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
|
/*
Copyright (C) 2004, 2005, 2006, 2007, 2008 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.
*/
#ifndef SegmentedString_h
#define SegmentedString_h
#include "PlatformString.h"
#include <wtf/Deque.h>
#include <wtf/text/TextPosition.h>
namespace WebCore {
class SegmentedString;
class SegmentedSubstring {
public:
SegmentedSubstring() : m_length(0), m_current(0), m_doNotExcludeLineNumbers(true) {}
SegmentedSubstring(const String& str)
: m_length(str.length())
, m_current(str.isEmpty() ? 0 : str.characters())
, m_string(str)
, m_doNotExcludeLineNumbers(true)
{
}
void clear() { m_length = 0; m_current = 0; }
bool excludeLineNumbers() const { return !m_doNotExcludeLineNumbers; }
bool doNotExcludeLineNumbers() const { return m_doNotExcludeLineNumbers; }
void setExcludeLineNumbers() { m_doNotExcludeLineNumbers = false; }
int numberOfCharactersConsumed() const { return m_string.length() - m_length; }
void appendTo(String& str) const
{
if (m_string.characters() == m_current) {
if (str.isEmpty())
str = m_string;
else
str.append(m_string);
} else {
str.append(String(m_current, m_length));
}
}
public:
int m_length;
const UChar* m_current;
private:
String m_string;
bool m_doNotExcludeLineNumbers;
};
class SegmentedString {
public:
SegmentedString()
: m_pushedChar1(0)
, m_pushedChar2(0)
, m_currentChar(0)
, m_numberOfCharactersConsumedPriorToCurrentString(0)
, m_numberOfCharactersConsumedPriorToCurrentLine(0)
, m_currentLine(0)
, m_composite(false)
, m_closed(false)
{
}
SegmentedString(const String& str)
: m_pushedChar1(0)
, m_pushedChar2(0)
, m_currentString(str)
, m_currentChar(m_currentString.m_current)
, m_numberOfCharactersConsumedPriorToCurrentString(0)
, m_numberOfCharactersConsumedPriorToCurrentLine(0)
, m_currentLine(0)
, m_composite(false)
, m_closed(false)
{
}
SegmentedString(const SegmentedString&);
const SegmentedString& operator=(const SegmentedString&);
void clear();
void close();
void append(const SegmentedString&);
void prepend(const SegmentedString&);
bool excludeLineNumbers() const { return m_currentString.excludeLineNumbers(); }
void setExcludeLineNumbers();
void push(UChar c)
{
if (!m_pushedChar1) {
m_pushedChar1 = c;
m_currentChar = m_pushedChar1 ? &m_pushedChar1 : m_currentString.m_current;
} else {
ASSERT(!m_pushedChar2);
m_pushedChar2 = c;
}
}
bool isEmpty() const { return !current(); }
unsigned length() const;
bool isClosed() const { return m_closed; }
enum LookAheadResult {
DidNotMatch,
DidMatch,
NotEnoughCharacters,
};
LookAheadResult lookAhead(const String& string) { return lookAheadInline<SegmentedString::equalsLiterally>(string); }
LookAheadResult lookAheadIgnoringCase(const String& string) { return lookAheadInline<SegmentedString::equalsIgnoringCase>(string); }
void advance()
{
if (!m_pushedChar1 && m_currentString.m_length > 1) {
--m_currentString.m_length;
m_currentChar = ++m_currentString.m_current;
return;
}
advanceSlowCase();
}
void advanceAndASSERT(UChar expectedCharacter)
{
ASSERT_UNUSED(expectedCharacter, *current() == expectedCharacter);
advance();
}
void advanceAndASSERTIgnoringCase(UChar expectedCharacter)
{
ASSERT_UNUSED(expectedCharacter, WTF::Unicode::foldCase(*current()) == WTF::Unicode::foldCase(expectedCharacter));
advance();
}
void advancePastNewline(int& lineNumber)
{
ASSERT(*current() == '\n');
if (!m_pushedChar1 && m_currentString.m_length > 1) {
int newLineFlag = m_currentString.doNotExcludeLineNumbers();
lineNumber += newLineFlag;
m_currentLine += newLineFlag;
if (newLineFlag)
m_numberOfCharactersConsumedPriorToCurrentLine = numberOfCharactersConsumed() + 1;
--m_currentString.m_length;
m_currentChar = ++m_currentString.m_current;
return;
}
advanceSlowCase(lineNumber);
}
void advancePastNonNewline()
{
ASSERT(*current() != '\n');
if (!m_pushedChar1 && m_currentString.m_length > 1) {
--m_currentString.m_length;
m_currentChar = ++m_currentString.m_current;
return;
}
advanceSlowCase();
}
void advance(int& lineNumber)
{
if (!m_pushedChar1 && m_currentString.m_length > 1) {
int newLineFlag = (*m_currentString.m_current == '\n') & m_currentString.doNotExcludeLineNumbers();
lineNumber += newLineFlag;
m_currentLine += newLineFlag;
if (newLineFlag)
m_numberOfCharactersConsumedPriorToCurrentLine = numberOfCharactersConsumed() + 1;
--m_currentString.m_length;
m_currentChar = ++m_currentString.m_current;
return;
}
advanceSlowCase(lineNumber);
}
// Writes the consumed characters into consumedCharacters, which must
// have space for at least |count| characters.
void advance(unsigned count, UChar* consumedCharacters);
bool escaped() const { return m_pushedChar1; }
int numberOfCharactersConsumed() const
{
int numberOfPushedCharacters = 0;
if (m_pushedChar1) {
++numberOfPushedCharacters;
if (m_pushedChar2)
++numberOfPushedCharacters;
}
return m_numberOfCharactersConsumedPriorToCurrentString + m_currentString.numberOfCharactersConsumed() - numberOfPushedCharacters;
}
String toString() const;
const UChar& operator*() const { return *current(); }
const UChar* operator->() const { return current(); }
// The method is moderately slow, comparing to currentLine method.
WTF::ZeroBasedNumber currentColumn() const;
WTF::ZeroBasedNumber currentLine() const;
// Sets value of line/column variables. Column is specified indirectly by a parameter columnAftreProlog
// which is a value of column that we should get after a prolog (first prologLength characters) has been consumed.
void setCurrentPosition(WTF::ZeroBasedNumber line, WTF::ZeroBasedNumber columnAftreProlog, int prologLength);
private:
void append(const SegmentedSubstring&);
void prepend(const SegmentedSubstring&);
void advanceSlowCase();
void advanceSlowCase(int& lineNumber);
void advanceSubstring();
const UChar* current() const { return m_currentChar; }
static bool equalsLiterally(const UChar* str1, const UChar* str2, size_t count) { return !memcmp(str1, str2, count * sizeof(UChar)); }
static bool equalsIgnoringCase(const UChar* str1, const UChar* str2, size_t count) { return !WTF::Unicode::umemcasecmp(str1, str2, count); }
template<bool equals(const UChar* str1, const UChar* str2, size_t count)>
inline LookAheadResult lookAheadInline(const String& string)
{
if (!m_pushedChar1 && string.length() <= static_cast<unsigned>(m_currentString.m_length)) {
if (equals(string.characters(), m_currentString.m_current, string.length()))
return DidMatch;
return DidNotMatch;
}
return lookAheadSlowCase<equals>(string);
}
template<bool equals(const UChar* str1, const UChar* str2, size_t count)>
LookAheadResult lookAheadSlowCase(const String& string)
{
unsigned count = string.length();
if (count > length())
return NotEnoughCharacters;
UChar* consumedCharacters;
String consumedString = String::createUninitialized(count, consumedCharacters);
advance(count, consumedCharacters);
LookAheadResult result = DidNotMatch;
if (equals(string.characters(), consumedCharacters, count))
result = DidMatch;
prepend(SegmentedString(consumedString));
return result;
}
UChar m_pushedChar1;
UChar m_pushedChar2;
SegmentedSubstring m_currentString;
const UChar* m_currentChar;
int m_numberOfCharactersConsumedPriorToCurrentString;
int m_numberOfCharactersConsumedPriorToCurrentLine;
int m_currentLine;
Deque<SegmentedSubstring> m_substrings;
bool m_composite;
bool m_closed;
};
}
#endif
|