| 1 | /* Test for initial conversion state. |
| 2 | Copyright (C) 2008-2020 Free Software Foundation, Inc. |
| 3 | Written by Bruno Haible <bruno@clisp.org>, 2008. |
| 4 | |
| 5 | This program is free software: you can redistribute it and/or modify |
| 6 | it under the terms of the GNU General Public License as published by |
| 7 | the Free Software Foundation; either version 3 of the License, or |
| 8 | (at your option) any later version. |
| 9 | |
| 10 | This program is distributed in the hope that it will be useful, |
| 11 | but WITHOUT ANY WARRANTY; without even the implied warranty of |
| 12 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
| 13 | GNU General Public License for more details. |
| 14 | |
| 15 | You should have received a copy of the GNU General Public License |
| 16 | along with this program. If not, see <https://www.gnu.org/licenses/>. */ |
| 17 | |
| 18 | #include <config.h> |
| 19 | |
| 20 | /* Specification. */ |
| 21 | #include <wchar.h> |
| 22 | |
| 23 | #include "verify.h" |
| 24 | |
| 25 | #if GNULIB_defined_mbstate_t |
| 26 | |
| 27 | /* Platforms that lack mbsinit() also lack mbrlen(), mbrtowc(), mbsrtowcs() |
| 28 | and wcrtomb(), wcsrtombs(). |
| 29 | We assume that |
| 30 | - sizeof (mbstate_t) >= 4, |
| 31 | - only stateless encodings are supported (such as UTF-8 and EUC-JP, but |
| 32 | not ISO-2022 variants), |
| 33 | - for each encoding, the number of bytes for a wide character is <= 4. |
| 34 | (This maximum is attained for UTF-8, GB18030, EUC-TW.) |
| 35 | We define the meaning of mbstate_t as follows: |
| 36 | - In mb -> wc direction, mbstate_t's first byte contains the number of |
| 37 | buffered bytes (in the range 0..3), followed by up to 3 buffered bytes. |
| 38 | See mbrtowc.c. |
| 39 | - In wc -> mb direction, mbstate_t contains no information. In other |
| 40 | words, it is always in the initial state. */ |
| 41 | |
| 42 | verify (sizeof (mbstate_t) >= 4); |
| 43 | |
| 44 | int |
| 45 | mbsinit (const mbstate_t *ps) |
| 46 | { |
| 47 | const char *pstate = (const char *)ps; |
| 48 | |
| 49 | return pstate == NULL || pstate[0] == 0; |
| 50 | } |
| 51 | |
| 52 | #else |
| 53 | |
| 54 | int |
| 55 | mbsinit (const mbstate_t *ps) |
| 56 | { |
| 57 | # if defined _WIN32 && !defined __CYGWIN__ |
| 58 | /* Native Windows. */ |
| 59 | /* MSVC defines 'mbstate_t' as an 8-byte struct; the first 4 bytes matter. |
| 60 | On mingw, 'mbstate_t' is sometimes defined as 'int', sometimes defined as |
| 61 | an 8-byte struct, of which the first 4 bytes matter. */ |
| 62 | return ps == NULL || *(const unsigned int *)ps == 0; |
| 63 | # else |
| 64 | /* Minix, HP-UX 11.00, Solaris 2.6, Interix, ... */ |
| 65 | /* Maybe this definition works, maybe not... */ |
| 66 | return ps == NULL || *(const char *)ps == 0; |
| 67 | # endif |
| 68 | } |
| 69 | |
| 70 | #endif |