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