1#ifndef CONVERT_UNICODE_H 2#define CONVERT_UNICODE_H 3 4#ifndef __TRANSMISSION__ 5#error only libtransmission should #include this header. 6#endif 7 8/* 9 * Copyright 2001-2004 Unicode, Inc. 10 * 11 * Disclaimer 12 * 13 * This source code is provided as is by Unicode, Inc. No claims are 14 * made as to fitness for any particular purpose. No warranties of any 15 * kind are expressed or implied. The recipient agrees to determine 16 * applicability of information provided. If this file has been 17 * purchased on magnetic or optical media from Unicode, Inc., the 18 * sole remedy for any claim will be exchange of defective media 19 * within 90 days of receipt. 20 * 21 * Limitations on Rights to Redistribute This Code 22 * 23 * Unicode, Inc. hereby grants the right to freely use the information 24 * supplied in this file in the creation of products supporting the 25 * Unicode Standard, and to make copies of this file in any form 26 * for internal or external distribution as long as this notice 27 * remains attached. 28 */ 29 30/* --------------------------------------------------------------------- 31 32 Conversions between UTF32, UTF-16, and UTF-8. Header file. 33 34 Several funtions are included here, forming a complete set of 35 conversions between the three formats. UTF-7 is not included 36 here, but is handled in a separate source file. 37 38 Each of these routines takes pointers to input buffers and output 39 buffers. The input buffers are const. 40 41 Each routine converts the text between *sourceStart and sourceEnd, 42 putting the result into the buffer between *targetStart and 43 targetEnd. Note: the end pointers are *after* the last item: e.g. 44 *(sourceEnd - 1) is the last item. 45 46 The return result indicates whether the conversion was successful, 47 and if not, whether the problem was in the source or target buffers. 48 (Only the first encountered problem is indicated.) 49 50 After the conversion, *sourceStart and *targetStart are both 51 updated to point to the end of last text successfully converted in 52 the respective buffers. 53 54 Input parameters: 55 sourceStart - pointer to a pointer to the source buffer. 56 The contents of this are modified on return so that 57 it points at the next thing to be converted. 58 targetStart - similarly, pointer to pointer to the target buffer. 59 sourceEnd, targetEnd - respectively pointers to the ends of the 60 two buffers, for overflow checking only. 61 62 These conversion functions take a ConversionFlags argument. When this 63 flag is set to strict, both irregular sequences and isolated surrogates 64 will cause an error. When the flag is set to lenient, both irregular 65 sequences and isolated surrogates are converted. 66 67 Whether the flag is strict or lenient, all illegal sequences will cause 68 an error return. This includes sequences such as: <F4 90 80 80>, <C0 80>, 69 or <A0> in UTF-8, and values above 0x10FFFF in UTF-32. Conformant code 70 must check for illegal sequences. 71 72 When the flag is set to lenient, characters over 0x10FFFF are converted 73 to the replacement character; otherwise (when the flag is set to strict) 74 they constitute an error. 75 76 Output parameters: 77 The value "sourceIllegal" is returned from some routines if the input 78 sequence is malformed. When "sourceIllegal" is returned, the source 79 value will point to the illegal value that caused the problem. E.g., 80 in UTF-8 when a sequence is malformed, it points to the start of the 81 malformed sequence. 82 83 Author: Mark E. Davis, 1994. 84 Rev History: Rick McGowan, fixes & updates May 2001. 85 Fixes & updates, Sept 2001. 86 87------------------------------------------------------------------------ */ 88 89/* --------------------------------------------------------------------- 90 The following 4 definitions are compiler-specific. 91 The C standard does not guarantee that wchar_t has at least 92 16 bits, so wchar_t is no less portable than unsigned short! 93 All should be unsigned values to avoid sign extension during 94 bit mask & shift operations. 95------------------------------------------------------------------------ */ 96 97typedef unsigned long UTF32; /* at least 32 bits */ 98typedef unsigned short UTF16; /* at least 16 bits */ 99typedef unsigned char UTF8; /* typically 8 bits */ 100typedef unsigned char Boolean; /* 0 or 1 */ 101 102/* Some fundamental constants */ 103#define UNI_REPLACEMENT_CHAR (UTF32)0x0000FFFD 104#define UNI_MAX_BMP (UTF32)0x0000FFFF 105#define UNI_MAX_UTF16 (UTF32)0x0010FFFF 106#define UNI_MAX_UTF32 (UTF32)0x7FFFFFFF 107#define UNI_MAX_LEGAL_UTF32 (UTF32)0x0010FFFF 108 109typedef enum { 110 conversionOK, /* conversion successful */ 111 sourceExhausted, /* partial character in source, but hit end */ 112 targetExhausted, /* insuff. room in target for conversion */ 113 sourceIllegal /* source sequence is illegal/malformed */ 114} ConversionResult; 115 116typedef enum { 117 strictConversion = 0, 118 lenientConversion 119} ConversionFlags; 120 121/* This is for C++ and does no harm in C */ 122#ifdef __cplusplus 123extern "C" { 124#endif 125 126ConversionResult ConvertUTF8toUTF16 ( 127 const UTF8** sourceStart, const UTF8* sourceEnd, 128 UTF16** targetStart, UTF16* targetEnd, ConversionFlags flags); 129 130ConversionResult ConvertUTF16toUTF8 ( 131 const UTF16** sourceStart, const UTF16* sourceEnd, 132 UTF8** targetStart, UTF8* targetEnd, ConversionFlags flags); 133 134ConversionResult ConvertUTF8toUTF32 ( 135 const UTF8** sourceStart, const UTF8* sourceEnd, 136 UTF32** targetStart, UTF32* targetEnd, ConversionFlags flags); 137 138ConversionResult ConvertUTF32toUTF8 ( 139 const UTF32** sourceStart, const UTF32* sourceEnd, 140 UTF8** targetStart, UTF8* targetEnd, ConversionFlags flags); 141 142ConversionResult ConvertUTF16toUTF32 ( 143 const UTF16** sourceStart, const UTF16* sourceEnd, 144 UTF32** targetStart, UTF32* targetEnd, ConversionFlags flags); 145 146ConversionResult ConvertUTF32toUTF16 ( 147 const UTF32** sourceStart, const UTF32* sourceEnd, 148 UTF16** targetStart, UTF16* targetEnd, ConversionFlags flags); 149 150Boolean isLegalUTF8Sequence(const UTF8 *source, const UTF8 *sourceEnd); 151 152 153/* intended to work the same as g_utf8_validate */ 154Boolean tr_utf8_validate( const char * str, int max_len, const char ** end ); 155 156 157#ifdef __cplusplus 158} 159#endif 160 161/* --------------------------------------------------------------------- */ 162 163#endif /* CONVERT_UNICODE_H */ 164