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
|
/*
* Copyright (C) 2005, 2007 Apple Inc. All rights reserved.
*
* 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 "break_lines.h"
#include "CharacterNames.h"
#include "TextBreakIterator.h"
#if PLATFORM(MAC)
#include <CoreServices/CoreServices.h>
#endif
namespace WebCore {
static inline bool isBreakableSpace(UChar ch, bool treatNoBreakSpaceAsBreak)
{
switch (ch) {
case ' ':
case '\n':
case '\t':
return true;
case noBreakSpace:
return treatNoBreakSpaceAsBreak;
default:
return false;
}
}
static inline bool shouldBreakAfter(UChar ch)
{
// Match WinIE's breaking strategy, which is to always allow breaks after hyphens and question marks.
// FIXME: it appears that IE behavior is more complex, see <http://bugs.webkit.org/show_bug.cgi?id=17475>.
switch (ch) {
case '-':
case '?':
#ifdef ANDROID_LAYOUT
// as '/' is used in uri which is always long, we would like to break it
case '/':
#endif
case softHyphen:
// FIXME: cases for ideographicComma and ideographicFullStop are a workaround for an issue in Unicode 5.0
// which is likely to be resolved in Unicode 5.1 <http://bugs.webkit.org/show_bug.cgi?id=17411>.
// We may want to remove or conditionalize this workaround at some point.
case ideographicComma:
case ideographicFullStop:
return true;
default:
return false;
}
}
static inline bool needsLineBreakIterator(UChar ch)
{
return ch > 0x7F && ch != noBreakSpace;
}
#if PLATFORM(MAC) && defined(BUILDING_ON_TIGER)
static inline TextBreakLocatorRef lineBreakLocator()
{
TextBreakLocatorRef locator = 0;
UCCreateTextBreakLocator(0, 0, kUCTextBreakLineMask, &locator);
return locator;
}
#endif
int nextBreakablePosition(const UChar* str, int pos, int len, bool treatNoBreakSpaceAsBreak)
{
#if !PLATFORM(MAC) || !defined(BUILDING_ON_TIGER)
TextBreakIterator* breakIterator = 0;
#endif
int nextBreak = -1;
UChar lastCh = pos > 0 ? str[pos - 1] : 0;
for (int i = pos; i < len; i++) {
UChar ch = str[i];
if (isBreakableSpace(ch, treatNoBreakSpaceAsBreak) || shouldBreakAfter(lastCh))
return i;
if (needsLineBreakIterator(ch) || needsLineBreakIterator(lastCh)) {
if (nextBreak < i && i) {
#if !PLATFORM(MAC) || !defined(BUILDING_ON_TIGER)
if (!breakIterator)
breakIterator = lineBreakIterator(str, len);
if (breakIterator)
nextBreak = textBreakFollowing(breakIterator, i - 1);
#else
static TextBreakLocatorRef breakLocator = lineBreakLocator();
if (breakLocator) {
UniCharArrayOffset nextUCBreak;
if (UCFindTextBreak(breakLocator, kUCTextBreakLineMask, 0, str, len, i, &nextUCBreak) == 0)
nextBreak = nextUCBreak;
}
#endif
}
if (i == nextBreak && !isBreakableSpace(lastCh, treatNoBreakSpaceAsBreak))
return i;
}
lastCh = ch;
}
return len;
}
} // namespace WebCore
|
