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 227235 2011-11-06 18:49:10Z ed $
  35  */
  36
  37 #include <err.h>
  38 #include <limits.h>
  39 #include <locale.h>
  40 #include <stdint.h>
  41 #define _WITH_GETLINE
  42 #include <stdio.h>
  43 #include <stdlib.h>
  44 #include <string.h>
  45 #include <unistd.h>
  46 #include <wchar.h>
  47 #include <wctype.h>
  48
  49 static int iflag;
  50 static const char *tabs[] = { "", "\t", "\t\t" };
  51
  52 static FILE     *file(const char *);
  53 static wchar_t  *convert(const char *);
  54 static void     show(FILE *, const char *, const char *, char **, size_t *);
  55 static void     usage(void);
  56
  57 int
  58 main(int argc, char *argv[])
  59 {
  60         int comp, read1, read2;
  61         int ch, flag1, flag2, flag3;
  62         FILE *fp1, *fp2;
  63         const char *col1, *col2, *col3;
  64         size_t line1len, line2len;
  65         char *line1, *line2;
  66         ssize_t n1, n2;
  67         wchar_t *tline1, *tline2;
  68         const char **p;
  69
  70         (void) setlocale(LC_ALL, "");
  71
  72         flag1 = flag2 = flag3 = 1;
  73
  74         while ((ch = getopt(argc, argv, "123i")) != -1)
  75                 switch(ch) {
  76                 case '1':
  77                         flag1 = 0;
  78                         break;
  79                 case '2':
  80                         flag2 = 0;
  81                         break;
  82                 case '3':
  83                         flag3 = 0;
  84                         break;
  85                 case 'i':
  86                         iflag = 1;
  87                         break;
  88                 case '?':
  89                 default:
  90                         usage();
  91                 }
  92         argc -= optind;
  93         argv += optind;
  94
  95         if (argc != 2)
  96                 usage();
  97
  98         fp1 = file(argv[0]);
  99         fp2 = file(argv[1]);
 100
 101         /* for each column printed, add another tab offset */
 102         p = tabs;
 103         col1 = col2 = col3 = NULL;
 104         if (flag1)
 105                 col1 = *p++;
 106         if (flag2)
 107                 col2 = *p++;
 108         if (flag3)
 109                 col3 = *p;
 110
 111         line1len = line2len = 0;
 112         line1 = line2 = NULL;
 113         n1 = n2 = -1;
 114
 115         for (read1 = read2 = 1;;) {
 116                 /* read next line, check for EOF */
 117                 if (read1) {
 118                         n1 = getline(&line1, &line1len, fp1);
 119                         if (n1 < 0 && ferror(fp1))
 120                                 err(1, "%s", argv[0]);
 121                         if (n1 > 0 && line1[n1 - 1] == '\n')
 122                                 line1[n1 - 1] = '\0';
 123
 124                 }
 125                 if (read2) {
 126                         n2 = getline(&line2, &line2len, fp2);
 127                         if (n2 < 0 && ferror(fp2))
 128                                 err(1, "%s", argv[1]);
 129                         if (n2 > 0 && line2[n2 - 1] == '\n')
 130                                 line2[n2 - 1] = '\0';
 131                 }
 132
 133                 /* if one file done, display the rest of the other file */
 134                 if (n1 < 0) {
 135                         if (n2 >= 0 && col2 != NULL)
 136                                 show(fp2, argv[1], col2, &line2, &line2len);
 137                         break;
 138                 }
 139                 if (n2 < 0) {
 140                         if (n1 >= 0 && col1 != NULL)
 141                                 show(fp1, argv[0], col1, &line1, &line1len);
 142                         break;
 143                 }
 144
 145                 tline2 = NULL;
 146                 if ((tline1 = convert(line1)) != NULL)
 147                         tline2 = convert(line2);
 148                 if (tline1 == NULL || tline2 == NULL)
 149                         comp = strcmp(line1, line2);
 150                 else
 151                         comp = wcscoll(tline1, tline2);
 152                 if (tline1 != NULL)
 153                         free(tline1);
 154                 if (tline2 != NULL)
 155                         free(tline2);
 156
 157                 /* lines are the same */
 158                 if (!comp) {
 159                         read1 = read2 = 1;
 160                         if (col3 != NULL)
 161                                 (void)printf("%s%s\n", col3, line1);
 162                         continue;
 163                 }
 164
 165                 /* lines are different */
 166                 if (comp < 0) {
 167                         read1 = 1;
 168                         read2 = 0;
 169                         if (col1 != NULL)
 170                                 (void)printf("%s%s\n", col1, line1);
 171                 } else {
 172                         read1 = 0;
 173                         read2 = 1;
 174                         if (col2 != NULL)
 175                                 (void)printf("%s%s\n", col2, line2);
 176                 }
 177         }
 178         exit(0);
 179 }
 180
 181 static wchar_t *
 182 convert(const char *str)
 183 {
 184         size_t n;
 185         wchar_t *buf, *p;
 186
 187         if ((n = mbstowcs(NULL, str, 0)) == (size_t)-1)
 188                 return (NULL);
 189         if (SIZE_MAX / sizeof(*buf) < n + 1)
 190                 errx(1, "conversion buffer length overflow");
 191         if ((buf = malloc((n + 1) * sizeof(*buf))) == NULL)
 192                 err(1, "malloc");
 193         if (mbstowcs(buf, str, n + 1) != n)
 194                 errx(1, "internal mbstowcs() error");
 195
 196         if (iflag) {
 197                 for (p = buf; *p != L'\0'; p++)
 198                         *p = towlower(*p);
 199         }
 200
 201         return (buf);
 202 }
 203
 204 static void
 205 show(FILE *fp, const char *fn, const char *offset, char **bufp, size_t *buflenp)
 206 {
 207         ssize_t n;
 208
 209         do {
 210                 (void)printf("%s%s\n", offset, *bufp);
 211                 if ((n = getline(bufp, buflenp, fp)) < 0)
 212                         break;
 213                 if (n > 0 && (*bufp)[n - 1] == '\n')
 214                         (*bufp)[n - 1] = '\0';
 215         } while (1);
 216         if (ferror(fp))
 217                 err(1, "%s", fn);
 218 }
 219
 220 static FILE *
 221 file(const char *name)
 222 {
 223         FILE *fp;
 224
 225         if (!strcmp(name, "-"))
 226                 return (stdin);
 227         if ((fp = fopen(name, "r")) == NULL) {
 228                 err(1, "%s", name);
 229         }
 230         return (fp);
 231 }
 232
 233 static void
 234 usage(void)
 235 {
 236         (void)fprintf(stderr, "usage: comm [-123i] file1 file2\n");
 237         exit(1);
 238 }