Pl_QPDFTokenizer.cc
3.61 KB
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
#include <qpdf/Pl_QPDFTokenizer.hh>
#include <qpdf/QPDF_String.hh>
#include <qpdf/QPDF_Name.hh>
#include <stdexcept>
#include <string.h>
Pl_QPDFTokenizer::Pl_QPDFTokenizer(char const* identifier, Pipeline* next) :
Pipeline(identifier, next),
newline_after_next_token(false),
just_wrote_nl(false),
last_char_was_cr(false),
unread_char(false),
char_to_unread('\0'),
pass_through(false)
{
}
Pl_QPDFTokenizer::~Pl_QPDFTokenizer()
{
}
void
Pl_QPDFTokenizer::writeNext(char const* buf, int len)
{
if (len)
{
unsigned char* t = new unsigned char[len];
memcpy(t, buf, len);
getNext()->write(t, len);
delete [] t;
this->just_wrote_nl = (buf[len-1] == '\n');
}
}
void
Pl_QPDFTokenizer::writeToken(QPDFTokenizer::Token& token)
{
std::string value = token.getRawValue();
switch (token.getType())
{
case QPDFTokenizer::tt_string:
value = QPDF_String(token.getValue()).unparse();
break;
case QPDFTokenizer::tt_name:
value = QPDF_Name(token.getValue()).unparse();
break;
default:
break;
}
writeNext(value.c_str(), value.length());
}
void
Pl_QPDFTokenizer::processChar(char ch)
{
if (this->pass_through)
{
// We're not normalizing anymore -- just write this without
// looking at it.
writeNext(&ch, 1);
return;
}
tokenizer.presentCharacter(ch);
QPDFTokenizer::Token token;
if (tokenizer.getToken(token, this->unread_char, this->char_to_unread))
{
writeToken(token);
if (this->newline_after_next_token)
{
writeNext("\n", 1);
this->newline_after_next_token = false;
}
if ((token.getType() == QPDFTokenizer::tt_word) &&
(token.getValue() == "BI"))
{
// Uh oh.... we're not sophisticated enough to handle
// inline images safely. We'd have to to set up all the
// filters and pipe the image data through it until the
// filtered output was the right size for an image of the
// specified dimensions. Then we'd either have to write
// out raw image data or continue to write filtered data,
// resuming normalization when we get to the end.
// Instead, for now, we'll just turn off normalization for
// the remainder of this stream.
this->pass_through = true;
if (this->unread_char)
{
writeNext(&this->char_to_unread, 1);
this->unread_char = false;
}
}
}
else
{
bool suppress = false;
if ((ch == '\n') && (this->last_char_was_cr))
{
// Always ignore \n following \r
suppress = true;
}
if ((this->last_char_was_cr = (ch == '\r')))
{
ch = '\n';
}
if (this->tokenizer.betweenTokens())
{
if (! suppress)
{
writeNext(&ch, 1);
}
}
else
{
if (ch == '\n')
{
this->newline_after_next_token = true;
}
}
}
}
void
Pl_QPDFTokenizer::checkUnread()
{
if (this->unread_char)
{
processChar(this->char_to_unread);
if (this->unread_char)
{
throw std::logic_error(
"INTERNAL ERROR: unread_char still true after processing "
"unread character");
}
}
}
void
Pl_QPDFTokenizer::write(unsigned char* buf, int len)
{
checkUnread();
for (int i = 0; i < len; ++i)
{
processChar(buf[i]);
checkUnread();
}
}
void
Pl_QPDFTokenizer::finish()
{
this->tokenizer.presentEOF();
if (! this->pass_through)
{
QPDFTokenizer::Token token;
if (tokenizer.getToken(token, this->unread_char, this->char_to_unread))
{
writeToken(token);
if (unread_char)
{
if (this->char_to_unread == '\r')
{
this->char_to_unread = '\n';
}
writeNext(&this->char_to_unread, 1);
}
}
}
if (! this->just_wrote_nl)
{
writeNext("\n", 1);
}
getNext()->finish();
}