1 /* $OpenBSD: fparseln.c,v 1.8 2023/01/04 13:00:11 jsg Exp $ */
2 /* $NetBSD: fparseln.c,v 1.7 1999/07/02 15:49:12 simonb Exp $ */
3
4 /*
5 * Copyright (c) 1997 Christos Zoulas. 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 *
16 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR
17 * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
18 * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
19 * IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT,
20 * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
21 * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
22 * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
23 * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
24 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
25 * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
26 */
27
28 #include <stdio.h>
29 #include <string.h>
30 #include <stdlib.h>
31
32 #include "util.h"
33
34 static int isescaped(const char *, const char *, int);
35
36 /* isescaped():
37 * Return true if the character in *p that belongs to a string
38 * that starts in *sp, is escaped by the escape character esc.
39 */
40 static int
isescaped(const char * sp,const char * p,int esc)41 isescaped(const char *sp, const char *p, int esc)
42 {
43 const char *cp;
44 size_t ne;
45
46 /* No escape character */
47 if (esc == '\0')
48 return 1;
49
50 /* Count the number of escape characters that precede ours */
51 for (ne = 0, cp = p; --cp >= sp && *cp == esc; ne++)
52 continue;
53
54 /* Return true if odd number of escape characters */
55 return (ne & 1) != 0;
56 }
57
58
59 /* fparseln():
60 * Read a line from a file parsing continuations ending in \
61 * and eliminating trailing newlines, or comments starting with
62 * the comment char.
63 */
64 char *
fparseln(FILE * fp,size_t * size,size_t * lineno,const char str[3],int flags)65 fparseln(FILE *fp, size_t *size, size_t *lineno, const char str[3],
66 int flags)
67 {
68 static const char dstr[3] = { '\\', '\\', '#' };
69 char *buf = NULL, *ptr, *cp, esc, con, nl, com;
70 size_t s, len = 0;
71 int cnt = 1;
72
73 if (str == NULL)
74 str = dstr;
75
76 esc = str[0];
77 con = str[1];
78 com = str[2];
79
80 /*
81 * XXX: it would be cool to be able to specify the newline character,
82 * but unfortunately, fgetln does not let us
83 */
84 nl = '\n';
85
86 while (cnt) {
87 cnt = 0;
88
89 if (lineno)
90 (*lineno)++;
91
92 if ((ptr = fgetln(fp, &s)) == NULL)
93 break;
94
95 if (s && com) { /* Check and eliminate comments */
96 for (cp = ptr; cp < ptr + s; cp++)
97 if (*cp == com && !isescaped(ptr, cp, esc)) {
98 s = cp - ptr;
99 cnt = s == 0 && buf == NULL;
100 break;
101 }
102 }
103
104 if (s && nl) { /* Check and eliminate newlines */
105 cp = &ptr[s - 1];
106
107 if (*cp == nl)
108 s--; /* forget newline */
109 }
110
111 if (s && con) { /* Check and eliminate continuations */
112 cp = &ptr[s - 1];
113
114 if (*cp == con && !isescaped(ptr, cp, esc)) {
115 s--; /* forget escape */
116 cnt = 1;
117 }
118 }
119
120 if (s == 0 && buf != NULL)
121 continue;
122
123 if ((cp = realloc(buf, len + s + 1)) == NULL) {
124 free(buf);
125 return NULL;
126 }
127 buf = cp;
128
129 (void) memcpy(buf + len, ptr, s);
130 len += s;
131 buf[len] = '\0';
132 }
133
134 if ((flags & FPARSELN_UNESCALL) != 0 && esc && buf != NULL &&
135 strchr(buf, esc) != NULL) {
136 ptr = cp = buf;
137 while (cp[0] != '\0') {
138 int skipesc;
139
140 while (cp[0] != '\0' && cp[0] != esc)
141 *ptr++ = *cp++;
142 if (cp[0] == '\0' || cp[1] == '\0')
143 break;
144
145 skipesc = 0;
146 if (cp[1] == com)
147 skipesc += (flags & FPARSELN_UNESCCOMM);
148 if (cp[1] == con)
149 skipesc += (flags & FPARSELN_UNESCCONT);
150 if (cp[1] == esc)
151 skipesc += (flags & FPARSELN_UNESCESC);
152 if (cp[1] != com && cp[1] != con && cp[1] != esc)
153 skipesc = (flags & FPARSELN_UNESCREST);
154
155 if (skipesc)
156 cp++;
157 else
158 *ptr++ = *cp++;
159 *ptr++ = *cp++;
160 }
161 *ptr = '\0';
162 len = strlen(buf);
163 }
164
165 if (size)
166 *size = len;
167 return buf;
168 }
169
170 #ifdef TEST
171
172 int main(int, char **);
173
174 int
main(argc,argv)175 main(argc, argv)
176 int argc;
177 char **argv;
178 {
179 char *ptr;
180 size_t size, line;
181
182 line = 0;
183 while ((ptr = fparseln(stdin, &size, &line, NULL,
184 FPARSELN_UNESCALL)) != NULL)
185 printf("line %d (%d) |%s|\n", line, size, ptr);
186 return 0;
187 }
188
189 /*
190
191 # This is a test
192 line 1
193 line 2 \
194 line 3 # Comment
195 line 4 \# Not comment \\\\
196
197 # And a comment \
198 line 5 \\\
199 line 6
200
201 */
202
203 #endif /* TEST */
204