blob: b9a0a567812de512d2e84310c998034d5707a632 (
plain)
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
|
/*
This file is part of the KDE project
Copyright (C) 2001 Ewald Snel <ewald@rambo.its.tudelft.nl>
Copyright (C) 2001 Tomasz Grobelny <grotk@poczta.onet.pl>
Copyright (C) 2005 Tommi Rantala <tommi.rantala@cs.helsinki.fi>
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.
*/
#include <kdebug.h>
#include "rtfimport_tokenizer.h"
RTFTokenizer::RTFTokenizer()
{
tokenText.resize( 4113 );
fileBuffer.resize( 4096 );
infile = 0L;
}
/**
* Open tokenizer from file.
* @param in the input file
*/
void RTFTokenizer::open( TQFile *in )
{
fileBufferPtr = 0L;
fileBufferEnd = 0L;
infile = in;
type = RTFTokenizer::PlainText;
}
int RTFTokenizer::nextChar()
{
if ( fileBufferPtr == fileBufferEnd ) {
int n = infile->readBlock( fileBuffer.data(), fileBuffer.size() );
fileBufferPtr = ( uchar* ) fileBuffer.data();
fileBufferEnd = fileBufferPtr;
if ( n <= 0 )
return -1;
fileBufferEnd = fileBufferPtr + n;
}
return *fileBufferPtr++;
}
/**
* Reads the next token.
*/
void RTFTokenizer::next()
{
int ch;
value=0;
if (!infile)
return;
do {
int n = nextChar();
if ( n <= 0 ) {
ch = '}';
break;
}
ch = n;
}
while (ch == '\n' || ch == '\r' && ch != 0);
// Skip one byte for prepend '@' to destinations
text = (tokenText.data() + 1);
hasParam = false;
uchar *_text = (uchar *)text;
if (ch == '{')
type = RTFTokenizer::OpenGroup;
else if (ch == '}')
type = RTFTokenizer::CloseGroup;
else if (ch == '\\')
{
type = RTFTokenizer::ControlWord;
int n = nextChar();
if ( n <= 0 ) {
// Return CloseGroup on EOF
type = RTFTokenizer::CloseGroup;
return;
}
ch = n;
// Type is either control word or control symbol
if ((ch >= 'a' && ch <= 'z') || (ch >= 'A' && ch <= 'Z'))
{
int v = 0;
// Read alphabetic string (command)
while (_text < ( uchar* )tokenText.data()+tokenText.size()-3 &&
((ch >= 'a' && ch <= 'z') || (ch >= 'A' && ch <= 'Z')) )
{
*_text++ = ch;
int n = nextChar();
if ( n <= 0 ) {
ch = ' ';
break;
}
ch = n;
}
// Read numeric parameter (param)
bool isneg = (ch == '-');
if (isneg) {
int n = nextChar();
if ( n <= 0 ) {
type = RTFTokenizer::CloseGroup;
return;
}
ch = n;
}
while (ch >= '0' && ch <= '9') {
v = (10 * v) + ch - '0';
hasParam = true;
int n = nextChar();
if ( n <= 0 )
n = ' ';
ch = n;
}
value = isneg ? -v : v;
// If delimiter is a space, it's part of the control word
if (ch != ' ')
{
--fileBufferPtr;
}
*_text = 0; // Just put an end of string for the test, it can then be over-written again
if ( !memcmp( tokenText.data()+1, "bin", 4 ) )
{ // We have \bin, so we need to read the bytes
kdDebug(30515) << "Token:" << tokenText << endl;
if (value > 0)
{
kdDebug(30515) << "\\bin" << value << endl;
type = RTFTokenizer::BinaryData;
binaryData.resize(value);
for (int i=0; i<value; i++)
{
int n = nextChar();
if ( n <= 0 ) {
type = RTFTokenizer::CloseGroup;
break;
}
binaryData[i] = n;
}
}
}
}
else if (ch=='\'')
{
// Got hex value, for example \'2d
type = RTFTokenizer::ControlWord;
*_text++ = ch;
for(int i=0;i<2;i++)
{
int n = nextChar();
if ( n <= 0 ) {
if ( i == 0 ) {
type = RTFTokenizer::CloseGroup;
return;
} else {
ch = ' ';
break;
}
}
ch = n;
hasParam = true;
value<<=4;
value=value|((ch + ((ch & 16) ? 0 : 9)) & 0xf);
}
}
else
{
type = RTFTokenizer::ControlWord;
*_text++ = ch;
}
}
else
{
type = RTFTokenizer::PlainText;
// Everything until next backslash, opener or closer
while ( ch != '\\' && ch != '{' && ch != '}' && ch != '\n' &&
ch != '\r')
{
*_text++ = ch;
if(fileBufferPtr >= fileBufferEnd)
break;
ch = *fileBufferPtr++;
}
if(fileBufferPtr < fileBufferEnd)
--fileBufferPtr; // give back the last char
}
*_text++ = 0;
}
|
