WPILibC++  2018.4.1-20180821013237-1172-g8d8f120
 All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Friends Modules Pages
ConvertUTF.h
1 /*===--- ConvertUTF.h - Universal Character Names conversions ---------------===
2  *
3  * The LLVM Compiler Infrastructure
4  *
5  * This file is distributed under the University of Illinois Open Source
6  * License. See LICENSE.TXT for details.
7  *
8  *==------------------------------------------------------------------------==*/
9 /*
10  * Copyright 2001-2004 Unicode, Inc.
11  *
12  * Disclaimer
13  *
14  * This source code is provided as is by Unicode, Inc. No claims are
15  * made as to fitness for any particular purpose. No warranties of any
16  * kind are expressed or implied. The recipient agrees to determine
17  * applicability of information provided. If this file has been
18  * purchased on magnetic or optical media from Unicode, Inc., the
19  * sole remedy for any claim will be exchange of defective media
20  * within 90 days of receipt.
21  *
22  * Limitations on Rights to Redistribute This Code
23  *
24  * Unicode, Inc. hereby grants the right to freely use the information
25  * supplied in this file in the creation of products supporting the
26  * Unicode Standard, and to make copies of this file in any form
27  * for internal or external distribution as long as this notice
28  * remains attached.
29  */
30 
31 /* ---------------------------------------------------------------------
32 
33  Conversions between UTF32, UTF-16, and UTF-8. Header file.
34 
35  Several funtions are included here, forming a complete set of
36  conversions between the three formats. UTF-7 is not included
37  here, but is handled in a separate source file.
38 
39  Each of these routines takes pointers to input buffers and output
40  buffers. The input buffers are const.
41 
42  Each routine converts the text between *sourceStart and sourceEnd,
43  putting the result into the buffer between *targetStart and
44  targetEnd. Note: the end pointers are *after* the last item: e.g.
45  *(sourceEnd - 1) is the last item.
46 
47  The return result indicates whether the conversion was successful,
48  and if not, whether the problem was in the source or target buffers.
49  (Only the first encountered problem is indicated.)
50 
51  After the conversion, *sourceStart and *targetStart are both
52  updated to point to the end of last text successfully converted in
53  the respective buffers.
54 
55  Input parameters:
56  sourceStart - pointer to a pointer to the source buffer.
57  The contents of this are modified on return so that
58  it points at the next thing to be converted.
59  targetStart - similarly, pointer to pointer to the target buffer.
60  sourceEnd, targetEnd - respectively pointers to the ends of the
61  two buffers, for overflow checking only.
62 
63  These conversion functions take a ConversionFlags argument. When this
64  flag is set to strict, both irregular sequences and isolated surrogates
65  will cause an error. When the flag is set to lenient, both irregular
66  sequences and isolated surrogates are converted.
67 
68  Whether the flag is strict or lenient, all illegal sequences will cause
69  an error return. This includes sequences such as: <F4 90 80 80>, <C0 80>,
70  or <A0> in UTF-8, and values above 0x10FFFF in UTF-32. Conformant code
71  must check for illegal sequences.
72 
73  When the flag is set to lenient, characters over 0x10FFFF are converted
74  to the replacement character; otherwise (when the flag is set to strict)
75  they constitute an error.
76 
77  Output parameters:
78  The value "sourceIllegal" is returned from some routines if the input
79  sequence is malformed. When "sourceIllegal" is returned, the source
80  value will point to the illegal value that caused the problem. E.g.,
81  in UTF-8 when a sequence is malformed, it points to the start of the
82  malformed sequence.
83 
84  Author: Mark E. Davis, 1994.
85  Rev History: Rick McGowan, fixes & updates May 2001.
86  Fixes & updates, Sept 2001.
87 
88 ------------------------------------------------------------------------ */
89 
90 #ifndef LLVM_SUPPORT_CONVERTUTF_H
91 #define LLVM_SUPPORT_CONVERTUTF_H
92 
93 #include "wpi/ArrayRef.h"
94 #include "wpi/StringRef.h"
95 
96 #include <cstddef>
97 #include <string>
98 
99 // Wrap everything in namespace wpi so that programs can link with wpiutil and
100 // their own version of the unicode libraries.
101 
102 namespace wpi {
103 
104 /* ---------------------------------------------------------------------
105  The following 4 definitions are compiler-specific.
106  The C standard does not guarantee that wchar_t has at least
107  16 bits, so wchar_t is no less portable than unsigned short!
108  All should be unsigned values to avoid sign extension during
109  bit mask & shift operations.
110 ------------------------------------------------------------------------ */
111 
112 typedef unsigned int UTF32; /* at least 32 bits */
113 typedef unsigned short UTF16; /* at least 16 bits */
114 typedef unsigned char UTF8; /* typically 8 bits */
115 typedef bool Boolean; /* 0 or 1 */
116 
117 /* Some fundamental constants */
118 #define UNI_REPLACEMENT_CHAR (UTF32)0x0000FFFD
119 #define UNI_MAX_BMP (UTF32)0x0000FFFF
120 #define UNI_MAX_UTF16 (UTF32)0x0010FFFF
121 #define UNI_MAX_UTF32 (UTF32)0x7FFFFFFF
122 #define UNI_MAX_LEGAL_UTF32 (UTF32)0x0010FFFF
123 
124 #define UNI_MAX_UTF8_BYTES_PER_CODE_POINT 4
125 
126 #define UNI_UTF16_BYTE_ORDER_MARK_NATIVE 0xFEFF
127 #define UNI_UTF16_BYTE_ORDER_MARK_SWAPPED 0xFFFE
128 
129 typedef enum {
130  conversionOK, /* conversion successful */
131  sourceExhausted, /* partial character in source, but hit end */
132  targetExhausted, /* insuff. room in target for conversion */
133  sourceIllegal /* source sequence is illegal/malformed */
134 } ConversionResult;
135 
136 typedef enum {
137  strictConversion = 0,
138  lenientConversion
139 } ConversionFlags;
140 
141 ConversionResult ConvertUTF8toUTF16 (
142  const UTF8** sourceStart, const UTF8* sourceEnd,
143  UTF16** targetStart, UTF16* targetEnd, ConversionFlags flags);
144 
149 ConversionResult ConvertUTF8toUTF32Partial(
150  const UTF8** sourceStart, const UTF8* sourceEnd,
151  UTF32** targetStart, UTF32* targetEnd, ConversionFlags flags);
152 
157 ConversionResult ConvertUTF8toUTF32(
158  const UTF8** sourceStart, const UTF8* sourceEnd,
159  UTF32** targetStart, UTF32* targetEnd, ConversionFlags flags);
160 
161 ConversionResult ConvertUTF16toUTF8 (
162  const UTF16** sourceStart, const UTF16* sourceEnd,
163  UTF8** targetStart, UTF8* targetEnd, ConversionFlags flags);
164 
165 ConversionResult ConvertUTF32toUTF8 (
166  const UTF32** sourceStart, const UTF32* sourceEnd,
167  UTF8** targetStart, UTF8* targetEnd, ConversionFlags flags);
168 
169 ConversionResult ConvertUTF16toUTF32 (
170  const UTF16** sourceStart, const UTF16* sourceEnd,
171  UTF32** targetStart, UTF32* targetEnd, ConversionFlags flags);
172 
173 ConversionResult ConvertUTF32toUTF16 (
174  const UTF32** sourceStart, const UTF32* sourceEnd,
175  UTF16** targetStart, UTF16* targetEnd, ConversionFlags flags);
176 
177 Boolean isLegalUTF8Sequence(const UTF8 *source, const UTF8 *sourceEnd);
178 
179 Boolean isLegalUTF8String(const UTF8 **source, const UTF8 *sourceEnd);
180 
181 unsigned getNumBytesForUTF8(UTF8 firstByte);
182 
183 /*************************************************************************/
184 /* Below are LLVM-specific wrappers of the functions above. */
185 
186 
197 bool ConvertCodePointToUTF8(unsigned Source, char *&ResultPtr);
198 
214 static inline ConversionResult convertUTF8Sequence(const UTF8 **source,
215  const UTF8 *sourceEnd,
216  UTF32 *target,
217  ConversionFlags flags) {
218  if (*source == sourceEnd)
219  return sourceExhausted;
220  unsigned size = getNumBytesForUTF8(**source);
221  if ((ptrdiff_t)size > sourceEnd - *source)
222  return sourceExhausted;
223  return ConvertUTF8toUTF32(source, *source + size, &target, target + 1, flags);
224 }
225 
230 bool hasUTF16ByteOrderMark(ArrayRef<char> SrcBytes);
231 
237 bool convertUTF16ToUTF8String(ArrayRef<UTF16> SrcUTF16,
238  SmallVectorImpl<char> &DstUTF8);
239 
245 bool convertUTF8ToUTF16String(StringRef SrcUTF8,
246  SmallVectorImpl<UTF16> &DstUTF16);
247 
248 } /* end namespace wpi */
249 
250 #endif
ConversionResult ConvertUTF8toUTF32Partial(const UTF8 **sourceStart, const UTF8 *sourceEnd, UTF32 **targetStart, UTF32 *targetEnd, ConversionFlags flags)
Convert a partial UTF8 sequence to UTF32.
WPILib C++ utilities (wpiutil) namespace.
Definition: SmallString.h:21
ConversionResult ConvertUTF8toUTF32(const UTF8 **sourceStart, const UTF8 *sourceEnd, UTF32 **targetStart, UTF32 *targetEnd, ConversionFlags flags)
Convert a partial UTF8 sequence to UTF32.
bool hasUTF16ByteOrderMark(ArrayRef< char > SrcBytes)
Returns true if a blob of text starts with a UTF-16 big or little endian byte order mark...
bool convertUTF8ToUTF16String(StringRef SrcUTF8, SmallVectorImpl< UTF16 > &DstUTF16)
Converts a UTF-8 string into a UTF-16 string with native endianness.
bool convertUTF16ToUTF8String(ArrayRef< UTF16 > SrcUTF16, SmallVectorImpl< char > &DstUTF8)
Converts a UTF-16 string into a UTF-8 string.
auto size(R &&Range, typename std::enable_if< std::is_same< typename std::iterator_traits< decltype(Range.begin())>::iterator_category, std::random_access_iterator_tag >::value, void >::type *=nullptr) -> decltype(std::distance(Range.begin(), Range.end()))
Get the size of a range.
Definition: STLExtras.h:999
bool ConvertCodePointToUTF8(unsigned Source, char *&ResultPtr)
Convert an Unicode code point to UTF8 sequence.