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
|
/*
* Copyright (C) 2008 Jürg Billeter <j@bitron.ch>
* Copyright (C) 2008 Dominik Röttsches <dominik.roettsches@access-company.com>
*
* This library is free software; you can redistribute it and/or
* modify it under the terms of the GNU Library General Public
* License as published by the Free Software Foundation; either
* version 2 of the License, or (at your option) any later version.
*
* This library is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Library General Public License for more details.
*
* You should have received a copy of the GNU Library General Public License
* along with this library; see the file COPYING.LIB. If not, write to
* the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
* Boston, MA 02110-1301, USA.
*
*/
#include "config.h"
#include "UnicodeGLib.h"
namespace WTF {
namespace Unicode {
UChar32 foldCase(UChar32 ch)
{
GOwnPtr<GError> gerror;
GOwnPtr<char> utf8char;
utf8char.set(g_ucs4_to_utf8(reinterpret_cast<gunichar*>(&ch), 1, 0, 0, &gerror.outPtr()));
if (gerror)
return ch;
GOwnPtr<char> utf8caseFolded;
utf8caseFolded.set(g_utf8_casefold(utf8char.get(), -1));
GOwnPtr<gunichar> ucs4Result;
ucs4Result.set(g_utf8_to_ucs4_fast(utf8caseFolded.get(), -1, 0));
return *ucs4Result;
}
int foldCase(UChar* result, int resultLength, const UChar* src, int srcLength, bool* error)
{
*error = false;
GOwnPtr<GError> gerror;
GOwnPtr<char> utf8src;
utf8src.set(g_utf16_to_utf8(src, srcLength, 0, 0, &gerror.outPtr()));
if (gerror) {
*error = true;
return -1;
}
GOwnPtr<char> utf8result;
utf8result.set(g_utf8_casefold(utf8src.get(), -1));
long utf16resultLength = -1;
GOwnPtr<UChar> utf16result;
utf16result.set(g_utf8_to_utf16(utf8result.get(), -1, 0, &utf16resultLength, &gerror.outPtr()));
if (gerror) {
*error = true;
return -1;
}
if (utf16resultLength > resultLength) {
*error = true;
return utf16resultLength;
}
memcpy(result, utf16result.get(), utf16resultLength * sizeof(UChar));
return utf16resultLength;
}
int toLower(UChar* result, int resultLength, const UChar* src, int srcLength, bool* error)
{
*error = false;
GOwnPtr<GError> gerror;
GOwnPtr<char> utf8src;
utf8src.set(g_utf16_to_utf8(src, srcLength, 0, 0, &gerror.outPtr()));
if (gerror) {
*error = true;
return -1;
}
GOwnPtr<char> utf8result;
utf8result.set(g_utf8_strdown(utf8src.get(), -1));
long utf16resultLength = -1;
GOwnPtr<UChar> utf16result;
utf16result.set(g_utf8_to_utf16(utf8result.get(), -1, 0, &utf16resultLength, &gerror.outPtr()));
if (gerror) {
*error = true;
return -1;
}
if (utf16resultLength > resultLength) {
*error = true;
return utf16resultLength;
}
memcpy(result, utf16result.get(), utf16resultLength * sizeof(UChar));
return utf16resultLength;
}
int toUpper(UChar* result, int resultLength, const UChar* src, int srcLength, bool* error)
{
*error = false;
GOwnPtr<GError> gerror;
GOwnPtr<char> utf8src;
utf8src.set(g_utf16_to_utf8(src, srcLength, 0, 0, &gerror.outPtr()));
if (gerror) {
*error = true;
return -1;
}
GOwnPtr<char> utf8result;
utf8result.set(g_utf8_strup(utf8src.get(), -1));
long utf16resultLength = -1;
GOwnPtr<UChar> utf16result;
utf16result.set(g_utf8_to_utf16(utf8result.get(), -1, 0, &utf16resultLength, &gerror.outPtr()));
if (gerror) {
*error = true;
return -1;
}
if (utf16resultLength > resultLength) {
*error = true;
return utf16resultLength;
}
memcpy(result, utf16result.get(), utf16resultLength * sizeof(UChar));
return utf16resultLength;
}
Direction direction(UChar32 c)
{
PangoBidiType type = pango_bidi_type_for_unichar(c);
switch (type) {
case PANGO_BIDI_TYPE_L:
return LeftToRight;
case PANGO_BIDI_TYPE_R:
return RightToLeft;
case PANGO_BIDI_TYPE_AL:
return RightToLeftArabic;
case PANGO_BIDI_TYPE_LRE:
return LeftToRightEmbedding;
case PANGO_BIDI_TYPE_RLE:
return RightToLeftEmbedding;
case PANGO_BIDI_TYPE_LRO:
return LeftToRightOverride;
case PANGO_BIDI_TYPE_RLO:
return RightToLeftOverride;
case PANGO_BIDI_TYPE_PDF:
return PopDirectionalFormat;
case PANGO_BIDI_TYPE_EN:
return EuropeanNumber;
case PANGO_BIDI_TYPE_AN:
return ArabicNumber;
case PANGO_BIDI_TYPE_ES:
return EuropeanNumberSeparator;
case PANGO_BIDI_TYPE_ET:
return EuropeanNumberTerminator;
case PANGO_BIDI_TYPE_CS:
return CommonNumberSeparator;
case PANGO_BIDI_TYPE_NSM:
return NonSpacingMark;
case PANGO_BIDI_TYPE_BN:
return BoundaryNeutral;
case PANGO_BIDI_TYPE_B:
return BlockSeparator;
case PANGO_BIDI_TYPE_S:
return SegmentSeparator;
case PANGO_BIDI_TYPE_WS:
return WhiteSpaceNeutral;
default:
return OtherNeutral;
}
}
int umemcasecmp(const UChar* a, const UChar* b, int len)
{
GOwnPtr<char> utf8a;
GOwnPtr<char> utf8b;
utf8a.set(g_utf16_to_utf8(a, len, 0, 0, 0));
utf8b.set(g_utf16_to_utf8(b, len, 0, 0, 0));
GOwnPtr<char> foldedA;
GOwnPtr<char> foldedB;
foldedA.set(g_utf8_casefold(utf8a.get(), -1));
foldedB.set(g_utf8_casefold(utf8b.get(), -1));
// FIXME: umemcasecmp needs to mimic u_memcasecmp of icu
// from the ICU docs:
// "Compare two strings case-insensitively using full case folding.
// his is equivalent to u_strcmp(u_strFoldCase(s1, n, options), u_strFoldCase(s2, n, options))."
//
// So it looks like we don't need the full g_utf8_collate here,
// but really a bitwise comparison of casefolded unicode chars (not utf-8 bytes).
// As there is no direct equivalent to this icu function in GLib, for now
// we'll use g_utf8_collate():
return g_utf8_collate(foldedA.get(), foldedB.get());
}
}
}
|
