WPILibC++  2020.3.2
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 #include <system_error>
99 
100 // Wrap everything in namespace wpi so that programs can link with wpiutil and
101 // their own version of the unicode libraries.
102 
103 namespace wpi {
104 
105 /* ---------------------------------------------------------------------
106  The following 4 definitions are compiler-specific.
107  The C standard does not guarantee that wchar_t has at least
108  16 bits, so wchar_t is no less portable than unsigned short!
109  All should be unsigned values to avoid sign extension during
110  bit mask & shift operations.
111 ------------------------------------------------------------------------ */
112 
113 typedef unsigned int UTF32; /* at least 32 bits */
114 typedef unsigned short UTF16; /* at least 16 bits */
115 typedef unsigned char UTF8; /* typically 8 bits */
116 typedef bool Boolean; /* 0 or 1 */
117 
118 /* Some fundamental constants */
119 #define UNI_REPLACEMENT_CHAR (UTF32)0x0000FFFD
120 #define UNI_MAX_BMP (UTF32)0x0000FFFF
121 #define UNI_MAX_UTF16 (UTF32)0x0010FFFF
122 #define UNI_MAX_UTF32 (UTF32)0x7FFFFFFF
123 #define UNI_MAX_LEGAL_UTF32 (UTF32)0x0010FFFF
124 
125 #define UNI_MAX_UTF8_BYTES_PER_CODE_POINT 4
126 
127 #define UNI_UTF16_BYTE_ORDER_MARK_NATIVE 0xFEFF
128 #define UNI_UTF16_BYTE_ORDER_MARK_SWAPPED 0xFFFE
129 
130 typedef enum {
131  conversionOK, /* conversion successful */
132  sourceExhausted, /* partial character in source, but hit end */
133  targetExhausted, /* insuff. room in target for conversion */
134  sourceIllegal /* source sequence is illegal/malformed */
135 } ConversionResult;
136 
137 typedef enum {
138  strictConversion = 0,
139  lenientConversion
140 } ConversionFlags;
141 
142 ConversionResult ConvertUTF8toUTF16 (
143  const UTF8** sourceStart, const UTF8* sourceEnd,
144  UTF16** targetStart, UTF16* targetEnd, ConversionFlags flags);
145 
150 ConversionResult ConvertUTF8toUTF32Partial(
151  const UTF8** sourceStart, const UTF8* sourceEnd,
152  UTF32** targetStart, UTF32* targetEnd, ConversionFlags flags);
153 
158 ConversionResult ConvertUTF8toUTF32(
159  const UTF8** sourceStart, const UTF8* sourceEnd,
160  UTF32** targetStart, UTF32* targetEnd, ConversionFlags flags);
161 
162 ConversionResult ConvertUTF16toUTF8 (
163  const UTF16** sourceStart, const UTF16* sourceEnd,
164  UTF8** targetStart, UTF8* targetEnd, ConversionFlags flags);
165 
166 ConversionResult ConvertUTF32toUTF8 (
167  const UTF32** sourceStart, const UTF32* sourceEnd,
168  UTF8** targetStart, UTF8* targetEnd, ConversionFlags flags);
169 
170 ConversionResult ConvertUTF16toUTF32 (
171  const UTF16** sourceStart, const UTF16* sourceEnd,
172  UTF32** targetStart, UTF32* targetEnd, ConversionFlags flags);
173 
174 ConversionResult ConvertUTF32toUTF16 (
175  const UTF32** sourceStart, const UTF32* sourceEnd,
176  UTF16** targetStart, UTF16* targetEnd, ConversionFlags flags);
177 
178 Boolean isLegalUTF8Sequence(const UTF8 *source, const UTF8 *sourceEnd);
179 
180 Boolean isLegalUTF8String(const UTF8 **source, const UTF8 *sourceEnd);
181 
182 unsigned getNumBytesForUTF8(UTF8 firstByte);
183 
184 /*************************************************************************/
185 /* Below are LLVM-specific wrappers of the functions above. */
186 
187 
198 bool ConvertCodePointToUTF8(unsigned Source, char *&ResultPtr);
199 
215 static inline ConversionResult convertUTF8Sequence(const UTF8 **source,
216  const UTF8 *sourceEnd,
217  UTF32 *target,
218  ConversionFlags flags) {
219  if (*source == sourceEnd)
220  return sourceExhausted;
221  unsigned size = getNumBytesForUTF8(**source);
222  if ((ptrdiff_t)size > sourceEnd - *source)
223  return sourceExhausted;
224  return ConvertUTF8toUTF32(source, *source + size, &target, target + 1, flags);
225 }
226 
231 bool hasUTF16ByteOrderMark(ArrayRef<char> SrcBytes);
232 
238 bool convertUTF16ToUTF8String(ArrayRef<UTF16> SrcUTF16,
239  SmallVectorImpl<char> &DstUTF8);
240 
246 bool convertUTF8ToUTF16String(StringRef SrcUTF8,
247  SmallVectorImpl<UTF16> &DstUTF16);
248 
249 #if defined(_WIN32)
250 namespace sys {
251 namespace windows {
252 std::error_code UTF8ToUTF16(StringRef utf8, SmallVectorImpl<wchar_t> &utf16);
254 std::error_code CurCPToUTF16(StringRef utf8, SmallVectorImpl<wchar_t> &utf16);
255 std::error_code UTF16ToUTF8(const wchar_t *utf16, size_t utf16_len,
256  SmallVectorImpl<char> &utf8);
258 std::error_code UTF16ToCurCP(const wchar_t *utf16, size_t utf16_len,
259  SmallVectorImpl<char> &utf8);
260 } // namespace windows
261 } // namespace sys
262 #endif
263 
264 } /* end namespace wpi */
265 
266 #endif
wpi::ConvertUTF8toUTF32Partial
ConversionResult ConvertUTF8toUTF32Partial(const UTF8 **sourceStart, const UTF8 *sourceEnd, UTF32 **targetStart, UTF32 *targetEnd, ConversionFlags flags)
Convert a partial UTF8 sequence to UTF32.
wpi
WPILib C++ utilities (wpiutil) namespace.
Definition: EventLoopRunner.h:17
wpi::convertUTF8ToUTF16String
bool convertUTF8ToUTF16String(StringRef SrcUTF8, SmallVectorImpl< UTF16 > &DstUTF16)
Converts a UTF-8 string into a UTF-16 string with native endianness.
wpi::hasUTF16ByteOrderMark
bool hasUTF16ByteOrderMark(ArrayRef< char > SrcBytes)
Returns true if a blob of text starts with a UTF-16 big or little endian byte order mark.
wpi::convertUTF8Sequence
static ConversionResult convertUTF8Sequence(const UTF8 **source, const UTF8 *sourceEnd, UTF32 *target, ConversionFlags flags)
Convert the first UTF8 sequence in the given source buffer to a UTF32 code point.
Definition: ConvertUTF.h:215
wpi::ConvertUTF8toUTF32
ConversionResult ConvertUTF8toUTF32(const UTF8 **sourceStart, const UTF8 *sourceEnd, UTF32 **targetStart, UTF32 *targetEnd, ConversionFlags flags)
Convert a partial UTF8 sequence to UTF32.
wpi::size
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:1007
wpi::ConvertCodePointToUTF8
bool ConvertCodePointToUTF8(unsigned Source, char *&ResultPtr)
Convert an Unicode code point to UTF8 sequence.
wpi::convertUTF16ToUTF8String
bool convertUTF16ToUTF8String(ArrayRef< UTF16 > SrcUTF16, SmallVectorImpl< char > &DstUTF8)
Converts a UTF-16 string into a UTF-8 string.