1 /* 2 * Copyright 2013 Garrett D'Amore <garrett@damore.org> 3 * Copyright 2011 Nexenta Systems, Inc. All rights reserved. 4 * Copyright (c) 2004 Tim J. Robbins. 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 #ifndef _MBLOCAL_H_ 30 #define _MBLOCAL_H_ 31 32 #include "runetype.h" 33 #include "lctype.h" 34 #include <uchar.h> 35 36 /* 37 * Actual implementation structures for mbstate_t data. 38 * 39 * All of the conversion states are independent of one another, with the 40 * exception of that used for mbrtoc16(). That needs to encode data not as a 41 * wide-character but as UTF-16 data, which means handling surrogate pairs. To 42 * minimize the amount of state in each locale, we instead have a conversion 43 * state for this which includes all the other conversion states, plus extra 44 * data to accomodate this. 45 */ 46 typedef struct { 47 wchar_t ch; 48 } _BIG5State; 49 50 typedef struct { 51 wchar_t ch; 52 int set; 53 int want; 54 } _EucState; 55 56 typedef struct { 57 int count; 58 uchar_t bytes[4]; 59 } _GB18030State; 60 61 typedef struct { 62 int count; 63 uchar_t bytes[2]; 64 } _GB2312State; 65 66 typedef struct { 67 wchar_t ch; 68 } _GBKState; 69 70 typedef struct { 71 wchar_t ch; 72 } _MSKanjiState; 73 74 typedef struct { 75 wchar_t ch; 76 int want; 77 wchar_t lbound; 78 } _UTF8State; 79 80 typedef struct { 81 union { 82 _BIG5State c16_big5; 83 _EucState c16_euc; 84 _GB18030State c16_gb18030; 85 _GB2312State c16_gb2312; 86 _GBKState c16_gbk; 87 _MSKanjiState c16_mskanji; 88 _UTF8State c16_utf8; 89 } c16_state; 90 char16_t c16_surrogate; 91 } _CHAR16State; 92 93 /* 94 * Rune initialization function prototypes. 95 */ 96 void _none_init(struct lc_ctype *); 97 void _UTF8_init(struct lc_ctype *); 98 void _EUC_CN_init(struct lc_ctype *); 99 void _EUC_JP_init(struct lc_ctype *); 100 void _EUC_KR_init(struct lc_ctype *); 101 void _EUC_TW_init(struct lc_ctype *); 102 void _GB18030_init(struct lc_ctype *); 103 void _GB2312_init(struct lc_ctype *); 104 void _GBK_init(struct lc_ctype *); 105 void _BIG5_init(struct lc_ctype *); 106 void _MSKanji_init(struct lc_ctype *); 107 108 typedef size_t (*mbrtowc_pfn_t)(wchar_t *_RESTRICT_KYWD, 109 const char *_RESTRICT_KYWD, size_t, mbstate_t *_RESTRICT_KYWD, boolean_t); 110 typedef size_t (*wcrtomb_pfn_t)(char *_RESTRICT_KYWD, wchar_t, 111 mbstate_t *_RESTRICT_KYWD); 112 size_t __mbsnrtowcs_std(wchar_t *_RESTRICT_KYWD, const char **_RESTRICT_KYWD, 113 size_t, size_t, mbstate_t *_RESTRICT_KYWD, mbrtowc_pfn_t); 114 size_t __wcsnrtombs_std(char *_RESTRICT_KYWD, const wchar_t **_RESTRICT_KYWD, 115 size_t, size_t, mbstate_t *_RESTRICT_KYWD, wcrtomb_pfn_t); 116 117 #define MIN(a, b) ((a) < (b) ? (a) : (b)) 118 119 #endif /* _MBLOCAL_H_ */ 120