1/* Character set conversion with error handling and autodetection. 2 Copyright (C) 2002, 2005, 2007-2010 Free Software Foundation, Inc. 3 Written by Bruno Haible. 4 5 This program is free software: you can redistribute it and/or modify 6 it under the terms of the GNU Lesser General Public License as published by 7 the Free Software Foundation; either version 3 of the License, or 8 (at your option) any later version. 9 10 This program is distributed in the hope that it will be useful, 11 but WITHOUT ANY WARRANTY; without even the implied warranty of 12 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 13 GNU Lesser General Public License for more details. 14 15 You should have received a copy of the GNU Lesser General Public License 16 along with this program. If not, see <http://www.gnu.org/licenses/>. */ 17 18#ifndef _STRICONVEHA_H 19#define _STRICONVEHA_H 20 21#include <stdbool.h> 22#include <stddef.h> 23 24#include "iconveh.h" 25 26 27#ifdef __cplusplus 28extern "C" { 29#endif 30 31 32/* Convert an entire string from one encoding to another, using iconv. 33 The original string is at [SRC,...,SRC+SRCLEN-1]. 34 The "from" encoding can also be a name defined for autodetection. 35 If TRANSLITERATE is true, transliteration will attempted to avoid conversion 36 errors, for iconv implementations that support this. Usually you'll choose 37 TRANSLITERATE = true if HANDLER != iconveh_error. 38 If OFFSETS is not NULL, it should point to an array of SRCLEN integers; this 39 array is filled with offsets into the result, i.e. the character starting 40 at SRC[i] corresponds to the character starting at (*RESULTP)[OFFSETS[i]], 41 and other offsets are set to (size_t)(-1). 42 *RESULTP and *LENGTH should initially be a scratch buffer and its size, 43 or *RESULTP can initially be NULL. 44 May erase the contents of the memory at *RESULTP. 45 Return value: 0 if successful, otherwise -1 and errno set. 46 If successful: The resulting string is stored in *RESULTP and its length 47 in *LENGTHP. *RESULTP is set to a freshly allocated memory block, or is 48 unchanged if no dynamic memory allocation was necessary. */ 49extern int 50 mem_iconveha (const char *src, size_t srclen, 51 const char *from_codeset, const char *to_codeset, 52 bool transliterate, 53 enum iconv_ilseq_handler handler, 54 size_t *offsets, 55 char **resultp, size_t *lengthp); 56 57/* Convert an entire string from one encoding to another, using iconv. 58 The original string is the NUL-terminated string starting at SRC. 59 Both the "from" and the "to" encoding must use a single NUL byte at the 60 end of the string (i.e. not UCS-2, UCS-4, UTF-16, UTF-32). 61 The "from" encoding can also be a name defined for autodetection. 62 If TRANSLITERATE is true, transliteration will attempted to avoid conversion 63 errors, for iconv implementations that support this. Usually you'll choose 64 TRANSLITERATE = true if HANDLER != iconveh_error. 65 Allocate a malloced memory block for the result. 66 Return value: the freshly allocated resulting NUL-terminated string if 67 successful, otherwise NULL and errno set. */ 68extern char * 69 str_iconveha (const char *src, 70 const char *from_codeset, const char *to_codeset, 71 bool transliterate, 72 enum iconv_ilseq_handler handler); 73 74 75/* In the above, FROM_CODESET can also be one of the following values: 76 "autodetect_utf8" supports ISO-8859-1 and UTF-8 77 "autodetect_jp" supports EUC-JP, ISO-2022-JP-2 and SHIFT_JIS 78 "autodetect_kr" supports EUC-KR and ISO-2022-KR 79 More names can be defined for autodetection. */ 80 81/* Registers an encoding name for autodetection. 82 TRY_IN_ORDER is a NULL terminated list of encodings to be tried. 83 Returns 0 upon success, or -1 (with errno set) in case of error. 84 Particular errno values: ENOMEM. */ 85extern int 86 uniconv_register_autodetect (const char *name, 87 const char * const *try_in_order); 88 89 90#ifdef __cplusplus 91} 92#endif 93 94 95#endif /* _STRICONVEHA_H */ 96