usr.bin/iconv/iconv.c

   1 /*      $NetBSD: iconv.c,v 1.15 2009/02/20 15:27:08 yamt Exp $ */
   2
   3 /*-
   4  * Copyright (c)2003 Citrus Project,
   5  * All rights reserved.
   6  *
   7  * Redistribution and use in source and binary forms, with or without
   8  * modification, are permitted provided that the following conditions
   9  * are met:
  10  * 1. Redistributions of source code must retain the above copyright
  11  *    notice, this list of conditions and the following disclaimer.
  12  * 2. Redistributions in binary form must reproduce the above copyright
  13  *    notice, this list of conditions and the following disclaimer in the
  14  *    documentation and/or other materials provided with the distribution.
  15  *
  16  * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
  17  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
  18  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
  19  * ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
  20  * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
  21  * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
  22  * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
  23  * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
  24  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
  25  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
  26  * SUCH DAMAGE.
  27  */
  28
  29 #include <sys/cdefs.h>
  30 #if defined(LIBC_SCCS) && !defined(lint)
  31 __RCSID("$NetBSD: iconv.c,v 1.15 2009/02/20 15:27:08 yamt Exp $");
  32 #endif /* LIBC_SCCS and not lint */
  33
  34 #include <err.h>
  35 #include <errno.h>
  36 #include <iconv.h>
  37 #include <langinfo.h>
  38 #include <locale.h>
  39 #include <stdio.h>
  40 #include <stdlib.h>
  41 #include <string.h>
  42 #include <unistd.h>
  43 #include <util.h>
  44
  45 static void usage(void) __unused;
  46 static int scmp(const void *, const void *);
  47 static void show_codesets(void);
  48 static void do_conv(const char *, FILE *, const char *, const char *, int, int);
  49
  50 static void
  51 usage(void)
  52 {
  53         (void)fprintf(stderr,
  54             "Usage:\t%1$s [-cs] -f <from_code> -t <to_code> [file ...]\n"
  55             "\t%1$s -f <from_code> [-cs] [-t <to_code>] [file ...]\n"
  56             "\t%1$s -t <to_code> [-cs] [-f <from_code>] [file ...]\n"
  57             "\t%1$s -l\n", getprogname());
  58         exit(1);
  59 }
  60
  61 /*
  62  * qsort() helper function
  63  */
  64 static int
  65 scmp(const void *v1, const void *v2)
  66 {
  67         const char * const *s1 = v1;
  68         const char * const *s2 = v2;
  69
  70         return strcasecmp(*s1, *s2);
  71 }
  72
  73 static void
  74 show_codesets(void)
  75 {
  76         char **list;
  77         size_t sz, i;
  78
  79         if (__iconv_get_list(&list, &sz))
  80                 err(EXIT_FAILURE, "__iconv_get_list()");
  81
  82         qsort(list, sz, sizeof(char *), scmp);
  83
  84         for (i = 0; i < sz; i++)
  85                 (void)printf("%s\n", list[i]);
  86
  87         __iconv_free_list(list, sz);
  88 }
  89
  90 #define INBUFSIZE 1024
  91 #define OUTBUFSIZE (INBUFSIZE * 2)
  92 static void
  93 do_conv(const char *fn, FILE *fp, const char *from, const char *to, int silent,
  94     int hide_invalid)
  95 {
  96         char inbuf[INBUFSIZE], outbuf[OUTBUFSIZE], *out;
  97         const char *in;
  98         size_t inbytes, outbytes, ret, invalids;
  99         iconv_t cd;
 100         uint32_t flags = 0;
 101
 102         if (hide_invalid)
 103                 flags |= __ICONV_F_HIDE_INVALID;
 104         cd = iconv_open(to, from);
 105         if (cd == (iconv_t)-1)
 106                 err(EXIT_FAILURE, "iconv_open(%s, %s)", to, from);
 107
 108         invalids = 0;
 109         while ((inbytes = fread(inbuf, 1, INBUFSIZE, fp)) > 0) {
 110                 in = inbuf;
 111                 while (inbytes > 0) {
 112                         size_t inval;
 113
 114                         out = outbuf;
 115                         outbytes = OUTBUFSIZE;
 116                         ret = __iconv(cd, &in, &inbytes, &out, &outbytes,
 117                             flags, &inval);
 118                         invalids += inval;
 119                         if (outbytes < OUTBUFSIZE)
 120                                 (void)fwrite(outbuf, 1, OUTBUFSIZE - outbytes,
 121                                     stdout);
 122                         if (ret == (size_t)-1 && errno != E2BIG) {
 123                                 /*
 124                                  * XXX: iconv(3) is bad interface.
 125                                  *   invalid character count is lost here.
 126                                  *   instead, we just provide __iconv function.
 127                                  */
 128                                 if (errno != EINVAL || in == inbuf)
 129                                         err(EXIT_FAILURE, "iconv()");
 130
 131                                 /* incomplete input character */
 132                                 (void)memmove(inbuf, in, inbytes);
 133                                 ret = fread(inbuf + inbytes, 1,
 134                                     INBUFSIZE - inbytes, fp);
 135                                 if (ret == 0) {
 136                                         fflush(stdout);
 137                                         if (feof(fp))
 138                                                 errx(EXIT_FAILURE,
 139                                                      "unexpected end of file; "
 140                                                      "the last character is "
 141                                                      "incomplete.");
 142                                         else
 143                                                 err(EXIT_FAILURE, "fread()");
 144                                 }
 145                                 in = inbuf;
 146                                 inbytes += ret;
 147                         }
 148                 }
 149         }
 150         /* reset the shift state of the output buffer */
 151         outbytes = OUTBUFSIZE;
 152         out = outbuf;
 153         ret = iconv(cd, NULL, NULL, &out, &outbytes);
 154         if (ret == (size_t)-1)
 155                 err(EXIT_FAILURE, "iconv()");
 156         if (outbytes < OUTBUFSIZE)
 157                 (void)fwrite(outbuf, 1, OUTBUFSIZE - outbytes, stdout);
 158
 159         if (invalids > 0 && !silent)
 160                 warnx("warning: invalid characters: %lu",
 161                     (unsigned long)invalids);
 162
 163         iconv_close(cd);
 164 }
 165
 166 int
 167 main(int argc, char **argv)
 168 {
 169         int ch, i;
 170         int opt_l = 0, opt_s = 0, opt_c = 0;
 171         char *opt_f = NULL, *opt_t = NULL;
 172         FILE *fp;
 173
 174         setlocale(LC_ALL, "");
 175         setprogname(argv[0]);
 176
 177         while ((ch = getopt(argc, argv, "cslf:t:")) != EOF) {
 178                 switch (ch) {
 179                 case 'c':
 180                         opt_c = 1;
 181                         break;
 182                 case 's':
 183                         opt_s = 1;
 184                         break;
 185                 case 'l':
 186                         /* list */
 187                         opt_l = 1;
 188                         break;
 189                 case 'f':
 190                         /* from */
 191                         opt_f = estrdup(optarg);
 192                         break;
 193                 case 't':
 194                         /* to */
 195                         opt_t = estrdup(optarg);
 196                         break;
 197                 default:
 198                         usage();
 199                 }
 200         }
 201         argc -= optind;
 202         argv += optind;
 203         if (opt_l) {
 204                 if (argc > 0 || opt_s || opt_f != NULL || opt_t != NULL) {
 205                         warnx("-l is not allowed with other flags.");
 206                         usage();
 207                 }
 208                 show_codesets();
 209         } else {
 210                 if (opt_f == NULL) {
 211                         if (opt_t == NULL)
 212                                 usage();
 213                         opt_f = nl_langinfo(CODESET);
 214                 } else if (opt_t == NULL)
 215                         opt_t = nl_langinfo(CODESET);
 216
 217                 if (argc == 0)
 218                         do_conv("<stdin>", stdin, opt_f, opt_t, opt_s, opt_c);
 219                 else {
 220                         for (i = 0; i < argc; i++) {
 221                                 fp = fopen(argv[i], "r");
 222                                 if (fp == NULL)
 223                                         err(EXIT_FAILURE, "Cannot open `%s'",
 224                                             argv[i]);
 225                                 do_conv(argv[i], fp, opt_f, opt_t, opt_s,
 226                                     opt_c);
 227                                 (void)fclose(fp);
 228                         }
 229                 }
 230         }
 231         return EXIT_SUCCESS;
 232 }