0
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
1 //===-- ConvertUTFWrapper.cpp - Wrap ConvertUTF.h with clang data types -----===
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
2 //
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
3 // The LLVM Compiler Infrastructure
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
4 //
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
5 // This file is distributed under the University of Illinois Open Source
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
6 // License. See LICENSE.TXT for details.
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
7 //
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
8 //===----------------------------------------------------------------------===//
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
9
|
120
|
10 #include "llvm/ADT/ArrayRef.h"
|
|
11 #include "llvm/ADT/StringRef.h"
|
121
|
12 #include "llvm/Support/ConvertUTF.h"
|
120
|
13 #include "llvm/Support/ErrorHandling.h"
|
0
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
14 #include "llvm/Support/SwapByteOrder.h"
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
15 #include <string>
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
16 #include <vector>
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
17
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
18 namespace llvm {
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
19
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
20 bool ConvertUTF8toWide(unsigned WideCharWidth, llvm::StringRef Source,
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
21 char *&ResultPtr, const UTF8 *&ErrorPtr) {
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
22 assert(WideCharWidth == 1 || WideCharWidth == 2 || WideCharWidth == 4);
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
23 ConversionResult result = conversionOK;
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
24 // Copy the character span over.
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
25 if (WideCharWidth == 1) {
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
26 const UTF8 *Pos = reinterpret_cast<const UTF8*>(Source.begin());
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
27 if (!isLegalUTF8String(&Pos, reinterpret_cast<const UTF8*>(Source.end()))) {
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
28 result = sourceIllegal;
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
29 ErrorPtr = Pos;
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
30 } else {
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
31 memcpy(ResultPtr, Source.data(), Source.size());
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
32 ResultPtr += Source.size();
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
33 }
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
34 } else if (WideCharWidth == 2) {
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
35 const UTF8 *sourceStart = (const UTF8*)Source.data();
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
36 // FIXME: Make the type of the result buffer correct instead of
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
37 // using reinterpret_cast.
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
38 UTF16 *targetStart = reinterpret_cast<UTF16*>(ResultPtr);
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
39 ConversionFlags flags = strictConversion;
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
40 result = ConvertUTF8toUTF16(
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
41 &sourceStart, sourceStart + Source.size(),
|
120
|
42 &targetStart, targetStart + Source.size(), flags);
|
0
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
43 if (result == conversionOK)
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
44 ResultPtr = reinterpret_cast<char*>(targetStart);
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
45 else
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
46 ErrorPtr = sourceStart;
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
47 } else if (WideCharWidth == 4) {
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
48 const UTF8 *sourceStart = (const UTF8*)Source.data();
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
49 // FIXME: Make the type of the result buffer correct instead of
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
50 // using reinterpret_cast.
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
51 UTF32 *targetStart = reinterpret_cast<UTF32*>(ResultPtr);
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
52 ConversionFlags flags = strictConversion;
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
53 result = ConvertUTF8toUTF32(
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
54 &sourceStart, sourceStart + Source.size(),
|
120
|
55 &targetStart, targetStart + Source.size(), flags);
|
0
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
56 if (result == conversionOK)
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
57 ResultPtr = reinterpret_cast<char*>(targetStart);
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
58 else
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
59 ErrorPtr = sourceStart;
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
60 }
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
61 assert((result != targetExhausted)
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
62 && "ConvertUTF8toUTFXX exhausted target buffer");
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
63 return result == conversionOK;
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
64 }
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
65
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
66 bool ConvertCodePointToUTF8(unsigned Source, char *&ResultPtr) {
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
67 const UTF32 *SourceStart = &Source;
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
68 const UTF32 *SourceEnd = SourceStart + 1;
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
69 UTF8 *TargetStart = reinterpret_cast<UTF8 *>(ResultPtr);
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
70 UTF8 *TargetEnd = TargetStart + 4;
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
71 ConversionResult CR = ConvertUTF32toUTF8(&SourceStart, SourceEnd,
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
72 &TargetStart, TargetEnd,
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
73 strictConversion);
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
74 if (CR != conversionOK)
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
75 return false;
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
76
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
77 ResultPtr = reinterpret_cast<char*>(TargetStart);
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
78 return true;
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
79 }
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
80
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
81 bool hasUTF16ByteOrderMark(ArrayRef<char> S) {
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
82 return (S.size() >= 2 &&
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
83 ((S[0] == '\xff' && S[1] == '\xfe') ||
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
84 (S[0] == '\xfe' && S[1] == '\xff')));
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
85 }
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
86
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
87 bool convertUTF16ToUTF8String(ArrayRef<char> SrcBytes, std::string &Out) {
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
88 assert(Out.empty());
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
89
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
90 // Error out on an uneven byte count.
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
91 if (SrcBytes.size() % 2)
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
92 return false;
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
93
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
94 // Avoid OOB by returning early on empty input.
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
95 if (SrcBytes.empty())
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
96 return true;
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
97
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
98 const UTF16 *Src = reinterpret_cast<const UTF16 *>(SrcBytes.begin());
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
99 const UTF16 *SrcEnd = reinterpret_cast<const UTF16 *>(SrcBytes.end());
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
100
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
101 // Byteswap if necessary.
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
102 std::vector<UTF16> ByteSwapped;
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
103 if (Src[0] == UNI_UTF16_BYTE_ORDER_MARK_SWAPPED) {
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
104 ByteSwapped.insert(ByteSwapped.end(), Src, SrcEnd);
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
105 for (unsigned I = 0, E = ByteSwapped.size(); I != E; ++I)
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
106 ByteSwapped[I] = llvm::sys::SwapByteOrder_16(ByteSwapped[I]);
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
107 Src = &ByteSwapped[0];
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
108 SrcEnd = &ByteSwapped[ByteSwapped.size() - 1] + 1;
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
109 }
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
110
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
111 // Skip the BOM for conversion.
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
112 if (Src[0] == UNI_UTF16_BYTE_ORDER_MARK_NATIVE)
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
113 Src++;
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
114
|
83
|
115 // Just allocate enough space up front. We'll shrink it later. Allocate
|
|
116 // enough that we can fit a null terminator without reallocating.
|
|
117 Out.resize(SrcBytes.size() * UNI_MAX_UTF8_BYTES_PER_CODE_POINT + 1);
|
0
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
118 UTF8 *Dst = reinterpret_cast<UTF8 *>(&Out[0]);
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
119 UTF8 *DstEnd = Dst + Out.size();
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
120
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
121 ConversionResult CR =
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
122 ConvertUTF16toUTF8(&Src, SrcEnd, &Dst, DstEnd, strictConversion);
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
123 assert(CR != targetExhausted);
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
124
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
125 if (CR != conversionOK) {
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
126 Out.clear();
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
127 return false;
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
128 }
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
129
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
130 Out.resize(reinterpret_cast<char *>(Dst) - &Out[0]);
|
83
|
131 Out.push_back(0);
|
|
132 Out.pop_back();
|
|
133 return true;
|
|
134 }
|
|
135
|
120
|
136 bool convertUTF16ToUTF8String(ArrayRef<UTF16> Src, std::string &Out)
|
|
137 {
|
|
138 return convertUTF16ToUTF8String(
|
|
139 llvm::ArrayRef<char>(reinterpret_cast<const char *>(Src.data()),
|
|
140 Src.size() * sizeof(UTF16)), Out);
|
|
141 }
|
|
142
|
83
|
143 bool convertUTF8ToUTF16String(StringRef SrcUTF8,
|
|
144 SmallVectorImpl<UTF16> &DstUTF16) {
|
|
145 assert(DstUTF16.empty());
|
|
146
|
|
147 // Avoid OOB by returning early on empty input.
|
|
148 if (SrcUTF8.empty()) {
|
|
149 DstUTF16.push_back(0);
|
|
150 DstUTF16.pop_back();
|
|
151 return true;
|
|
152 }
|
|
153
|
|
154 const UTF8 *Src = reinterpret_cast<const UTF8 *>(SrcUTF8.begin());
|
|
155 const UTF8 *SrcEnd = reinterpret_cast<const UTF8 *>(SrcUTF8.end());
|
|
156
|
|
157 // Allocate the same number of UTF-16 code units as UTF-8 code units. Encoding
|
|
158 // as UTF-16 should always require the same amount or less code units than the
|
|
159 // UTF-8 encoding. Allocate one extra byte for the null terminator though,
|
|
160 // so that someone calling DstUTF16.data() gets a null terminated string.
|
|
161 // We resize down later so we don't have to worry that this over allocates.
|
|
162 DstUTF16.resize(SrcUTF8.size()+1);
|
|
163 UTF16 *Dst = &DstUTF16[0];
|
|
164 UTF16 *DstEnd = Dst + DstUTF16.size();
|
|
165
|
|
166 ConversionResult CR =
|
|
167 ConvertUTF8toUTF16(&Src, SrcEnd, &Dst, DstEnd, strictConversion);
|
|
168 assert(CR != targetExhausted);
|
|
169
|
|
170 if (CR != conversionOK) {
|
|
171 DstUTF16.clear();
|
|
172 return false;
|
|
173 }
|
|
174
|
|
175 DstUTF16.resize(Dst - &DstUTF16[0]);
|
|
176 DstUTF16.push_back(0);
|
|
177 DstUTF16.pop_back();
|
0
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
178 return true;
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
179 }
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
180
|
120
|
181 static_assert(sizeof(wchar_t) == 1 || sizeof(wchar_t) == 2 ||
|
|
182 sizeof(wchar_t) == 4,
|
|
183 "Expected wchar_t to be 1, 2, or 4 bytes");
|
|
184
|
|
185 template <typename TResult>
|
|
186 static inline bool ConvertUTF8toWideInternal(llvm::StringRef Source,
|
|
187 TResult &Result) {
|
|
188 // Even in the case of UTF-16, the number of bytes in a UTF-8 string is
|
|
189 // at least as large as the number of elements in the resulting wide
|
|
190 // string, because surrogate pairs take at least 4 bytes in UTF-8.
|
|
191 Result.resize(Source.size() + 1);
|
|
192 char *ResultPtr = reinterpret_cast<char *>(&Result[0]);
|
|
193 const UTF8 *ErrorPtr;
|
|
194 if (!ConvertUTF8toWide(sizeof(wchar_t), Source, ResultPtr, ErrorPtr)) {
|
|
195 Result.clear();
|
|
196 return false;
|
|
197 }
|
|
198 Result.resize(reinterpret_cast<wchar_t *>(ResultPtr) - &Result[0]);
|
|
199 return true;
|
|
200 }
|
|
201
|
|
202 bool ConvertUTF8toWide(llvm::StringRef Source, std::wstring &Result) {
|
|
203 return ConvertUTF8toWideInternal(Source, Result);
|
|
204 }
|
|
205
|
|
206 bool ConvertUTF8toWide(const char *Source, std::wstring &Result) {
|
|
207 if (!Source) {
|
|
208 Result.clear();
|
|
209 return true;
|
|
210 }
|
|
211 return ConvertUTF8toWide(llvm::StringRef(Source), Result);
|
|
212 }
|
|
213
|
|
214 bool convertWideToUTF8(const std::wstring &Source, std::string &Result) {
|
|
215 if (sizeof(wchar_t) == 1) {
|
|
216 const UTF8 *Start = reinterpret_cast<const UTF8 *>(Source.data());
|
|
217 const UTF8 *End =
|
|
218 reinterpret_cast<const UTF8 *>(Source.data() + Source.size());
|
|
219 if (!isLegalUTF8String(&Start, End))
|
|
220 return false;
|
|
221 Result.resize(Source.size());
|
|
222 memcpy(&Result[0], Source.data(), Source.size());
|
|
223 return true;
|
|
224 } else if (sizeof(wchar_t) == 2) {
|
|
225 return convertUTF16ToUTF8String(
|
|
226 llvm::ArrayRef<UTF16>(reinterpret_cast<const UTF16 *>(Source.data()),
|
|
227 Source.size()),
|
|
228 Result);
|
|
229 } else if (sizeof(wchar_t) == 4) {
|
|
230 const UTF32 *Start = reinterpret_cast<const UTF32 *>(Source.data());
|
|
231 const UTF32 *End =
|
|
232 reinterpret_cast<const UTF32 *>(Source.data() + Source.size());
|
|
233 Result.resize(UNI_MAX_UTF8_BYTES_PER_CODE_POINT * Source.size());
|
|
234 UTF8 *ResultPtr = reinterpret_cast<UTF8 *>(&Result[0]);
|
|
235 UTF8 *ResultEnd = reinterpret_cast<UTF8 *>(&Result[0] + Result.size());
|
|
236 if (ConvertUTF32toUTF8(&Start, End, &ResultPtr, ResultEnd,
|
|
237 strictConversion) == conversionOK) {
|
|
238 Result.resize(reinterpret_cast<char *>(ResultPtr) - &Result[0]);
|
|
239 return true;
|
|
240 } else {
|
|
241 Result.clear();
|
|
242 return false;
|
|
243 }
|
|
244 } else {
|
|
245 llvm_unreachable(
|
|
246 "Control should never reach this point; see static_assert further up");
|
|
247 }
|
|
248 }
|
|
249
|
0
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
250 } // end namespace llvm
|
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff
changeset
|
251
|