text_cmds/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. All advertising materials mentioning features or use of this software
  17  *    must display the following acknowledgement:
  18  *      This product includes software developed by the University of
  19  *      California, Berkeley and its contributors.
  20  * 4. Neither the name of the University nor the names of its contributors
  21  *    may be used to endorse or promote products derived from this software
  22  *    without specific prior written permission.
  23  *
  24  * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
  25  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
  26  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
  27  * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
  28  * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
  29  * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
  30  * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
  31  * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
  32  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
  33  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
  34  * SUCH DAMAGE.
  35  */
  36
  37 #ifndef lint
  38 static const char copyright[] =
  39 "@(#) Copyright (c) 1989, 1993, 1994\n\
  40         The Regents of the University of California.  All rights reserved.\n";
  41 #endif
  42
  43 #if 0
  44 #ifndef lint
  45 static char sccsid[] = "From: @(#)comm.c        8.4 (Berkeley) 5/4/95";
  46 #endif
  47 #endif
  48
  49 #include <sys/cdefs.h>
  50 __FBSDID("$FreeBSD: src/usr.bin/comm/comm.c,v 1.21 2004/07/02 22:48:29 tjr Exp $");
  51
  52 #include <err.h>
  53 #include <limits.h>
  54 #include <locale.h>
  55 #include <stdio.h>
  56 #include <stdlib.h>
  57 #include <string.h>
  58 #include <unistd.h>
  59 #include <wchar.h>
  60 #include <wctype.h>
  61
  62 #define MAXLINELEN      (LINE_MAX + 1)
  63
  64 const wchar_t *tabs[] = { L"", L"\t", L"\t\t" };
  65
  66 FILE   *file(const char *);
  67 void    show(FILE *, const char *, const wchar_t *, wchar_t *);
  68 int     wcsicoll(const wchar_t *, const wchar_t *);
  69 static void     usage(void);
  70
  71 int
  72 main(int argc, char *argv[])
  73 {
  74         int comp, file1done = 0, file2done = 0, read1, read2;
  75         int ch, flag1, flag2, flag3, iflag;
  76         FILE *fp1, *fp2;
  77         const wchar_t *col1, *col2, *col3;
  78         wchar_t line1[MAXLINELEN], line2[MAXLINELEN];
  79         const wchar_t **p;
  80
  81         flag1 = flag2 = flag3 = 1;
  82         iflag = 0;
  83
  84         (void) setlocale(LC_ALL, "");
  85
  86         while ((ch = getopt(argc, argv, "123i")) != -1)
  87                 switch(ch) {
  88                 case '1':
  89                         flag1 = 0;
  90                         break;
  91                 case '2':
  92                         flag2 = 0;
  93                         break;
  94                 case '3':
  95                         flag3 = 0;
  96                         break;
  97                 case 'i':
  98                         iflag = 1;
  99                         break;
 100                 case '?':
 101                 default:
 102                         usage();
 103                 }
 104         argc -= optind;
 105         argv += optind;
 106
 107         if (argc != 2 || !argv[0] || !argv[1])
 108                 usage();
 109
 110         fp1 = file(argv[0]);
 111         fp2 = file(argv[1]);
 112
 113         /* for each column printed, add another tab offset */
 114         p = tabs;
 115         col1 = col2 = col3 = NULL;
 116         if (flag1)
 117                 col1 = *p++;
 118         if (flag2)
 119                 col2 = *p++;
 120         if (flag3)
 121                 col3 = *p;
 122
 123         for (read1 = read2 = 1;;) {
 124                 /* read next line, check for EOF */
 125                 if (read1) {
 126                         file1done = !fgetws(line1, MAXLINELEN, fp1);
 127                         if (file1done && ferror(fp1))
 128                                 err(1, "%s", argv[0]);
 129                 }
 130                 if (read2) {
 131                         file2done = !fgetws(line2, MAXLINELEN, fp2);
 132                         if (file2done && ferror(fp2))
 133                                 err(1, "%s", argv[1]);
 134                 }
 135
 136                 /* if one file done, display the rest of the other file */
 137                 if (file1done) {
 138                         if (!file2done && col2)
 139                                 show(fp2, argv[1], col2, line2);
 140                         break;
 141                 }
 142                 if (file2done) {
 143                         if (!file1done && col1)
 144                                 show(fp1, argv[0], col1, line1);
 145                         break;
 146                 }
 147
 148                 /* lines are the same */
 149                 if(iflag)
 150                         comp = wcsicoll(line1, line2);
 151                 else
 152                         comp = wcscoll(line1, line2);
 153
 154                 if (!comp) {
 155                         read1 = read2 = 1;
 156                         if (col3)
 157                                 (void)printf("%ls%ls", col3, line1);
 158                         continue;
 159                 }
 160
 161                 /* lines are different */
 162                 if (comp < 0) {
 163                         read1 = 1;
 164                         read2 = 0;
 165                         if (col1)
 166                                 (void)printf("%ls%ls", col1, line1);
 167                 } else {
 168                         read1 = 0;
 169                         read2 = 1;
 170                         if (col2)
 171                                 (void)printf("%ls%ls", col2, line2);
 172                 }
 173         }
 174         exit(0);
 175 }
 176
 177 void
 178 show(FILE *fp, const char *fn, const wchar_t *offset, wchar_t *buf)
 179 {
 180
 181         do {
 182                 (void)printf("%ls%ls", offset, buf);
 183         } while (fgetws(buf, MAXLINELEN, fp));
 184         if (ferror(fp))
 185                 err(1, "%s", fn);
 186 }
 187
 188 FILE *
 189 file(const char *name)
 190 {
 191         FILE *fp;
 192
 193         if (!strcmp(name, "-"))
 194                 return (stdin);
 195         if ((fp = fopen(name, "r")) == NULL) {
 196                 err(1, "%s", name);
 197         }
 198         return (fp);
 199 }
 200
 201 static void
 202 usage(void)
 203 {
 204         (void)fprintf(stderr, "usage: comm [-123i] file1 file2\n");
 205         exit(1);
 206 }
 207
 208 int
 209 wcsicoll(const wchar_t *s1, const wchar_t *s2)
 210 {
 211         wchar_t *p, line1[MAXLINELEN], line2[MAXLINELEN];
 212
 213         for (p = line1; *s1; s1++)
 214                 *p++ = towlower(*s1);
 215         *p = '\0';
 216         for (p = line2; *s2; s2++)
 217                 *p++ = towlower(*s2);
 218         *p = '\0';
 219         return (wcscoll(line1, line2));
 220 }