1 /*- 2 * SPDX-License-Identifier: BSD-2-Clause 3 * 4 * Copyright (c) 2013 Ed Schouten <ed@FreeBSD.org> 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 #include <sys/cdefs.h> 30 __FBSDID("$FreeBSD$"); 31 32 #include <sys/queue.h> 33 34 #include <assert.h> 35 #include <errno.h> 36 #include <langinfo.h> 37 #include <limits.h> 38 #include <string.h> 39 #include <uchar.h> 40 41 #include "../iconv/citrus_hash.h" 42 #include "../iconv/citrus_module.h" 43 #include "../iconv/citrus_iconv.h" 44 #include "mblocal.h" 45 46 typedef struct { 47 bool initialized; 48 struct _citrus_iconv iconv; 49 char srcbuf[MB_LEN_MAX]; 50 size_t srcbuf_len; 51 union { 52 charXX_t widechar[DSTBUF_LEN]; 53 char bytes[sizeof(charXX_t) * DSTBUF_LEN]; 54 } dstbuf; 55 size_t dstbuf_len; 56 } _ConversionState; 57 _Static_assert(sizeof(_ConversionState) <= sizeof(mbstate_t), 58 "Size of _ConversionState must not exceed mbstate_t's size."); 59 60 size_t 61 mbrtocXX_l(charXX_t * __restrict pc, const char * __restrict s, size_t n, 62 mbstate_t * __restrict ps, locale_t locale) 63 { 64 _ConversionState *cs; 65 struct _citrus_iconv *handle; 66 size_t i, retval; 67 charXX_t retchar; 68 69 FIX_LOCALE(locale); 70 if (ps == NULL) 71 ps = &(XLOCALE_CTYPE(locale)->mbrtocXX); 72 cs = (_ConversionState *)ps; 73 handle = &cs->iconv; 74 75 /* Reinitialize mbstate_t. */ 76 if (s == NULL || !cs->initialized) { 77 if (_citrus_iconv_open(&handle, 78 nl_langinfo_l(CODESET, locale), UTF_XX_INTERNAL) != 0) { 79 cs->initialized = false; 80 errno = EINVAL; 81 return (-1); 82 } 83 handle->cv_shared->ci_discard_ilseq = true; 84 handle->cv_shared->ci_hooks = NULL; 85 cs->srcbuf_len = cs->dstbuf_len = 0; 86 cs->initialized = true; 87 if (s == NULL) 88 return (0); 89 } 90 91 /* See if we still have characters left from the previous invocation. */ 92 if (cs->dstbuf_len > 0) { 93 retval = (size_t)-3; 94 goto return_char; 95 } 96 97 /* Fill up the read buffer as far as possible. */ 98 if (n > sizeof(cs->srcbuf) - cs->srcbuf_len) 99 n = sizeof(cs->srcbuf) - cs->srcbuf_len; 100 memcpy(cs->srcbuf + cs->srcbuf_len, s, n); 101 102 /* Convert as few characters to the dst buffer as possible. */ 103 for (i = 0; ; i++) { 104 char *src, *dst; 105 size_t srcleft, dstleft, invlen; 106 int err; 107 108 src = cs->srcbuf; 109 srcleft = cs->srcbuf_len + n; 110 dst = cs->dstbuf.bytes; 111 dstleft = i * sizeof(charXX_t); 112 assert(srcleft <= sizeof(cs->srcbuf) && 113 dstleft <= sizeof(cs->dstbuf.bytes)); 114 err = _citrus_iconv_convert(handle, &src, &srcleft, 115 &dst, &dstleft, 0, &invlen); 116 cs->dstbuf_len = (dst - cs->dstbuf.bytes) / sizeof(charXX_t); 117 118 /* Got new character(s). Return the first. */ 119 if (cs->dstbuf_len > 0) { 120 assert(src - cs->srcbuf > cs->srcbuf_len); 121 retval = src - cs->srcbuf - cs->srcbuf_len; 122 cs->srcbuf_len = 0; 123 goto return_char; 124 } 125 126 /* Increase dst buffer size, to obtain the surrogate pair. */ 127 if (err == E2BIG) 128 continue; 129 130 /* Illegal sequence. */ 131 if (invlen > 0) { 132 cs->srcbuf_len = 0; 133 errno = EILSEQ; 134 return ((size_t)-1); 135 } 136 137 /* Save unprocessed remainder for the next invocation. */ 138 memmove(cs->srcbuf, src, srcleft); 139 cs->srcbuf_len = srcleft; 140 return ((size_t)-2); 141 } 142 143 return_char: 144 retchar = cs->dstbuf.widechar[0]; 145 memmove(&cs->dstbuf.widechar[0], &cs->dstbuf.widechar[1], 146 --cs->dstbuf_len * sizeof(charXX_t)); 147 if (pc != NULL) 148 *pc = retchar; 149 if (retchar == 0) 150 return (0); 151 return (retval); 152 } 153 154 size_t 155 mbrtocXX(charXX_t * __restrict pc, const char * __restrict s, size_t n, 156 mbstate_t * __restrict ps) 157 { 158 159 return (mbrtocXX_l(pc, s, n, ps, __get_locale())); 160 } 161