1 /*- 2 * Copyright (c) 2013 Ed Schouten <ed@FreeBSD.org> 3 * All rights reserved. 4 * 5 * Redistribution and use in source and binary forms, with or without 6 * modification, are permitted provided that the following conditions 7 * are met: 8 * 1. Redistributions of source code must retain the above copyright 9 * notice, this list of conditions and the following disclaimer. 10 * 2. Redistributions in binary form must reproduce the above copyright 11 * notice, this list of conditions and the following disclaimer in the 12 * documentation and/or other materials provided with the distribution. 13 * 14 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND 15 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 16 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 17 * ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE 18 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL 19 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS 20 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) 21 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 22 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY 23 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF 24 * SUCH DAMAGE. 25 * 26 * $FreeBSD: head/lib/libc/locale/mbrtocXX_iconv.h 281550 2015-04-15 09:09:20Z tijl $ 27 */ 28 29 #include <sys/queue.h> 30 31 #include <assert.h> 32 #include <errno.h> 33 #include <langinfo.h> 34 #include <limits.h> 35 #include <string.h> 36 #include <uchar.h> 37 38 #include "../citrus/citrus_hash.h" 39 #include "../citrus/citrus_module.h" 40 #include "../citrus/citrus_iconv.h" 41 #include "xlocale_private.h" 42 43 typedef struct { 44 bool initialized; 45 struct _citrus_iconv iconv; 46 char srcbuf[MB_LEN_MAX]; 47 size_t srcbuf_len; 48 union { 49 charXX_t widechar[DSTBUF_LEN]; 50 char bytes[sizeof(charXX_t) * DSTBUF_LEN]; 51 } dstbuf; 52 size_t dstbuf_len; 53 } _ConversionState; 54 _Static_assert(sizeof(_ConversionState) <= sizeof(mbstate_t), 55 "Size of _ConversionState must not exceed mbstate_t's size."); 56 57 size_t 58 mbrtocXX_l(charXX_t * __restrict pc, const char * __restrict s, size_t n, 59 mbstate_t * __restrict ps, locale_t locale) 60 { 61 _ConversionState *cs; 62 struct _citrus_iconv *handle; 63 size_t i, retval; 64 charXX_t retchar; 65 66 FIX_LOCALE(locale); 67 if (ps == NULL) 68 ps = &locale->mbrtocXX; 69 cs = (_ConversionState *)ps; 70 handle = &cs->iconv; 71 72 /* Reinitialize mbstate_t. */ 73 if (s == NULL || !cs->initialized) { 74 if (_citrus_iconv_open(&handle, 75 nl_langinfo_l(CODESET, locale), UTF_XX_INTERNAL) != 0) { 76 cs->initialized = false; 77 errno = EINVAL; 78 return (-1); 79 } 80 handle->cv_shared->ci_discard_ilseq = true; 81 handle->cv_shared->ci_hooks = NULL; 82 cs->srcbuf_len = cs->dstbuf_len = 0; 83 cs->initialized = true; 84 if (s == NULL) 85 return (0); 86 } 87 88 /* See if we still have characters left from the previous invocation. */ 89 if (cs->dstbuf_len > 0) { 90 retval = (size_t)-3; 91 goto return_char; 92 } 93 94 /* Fill up the read buffer as far as possible. */ 95 if (n > sizeof(cs->srcbuf) - cs->srcbuf_len) 96 n = sizeof(cs->srcbuf) - cs->srcbuf_len; 97 memcpy(cs->srcbuf + cs->srcbuf_len, s, n); 98 99 /* Convert as few characters to the dst buffer as possible. */ 100 for (i = 0; ; i++) { 101 char *src, *dst; 102 size_t srcleft, dstleft, invlen; 103 int err; 104 105 src = cs->srcbuf; 106 srcleft = cs->srcbuf_len + n; 107 dst = cs->dstbuf.bytes; 108 dstleft = i * sizeof(charXX_t); 109 assert(srcleft <= sizeof(cs->srcbuf) && 110 dstleft <= sizeof(cs->dstbuf.bytes)); 111 err = _citrus_iconv_convert(handle, &src, &srcleft, 112 &dst, &dstleft, 0, &invlen); 113 cs->dstbuf_len = (dst - cs->dstbuf.bytes) / sizeof(charXX_t); 114 115 /* Got new character(s). Return the first. */ 116 if (cs->dstbuf_len > 0) { 117 assert(src - cs->srcbuf > cs->srcbuf_len); 118 retval = src - cs->srcbuf - cs->srcbuf_len; 119 cs->srcbuf_len = 0; 120 goto return_char; 121 } 122 123 /* Increase dst buffer size, to obtain the surrogate pair. */ 124 if (err == E2BIG) 125 continue; 126 127 /* Illegal sequence. */ 128 if (invlen > 0) { 129 cs->srcbuf_len = 0; 130 errno = EILSEQ; 131 return ((size_t)-1); 132 } 133 134 /* Save unprocessed remainder for the next invocation. */ 135 memmove(cs->srcbuf, src, srcleft); 136 cs->srcbuf_len = srcleft; 137 return ((size_t)-2); 138 } 139 140 return_char: 141 retchar = cs->dstbuf.widechar[0]; 142 memmove(&cs->dstbuf.widechar[0], &cs->dstbuf.widechar[1], 143 --cs->dstbuf_len * sizeof(charXX_t)); 144 if (pc != NULL) 145 *pc = retchar; 146 if (retchar == 0) 147 return (0); 148 return (retval); 149 } 150 151 size_t 152 mbrtocXX(charXX_t * __restrict pc, const char * __restrict s, size_t n, 153 mbstate_t * __restrict ps) 154 { 155 156 return (mbrtocXX_l(pc, s, n, ps, __get_locale())); 157 } 158