aboutsummaryrefslogtreecommitdiffstats
path: root/contrib/libs/llvm16/lib/Support/ConvertUTFWrapper.cpp
blob: 9bf3f8f8b897c4f2c49fa65d8036412675526369 (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
//===-- ConvertUTFWrapper.cpp - Wrap ConvertUTF.h with clang data types -----===
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//

#include "llvm/ADT/ArrayRef.h"
#include "llvm/ADT/StringRef.h"
#include "llvm/Support/ConvertUTF.h"
#include "llvm/Support/ErrorHandling.h"
#include "llvm/Support/SwapByteOrder.h"
#include <string>
#include <vector>

namespace llvm {

bool ConvertUTF8toWide(unsigned WideCharWidth, llvm::StringRef Source,
                       char *&ResultPtr, const UTF8 *&ErrorPtr) {
  assert(WideCharWidth == 1 || WideCharWidth == 2 || WideCharWidth == 4);
  ConversionResult result = conversionOK;
  // Copy the character span over.
  if (WideCharWidth == 1) {
    const UTF8 *Pos = reinterpret_cast<const UTF8*>(Source.begin());
    if (!isLegalUTF8String(&Pos, reinterpret_cast<const UTF8*>(Source.end()))) {
      result = sourceIllegal;
      ErrorPtr = Pos;
    } else {
      memcpy(ResultPtr, Source.data(), Source.size());
      ResultPtr += Source.size();
    }
  } else if (WideCharWidth == 2) {
    const UTF8 *sourceStart = (const UTF8*)Source.data();
    // FIXME: Make the type of the result buffer correct instead of
    // using reinterpret_cast.
    UTF16 *targetStart = reinterpret_cast<UTF16 *>(ResultPtr);
    ConversionFlags flags = strictConversion;
    result =
        ConvertUTF8toUTF16(&sourceStart, sourceStart + Source.size(),
                           &targetStart, targetStart + Source.size(), flags);
    if (result == conversionOK)
      ResultPtr = reinterpret_cast<char *>(targetStart);
    else
      ErrorPtr = sourceStart;
  } else if (WideCharWidth == 4) {
    const UTF8 *sourceStart = (const UTF8 *)Source.data();
    // FIXME: Make the type of the result buffer correct instead of
    // using reinterpret_cast.
    UTF32 *targetStart = reinterpret_cast<UTF32 *>(ResultPtr);
    ConversionFlags flags = strictConversion;
    result =
        ConvertUTF8toUTF32(&sourceStart, sourceStart + Source.size(),
                           &targetStart, targetStart + Source.size(), flags);
    if (result == conversionOK)
      ResultPtr = reinterpret_cast<char *>(targetStart);
    else
      ErrorPtr = sourceStart;
  }
  assert((result != targetExhausted) &&
         "ConvertUTF8toUTFXX exhausted target buffer");
  return result == conversionOK;
}

bool ConvertCodePointToUTF8(unsigned Source, char *&ResultPtr) {
  const UTF32 *SourceStart = &Source;
  const UTF32 *SourceEnd = SourceStart + 1;
  UTF8 *TargetStart = reinterpret_cast<UTF8 *>(ResultPtr);
  UTF8 *TargetEnd = TargetStart + 4;
  ConversionResult CR = ConvertUTF32toUTF8(
      &SourceStart, SourceEnd, &TargetStart, TargetEnd, strictConversion);
  if (CR != conversionOK)
    return false;

  ResultPtr = reinterpret_cast<char *>(TargetStart);
  return true;
}

bool hasUTF16ByteOrderMark(ArrayRef<char> S) {
  return (S.size() >= 2 && ((S[0] == '\xff' && S[1] == '\xfe') ||
                            (S[0] == '\xfe' && S[1] == '\xff')));
}

bool convertUTF16ToUTF8String(ArrayRef<char> SrcBytes, std::string &Out) {
  assert(Out.empty());

  // Error out on an uneven byte count.
  if (SrcBytes.size() % 2)
    return false;

  // Avoid OOB by returning early on empty input.
  if (SrcBytes.empty())
    return true;

  const UTF16 *Src = reinterpret_cast<const UTF16 *>(SrcBytes.begin());
  const UTF16 *SrcEnd = reinterpret_cast<const UTF16 *>(SrcBytes.end());

  assert((uintptr_t)Src % sizeof(UTF16) == 0);

  // Byteswap if necessary.
  std::vector<UTF16> ByteSwapped;
  if (Src[0] == UNI_UTF16_BYTE_ORDER_MARK_SWAPPED) {
    ByteSwapped.insert(ByteSwapped.end(), Src, SrcEnd);
    for (UTF16 &I : ByteSwapped)
      I = llvm::ByteSwap_16(I);
    Src = &ByteSwapped[0];
    SrcEnd = &ByteSwapped[ByteSwapped.size() - 1] + 1;
  }

  // Skip the BOM for conversion.
  if (Src[0] == UNI_UTF16_BYTE_ORDER_MARK_NATIVE)
    Src++;

  // Just allocate enough space up front.  We'll shrink it later.  Allocate
  // enough that we can fit a null terminator without reallocating.
  Out.resize(SrcBytes.size() * UNI_MAX_UTF8_BYTES_PER_CODE_POINT + 1);
  UTF8 *Dst = reinterpret_cast<UTF8 *>(&Out[0]);
  UTF8 *DstEnd = Dst + Out.size();

  ConversionResult CR =
      ConvertUTF16toUTF8(&Src, SrcEnd, &Dst, DstEnd, strictConversion);
  assert(CR != targetExhausted);

  if (CR != conversionOK) {
    Out.clear();
    return false;
  }

  Out.resize(reinterpret_cast<char *>(Dst) - &Out[0]);
  Out.push_back(0);
  Out.pop_back();
  return true;
}

bool convertUTF16ToUTF8String(ArrayRef<UTF16> Src, std::string &Out) {
  return convertUTF16ToUTF8String(
      llvm::ArrayRef<char>(reinterpret_cast<const char *>(Src.data()),
                           Src.size() * sizeof(UTF16)),
      Out);
}

bool convertUTF32ToUTF8String(ArrayRef<char> SrcBytes, std::string &Out) {
  assert(Out.empty());

  // Error out on an uneven byte count.
  if (SrcBytes.size() % 4)
    return false;

  // Avoid OOB by returning early on empty input.
  if (SrcBytes.empty())
    return true;

  const UTF32 *Src = reinterpret_cast<const UTF32 *>(SrcBytes.begin());
  const UTF32 *SrcEnd = reinterpret_cast<const UTF32 *>(SrcBytes.end());

  assert((uintptr_t)Src % sizeof(UTF32) == 0);

  // Byteswap if necessary.
  std::vector<UTF32> ByteSwapped;
  if (Src[0] == UNI_UTF32_BYTE_ORDER_MARK_SWAPPED) {
    ByteSwapped.insert(ByteSwapped.end(), Src, SrcEnd);
    for (UTF32 &I : ByteSwapped)
      I = llvm::ByteSwap_32(I);
    Src = &ByteSwapped[0];
    SrcEnd = &ByteSwapped[ByteSwapped.size() - 1] + 1;
  }

  // Skip the BOM for conversion.
  if (Src[0] == UNI_UTF32_BYTE_ORDER_MARK_NATIVE)
    Src++;

  // Just allocate enough space up front.  We'll shrink it later.  Allocate
  // enough that we can fit a null terminator without reallocating.
  Out.resize(SrcBytes.size() * UNI_MAX_UTF8_BYTES_PER_CODE_POINT + 1);
  UTF8 *Dst = reinterpret_cast<UTF8 *>(&Out[0]);
  UTF8 *DstEnd = Dst + Out.size();

  ConversionResult CR =
      ConvertUTF32toUTF8(&Src, SrcEnd, &Dst, DstEnd, strictConversion);
  assert(CR != targetExhausted);

  if (CR != conversionOK) {
    Out.clear();
    return false;
  }

  Out.resize(reinterpret_cast<char *>(Dst) - &Out[0]);
  Out.push_back(0);
  Out.pop_back();
  return true;
}

bool convertUTF32ToUTF8String(ArrayRef<UTF32> Src, std::string &Out) {
  return convertUTF32ToUTF8String(
      llvm::ArrayRef<char>(reinterpret_cast<const char *>(Src.data()),
                           Src.size() * sizeof(UTF32)),
      Out);
}

bool convertUTF8ToUTF16String(StringRef SrcUTF8,
                              SmallVectorImpl<UTF16> &DstUTF16) {
  assert(DstUTF16.empty());

  // Avoid OOB by returning early on empty input.
  if (SrcUTF8.empty()) {
    DstUTF16.push_back(0);
    DstUTF16.pop_back();
    return true;
  }

  const UTF8 *Src = reinterpret_cast<const UTF8 *>(SrcUTF8.begin());
  const UTF8 *SrcEnd = reinterpret_cast<const UTF8 *>(SrcUTF8.end());

  // Allocate the same number of UTF-16 code units as UTF-8 code units. Encoding
  // as UTF-16 should always require the same amount or less code units than the
  // UTF-8 encoding.  Allocate one extra byte for the null terminator though,
  // so that someone calling DstUTF16.data() gets a null terminated string.
  // We resize down later so we don't have to worry that this over allocates.
  DstUTF16.resize(SrcUTF8.size()+1);
  UTF16 *Dst = &DstUTF16[0];
  UTF16 *DstEnd = Dst + DstUTF16.size();

  ConversionResult CR =
      ConvertUTF8toUTF16(&Src, SrcEnd, &Dst, DstEnd, strictConversion);
  assert(CR != targetExhausted);

  if (CR != conversionOK) {
    DstUTF16.clear();
    return false;
  }

  DstUTF16.resize(Dst - &DstUTF16[0]);
  DstUTF16.push_back(0);
  DstUTF16.pop_back();
  return true;
}

static_assert(sizeof(wchar_t) == 1 || sizeof(wchar_t) == 2 ||
                  sizeof(wchar_t) == 4,
              "Expected wchar_t to be 1, 2, or 4 bytes");

template <typename TResult>
static inline bool ConvertUTF8toWideInternal(llvm::StringRef Source,
                                             TResult &Result) {
  // Even in the case of UTF-16, the number of bytes in a UTF-8 string is
  // at least as large as the number of elements in the resulting wide
  // string, because surrogate pairs take at least 4 bytes in UTF-8.
  Result.resize(Source.size() + 1);
  char *ResultPtr = reinterpret_cast<char *>(&Result[0]);
  const UTF8 *ErrorPtr;
  if (!ConvertUTF8toWide(sizeof(wchar_t), Source, ResultPtr, ErrorPtr)) {
    Result.clear();
    return false;
  }
  Result.resize(reinterpret_cast<wchar_t *>(ResultPtr) - &Result[0]);
  return true;
}

bool ConvertUTF8toWide(llvm::StringRef Source, std::wstring &Result) {
  return ConvertUTF8toWideInternal(Source, Result);
}

bool ConvertUTF8toWide(const char *Source, std::wstring &Result) {
  if (!Source) {
    Result.clear();
    return true;
  }
  return ConvertUTF8toWide(llvm::StringRef(Source), Result);
}

bool convertWideToUTF8(const std::wstring &Source, std::string &Result) {
  if (sizeof(wchar_t) == 1) {
    const UTF8 *Start = reinterpret_cast<const UTF8 *>(Source.data());
    const UTF8 *End =
        reinterpret_cast<const UTF8 *>(Source.data() + Source.size());
    if (!isLegalUTF8String(&Start, End))
      return false;
    Result.resize(Source.size());
    memcpy(&Result[0], Source.data(), Source.size());
    return true;
  } else if (sizeof(wchar_t) == 2) {
    return convertUTF16ToUTF8String(
        llvm::ArrayRef<UTF16>(reinterpret_cast<const UTF16 *>(Source.data()),
                              Source.size()),
        Result);
  } else if (sizeof(wchar_t) == 4) {
    const UTF32 *Start = reinterpret_cast<const UTF32 *>(Source.data());
    const UTF32 *End =
        reinterpret_cast<const UTF32 *>(Source.data() + Source.size());
    Result.resize(UNI_MAX_UTF8_BYTES_PER_CODE_POINT * Source.size());
    UTF8 *ResultPtr = reinterpret_cast<UTF8 *>(&Result[0]);
    UTF8 *ResultEnd = reinterpret_cast<UTF8 *>(&Result[0] + Result.size());
    if (ConvertUTF32toUTF8(&Start, End, &ResultPtr, ResultEnd,
                           strictConversion) == conversionOK) {
      Result.resize(reinterpret_cast<char *>(ResultPtr) - &Result[0]);
      return true;
    } else {
      Result.clear();
      return false;
    }
  } else {
    llvm_unreachable(
        "Control should never reach this point; see static_assert further up");
  }
}

} // end namespace llvm