lib/libutil/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  * $FreeBSD: head/lib/libutil/fparseln.c 121193 2003-10-18 10:04:16Z markm $
  32  */
  33
  34 #include <sys/types.h>
  35 #include <assert.h>
  36 #include <errno.h>
  37 #include <stdio.h>
  38 #include <string.h>
  39 #include <stdlib.h>
  40 #include <libutil.h>
  41
  42 static int isescaped(const char *, const char *, int);
  43
  44 /* isescaped():
  45  *      Return true if the character in *p that belongs to a string
  46  *      that starts in *sp, is escaped by the escape character esc.
  47  */
  48 static int
  49 isescaped(const char *sp, const char *p, int esc)
  50 {
  51         const char     *cp;
  52         size_t          ne;
  53
  54 #if 0
  55         _DIAGASSERT(sp != NULL);
  56         _DIAGASSERT(p != NULL);
  57 #endif
  58
  59         /* No escape character */
  60         if (esc == '\0')
  61                 return 1;
  62
  63         /* Count the number of escape characters that precede ours */
  64         for (ne = 0, cp = p; --cp >= sp && *cp == esc; ne++)
  65                 continue;
  66
  67         /* Return true if odd number of escape characters */
  68         return (ne & 1) != 0;
  69 }
  70
  71
  72 /* fparseln():
  73  *      Read a line from a file parsing continuations ending in \
  74  *      and eliminating trailing newlines, or comments starting with
  75  *      the comment char.
  76  */
  77 char *
  78 fparseln(FILE *fp, size_t *size, size_t *lineno, const char str[3], int flags)
  79 {
  80         static const char dstr[3] = { '\\', '\\', '#' };
  81
  82         size_t  s, len;
  83         char   *buf;
  84         char   *ptr, *cp;
  85         int     cnt;
  86         char    esc, con, nl, com;
  87
  88 #if 0
  89         _DIAGASSERT(fp != NULL);
  90 #endif
  91
  92         len = 0;
  93         buf = NULL;
  94         cnt = 1;
  95
  96         if (str == NULL)
  97                 str = dstr;
  98
  99         esc = str[0];
 100         con = str[1];
 101         com = str[2];
 102         /*
 103          * XXX: it would be cool to be able to specify the newline character,
 104          * but unfortunately, fgetln does not let us
 105          */
 106         nl  = '\n';
 107
 108         while (cnt) {
 109                 cnt = 0;
 110
 111                 if (lineno)
 112                         (*lineno)++;
 113
 114                 if ((ptr = fgetln(fp, &s)) == NULL)
 115                         break;
 116
 117                 if (s && com) {         /* Check and eliminate comments */
 118                         for (cp = ptr; cp < ptr + s; cp++)
 119                                 if (*cp == com && !isescaped(ptr, cp, esc)) {
 120                                         s = cp - ptr;
 121                                         cnt = s == 0 && buf == NULL;
 122                                         break;
 123                                 }
 124                 }
 125
 126                 if (s && nl) {          /* Check and eliminate newlines */
 127                         cp = &ptr[s - 1];
 128
 129                         if (*cp == nl)
 130                                 s--;    /* forget newline */
 131                 }
 132
 133                 if (s && con) {         /* Check and eliminate continuations */
 134                         cp = &ptr[s - 1];
 135
 136                         if (*cp == con && !isescaped(ptr, cp, esc)) {
 137                                 s--;    /* forget escape */
 138                                 cnt = 1;
 139                         }
 140                 }
 141
 142                 if (s == 0 && buf != NULL)
 143                         continue;
 144
 145                 if ((cp = realloc(buf, len + s + 1)) == NULL) {
 146                         free(buf);
 147                         return NULL;
 148                 }
 149                 buf = cp;
 150
 151                 (void) memcpy(buf + len, ptr, s);
 152                 len += s;
 153                 buf[len] = '\0';
 154         }
 155
 156         if ((flags & FPARSELN_UNESCALL) != 0 && esc && buf != NULL &&
 157             strchr(buf, esc) != NULL) {
 158                 ptr = cp = buf;
 159                 while (cp[0] != '\0') {
 160                         int skipesc;
 161
 162                         while (cp[0] != '\0' && cp[0] != esc)
 163                                 *ptr++ = *cp++;
 164                         if (cp[0] == '\0' || cp[1] == '\0')
 165                                 break;
 166
 167                         skipesc = 0;
 168                         if (cp[1] == com)
 169                                 skipesc += (flags & FPARSELN_UNESCCOMM);
 170                         if (cp[1] == con)
 171                                 skipesc += (flags & FPARSELN_UNESCCONT);
 172                         if (cp[1] == esc)
 173                                 skipesc += (flags & FPARSELN_UNESCESC);
 174                         if (cp[1] != com && cp[1] != con && cp[1] != esc)
 175                                 skipesc = (flags & FPARSELN_UNESCREST);
 176
 177                         if (skipesc)
 178                                 cp++;
 179                         else
 180                                 *ptr++ = *cp++;
 181                         *ptr++ = *cp++;
 182                 }
 183                 *ptr = '\0';
 184                 len = strlen(buf);
 185         }
 186
 187         if (size)
 188                 *size = len;
 189         return buf;
 190 }
 191
 192 #ifdef TEST
 193
 194 int
 195 main(int argc, char *argv[])
 196 {
 197         char   *ptr;
 198         size_t  size, line;
 199
 200         line = 0;
 201         while ((ptr = fparseln(stdin, &size, &line, NULL,
 202             FPARSELN_UNESCALL)) != NULL)
 203                 printf("line %d (%d) |%s|\n", line, size, ptr);
 204         return 0;
 205 }
 206
 207 /*
 208
 209 # This is a test
 210 line 1
 211 line 2 \
 212 line 3 # Comment
 213 line 4 \# Not comment \\\\
 214
 215 # And a comment \
 216 line 5 \\\
 217 line 6
 218
 219 */
 220
 221 #endif /* TEST */