1 /* $NetBSD: fparseln.c,v 1.10 2009/10/21 01:07:45 snj 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 *
15 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR
16 * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
17 * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
18 * IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT,
19 * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
20 * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
21 * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
22 * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
23 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
24 * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
25 */
26
27 #include <sys/types.h>
28 #include <assert.h>
29 #include <errno.h>
30 #include <stdio.h>
31 #include <string.h>
32 #include <stdlib.h>
33 #include <libutil.h>
34
35 static int isescaped(const char *, const char *, int);
36
37 /* isescaped():
38 * Return true if the character in *p that belongs to a string
39 * that starts in *sp, is escaped by the escape character esc.
40 */
41 static int
isescaped(const char * sp,const char * p,int esc)42 isescaped(const char *sp, const char *p, int esc)
43 {
44 const char *cp;
45 size_t ne;
46
47 #if 0
48 _DIAGASSERT(sp != NULL);
49 _DIAGASSERT(p != NULL);
50 #endif
51
52 /* No escape character */
53 if (esc == '\0')
54 return 0;
55
56 /* Count the number of escape characters that precede ours */
57 for (ne = 0, cp = p; --cp >= sp && *cp == esc; ne++)
58 continue;
59
60 /* Return true if odd number of escape characters */
61 return (ne & 1) != 0;
62 }
63
64
65 /* fparseln():
66 * Read a line from a file parsing continuations ending in \
67 * and eliminating trailing newlines, or comments starting with
68 * the comment char.
69 */
70 char *
fparseln(FILE * fp,size_t * size,size_t * lineno,const char str[3],int flags)71 fparseln(FILE *fp, size_t *size, size_t *lineno, const char str[3], int flags)
72 {
73 static const char dstr[3] = { '\\', '\\', '#' };
74
75 size_t s, len;
76 char *buf;
77 char *ptr, *cp;
78 int cnt;
79 char esc, con, nl, com;
80
81 #if 0
82 _DIAGASSERT(fp != NULL);
83 #endif
84
85 len = 0;
86 buf = NULL;
87 cnt = 1;
88
89 if (str == NULL)
90 str = dstr;
91
92 esc = str[0];
93 con = str[1];
94 com = str[2];
95 /*
96 * XXX: it would be cool to be able to specify the newline character,
97 * but unfortunately, fgetln does not let us
98 */
99 nl = '\n';
100
101 while (cnt) {
102 cnt = 0;
103
104 if (lineno)
105 (*lineno)++;
106
107 if ((ptr = fgetln(fp, &s)) == NULL)
108 break;
109
110 if (s && com) { /* Check and eliminate comments */
111 for (cp = ptr; cp < ptr + s; cp++)
112 if (*cp == com && !isescaped(ptr, cp, esc)) {
113 s = cp - ptr;
114 cnt = s == 0 && buf == NULL;
115 break;
116 }
117 }
118
119 if (s && nl) { /* Check and eliminate newlines */
120 cp = &ptr[s - 1];
121
122 if (*cp == nl)
123 s--; /* forget newline */
124 }
125
126 if (s && con) { /* Check and eliminate continuations */
127 cp = &ptr[s - 1];
128
129 if (*cp == con && !isescaped(ptr, cp, esc)) {
130 s--; /* forget continuation char */
131 cnt = 1;
132 }
133 }
134
135 if (s == 0) {
136 /*
137 * nothing to add, skip realloc except in case
138 * we need a minimal buf to return an empty line
139 */
140 if (cnt || buf != NULL)
141 continue;
142 }
143
144 if ((cp = realloc(buf, len + s + 1)) == NULL) {
145 free(buf);
146 return NULL;
147 }
148 buf = cp;
149
150 (void) memcpy(buf + len, ptr, s);
151 len += s;
152 buf[len] = '\0';
153 }
154
155 if ((flags & FPARSELN_UNESCALL) != 0 && esc && buf != NULL &&
156 strchr(buf, esc) != NULL) {
157 ptr = cp = buf;
158 while (cp[0] != '\0') {
159 int skipesc;
160
161 while (cp[0] != '\0' && cp[0] != esc)
162 *ptr++ = *cp++;
163 if (cp[0] == '\0' || cp[1] == '\0')
164 break;
165
166 skipesc = 0;
167 if (cp[1] == com)
168 skipesc += (flags & FPARSELN_UNESCCOMM);
169 if (cp[1] == con)
170 skipesc += (flags & FPARSELN_UNESCCONT);
171 if (cp[1] == esc)
172 skipesc += (flags & FPARSELN_UNESCESC);
173 if (cp[1] != com && cp[1] != con && cp[1] != esc)
174 skipesc = (flags & FPARSELN_UNESCREST);
175
176 if (skipesc)
177 cp++;
178 else
179 *ptr++ = *cp++;
180 *ptr++ = *cp++;
181 }
182 *ptr = '\0';
183 len = strlen(buf);
184 }
185
186 if (size)
187 *size = len;
188 return buf;
189 }
190
191 #ifdef TEST
192
193 int
main(int argc,char * argv[])194 main(int argc, char *argv[])
195 {
196 char *ptr;
197 size_t size, line;
198
199 line = 0;
200 while ((ptr = fparseln(stdin, &size, &line, NULL,
201 FPARSELN_UNESCALL)) != NULL)
202 printf("line %d (%d) |%s|\n", line, size, ptr);
203 return 0;
204 }
205
206 /*
207
208 # This is a test
209 line 1
210 line 2 \
211 line 3 # Comment
212 line 4 \# Not comment \\\\
213
214 # And a comment \
215 line 5 \\\
216 line 6
217
218 */
219
220 #endif /* TEST */
221