1 /* $NetBSD: fparseln.c,v 1.9 1999/09/20 04:48:06 lukem Exp $ */
2
3 /*
4 * Copyright (c) 1997 Christos Zoulas. All rights reserved.
5 *
6 * Redistribution and use in source and binary forms, with or without
7 * modification, are permitted provided that the following conditions
8 * are met:
9 * 1. Redistributions of source code must retain the above copyright
10 * notice, this list of conditions and the following disclaimer.
11 * 2. Redistributions in binary form must reproduce the above copyright
12 * notice, this list of conditions and the following disclaimer in the
13 * documentation and/or other materials provided with the distribution.
14 * 3. All advertising materials mentioning features or use of this software
15 * must display the following acknowledgement:
16 * This product includes software developed by Christos Zoulas.
17 * 4. The name of the author may not be used to endorse or promote products
18 * derived from this software without specific prior written permission.
19 *
20 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR
21 * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
22 * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
23 * IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT,
24 * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
25 * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
26 * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
27 * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
28 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
29 * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
30 */
31
32 #include <stdio.h>
33 #include <string.h>
34 #include <stdlib.h>
35 #include <compat.h>
36
37 static int isescaped(const char *, const char *, int);
38
39 /* isescaped():
40 * Return true if the character in *p that belongs to a string
41 * that starts in *sp, is escaped by the escape character esc.
42 */
43 static int
44 isescaped(const char *sp, const char *p, int esc)
45 {
46 const char *cp;
47 size_t ne;
48
49 /* No escape character */
50 if (esc == '\0')
51 return 1;
52
53 /* Count the number of escape characters that precede ours */
54 for (ne = 0, cp = p; --cp >= sp && *cp == esc; ne++)
55 continue;
56
57 /* Return true if odd number of escape characters */
58 return (ne & 1) != 0;
59 }
60
61
62 /* fparseln():
63 * Read a line from a file parsing continuations ending in \
64 * and eliminating trailing newlines, or comments starting with
65 * the comment char.
66 */
67 char *
68 fparseln(FILE *fp, size_t *size, size_t *lineno, const char str[3], int flags)
69 {
70 static const char dstr[3] = { '\\', '\\', '#' };
71
72 size_t s, len;
73 char *buf;
74 char *ptr, *cp;
75 int cnt;
76 char esc, con, nl, com;
77
78 len = 0;
79 buf = NULL;
80 cnt = 1;
81
82 if (str == NULL)
83 str = dstr;
84
85 esc = str[0];
86 con = str[1];
87 com = str[2];
88 /*
89 * XXX: it would be cool to be able to specify the newline character,
90 * but unfortunately, fgetln does not let us
91 */
92 nl = '\n';
93
94 while (cnt) {
95 cnt = 0;
96
97 if (lineno)
98 (*lineno)++;
99
100 if ((ptr = fgetln(fp, &s)) == NULL)
101 break;
102
103 if (s && com) { /* Check and eliminate comments */
104 for (cp = ptr; cp < ptr + s; cp++)
105 if (*cp == com && !isescaped(ptr, cp, esc)) {
106 s = cp - ptr;
107 cnt = s == 0 && buf == NULL;
108 break;
109 }
110 }
111
112 if (s && nl) { /* Check and eliminate newlines */
113 cp = &ptr[s - 1];
114
115 if (*cp == nl)
116 s--; /* forget newline */
117 }
118
119 if (s && con) { /* Check and eliminate continuations */
120 cp = &ptr[s - 1];
121
122 if (*cp == con && !isescaped(ptr, cp, esc)) {
123 s--; /* forget escape */
124 cnt = 1;
125 }
126 }
127
128 if (s == 0 && buf != NULL)
129 continue;
130
131 if ((cp = realloc(buf, len + s + 1)) == NULL) {
132 free(buf);
133 return NULL;
134 }
135 buf = cp;
136
137 (void) memcpy(buf + len, ptr, s);
138 len += s;
139 buf[len] = '\0';
140 }
141
142 if ((flags & FPARSELN_UNESCALL) != 0 && esc && buf != NULL &&
143 strchr(buf, esc) != NULL) {
144 ptr = cp = buf;
145 while (cp[0] != '\0') {
146 int skipesc;
147
148 while (cp[0] != '\0' && cp[0] != esc)
149 *ptr++ = *cp++;
150 if (cp[0] == '\0' || cp[1] == '\0')
151 break;
152
153 skipesc = 0;
154 if (cp[1] == com)
155 skipesc += (flags & FPARSELN_UNESCCOMM);
156 if (cp[1] == con)
157 skipesc += (flags & FPARSELN_UNESCCONT);
158 if (cp[1] == esc)
159 skipesc += (flags & FPARSELN_UNESCESC);
160 if (cp[1] != com && cp[1] != con && cp[1] != esc)
161 skipesc = (flags & FPARSELN_UNESCREST);
162
163 if (skipesc)
164 cp++;
165 else
166 *ptr++ = *cp++;
167 *ptr++ = *cp++;
168 }
169 *ptr = '\0';
170 len = strlen(buf);
171 }
172
173 if (size)
174 *size = len;
175 return buf;
176 }
177
178 #ifdef TEST
179
180 int
181 main(int argc, char *argv[])
182 {
183 char *ptr;
184 size_t size, line;
185
186 line = 0;
187 while ((ptr = fparseln(stdin, &size, &line, NULL,
188 FPARSELN_UNESCALL)) != NULL)
189 printf("line %d (%d) |%s|\n", line, size, ptr);
190 return 0;
191 }
192
193 /*
194
195 # This is a test
196 line 1
197 line 2 \
198 line 3 # Comment
199 line 4 \# Not comment \\\\
200
201 # And a comment \
202 line 5 \\\
203 line 6
204
205 */
206
207 #endif /* TEST */