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
base / i18n / icu_string_conversions.cc [blame]
// Copyright 2012 The Chromium Authors
// Use of this source code is governed by a BSD-style license that can be
// found in the LICENSE file.
#include "base/i18n/icu_string_conversions.h"
#include <stddef.h>
#include <stdint.h>
#include <memory>
#include <string_view>
#include "base/check.h"
#include "base/types/fixed_array.h"
#include "base/notreached.h"
#include "base/strings/string_util.h"
#include "base/strings/utf_string_conversions.h"
#include "third_party/icu/source/common/unicode/normalizer2.h"
#include "third_party/icu/source/common/unicode/ucnv.h"
#include "third_party/icu/source/common/unicode/ucnv_cb.h"
#include "third_party/icu/source/common/unicode/ucnv_err.h"
#include "third_party/icu/source/common/unicode/ustring.h"
namespace base {
namespace {
// ToUnicodeCallbackSubstitute() is based on UCNV_TO_U_CALLBACK_SUBSTITUTE
// in source/common/ucnv_err.c.
// Copyright (c) 1995-2006 International Business Machines Corporation
// and others
//
// All rights reserved.
//
// Permission is hereby granted, free of charge, to any person obtaining a
// copy of this software and associated documentation files (the "Software"),
// to deal in the Software without restriction, including without limitation
// the rights to use, copy, modify, merge, publish, distribute, and/or
// sell copies of the Software, and to permit persons to whom the Software
// is furnished to do so, provided that the above copyright notice(s) and
// this permission notice appear in all copies of the Software and that
// both the above copyright notice(s) and this permission notice appear in
// supporting documentation.
//
// THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
// EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
// MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT
// OF THIRD PARTY RIGHTS. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR HOLDERS
// INCLUDED IN THIS NOTICE BE LIABLE FOR ANY CLAIM, OR ANY SPECIAL INDIRECT
// OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS
// OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE
// OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE
// OR PERFORMANCE OF THIS SOFTWARE.
//
// Except as contained in this notice, the name of a copyright holder
// shall not be used in advertising or otherwise to promote the sale, use
// or other dealings in this Software without prior written authorization
// of the copyright holder.
// ___________________________________________________________________________
//
// All trademarks and registered trademarks mentioned herein are the property
// of their respective owners.
void ToUnicodeCallbackSubstitute(const void* context,
UConverterToUnicodeArgs *to_args,
const char* code_units,
int32_t length,
UConverterCallbackReason reason,
UErrorCode * err) {
static const UChar kReplacementChar = 0xFFFD;
if (reason <= UCNV_IRREGULAR) {
if (context == nullptr ||
(*(reinterpret_cast<const char*>(context)) == 'i' &&
reason == UCNV_UNASSIGNED)) {
*err = U_ZERO_ERROR;
ucnv_cbToUWriteUChars(to_args, &kReplacementChar, 1, 0, err);
}
// else the caller must have set the error code accordingly.
}
// else ignore the reset, close and clone calls.
}
bool ConvertFromUTF16(UConverter* converter,
std::u16string_view src,
OnStringConversionError::Type on_error,
std::string* encoded) {
int encoded_max_length = UCNV_GET_MAX_BYTES_FOR_STRING(
src.length(), ucnv_getMaxCharSize(converter));
encoded->resize(encoded_max_length);
UErrorCode status = U_ZERO_ERROR;
// Setup our error handler.
switch (on_error) {
case OnStringConversionError::FAIL:
ucnv_setFromUCallBack(converter, UCNV_FROM_U_CALLBACK_STOP, nullptr,
nullptr, nullptr, &status);
break;
case OnStringConversionError::SKIP:
case OnStringConversionError::SUBSTITUTE:
ucnv_setFromUCallBack(converter, UCNV_FROM_U_CALLBACK_SKIP, nullptr,
nullptr, nullptr, &status);
break;
}
// ucnv_fromUChars returns size not including terminating null
int actual_size =
ucnv_fromUChars(converter, &(*encoded)[0], encoded_max_length, src.data(),
src.length(), &status);
encoded->resize(actual_size);
ucnv_close(converter);
if (U_SUCCESS(status))
return true;
encoded->clear(); // Make sure the output is empty on error.
return false;
}
// Set up our error handler for ToUTF-16 converters
void SetUpErrorHandlerForToUChars(OnStringConversionError::Type on_error,
UConverter* converter, UErrorCode* status) {
switch (on_error) {
case OnStringConversionError::FAIL:
ucnv_setToUCallBack(converter, UCNV_TO_U_CALLBACK_STOP, nullptr, nullptr,
nullptr, status);
break;
case OnStringConversionError::SKIP:
ucnv_setToUCallBack(converter, UCNV_TO_U_CALLBACK_SKIP, nullptr, nullptr,
nullptr, status);
break;
case OnStringConversionError::SUBSTITUTE:
ucnv_setToUCallBack(converter, ToUnicodeCallbackSubstitute, nullptr,
nullptr, nullptr, status);
break;
}
}
} // namespace
// Codepage <-> Wide/UTF-16 ---------------------------------------------------
bool UTF16ToCodepage(std::u16string_view utf16,
const char* codepage_name,
OnStringConversionError::Type on_error,
std::string* encoded) {
encoded->clear();
UErrorCode status = U_ZERO_ERROR;
UConverter* converter = ucnv_open(codepage_name, &status);
if (!U_SUCCESS(status))
return false;
return ConvertFromUTF16(converter, utf16, on_error, encoded);
}
bool CodepageToUTF16(std::string_view encoded,
const char* codepage_name,
OnStringConversionError::Type on_error,
std::u16string* utf16) {
utf16->clear();
UErrorCode status = U_ZERO_ERROR;
UConverter* converter = ucnv_open(codepage_name, &status);
if (!U_SUCCESS(status))
return false;
// Even in the worst case, the maximum length in 2-byte units of UTF-16
// output would be at most the same as the number of bytes in input. There
// is no single-byte encoding in which a character is mapped to a
// non-BMP character requiring two 2-byte units.
//
// Moreover, non-BMP characters in legacy multibyte encodings
// (e.g. EUC-JP, GB18030) take at least 2 bytes. The only exceptions are
// BOCU and SCSU, but we don't care about them.
size_t uchar_max_length = encoded.length() + 1;
SetUpErrorHandlerForToUChars(on_error, converter, &status);
base::FixedArray<char16_t> buffer(uchar_max_length);
int actual_size = ucnv_toUChars(
converter, buffer.data(), static_cast<int>(uchar_max_length),
encoded.data(), static_cast<int>(encoded.length()), &status);
ucnv_close(converter);
if (!U_SUCCESS(status)) {
utf16->clear(); // Make sure the output is empty on error.
return false;
}
utf16->assign(buffer.data(), actual_size);
return true;
}
bool ConvertToUtf8AndNormalize(std::string_view text,
const std::string& charset,
std::string* result) {
result->clear();
std::u16string utf16;
if (!CodepageToUTF16(text, charset.c_str(), OnStringConversionError::FAIL,
&utf16))
return false;
UErrorCode status = U_ZERO_ERROR;
const icu::Normalizer2* normalizer = icu::Normalizer2::getNFCInstance(status);
DCHECK(U_SUCCESS(status));
if (U_FAILURE(status))
return false;
int32_t utf16_length = static_cast<int32_t>(utf16.length());
icu::UnicodeString normalized(utf16.data(), utf16_length);
int32_t normalized_prefix_length =
normalizer->spanQuickCheckYes(normalized, status);
if (normalized_prefix_length < utf16_length) {
icu::UnicodeString un_normalized(normalized, normalized_prefix_length);
normalized.truncate(normalized_prefix_length);
normalizer->normalizeSecondAndAppend(normalized, un_normalized, status);
}
if (U_FAILURE(status))
return false;
normalized.toUTF8String(*result);
return true;
}
} // namespace base