isutf8.c

   1 /*
   2  * isutf8.c - do the input files look like valid utf-8 byte streams?
   3  *
   4  * Copyright (C) 2005  Lars Wirzenius
   5  *
   6  * This program is free software; you can redistribute it and/or modify
   7  * it under the terms of the GNU General Public License as published by
   8  * the Free Software Foundation; either version 2 of the License, or
   9  * (at your option) any later version.
  10  *
  11  * This program is distributed in the hope that it will be useful,
  12  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  13  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  14  * GNU General Public License for more details.
  15  *
  16  * You should have received a copy of the GNU General Public License
  17  * along with this program; if not, write to the Free Software
  18  * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301 USA
  19  */
  20
  21 #include <stdio.h>
  22 #include <stdlib.h>
  23 #include <errno.h>
  24 #include <string.h>
  25 #include <getopt.h>
  26
  27 #define VERSION "1.0"
  28
  29 /*
  30  * I'm pretty sure there is a fancy trick to do this without a loop,
  31  * but I'm too tired to figure it out now. --liw
  32  */
  33 static int high_ones(int c) {
  34         int n;
  35
  36         for (n = 0; (c & 0x80) == 0x80; c <<= 1)
  37                 ++n;
  38         return n;
  39 }
  40
  41 static int is_utf8_byte_stream(FILE *file, char *filename, int quiet) {
  42         int c, n, remaining_bytes;
  43         unsigned long line, col;
  44
  45         remaining_bytes = 0;
  46         line = 1;
  47         col = 1;
  48         while ((c = getc(file)) != EOF) {
  49                 n = high_ones(c);
  50                 if (remaining_bytes > 0) {
  51                         if (n == 1) {
  52                                 --remaining_bytes;
  53                                 if (remaining_bytes == 0)
  54                                         ++col;
  55                         } else
  56                                 goto error;
  57                 } else if (n == 0) {
  58                         /* 7-bit character, skip, but adjust position */
  59                         if (c == '\n') {
  60                                 ++line;
  61                                 col = 1;
  62                         } else
  63                                 ++col;
  64                 } else if (n == 1)
  65                         goto error; /* wrong place for continuation byte */
  66                 else
  67                         remaining_bytes = n - 1; /* start of multi-byte sequence */
  68         }
  69         if (remaining_bytes > 0)
  70                 goto error;
  71         return 1;
  72
  73 error:
  74         if (!quiet) {
  75                 printf("%s: line %lu, col %lu: invalid UTF-8 code\n",
  76                        filename, line, col);
  77         }
  78         return 0;
  79 }
  80
  81 static void usage(const char *program_name) {
  82         printf("Usage: %s [-hq] [--help] [--quiet] [file ...]\n", program_name);
  83         printf("Check whether input files are valid UTF-8.\n");
  84         printf("This is version %s.\n", VERSION);
  85 }
  86
  87 int main(int argc, char **argv) {
  88         int i, ok;
  89         FILE *file;
  90
  91         int quiet;
  92         struct option options[] = {
  93                 { "help", no_argument, NULL, 'h' },
  94                 { "quiet", no_argument, &quiet, 1 },
  95         };
  96         int opt;
  97
  98         quiet = 0;
  99
 100         while ((opt = getopt_long(argc, argv, "hq", options, NULL)) != -1) {
 101                 switch (opt) {
 102                 case 0:
 103                         break;
 104
 105                 case 'h':
 106                         usage(argv[0]);
 107                         exit(0);
 108                         break;
 109
 110                 case 'q':
 111                         quiet = 1;
 112                         break;
 113
 114                 case '?':
 115                         exit(EXIT_FAILURE);
 116
 117                 default:
 118                         abort();
 119                 }
 120         }
 121
 122         if (optind == argc)
 123                 ok = is_utf8_byte_stream(stdin, "stdin", quiet);
 124         else {
 125                 ok = 1;
 126                 for (i = optind; i < argc; ++i) {
 127                         file = fopen(argv[i], "r");
 128                         if (file == NULL) {
 129                                 fprintf(stderr, "isutf8: %s: error %d: %s\n",
 130                                                 argv[i], errno, strerror(errno));
 131                                 ok = 0;
 132                         } else {
 133                                 ok = is_utf8_byte_stream(file, argv[i], quiet) && ok;
 134                                 (void) fclose(file);
 135                         }
 136                 }
 137         }
 138
 139         if (ok)
 140                 exit(0);
 141         exit(EXIT_FAILURE);
 142 }