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
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
|
// Copyright (c) 2018 The Chromium Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
// found in the LICENSE file.
#include "base/strings/utf_string_conversions.h"
#include <limits.h>
#include <stdint.h>
#include <type_traits>
#include "base/strings/string_piece.h"
#include "base/strings/string_util.h"
#include "base/strings/utf_string_conversion_utils.h"
#include "base/third_party/icu/icu_utf.h"
#include "build/build_config.h"
namespace base {
namespace {
constexpr int32_t kErrorCodePoint = 0xFFFD;
// Size coefficient ----------------------------------------------------------
// The maximum number of codeunits in the destination encoding corresponding to
// one codeunit in the source encoding.
template <typename SrcChar, typename DestChar>
struct SizeCoefficient {
static_assert(sizeof(SrcChar) < sizeof(DestChar),
"Default case: from a smaller encoding to the bigger one");
// ASCII symbols are encoded by one codeunit in all encodings.
static constexpr int value = 1;
};
template <>
struct SizeCoefficient<char16, char> {
// One UTF-16 codeunit corresponds to at most 3 codeunits in UTF-8.
static constexpr int value = 3;
};
#if defined(WCHAR_T_IS_UTF32)
template <>
struct SizeCoefficient<wchar_t, char> {
// UTF-8 uses at most 4 codeunits per character.
static constexpr int value = 4;
};
template <>
struct SizeCoefficient<wchar_t, char16> {
// UTF-16 uses at most 2 codeunits per character.
static constexpr int value = 2;
};
#endif // defined(WCHAR_T_IS_UTF32)
template <typename SrcChar, typename DestChar>
constexpr int size_coefficient_v =
SizeCoefficient<std::decay_t<SrcChar>, std::decay_t<DestChar>>::value;
// UnicodeAppendUnsafe --------------------------------------------------------
// Function overloads that write code_point to the output string. Output string
// has to have enough space for the codepoint.
// Convenience typedef that checks whether the passed in type is integral (i.e.
// bool, char, int or their extended versions) and is of the correct size.
template <typename Char, size_t N>
using EnableIfBitsAre = std::enable_if_t<std::is_integral<Char>::value &&
CHAR_BIT * sizeof(Char) == N,
bool>;
template <typename Char, EnableIfBitsAre<Char, 8> = true>
void UnicodeAppendUnsafe(Char* out, int32_t* size, uint32_t code_point) {
CBU8_APPEND_UNSAFE(out, *size, code_point);
}
template <typename Char, EnableIfBitsAre<Char, 16> = true>
void UnicodeAppendUnsafe(Char* out, int32_t* size, uint32_t code_point) {
CBU16_APPEND_UNSAFE(out, *size, code_point);
}
template <typename Char, EnableIfBitsAre<Char, 32> = true>
void UnicodeAppendUnsafe(Char* out, int32_t* size, uint32_t code_point) {
out[(*size)++] = code_point;
}
// DoUTFConversion ------------------------------------------------------------
// Main driver of UTFConversion specialized for different Src encodings.
// dest has to have enough room for the converted text.
template <typename DestChar>
bool DoUTFConversion(const char* src,
int32_t src_len,
DestChar* dest,
int32_t* dest_len) {
bool success = true;
for (int32_t i = 0; i < src_len;) {
int32_t code_point;
CBU8_NEXT(src, i, src_len, code_point);
if (!IsValidCodepoint(code_point)) {
success = false;
code_point = kErrorCodePoint;
}
UnicodeAppendUnsafe(dest, dest_len, code_point);
}
return success;
}
template <typename DestChar>
bool DoUTFConversion(const char16* src,
int32_t src_len,
DestChar* dest,
int32_t* dest_len) {
bool success = true;
auto ConvertSingleChar = [&success](char16 in) -> int32_t {
if (!CBU16_IS_SINGLE(in) || !IsValidCodepoint(in)) {
success = false;
return kErrorCodePoint;
}
return in;
};
int32_t i = 0;
// Always have another symbol in order to avoid checking boundaries in the
// middle of the surrogate pair.
while (i < src_len - 1) {
int32_t code_point;
if (CBU16_IS_LEAD(src[i]) && CBU16_IS_TRAIL(src[i + 1])) {
code_point = CBU16_GET_SUPPLEMENTARY(src[i], src[i + 1]);
if (!IsValidCodepoint(code_point)) {
code_point = kErrorCodePoint;
success = false;
}
i += 2;
} else {
code_point = ConvertSingleChar(src[i]);
++i;
}
UnicodeAppendUnsafe(dest, dest_len, code_point);
}
if (i < src_len)
UnicodeAppendUnsafe(dest, dest_len, ConvertSingleChar(src[i]));
return success;
}
#if defined(WCHAR_T_IS_UTF32)
template <typename DestChar>
bool DoUTFConversion(const wchar_t* src,
int32_t src_len,
DestChar* dest,
int32_t* dest_len) {
bool success = true;
for (int32_t i = 0; i < src_len; ++i) {
int32_t code_point = src[i];
if (!IsValidCodepoint(code_point)) {
success = false;
code_point = kErrorCodePoint;
}
UnicodeAppendUnsafe(dest, dest_len, code_point);
}
return success;
}
#endif // defined(WCHAR_T_IS_UTF32)
// UTFConversion --------------------------------------------------------------
// Function template for generating all UTF conversions.
template <typename InputString, typename DestString>
bool UTFConversion(const InputString& src_str, DestString* dest_str) {
if (IsStringASCII(src_str)) {
dest_str->assign(src_str.begin(), src_str.end());
return true;
}
dest_str->resize(src_str.length() *
size_coefficient_v<typename InputString::value_type,
typename DestString::value_type>);
// Empty string is ASCII => it OK to call operator[].
auto* dest = &(*dest_str)[0];
// ICU requires 32 bit numbers.
int32_t src_len32 = static_cast<int32_t>(src_str.length());
int32_t dest_len32 = 0;
bool res = DoUTFConversion(src_str.data(), src_len32, dest, &dest_len32);
dest_str->resize(dest_len32);
dest_str->shrink_to_fit();
return res;
}
} // namespace
// UTF16 <-> UTF8 --------------------------------------------------------------
bool UTF8ToUTF16(const char* src, size_t src_len, string16* output) {
return UTFConversion(StringPiece(src, src_len), output);
}
string16 UTF8ToUTF16(StringPiece utf8) {
string16 ret;
// Ignore the success flag of this call, it will do the best it can for
// invalid input, which is what we want here.
UTF8ToUTF16(utf8.data(), utf8.size(), &ret);
return ret;
}
bool UTF16ToUTF8(const char16* src, size_t src_len, std::string* output) {
return UTFConversion(StringPiece16(src, src_len), output);
}
std::string UTF16ToUTF8(StringPiece16 utf16) {
std::string ret;
// Ignore the success flag of this call, it will do the best it can for
// invalid input, which is what we want here.
UTF16ToUTF8(utf16.data(), utf16.length(), &ret);
return ret;
}
// UTF-16 <-> Wide -------------------------------------------------------------
#if defined(WCHAR_T_IS_UTF16)
// When wide == UTF-16 the conversions are a NOP.
bool WideToUTF16(const wchar_t* src, size_t src_len, string16* output) {
output->assign(src, src + src_len);
return true;
}
string16 WideToUTF16(WStringPiece wide) {
return string16(wide.begin(), wide.end());
}
bool UTF16ToWide(const char16* src, size_t src_len, std::wstring* output) {
output->assign(src, src + src_len);
return true;
}
std::wstring UTF16ToWide(StringPiece16 utf16) {
return std::wstring(utf16.begin(), utf16.end());
}
#elif defined(WCHAR_T_IS_UTF32)
bool WideToUTF16(const wchar_t* src, size_t src_len, string16* output) {
return UTFConversion(base::WStringPiece(src, src_len), output);
}
string16 WideToUTF16(WStringPiece wide) {
string16 ret;
// Ignore the success flag of this call, it will do the best it can for
// invalid input, which is what we want here.
WideToUTF16(wide.data(), wide.length(), &ret);
return ret;
}
bool UTF16ToWide(const char16* src, size_t src_len, std::wstring* output) {
return UTFConversion(StringPiece16(src, src_len), output);
}
std::wstring UTF16ToWide(StringPiece16 utf16) {
std::wstring ret;
// Ignore the success flag of this call, it will do the best it can for
// invalid input, which is what we want here.
UTF16ToWide(utf16.data(), utf16.length(), &ret);
return ret;
}
#endif // defined(WCHAR_T_IS_UTF32)
// UTF-8 <-> Wide --------------------------------------------------------------
// UTF8ToWide is the same code, regardless of whether wide is 16 or 32 bits
bool UTF8ToWide(const char* src, size_t src_len, std::wstring* output) {
return UTFConversion(StringPiece(src, src_len), output);
}
std::wstring UTF8ToWide(StringPiece utf8) {
std::wstring ret;
// Ignore the success flag of this call, it will do the best it can for
// invalid input, which is what we want here.
UTF8ToWide(utf8.data(), utf8.length(), &ret);
return ret;
}
#if defined(WCHAR_T_IS_UTF16)
// Easy case since we can use the "utf" versions we already wrote above.
bool WideToUTF8(const wchar_t* src, size_t src_len, std::string* output) {
return UTF16ToUTF8(as_u16cstr(src), src_len, output);
}
std::string WideToUTF8(WStringPiece wide) {
return UTF16ToUTF8(StringPiece16(as_u16cstr(wide), wide.size()));
}
#elif defined(WCHAR_T_IS_UTF32)
bool WideToUTF8(const wchar_t* src, size_t src_len, std::string* output) {
return UTFConversion(WStringPiece(src, src_len), output);
}
std::string WideToUTF8(WStringPiece wide) {
std::string ret;
// Ignore the success flag of this call, it will do the best it can for
// invalid input, which is what we want here.
WideToUTF8(wide.data(), wide.length(), &ret);
return ret;
}
#endif // defined(WCHAR_T_IS_UTF32)
string16 ASCIIToUTF16(StringPiece ascii) {
DCHECK(IsStringASCII(ascii)) << ascii;
return string16(ascii.begin(), ascii.end());
}
std::string UTF16ToASCII(StringPiece16 utf16) {
DCHECK(IsStringASCII(utf16)) << UTF16ToUTF8(utf16);
return std::string(utf16.begin(), utf16.end());
}
} // namespace base
|