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
|
// Copyright (c) 2010 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/i18n/rtl.h"
#include "base/file_path.h"
#include "base/logging.h"
#include "base/string_util.h"
#include "base/utf_string_conversions.h"
#include "base/sys_string_conversions.h"
#include "unicode/coll.h"
#include "unicode/locid.h"
#include "unicode/uchar.h"
#include "unicode/uscript.h"
#if defined(TOOLKIT_USES_GTK)
#include <gtk/gtk.h>
#endif
namespace {
// Extract language and country, ignore keywords, concatenate using dash.
std::string GetLocaleString(const icu::Locale& locale) {
const char* language = locale.getLanguage();
const char* country = locale.getCountry();
std::string result =
(language != NULL && *language != '\0') ? language : "und";
if (country != NULL && *country != '\0') {
result += '-';
result += country;
}
return result;
}
} // namespace
namespace base {
namespace i18n {
// Represents the locale-specific ICU text direction.
static TextDirection g_icu_text_direction = UNKNOWN_DIRECTION;
// Convert the ICU default locale to a string.
std::string GetConfiguredLocale() {
return GetLocaleString(icu::Locale::getDefault());
}
// Convert the ICU canonicalized locale to a string.
std::string GetCanonicalLocale(const char* locale) {
return GetLocaleString(icu::Locale::createCanonical(locale));
}
// Convert Chrome locale name to ICU locale name
std::string ICULocaleName(const std::string& locale_string) {
// If not Spanish, just return it.
if (locale_string.substr(0, 2) != "es")
return locale_string;
// Expand es to es-ES.
if (LowerCaseEqualsASCII(locale_string, "es"))
return "es-ES";
// Map es-419 (Latin American Spanish) to es-FOO depending on the system
// locale. If it's es-RR other than es-ES, map to es-RR. Otherwise, map
// to es-MX (the most populous in Spanish-speaking Latin America).
if (LowerCaseEqualsASCII(locale_string, "es-419")) {
const icu::Locale& locale = icu::Locale::getDefault();
std::string language = locale.getLanguage();
const char* country = locale.getCountry();
if (LowerCaseEqualsASCII(language, "es") &&
!LowerCaseEqualsASCII(country, "es")) {
language += '-';
language += country;
return language;
}
return "es-MX";
}
// Currently, Chrome has only "es" and "es-419", but later we may have
// more specific "es-RR".
return locale_string;
}
void SetICUDefaultLocale(const std::string& locale_string) {
icu::Locale locale(ICULocaleName(locale_string).c_str());
UErrorCode error_code = U_ZERO_ERROR;
icu::Locale::setDefault(locale, error_code);
// This return value is actually bogus because Locale object is
// an ID and setDefault seems to always succeed (regardless of the
// presence of actual locale data). However,
// it does not hurt to have it as a sanity check.
DCHECK(U_SUCCESS(error_code));
g_icu_text_direction = UNKNOWN_DIRECTION;
// If we use Views toolkit on top of GtkWidget, then we need to keep
// GtkWidget's default text direction consistent with ICU's text direction.
// Because in this case ICU's text direction will be used instead.
// See IsRTL() function below.
#if defined(TOOLKIT_USES_GTK) && !defined(TOOLKIT_GTK)
gtk_widget_set_default_direction(
ICUIsRTL() ? GTK_TEXT_DIR_RTL : GTK_TEXT_DIR_LTR);
#endif
}
bool IsRTL() {
#if defined(TOOLKIT_GTK)
GtkTextDirection gtk_dir = gtk_widget_get_default_direction();
return (gtk_dir == GTK_TEXT_DIR_RTL);
#else
return ICUIsRTL();
#endif
}
bool ICUIsRTL() {
if (g_icu_text_direction == UNKNOWN_DIRECTION) {
const icu::Locale& locale = icu::Locale::getDefault();
g_icu_text_direction = GetTextDirectionForLocale(locale.getName());
}
return g_icu_text_direction == RIGHT_TO_LEFT;
}
TextDirection GetTextDirectionForLocale(const char* locale_name) {
UErrorCode status = U_ZERO_ERROR;
ULayoutType layout_dir = uloc_getCharacterOrientation(locale_name, &status);
DCHECK(U_SUCCESS(status));
// Treat anything other than RTL as LTR.
return (layout_dir != ULOC_LAYOUT_RTL) ? LEFT_TO_RIGHT : RIGHT_TO_LEFT;
}
TextDirection GetFirstStrongCharacterDirection(const string16& text) {
const UChar* string = text.c_str();
size_t length = text.length();
size_t position = 0;
while (position < length) {
UChar32 character;
size_t next_position = position;
U16_NEXT(string, next_position, length, character);
// Now that we have the character, we use ICU in order to query for the
// appropriate Unicode BiDi character type.
int32_t property = u_getIntPropertyValue(character, UCHAR_BIDI_CLASS);
if ((property == U_RIGHT_TO_LEFT) ||
(property == U_RIGHT_TO_LEFT_ARABIC) ||
(property == U_RIGHT_TO_LEFT_EMBEDDING) ||
(property == U_RIGHT_TO_LEFT_OVERRIDE)) {
return RIGHT_TO_LEFT;
} else if ((property == U_LEFT_TO_RIGHT) ||
(property == U_LEFT_TO_RIGHT_EMBEDDING) ||
(property == U_LEFT_TO_RIGHT_OVERRIDE)) {
return LEFT_TO_RIGHT;
}
position = next_position;
}
return LEFT_TO_RIGHT;
}
#if defined(WCHAR_T_IS_UTF32)
TextDirection GetFirstStrongCharacterDirection(const std::wstring& text) {
return GetFirstStrongCharacterDirection(WideToUTF16(text));
}
#endif
bool AdjustStringForLocaleDirection(string16* text) {
if (!IsRTL() || text->empty())
return false;
// Marking the string as LTR if the locale is RTL and the string does not
// contain strong RTL characters. Otherwise, mark the string as RTL.
bool has_rtl_chars = StringContainsStrongRTLChars(*text);
if (!has_rtl_chars)
WrapStringWithLTRFormatting(text);
else
WrapStringWithRTLFormatting(text);
return true;
}
#if defined(WCHAR_T_IS_UTF32)
bool AdjustStringForLocaleDirection(std::wstring* text) {
string16 temp = WideToUTF16(*text);
if (AdjustStringForLocaleDirection(&temp)) {
// We should only touch the output on success.
*text = UTF16ToWide(temp);
return true;
}
return false;
}
#endif
bool StringContainsStrongRTLChars(const string16& text) {
const UChar* string = text.c_str();
size_t length = text.length();
size_t position = 0;
while (position < length) {
UChar32 character;
size_t next_position = position;
U16_NEXT(string, next_position, length, character);
// Now that we have the character, we use ICU in order to query for the
// appropriate Unicode BiDi character type.
int32_t property = u_getIntPropertyValue(character, UCHAR_BIDI_CLASS);
if ((property == U_RIGHT_TO_LEFT) || (property == U_RIGHT_TO_LEFT_ARABIC))
return true;
position = next_position;
}
return false;
}
#if defined(WCHAR_T_IS_UTF32)
bool StringContainsStrongRTLChars(const std::wstring& text) {
return StringContainsStrongRTLChars(WideToUTF16(text));
}
#endif
void WrapStringWithLTRFormatting(string16* text) {
if (text->empty())
return;
// Inserting an LRE (Left-To-Right Embedding) mark as the first character.
text->insert(0, 1, kLeftToRightEmbeddingMark);
// Inserting a PDF (Pop Directional Formatting) mark as the last character.
text->push_back(kPopDirectionalFormatting);
}
#if defined(WCHAR_T_IS_UTF32)
void WrapStringWithLTRFormatting(std::wstring* text) {
if (text->empty())
return;
// Inserting an LRE (Left-To-Right Embedding) mark as the first character.
text->insert(0, 1, static_cast<wchar_t>(kLeftToRightEmbeddingMark));
// Inserting a PDF (Pop Directional Formatting) mark as the last character.
text->push_back(static_cast<wchar_t>(kPopDirectionalFormatting));
}
#endif
void WrapStringWithRTLFormatting(string16* text) {
if (text->empty())
return;
// Inserting an RLE (Right-To-Left Embedding) mark as the first character.
text->insert(0, 1, kRightToLeftEmbeddingMark);
// Inserting a PDF (Pop Directional Formatting) mark as the last character.
text->push_back(kPopDirectionalFormatting);
}
#if defined(WCHAR_T_IS_UTF32)
void WrapStringWithRTLFormatting(std::wstring* text) {
if (text->empty())
return;
// Inserting an RLE (Right-To-Left Embedding) mark as the first character.
text->insert(0, 1, static_cast<wchar_t>(kRightToLeftEmbeddingMark));
// Inserting a PDF (Pop Directional Formatting) mark as the last character.
text->push_back(static_cast<wchar_t>(kPopDirectionalFormatting));
}
#endif
void WrapPathWithLTRFormatting(const FilePath& path,
string16* rtl_safe_path) {
// Wrap the overall path with LRE-PDF pair which essentialy marks the
// string as a Left-To-Right string.
// Inserting an LRE (Left-To-Right Embedding) mark as the first character.
rtl_safe_path->push_back(kLeftToRightEmbeddingMark);
#if defined(OS_MACOSX)
rtl_safe_path->append(UTF8ToUTF16(path.value()));
#elif defined(OS_WIN)
rtl_safe_path->append(path.value());
#else // defined(OS_POSIX) && !defined(OS_MACOSX)
std::wstring wide_path = base::SysNativeMBToWide(path.value());
rtl_safe_path->append(WideToUTF16(wide_path));
#endif
// Inserting a PDF (Pop Directional Formatting) mark as the last character.
rtl_safe_path->push_back(kPopDirectionalFormatting);
}
string16 GetDisplayStringInLTRDirectionality(const string16& text) {
if (!IsRTL())
return text;
string16 text_mutable(text);
WrapStringWithLTRFormatting(&text_mutable);
return text_mutable;
}
const string16 StripWrappingBidiControlCharacters(const string16& text) {
if (text.empty())
return text;
size_t begin_index = 0;
char16 begin = text[begin_index];
if (begin == kLeftToRightEmbeddingMark ||
begin == kRightToLeftEmbeddingMark ||
begin == kLeftToRightOverride ||
begin == kRightToLeftOverride)
++begin_index;
size_t end_index = text.length() - 1;
if (text[end_index] == kPopDirectionalFormatting)
--end_index;
return text.substr(begin_index, end_index - begin_index + 1);
}
} // namespace i18n
} // namespace base
|