1 /* 2 * Copyright 2001-2004 Unicode, Inc. 3 * 4 * Disclaimer 5 * 6 * This source code is provided as is by Unicode, Inc. No claims are 7 * made as to fitness for any particular purpose. No warranties of any 8 * kind are expressed or implied. The recipient agrees to determine 9 * applicability of information provided. If this file has been 10 * purchased on magnetic or optical media from Unicode, Inc., the 11 * sole remedy for any claim will be exchange of defective media 12 * within 90 days of receipt. 13 * 14 * Limitations on Rights to Redistribute This Code 15 * 16 * Unicode, Inc. hereby grants the right to freely use the information 17 * supplied in this file in the creation of products supporting the 18 * Unicode Standard, and to make copies of this file in any form 19 * for internal or external distribution as long as this notice 20 * remains attached. 21 */ 22 23 /* --------------------------------------------------------------------- 24 25 Conversions between UTF32, UTF-16, and UTF-8. Header file. 26 27 Several functions are included here, forming a complete set of 28 conversions between the three formats. UTF-7 is not included 29 here, but is handled in a separate source file. 30 31 Each of these routines takes pointers to input buffers and output 32 buffers. The input buffers are const. 33 34 Each routine converts the text between *sourceStart and sourceEnd, 35 putting the result into the buffer between *targetStart and 36 targetEnd. Note: the end pointers are *after* the last item: e.g. 37 *(sourceEnd - 1) is the last item. 38 39 The return result indicates whether the conversion was successful, 40 and if not, whether the problem was in the source or target buffers. 41 (Only the first encountered problem is indicated.) 42 43 After the conversion, *sourceStart and *targetStart are both 44 updated to point to the end of last text successfully converted in 45 the respective buffers. 46 47 Input parameters: 48 sourceStart - pointer to a pointer to the source buffer. 49 The contents of this are modified on return so that 50 it points at the next thing to be converted. 51 targetStart - similarly, pointer to pointer to the target buffer. 52 sourceEnd, targetEnd - respectively pointers to the ends of the 53 two buffers, for overflow checking only. 54 55 These conversion functions take a ConversionFlags argument. When this 56 flag is set to strict, both irregular sequences and isolated surrogates 57 will cause an error. When the flag is set to lenient, both irregular 58 sequences and isolated surrogates are converted. 59 60 Whether the flag is strict or lenient, all illegal sequences will cause 61 an error return. This includes sequences such as: <F4 90 80 80>, <C0 80>, 62 or <A0> in UTF-8, and values above 0x10FFFF in UTF-32. Conformant code 63 must check for illegal sequences. 64 65 When the flag is set to lenient, characters over 0x10FFFF are converted 66 to the replacement character; otherwise (when the flag is set to strict) 67 they constitute an error. 68 69 Output parameters: 70 The value "sourceIllegal" is returned from some routines if the input 71 sequence is malformed. When "sourceIllegal" is returned, the source 72 value will point to the illegal value that caused the problem. E.g., 73 in UTF-8 when a sequence is malformed, it points to the start of the 74 malformed sequence. 75 76 Author: Mark E. Davis, 1994. 77 Rev History: Rick McGowan, fixes & updates May 2001. 78 Fixes & updates, Sept 2001. 79 80 ------------------------------------------------------------------------ */ 81 82 /* --------------------------------------------------------------------- 83 The following 4 definitions are compiler-specific. 84 The C standard does not guarantee that wchar_t has at least 85 16 bits, so wchar_t is no less portable than unsigned short! 86 All should be unsigned values to avoid sign extension during 87 bit mask & shift operations. 88 ------------------------------------------------------------------------ */ 89 90 91 // Changes for ANTLR3 - Jim Idle, January 2008. 92 // builtin types defined for Unicode types changed to 93 // aliases for the types that are system determined by 94 // ANTLR at compile time. 95 // 96 // typedef unsigned long UTF32; /* at least 32 bits */ 97 // typedef unsigned short UTF16; /* at least 16 bits */ 98 // typedef unsigned char UTF8; /* typically 8 bits */ 99 // typedef unsigned char Boolean; /* 0 or 1 */ 100 101 #ifndef _ANTLR3_CONVERTUTF_H 102 #define _ANTLR3_CONVERTUTF_H 103 104 #include <antlr3defs.h> 105 106 typedef ANTLR3_UINT32 UTF32; /* at least 32 bits */ 107 typedef ANTLR3_UINT16 UTF16; /* at least 16 bits */ 108 typedef ANTLR3_UINT8 UTF8; /* typically 8 bits */ 109 110 /* Some fundamental constants */ 111 #define UNI_REPLACEMENT_CHAR (UTF32)0x0000FFFD 112 #define UNI_MAX_BMP (UTF32)0x0000FFFF 113 #define UNI_MAX_UTF16 (UTF32)0x0010FFFF 114 #define UNI_MAX_UTF32 (UTF32)0x7FFFFFFF 115 #define UNI_MAX_LEGAL_UTF32 (UTF32)0x0010FFFF 116 117 #define UNI_SUR_HIGH_START (UTF32)0xD800 118 #define UNI_SUR_HIGH_END (UTF32)0xDBFF 119 #define UNI_SUR_LOW_START (UTF32)0xDC00 120 #define UNI_SUR_LOW_END (UTF32)0xDFFF 121 #define false ANTLR3_FALSE 122 #define true ANTLR3_TRUE 123 #define halfShift ((UTF32)10) 124 #define halfBase ((UTF32)0x0010000UL) 125 #define halfMask ((UTF32)0x3FFUL) 126 127 typedef enum { 128 conversionOK, /* conversion successful */ 129 sourceExhausted, /* partial character in source, but hit end */ 130 targetExhausted, /* insuff. room in target for conversion */ 131 sourceIllegal /* source sequence is illegal/malformed */ 132 } ConversionResult; 133 134 typedef enum { 135 strictConversion = 0, 136 lenientConversion 137 } ConversionFlags; 138 139 /* This is for C++ and does no harm in C */ 140 #ifdef __cplusplus 141 extern "C" { 142 #endif 143 144 ConversionResult ConvertUTF8toUTF16 ( 145 const UTF8** sourceStart, const UTF8* sourceEnd, 146 UTF16** targetStart, UTF16* targetEnd, ConversionFlags flags); 147 148 ConversionResult ConvertUTF16toUTF8 ( 149 const UTF16** sourceStart, const UTF16* sourceEnd, 150 UTF8** targetStart, UTF8* targetEnd, ConversionFlags flags); 151 152 ConversionResult ConvertUTF8toUTF32 ( 153 const UTF8** sourceStart, const UTF8* sourceEnd, 154 UTF32** targetStart, UTF32* targetEnd, ConversionFlags flags); 155 156 ConversionResult ConvertUTF32toUTF8 ( 157 const UTF32** sourceStart, const UTF32* sourceEnd, 158 UTF8** targetStart, UTF8* targetEnd, ConversionFlags flags); 159 160 ConversionResult ConvertUTF16toUTF32 ( 161 const UTF16** sourceStart, const UTF16* sourceEnd, 162 UTF32** targetStart, UTF32* targetEnd, ConversionFlags flags); 163 164 ConversionResult ConvertUTF32toUTF16 ( 165 const UTF32** sourceStart, const UTF32* sourceEnd, 166 UTF16** targetStart, UTF16* targetEnd, ConversionFlags flags); 167 168 ANTLR3_BOOLEAN isLegalUTF8Sequence(const UTF8 *source, const UTF8 *sourceEnd); 169 170 #ifdef __cplusplus 171 } 172 #endif 173 174 #endif 175 176 /* --------------------------------------------------------------------- */ 177