util/fparseln.c

   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 <sys/cdefs.h>
  33 __FBSDID("$FreeBSD: src/lib/libutil/fparseln.c,v 1.5 2002/03/21 23:52:49 obrien Exp $");
  34
  35 #include <sys/types.h>
  36 #include <assert.h>
  37 #include <errno.h>
  38 #include <stdio.h>
  39 #include <string.h>
  40 #include <stdlib.h>
  41 #include <util.h>
  42
  43 static int isescaped(const char *, const char *, int);
  44
  45 /* isescaped():
  46  *      Return true if the character in *p that belongs to a string
  47  *      that starts in *sp, is escaped by the escape character esc.
  48  */
  49 static int
  50 isescaped(sp, p, esc)
  51         const char *sp, *p;
  52         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 1;
  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  */
  80 char *
  81 fparseln(fp, size, lineno, str, flags)
  82         FILE            *fp;
  83         size_t          *size;
  84         size_t          *lineno;
  85         const char       str[3];
  86         int              flags;
  87 {
  88         static const char dstr[3] = { '\\', '\\', '#' };
  89
  90         size_t  s, len;
  91         char   *buf;
  92         char   *ptr, *cp;
  93         int     cnt;
  94         char    esc, con, nl, com;
  95
  96 #if 0
  97         _DIAGASSERT(fp != NULL);
  98 #endif
  99
 100         len = 0;
 101         buf = NULL;
 102         cnt = 1;
 103
 104         if (str == NULL)
 105                 str = dstr;
 106
 107         esc = str[0];
 108         con = str[1];
 109         com = str[2];
 110         /*
 111          * XXX: it would be cool to be able to specify the newline character,
 112          * but unfortunately, fgetln does not let us
 113          */
 114         nl  = '\n';
 115
 116         while (cnt) {
 117                 cnt = 0;
 118
 119                 if (lineno)
 120                         (*lineno)++;
 121
 122                 if ((ptr = fgetln(fp, &s)) == NULL)
 123                         break;
 124
 125                 if (s && com) {         /* Check and eliminate comments */
 126                         for (cp = ptr; cp < ptr + s; cp++)
 127                                 if (*cp == com && !isescaped(ptr, cp, esc)) {
 128                                         s = cp - ptr;
 129                                         cnt = s == 0 && buf == NULL;
 130                                         break;
 131                                 }
 132                 }
 133
 134                 if (s && nl) {          /* Check and eliminate newlines */
 135                         cp = &ptr[s - 1];
 136
 137                         if (*cp == nl)
 138                                 s--;    /* forget newline */
 139                 }
 140
 141                 if (s && con) {         /* Check and eliminate continuations */
 142                         cp = &ptr[s - 1];
 143
 144                         if (*cp == con && !isescaped(ptr, cp, esc)) {
 145                                 s--;    /* forget escape */
 146                                 cnt = 1;
 147                         }
 148                 }
 149
 150                 if (s == 0 && buf != NULL)
 151                         continue;
 152
 153                 if ((cp = realloc(buf, len + s + 1)) == NULL) {
 154                         free(buf);
 155                         return NULL;
 156                 }
 157                 buf = cp;
 158
 159                 (void) memcpy(buf + len, ptr, s);
 160                 len += s;
 161                 buf[len] = '\0';
 162         }
 163
 164         if ((flags & FPARSELN_UNESCALL) != 0 && esc && buf != NULL &&
 165             strchr(buf, esc) != NULL) {
 166                 ptr = cp = buf;
 167                 while (cp[0] != '\0') {
 168                         int skipesc;
 169
 170                         while (cp[0] != '\0' && cp[0] != esc)
 171                                 *ptr++ = *cp++;
 172                         if (cp[0] == '\0' || cp[1] == '\0')
 173                                 break;
 174
 175                         skipesc = 0;
 176                         if (cp[1] == com)
 177                                 skipesc += (flags & FPARSELN_UNESCCOMM);
 178                         if (cp[1] == con)
 179                                 skipesc += (flags & FPARSELN_UNESCCONT);
 180                         if (cp[1] == esc)
 181                                 skipesc += (flags & FPARSELN_UNESCESC);
 182                         if (cp[1] != com && cp[1] != con && cp[1] != esc)
 183                                 skipesc = (flags & FPARSELN_UNESCREST);
 184
 185                         if (skipesc)
 186                                 cp++;
 187                         else
 188                                 *ptr++ = *cp++;
 189                         *ptr++ = *cp++;
 190                 }
 191                 *ptr = '\0';
 192                 len = strlen(buf);
 193         }
 194
 195         if (size)
 196                 *size = len;
 197         return buf;
 198 }
 199
 200 #ifdef TEST
 201
 202 int main(int, char **);
 203
 204 int
 205 main(argc, argv)
 206         int argc;
 207         char **argv;
 208 {
 209         char   *ptr;
 210         size_t  size, line;
 211
 212         line = 0;
 213         while ((ptr = fparseln(stdin, &size, &line, NULL,
 214             FPARSELN_UNESCALL)) != NULL)
 215                 printf("line %d (%d) |%s|\n", line, size, ptr);
 216         return 0;
 217 }
 218
 219 /*
 220
 221 # This is a test
 222 line 1
 223 line 2 \
 224 line 3 # Comment
 225 line 4 \# Not comment \\\\
 226
 227 # And a comment \
 228 line 5 \\\
 229 line 6
 230
 231 */
 232
 233 #endif /* TEST */