1 /* $NetBSD: iconv.c,v 1.5 2004/02/21 09:16:25 jdolecek 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 1.5 2004/02/21 09:16:25 jdolecek Exp $"); 32 #endif /* LIBC_SCCS and not lint */ 33 34 #include <errno.h> 35 #include <stdio.h> 36 #include <stdlib.h> 37 #include <string.h> 38 #include <iconv.h> 39 #include <unistd.h> 40 #include <err.h> 41 42 static void 43 usage(void) 44 { 45 fprintf(stderr, 46 "usage:\n" 47 "\t%s [-cs] -f <from> -t <to> [file ...]\n" 48 "\t%s -l\n", 49 getprogname(), getprogname()); 50 exit(1); 51 } 52 53 /* 54 * qsort() helper function 55 */ 56 static int 57 scmp(const void *s1, const void *s2) 58 { 59 return strcasecmp(*(const char **)s1, *(const char **)s2); 60 } 61 62 static void 63 show_codesets(void) 64 { 65 char **list; 66 size_t sz, i; 67 68 if (__iconv_get_list(&list, &sz)) 69 err(EXIT_FAILURE, "__iconv_get_list()"); 70 71 qsort(list, sz, sizeof(char *), scmp); 72 73 for (i=0; i<sz; i++) { 74 printf("%s\n", list[i]); 75 } 76 77 __iconv_free_list(list, sz); 78 } 79 80 #define INBUFSIZE 1024 81 #define OUTBUFSIZE (INBUFSIZE*2) 82 static void 83 do_conv(const char *fn, FILE *fp, const char *from, const char *to, int silent, 84 int hide_invalid) 85 { 86 char inbuf[INBUFSIZE], outbuf[OUTBUFSIZE], *out; 87 const char *in; 88 size_t inbytes, outbytes, ret, invalids; 89 iconv_t cd; 90 u_int32_t flags = 0; 91 92 if (hide_invalid) 93 flags |= __ICONV_F_HIDE_INVALID; 94 cd = iconv_open(to, from); 95 if (cd == (iconv_t)-1) 96 err(EXIT_FAILURE, "iconv_open(%s, %s)", to, from); 97 98 invalids = 0; 99 while ((inbytes = fread(inbuf, 1, INBUFSIZE, fp)) > 0) { 100 in = inbuf; 101 while (inbytes>0) { 102 size_t inval; 103 104 out = outbuf; 105 outbytes = OUTBUFSIZE; 106 ret = __iconv(cd, &in, &inbytes, &out, &outbytes, 107 flags, &inval); 108 invalids += inval; 109 if (ret==(size_t)-1 && errno != E2BIG) { 110 /* 111 * XXX: iconv(3) is bad interface. 112 * invalid character count is lost here. 113 * instead, we just provide __iconv function. 114 */ 115 if (errno != EINVAL || in == inbuf) 116 err(EXIT_FAILURE, "iconv()"); 117 118 /* incomplete input character */ 119 memmove(inbuf, in, inbytes); 120 ret = fread(inbuf+inbytes, 1, 121 INBUFSIZE-inbytes, fp); 122 if (ret == 0) { 123 if (feof(fp)) 124 errx(EXIT_FAILURE, 125 "iconv(): %s", 126 strerror(EINVAL)); 127 else 128 err(EXIT_FAILURE, "fread()"); 129 } 130 in = inbuf; 131 inbytes += ret; 132 } 133 if (outbytes < OUTBUFSIZE) 134 fwrite(outbuf, 1, OUTBUFSIZE-outbytes, stdout); 135 } 136 } 137 /* reset the shift state of the output buffer */ 138 outbytes = OUTBUFSIZE; 139 out = outbuf; 140 ret = iconv(cd, NULL, NULL, &out, &outbytes); 141 if (ret == -1) 142 err(EXIT_FAILURE, "iconv()"); 143 if (outbytes < OUTBUFSIZE) 144 fwrite(outbuf, 1, OUTBUFSIZE-outbytes, stdout); 145 146 if (invalids > 0 && !silent) 147 warnx("warning: invalid characters: %lu", 148 (unsigned long)invalids); 149 150 iconv_close(cd); 151 } 152 153 int 154 main(int argc, char **argv) 155 { 156 int ch, i; 157 extern char *optarg; 158 extern int optind; 159 int opt_l = 0, opt_s = 0, opt_c = 0; 160 char *opt_f = NULL, *opt_t = NULL; 161 FILE *fp; 162 163 while ((ch=getopt(argc, argv, "cslf:t:")) != EOF) { 164 switch (ch) { 165 case 'c': 166 opt_c = 1; 167 break; 168 case 's': 169 opt_s = 1; 170 break; 171 case 'l': 172 /* list */ 173 opt_l = 1; 174 break; 175 case 'f': 176 /* from */ 177 opt_f = strdup(optarg); 178 break; 179 case 't': 180 /* to */ 181 opt_t = strdup(optarg); 182 break; 183 default: 184 usage(); 185 } 186 } 187 argc-=optind; 188 argv+=optind; 189 if (opt_l) { 190 if (argc>0 || opt_s || opt_f != NULL || opt_t != NULL) { 191 warnx("%s: -l should be specified solely.", 192 getprogname()); 193 usage(); 194 } 195 show_codesets(); 196 } else { 197 if (opt_f == NULL || opt_t == NULL) 198 usage(); 199 200 if (argc == 0) 201 do_conv("<stdin>", stdin, opt_f, opt_t, opt_s, opt_c); 202 else { 203 for (i=0; i<argc; i++) { 204 fp = fopen(argv[i], "r"); 205 if (fp == NULL) 206 errx(EXIT_FAILURE, "%s: %s:%s", 207 getprogname(), argv[i], 208 strerror(errno)); 209 do_conv(argv[i], fp, opt_f, opt_t, opt_s, 210 opt_c); 211 fclose(fp); 212 } 213 } 214 } 215 216 return EXIT_SUCCESS; 217 } 218