1 /* $NetBSD: iconv.c,v 1.20 2019/10/24 18:18:00 kamil 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 1.20 2019/10/24 18:18:00 kamil Exp $");
32 #endif /* LIBC_SCCS and not lint */
33
34 #include <err.h>
35 #include <errno.h>
36 #include <iconv.h>
37 #include <langinfo.h>
38 #include <locale.h>
39 #include <stdio.h>
40 #include <stdlib.h>
41 #include <string.h>
42 #include <unistd.h>
43 #include <util.h>
44
45 static void usage(void) __dead;
46 static int scmp(const void *, const void *);
47 static void show_codesets(void);
48 static void do_conv(const char *, FILE *, const char *, const char *, int, int);
49
50 static void
usage(void)51 usage(void)
52 {
53 (void)fprintf(stderr,
54 "Usage:\t%1$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
scmp(const void * v1,const void * v2)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
show_codesets(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 /*ARGSUSED*/
93 static void
do_conv(const char * fn,FILE * fp,const char * from,const char * to,int silent,int hide_invalid)94 do_conv(const char *fn, FILE *fp, const char *from, const char *to, int silent,
95 int hide_invalid)
96 {
97 char inbuf[INBUFSIZE], outbuf[OUTBUFSIZE], *out;
98 const char *in;
99 size_t inbytes, outbytes, ret, invalids;
100 iconv_t cd;
101 uint32_t flags = 0;
102 int serrno;
103
104 if (hide_invalid)
105 flags |= __ICONV_F_HIDE_INVALID;
106 cd = iconv_open(to, from);
107 if (cd == (iconv_t)-1)
108 err(EXIT_FAILURE, "iconv_open(%s, %s)", to, from);
109
110 invalids = 0;
111 while ((inbytes = fread(inbuf, 1, INBUFSIZE, fp)) > 0) {
112 in = inbuf;
113 while (inbytes > 0) {
114 size_t inval;
115
116 out = outbuf;
117 outbytes = OUTBUFSIZE;
118 ret = __iconv(cd, __UNCONST(&in), &inbytes, &out,
119 &outbytes, flags, &inval);
120 serrno = errno;
121 invalids += inval;
122 if (outbytes < OUTBUFSIZE)
123 (void)fwrite(outbuf, 1, OUTBUFSIZE - outbytes,
124 stdout);
125 errno = serrno;
126 if (ret == (size_t)-1 && errno != E2BIG) {
127 /*
128 * XXX: iconv(3) is bad interface.
129 * invalid character count is lost here.
130 * instead, we just provide __iconv function.
131 */
132 if (errno != EINVAL || in == inbuf)
133 err(EXIT_FAILURE, "iconv()");
134
135 /* incomplete input character */
136 (void)memmove(inbuf, in, inbytes);
137 ret = fread(inbuf + inbytes, 1,
138 INBUFSIZE - inbytes, fp);
139 if (ret == 0) {
140 fflush(stdout);
141 if (feof(fp))
142 errx(EXIT_FAILURE,
143 "unexpected end of file; "
144 "the last character is "
145 "incomplete.");
146 else
147 err(EXIT_FAILURE, "fread()");
148 }
149 in = inbuf;
150 inbytes += ret;
151 }
152 }
153 }
154 /* reset the shift state of the output buffer */
155 outbytes = OUTBUFSIZE;
156 out = outbuf;
157 ret = iconv(cd, NULL, NULL, &out, &outbytes);
158 if (ret == (size_t)-1)
159 err(EXIT_FAILURE, "iconv()");
160 if (outbytes < OUTBUFSIZE)
161 (void)fwrite(outbuf, 1, OUTBUFSIZE - outbytes, stdout);
162
163 if (invalids > 0 && !silent)
164 warnx("warning: invalid characters: %lu",
165 (unsigned long)invalids);
166
167 iconv_close(cd);
168 }
169
170 int
main(int argc,char ** argv)171 main(int argc, char **argv)
172 {
173 int ch, i;
174 int opt_l = 0, opt_s = 0, opt_c = 0;
175 char *opt_f = NULL, *opt_t = NULL;
176 FILE *fp;
177
178 setlocale(LC_ALL, "");
179 setprogname(argv[0]);
180
181 while ((ch = getopt(argc, argv, "cslf:t:")) != EOF) {
182 switch (ch) {
183 case 'c':
184 opt_c = 1;
185 break;
186 case 's':
187 opt_s = 1;
188 break;
189 case 'l':
190 /* list */
191 opt_l = 1;
192 break;
193 case 'f':
194 /* from */
195 opt_f = estrdup(optarg);
196 break;
197 case 't':
198 /* to */
199 opt_t = estrdup(optarg);
200 break;
201 default:
202 usage();
203 }
204 }
205 argc -= optind;
206 argv += optind;
207 if (opt_l) {
208 if (argc > 0 || opt_s || opt_f != NULL || opt_t != NULL) {
209 warnx("-l is not allowed with other flags.");
210 usage();
211 }
212 show_codesets();
213 } else {
214 if (opt_f == NULL) {
215 if (opt_t == NULL)
216 usage();
217 opt_f = nl_langinfo(CODESET);
218 } else if (opt_t == NULL)
219 opt_t = nl_langinfo(CODESET);
220
221 if (argc == 0)
222 do_conv("<stdin>", stdin, opt_f, opt_t, opt_s, opt_c);
223 else {
224 for (i = 0; i < argc; i++) {
225 fp = fopen(argv[i], "r");
226 if (fp == NULL)
227 err(EXIT_FAILURE, "Cannot open `%s'",
228 argv[i]);
229 do_conv(argv[i], fp, opt_f, opt_t, opt_s,
230 opt_c);
231 (void)fclose(fp);
232 }
233 }
234 }
235 return EXIT_SUCCESS;
236 }
237