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
|
/* -*- Mode: C++; tab-width: 2; indent-tabs-mode: nil; c-basic-offset: 2 -*- */
/* This Source Code Form is subject to the terms of the Mozilla Public
* License, v. 2.0. If a copy of the MPL was not distributed with this
* file, You can obtain one at http://mozilla.org/MPL/2.0/. */
/**
* MODULE NOTES:
* @update gess 4/1/98
*
* The scanner is a low-level service class that knows
* how to consume characters out of an (internal) stream.
* This class also offers a series of utility methods
* that most tokenizers want, such as readUntil()
* and SkipWhitespace().
*/
#ifndef SCANNER
#define SCANNER
#include "nsCharsetSource.h"
#include "nsCOMPtr.h"
#include "nsString.h"
#include "nsIParser.h"
#include "mozilla/Encoding.h"
#include "nsScannerString.h"
#include "mozilla/CheckedInt.h"
class nsReadEndCondition {
public:
const char16_t* mChars;
char16_t mFilter;
explicit nsReadEndCondition(const char16_t* aTerminateChars);
private:
nsReadEndCondition(const nsReadEndCondition& aOther); // No copying
void operator=(const nsReadEndCondition& aOther); // No assigning
};
class nsScanner final {
using Encoding = mozilla::Encoding;
template <typename T>
using NotNull = mozilla::NotNull<T>;
public:
/**
* Use this constructor for the XML fragment parsing case
*/
nsScanner(const nsAString& anHTMLString, bool aIncremental);
/**
* Use this constructor if you want i/o to be based on
* a file (therefore a stream) or just data you provide via Append().
*/
explicit nsScanner(nsIURI* aURI);
~nsScanner();
/**
* retrieve next char from internal input stream
*
* @update gess 3/25/98
* @param ch is the char to accept new value
* @return error code reflecting read status
*/
nsresult GetChar(char16_t& ch);
/**
* Records current offset position in input stream. This allows us
* to back up to this point if the need should arise, such as when
* tokenization gets interrupted.
*
* @update gess 5/12/98
* @param
* @return
*/
int32_t Mark(void);
/**
* Resets current offset position of input stream to marked position.
* This allows us to back up to this point if the need should arise,
* such as when tokenization gets interrupted.
* NOTE: IT IS REALLY BAD FORM TO CALL RELEASE WITHOUT CALLING MARK FIRST!
*
* @update gess 5/12/98
* @param
* @return
*/
void RewindToMark(void);
/**
*
*
* @update harishd 01/12/99
* @param
* @return
*/
bool UngetReadable(const nsAString& aBuffer);
/**
*
*
* @update gess 5/13/98
* @param
* @return
*/
nsresult Append(const nsAString& aBuffer);
/**
*
*
* @update gess 5/21/98
* @param
* @return
*/
nsresult Append(const char* aBuffer, uint32_t aLen);
/**
* Call this to copy bytes out of the scanner that have not yet been consumed
* by the tokenization process.
*
* @update gess 5/12/98
* @param aCopyBuffer is where the scanner buffer will be copied to
* @return true if OK or false on OOM
*/
bool CopyUnusedData(nsString& aCopyBuffer);
/**
* Retrieve the URI of the file that the scanner is reading from.
* In some cases, it's just a given name, because the scanner isn't
* really reading from a file.
*/
nsIURI* GetURI(void) const { return mURI; }
static void SelfTest();
/**
* Use this setter to change the scanner's unicode decoder
*
* @update ftang 3/02/99
* @param aCharset a normalized (alias resolved) charset name
* @param aCharsetSource- where the charset info came from
* @return
*/
nsresult SetDocumentCharset(NotNull<const Encoding*> aEncoding,
int32_t aSource);
void BindSubstring(nsScannerSubstring& aSubstring,
const nsScannerIterator& aStart,
const nsScannerIterator& aEnd);
void CurrentPosition(nsScannerIterator& aPosition);
void EndReading(nsScannerIterator& aPosition);
void SetPosition(nsScannerIterator& aPosition, bool aTruncate = false);
/**
* Internal method used to cause the internal buffer to
* be filled with data.
*
* @update gess4/3/98
*/
bool IsIncremental(void) { return mIncremental; }
void SetIncremental(bool anIncrValue) { mIncremental = anIncrValue; }
protected:
void AppendToBuffer(nsScannerString::Buffer* aBuffer);
bool AppendToBuffer(const nsAString& aStr) {
nsScannerString::Buffer* buf = nsScannerString::AllocBufferFromString(aStr);
if (!buf) return false;
AppendToBuffer(buf);
return true;
}
mozilla::UniquePtr<nsScannerString> mSlidingBuffer;
nsScannerIterator mCurrentPosition; // The position we will next read from in
// the scanner buffer
nsScannerIterator
mMarkPosition; // The position last marked (we may rewind to here)
nsScannerIterator mEndPosition; // The current end of the scanner buffer
nsCOMPtr<nsIURI> mURI;
bool mIncremental;
int32_t mCharsetSource = kCharsetUninitialized;
nsCString mCharset;
mozilla::UniquePtr<mozilla::Decoder> mUnicodeDecoder;
private:
nsScanner& operator=(const nsScanner&); // Not implemented.
};
#endif
|
