Improved unicode fileio support.
[reactos.git] / reactos / lib / msvcrt / stdlib / wctomb.c
1 /* Copyright (C) 1991, 1992, 1995, 1996, 1997 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 Library General Public License as
6 published by the Free Software Foundation; either version 2 of the
7 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 Library General Public License for more details.
13
14 You should have received a copy of the GNU Library General Public
15 License along with the GNU C Library; see the file COPYING.LIB. If not,
16 write to the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
17 Boston, MA 02111-1307, USA. */
18
19 #include <windows.h>
20 #include <msvcrt/stdlib.h>
21 #include <msvcrt/ctype.h>
22 #include <msvcrt/wchar.h>
23 #include <msvcrt/errno.h>
24 #include <msvcrt/internal/file.h>
25
26
27 int
28 STDCALL
29 WideCharToMultiByte(
30 UINT CodePage,
31 DWORD dwFlags,
32 LPCWSTR lpWideCharStr,
33 int cchWideChar,
34 LPSTR lpMultiByteStr,
35 int cchMultiByte,
36 LPCSTR lpDefaultChar,
37 LPBOOL lpUsedDefaultChar);
38
39
40 int wctomb(char* dst, wchar_t ch)
41 {
42 #if 0
43 return WideCharToMultiByte(CP_ACP, 0, &ch, 1, dst, 6, NULL, NULL);
44 #else
45 if (dst == NULL) {
46 return 1;
47 }
48 *dst = ch;
49 return 1;
50 #endif
51 }
52
53
54 #if 0
55
56 #ifndef EILSEQ
57 #define EILSEQ EINVAL
58 #endif
59
60 static const wchar_t encoding_mask[] =
61 {
62 /* This reflects the sources *nix origin where type wchar_t
63 was 32 bits wide. Since our type wchar_t is only 16 bits
64 wide all this module will need to be reviewed.
65 Simplest option may well be to forward this modules work
66 on to the kernel which already has support for this.
67 */
68 ~0x7ff, ~0xffff, ~0x1fffff, ~0x3ffffff
69 //~0x0000-07ff, ~0x0000-ffff, ~0x001f-ffff, ~0x03ff-ffff
70 };
71
72 static const unsigned char encoding_byte[] =
73 {
74 0xc0, 0xe0, 0xf0, 0xf8, 0xfc
75 };
76
77 /* The state is for this UTF8 encoding not used. */
78 //static mbstate_t internal;
79 //extern mbstate_t __no_r_state; /* Defined in mbtowc.c. */
80
81 size_t __wcrtomb(char *s, wchar_t wc);
82
83 /* Convert WCHAR into its multibyte character representation,
84 putting this in S and returning its length.
85
86 Attention: this function should NEVER be intentionally used.
87 The interface is completely stupid. The state is shared between
88 all conversion functions. You should use instead the restartable
89 version `wcrtomb'. */
90
91 int wctomb(char *s, wchar_t wchar)
92 {
93 /* If S is NULL the function has to return null or not null
94 depending on the encoding having a state depending encoding or
95 not. This is nonsense because any multibyte encoding has a
96 state. The ISO C amendment 1 corrects this while introducing the
97 restartable functions. We simply say here all encodings have a
98 state. */
99 if (s == NULL) {
100 return 1;
101 }
102 return __wcrtomb(s, wchar);
103 }
104
105 size_t __wcrtomb(char *s, wchar_t wc)
106 {
107 char fake[1];
108 size_t written = 0;
109
110 if (s == NULL) {
111 s = fake;
112 wc = L'\0';
113 }
114 /* Store the UTF8 representation of WC. */
115 //if (wc < 0 || wc > 0x7fffffff) {
116 if (wc < 0 || wc > 0x7fff) {
117 /* This is no correct ISO 10646 character. */
118 __set_errno (EILSEQ);
119 return (size_t) -1;
120 }
121 if (wc < 0x80) {
122 /* It's a one byte sequence. */
123 if (s != NULL) {
124 *s = (char)wc;
125 }
126 return 1;
127 }
128 for (written = 2; written < 6; ++written) {
129 if ((wc & encoding_mask[written - 2]) == 0) {
130 break;
131 }
132 }
133 if (s != NULL) {
134 size_t cnt = written;
135 s[0] = encoding_byte[cnt - 2];
136 --cnt;
137 do {
138 s[cnt] = 0x80 | (wc & 0x3f);
139 wc >>= 6;
140 } while (--cnt > 0);
141 s[0] |= wc;
142 }
143 return written;
144 }
145
146 #endif