
220line 2 \
221line 3 # Comment
222line 4 \# Not comment \\\\
223
224# And a comment \
225line 5 \\\
226line 6
227
228*/
229
230#endif /* TEST */
231