usr.bin/comm/comm.c

   1 /*
   2  * Copyright (c) 1989, 1993, 1994
   3  *      The Regents of the University of California.  All rights reserved.
   4  *
   5  * This code is derived from software contributed to Berkeley by
   6  * Case Larsen.
   7  *
   8  * Redistribution and use in source and binary forms, with or without
   9  * modification, are permitted provided that the following conditions
  10  * are met:
  11  * 1. Redistributions of source code must retain the above copyright
  12  *    notice, this list of conditions and the following disclaimer.
  13  * 2. Redistributions in binary form must reproduce the above copyright
  14  *    notice, this list of conditions and the following disclaimer in the
  15  *    documentation and/or other materials provided with the distribution.
  16  * 3. Neither the name of the University nor the names of its contributors
  17  *    may be used to endorse or promote products derived from this software
  18  *    without specific prior written permission.
  19  *
  20  * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
  21  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
  22  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
  23  * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
  24  * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
  25  * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
  26  * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
  27  * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
  28  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
  29  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
  30  * SUCH DAMAGE.
  31  *
  32  * @(#) Copyright (c) 1989, 1993, 1994 The Regents of the University of California.  All rights reserved.
  33  * @(#)comm.c   8.4 (Berkeley) 5/4/95
  34  * $FreeBSD: head/usr.bin/comm/comm.c 303526 2016-07-30 01:07:47Z bapt $
  35  */
  36
  37 #include <err.h>
  38 #include <limits.h>
  39 #include <locale.h>
  40 #include <stdint.h>
  41 #include <stdio.h>
  42 #include <stdlib.h>
  43 #include <string.h>
  44 #include <unistd.h>
  45 #include <wchar.h>
  46 #include <wctype.h>
  47
  48 static int iflag;
  49 static const char *tabs[] = { "", "\t", "\t\t" };
  50
  51 static FILE     *file(const char *);
  52 static wchar_t  *convert(const char *);
  53 static void     show(FILE *, const char *, const char *, char **, size_t *);
  54 static void     usage(void);
  55
  56 int
  57 main(int argc, char *argv[])
  58 {
  59         int comp, read1, read2;
  60         int ch, flag1, flag2, flag3;
  61         FILE *fp1, *fp2;
  62         const char *col1, *col2, *col3;
  63         size_t line1len, line2len;
  64         char *line1, *line2;
  65         ssize_t n1, n2;
  66         wchar_t *tline1, *tline2;
  67         const char **p;
  68
  69         (void) setlocale(LC_ALL, "");
  70
  71         flag1 = flag2 = flag3 = 1;
  72
  73         while ((ch = getopt(argc, argv, "123i")) != -1)
  74                 switch(ch) {
  75                 case '1':
  76                         flag1 = 0;
  77                         break;
  78                 case '2':
  79                         flag2 = 0;
  80                         break;
  81                 case '3':
  82                         flag3 = 0;
  83                         break;
  84                 case 'i':
  85                         iflag = 1;
  86                         break;
  87                 case '?':
  88                 default:
  89                         usage();
  90                 }
  91         argc -= optind;
  92         argv += optind;
  93
  94         if (argc != 2)
  95                 usage();
  96
  97         fp1 = file(argv[0]);
  98         fp2 = file(argv[1]);
  99
 100         /* for each column printed, add another tab offset */
 101         p = tabs;
 102         col1 = col2 = col3 = NULL;
 103         if (flag1)
 104                 col1 = *p++;
 105         if (flag2)
 106                 col2 = *p++;
 107         if (flag3)
 108                 col3 = *p;
 109
 110         line1len = line2len = 0;
 111         line1 = line2 = NULL;
 112         n1 = n2 = -1;
 113
 114         for (read1 = read2 = 1;;) {
 115                 /* read next line, check for EOF */
 116                 if (read1) {
 117                         n1 = getline(&line1, &line1len, fp1);
 118                         if (n1 < 0 && ferror(fp1))
 119                                 err(1, "%s", argv[0]);
 120                         if (n1 > 0 && line1[n1 - 1] == '\n')
 121                                 line1[n1 - 1] = '\0';
 122
 123                 }
 124                 if (read2) {
 125                         n2 = getline(&line2, &line2len, fp2);
 126                         if (n2 < 0 && ferror(fp2))
 127                                 err(1, "%s", argv[1]);
 128                         if (n2 > 0 && line2[n2 - 1] == '\n')
 129                                 line2[n2 - 1] = '\0';
 130                 }
 131
 132                 /* if one file done, display the rest of the other file */
 133                 if (n1 < 0) {
 134                         if (n2 >= 0 && col2 != NULL)
 135                                 show(fp2, argv[1], col2, &line2, &line2len);
 136                         break;
 137                 }
 138                 if (n2 < 0) {
 139                         if (n1 >= 0 && col1 != NULL)
 140                                 show(fp1, argv[0], col1, &line1, &line1len);
 141                         break;
 142                 }
 143
 144                 tline2 = NULL;
 145                 if ((tline1 = convert(line1)) != NULL)
 146                         tline2 = convert(line2);
 147                 if (tline1 == NULL || tline2 == NULL)
 148                         comp = strcmp(line1, line2);
 149                 else
 150                         comp = wcscoll(tline1, tline2);
 151                 if (tline1 != NULL)
 152                         free(tline1);
 153                 if (tline2 != NULL)
 154                         free(tline2);
 155
 156                 /* lines are the same */
 157                 if (!comp) {
 158                         read1 = read2 = 1;
 159                         if (col3 != NULL)
 160                                 (void)printf("%s%s\n", col3, line1);
 161                         continue;
 162                 }
 163
 164                 /* lines are different */
 165                 if (comp < 0) {
 166                         read1 = 1;
 167                         read2 = 0;
 168                         if (col1 != NULL)
 169                                 (void)printf("%s%s\n", col1, line1);
 170                 } else {
 171                         read1 = 0;
 172                         read2 = 1;
 173                         if (col2 != NULL)
 174                                 (void)printf("%s%s\n", col2, line2);
 175                 }
 176         }
 177         exit(0);
 178 }
 179
 180 static wchar_t *
 181 convert(const char *str)
 182 {
 183         size_t n;
 184         wchar_t *buf, *p;
 185
 186         if ((n = mbstowcs(NULL, str, 0)) == (size_t)-1)
 187                 return (NULL);
 188         if (SIZE_MAX / sizeof(*buf) < n + 1)
 189                 errx(1, "conversion buffer length overflow");
 190         if ((buf = malloc((n + 1) * sizeof(*buf))) == NULL)
 191                 err(1, "malloc");
 192         if (mbstowcs(buf, str, n + 1) != n)
 193                 errx(1, "internal mbstowcs() error");
 194
 195         if (iflag) {
 196                 for (p = buf; *p != L'\0'; p++)
 197                         *p = towlower(*p);
 198         }
 199
 200         return (buf);
 201 }
 202
 203 static void
 204 show(FILE *fp, const char *fn, const char *offset, char **bufp, size_t *buflenp)
 205 {
 206         ssize_t n;
 207
 208         do {
 209                 (void)printf("%s%s\n", offset, *bufp);
 210                 if ((n = getline(bufp, buflenp, fp)) < 0)
 211                         break;
 212                 if (n > 0 && (*bufp)[n - 1] == '\n')
 213                         (*bufp)[n - 1] = '\0';
 214         } while (1);
 215         if (ferror(fp))
 216                 err(1, "%s", fn);
 217 }
 218
 219 static FILE *
 220 file(const char *name)
 221 {
 222         FILE *fp;
 223
 224         if (!strcmp(name, "-"))
 225                 return (stdin);
 226         if ((fp = fopen(name, "r")) == NULL) {
 227                 err(1, "%s", name);
 228         }
 229         return (fp);
 230 }
 231
 232 static void
 233 usage(void)
 234 {
 235         (void)fprintf(stderr, "usage: comm [-123i] file1 file2\n");
 236         exit(1);
 237 }