1 | /* Copyright (C) 2000-2022 Free Software Foundation, Inc. |
2 | This file is part of the GNU C Library. |
3 | |
4 | The GNU C Library is free software; you can redistribute it and/or |
5 | modify it under the terms of the GNU Lesser General Public |
6 | License as published by the Free Software Foundation; either |
7 | version 2.1 of the License, or (at your option) any later version. |
8 | |
9 | The GNU C Library is distributed in the hope that it will be useful, |
10 | but WITHOUT ANY WARRANTY; without even the implied warranty of |
11 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU |
12 | Lesser General Public License for more details. |
13 | |
14 | You should have received a copy of the GNU Lesser General Public |
15 | License along with the GNU C Library; if not, see |
16 | <https://www.gnu.org/licenses/>. */ |
17 | |
18 | /* Create a table from Unicode to CHARSET. |
19 | This is a good test for CHARSET's iconv() module, in particular the |
20 | TO_LOOP BODY macro. */ |
21 | |
22 | #include <stddef.h> |
23 | #include <stdio.h> |
24 | #include <stdlib.h> |
25 | #include <string.h> |
26 | #include <iconv.h> |
27 | #include <errno.h> |
28 | |
29 | int |
30 | main (int argc, char *argv[]) |
31 | { |
32 | const char *charset; |
33 | iconv_t cd; |
34 | int bmp_only; |
35 | |
36 | if (argc != 2) |
37 | { |
38 | fprintf (stderr, format: "Usage: tst-table-to charset\n" ); |
39 | return 1; |
40 | } |
41 | charset = argv[1]; |
42 | |
43 | cd = iconv_open (tocode: charset, fromcode: "UTF-8" ); |
44 | if (cd == (iconv_t)(-1)) |
45 | { |
46 | perror (s: "iconv_open" ); |
47 | return 1; |
48 | } |
49 | |
50 | /* When testing UTF-8 or GB18030, stop at 0x10000, otherwise the output |
51 | file gets too big. */ |
52 | bmp_only = (strcmp (s1: charset, s2: "UTF-8" ) == 0 |
53 | || strcmp (s1: charset, s2: "GB18030" ) == 0); |
54 | |
55 | { |
56 | unsigned int i; |
57 | unsigned char buf[10]; |
58 | |
59 | for (i = 0; i < (bmp_only ? 0x10000 : 0x30000); i++) |
60 | { |
61 | unsigned char in[6]; |
62 | unsigned int incount = |
63 | (i < 0x80 ? (in[0] = i, 1) |
64 | : i < 0x800 ? (in[0] = 0xc0 | (i >> 6), |
65 | in[1] = 0x80 | (i & 0x3f), 2) |
66 | : i < 0x10000 ? (in[0] = 0xe0 | (i >> 12), |
67 | in[1] = 0x80 | ((i >> 6) & 0x3f), |
68 | in[2] = 0x80 | (i & 0x3f), 3) |
69 | : /* i < 0x200000 */ (in[0] = 0xf0 | (i >> 18), |
70 | in[1] = 0x80 | ((i >> 12) & 0x3f), |
71 | in[2] = 0x80 | ((i >> 6) & 0x3f), |
72 | in[3] = 0x80 | (i & 0x3f), 4)); |
73 | const char *inbuf = (const char *) in; |
74 | size_t inbytesleft = incount; |
75 | char *outbuf = (char *) buf; |
76 | size_t outbytesleft = sizeof (buf); |
77 | size_t result; |
78 | size_t result2 = 0; |
79 | |
80 | iconv (cd: cd, NULL, NULL, NULL, NULL); |
81 | result = iconv (cd: cd, |
82 | inbuf: (char **) &inbuf, inbytesleft: &inbytesleft, |
83 | outbuf: &outbuf, outbytesleft: &outbytesleft); |
84 | if (result != (size_t)(-1)) |
85 | result2 = iconv (cd: cd, NULL, NULL, outbuf: &outbuf, outbytesleft: &outbytesleft); |
86 | |
87 | if (result == (size_t)(-1) || result2 == (size_t)(-1)) |
88 | { |
89 | if (errno != EILSEQ) |
90 | { |
91 | int saved_errno = errno; |
92 | fprintf (stderr, format: "0x%02X: iconv error: " , i); |
93 | errno = saved_errno; |
94 | perror (s: "" ); |
95 | return 1; |
96 | } |
97 | } |
98 | else if (result == 0) /* ignore conversions with transliteration */ |
99 | { |
100 | unsigned int j, jmax; |
101 | if (inbytesleft != 0 || outbytesleft == sizeof (buf)) |
102 | { |
103 | fprintf (stderr, format: "0x%02X: inbytes = %ld, outbytes = %ld\n" , i, |
104 | (long) (incount - inbytesleft), |
105 | (long) (sizeof (buf) - outbytesleft)); |
106 | return 1; |
107 | } |
108 | jmax = sizeof (buf) - outbytesleft; |
109 | printf (format: "0x" ); |
110 | for (j = 0; j < jmax; j++) |
111 | printf (format: "%02X" , buf[j]); |
112 | printf (format: "\t0x%04X\n" , i); |
113 | } |
114 | } |
115 | } |
116 | |
117 | if (iconv_close (cd: cd) < 0) |
118 | { |
119 | perror (s: "iconv_close" ); |
120 | return 1; |
121 | } |
122 | |
123 | if (ferror (stdin) || fflush (stdout) || ferror (stdout)) |
124 | { |
125 | fprintf (stderr, format: "I/O error\n" ); |
126 | return 1; |
127 | } |
128 | |
129 | return 0; |
130 | } |
131 | |