1 /* 2 * Copyright 2010 Nexenta Systems, Inc. All rights reserved. 3 * Use is subject to license terms. 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 27 #include "lint.h" 28 #include <stdlib.h> 29 #include <string.h> 30 #include <wchar.h> 31 32 /* 33 * This function is apparently referenced by parts of ON. It is 34 * not intended for public API usage -- and it is not documented. 35 * 36 * The usage appears to be to consume bytes until a character is 37 * gathered, using a supplied function. It reads exactly one 38 * character and returns the number of bytes in the multibyte string 39 * that were consumed. 40 * 41 * The string "s" is storage for the multibyte string, the 42 * wc will receive the interpreted character, the peek function 43 * obtains the next character (as an int so we can get EOF), 44 * and errorc is stuffed with the character that is responsible 45 * for a parse error, if any. 46 */ 47 48 int 49 _mbftowc(char *s, wchar_t *wc, int (*peek)(void), int *errorc) 50 { 51 int c; 52 mbstate_t mbs; 53 char *start = s; 54 size_t cons = 0; 55 56 for (;;) { 57 c = peek(); 58 if (c < 0) { 59 /* No bytes returned? */ 60 return (s - start); 61 } 62 63 *s = (char)c; 64 s++; 65 66 (void) memset(&mbs, 0, sizeof (mbs)); 67 cons = mbrtowc(wc, start, s - start, &mbs); 68 if ((int)cons >= 0) { 69 /* fully translated character */ 70 return (cons); 71 } 72 if (cons == (size_t)-2) { 73 /* incomplete, recycle */ 74 continue; 75 } 76 77 /* 78 * Parse error, don't consider the first character part 79 * of the error. 80 */ 81 s--; 82 cons = (s - start); 83 *errorc = c >= 0 ? c : 0; 84 break; 85 } 86 87 return (cons); 88 } 89