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
|
// Copyright 2014 PDFium Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
// found in the LICENSE file.
// Original code copyright 2014 Foxit Software Inc. http://www.foxitsoftware.com
#include "core/fpdfapi/fpdf_parser/fpdf_parser_utility.h"
#include "core/fpdfapi/fpdf_parser/include/cpdf_array.h"
#include "core/fpdfapi/fpdf_parser/include/cpdf_dictionary.h"
#include "core/fpdfapi/fpdf_parser/include/cpdf_number.h"
#include "core/fpdfapi/fpdf_parser/include/cpdf_reference.h"
#include "core/fpdfapi/fpdf_parser/include/cpdf_stream.h"
#include "core/fpdfapi/fpdf_parser/include/cpdf_stream_acc.h"
#include "core/fpdfapi/fpdf_parser/include/cpdf_string.h"
#include "core/fpdfapi/fpdf_parser/include/fpdf_parser_decode.h"
#include "core/fxcrt/include/fx_ext.h"
// Indexed by 8-bit character code, contains either:
// 'W' - for whitespace: NUL, TAB, CR, LF, FF, SPACE, 0x80, 0xff
// 'N' - for numeric: 0123456789+-.
// 'D' - for delimiter: %()/<>[]{}
// 'R' - otherwise.
const char PDF_CharType[256] = {
// NUL SOH STX ETX EOT ENQ ACK BEL BS HT LF VT FF CR SO
// SI
'W', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'W', 'W', 'R', 'W', 'W', 'R',
'R',
// DLE DC1 DC2 DC3 DC4 NAK SYN ETB CAN EM SUB ESC FS GS RS
// US
'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R',
'R',
// SP ! " # $ % & ´ ( ) * + , - .
// /
'W', 'R', 'R', 'R', 'R', 'D', 'R', 'R', 'D', 'D', 'R', 'N', 'R', 'N', 'N',
'D',
// 0 1 2 3 4 5 6 7 8 9 : ; < = > ?
'N', 'N', 'N', 'N', 'N', 'N', 'N', 'N', 'N', 'N', 'R', 'R', 'D', 'R', 'D',
'R',
// @ A B C D E F G H I J K L M N O
'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R',
'R',
// P Q R S T U V W X Y Z [ \ ] ^ _
'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'D', 'R', 'D', 'R',
'R',
// ` a b c d e f g h i j k l m n o
'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R',
'R',
// p q r s t u v w x y z { | } ~
// DEL
'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'D', 'R', 'D', 'R',
'R',
'W', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R',
'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R',
'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R',
'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R',
'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R',
'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R',
'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R',
'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R',
'R', 'R', 'R', 'R', 'R', 'R', 'R', 'W'};
int32_t GetHeaderOffset(IFX_FileRead* pFile) {
const size_t kBufSize = 4;
uint8_t buf[kBufSize];
for (int32_t offset = 0; offset <= 1024; ++offset) {
if (!pFile->ReadBlock(buf, offset, kBufSize))
return -1;
if (memcmp(buf, "%PDF", 4) == 0)
return offset;
}
return -1;
}
int32_t GetDirectInteger(CPDF_Dictionary* pDict, const CFX_ByteStringC& key) {
CPDF_Number* pObj = ToNumber(pDict->GetElement(key));
return pObj ? pObj->GetInteger() : 0;
}
CFX_ByteString PDF_NameDecode(const CFX_ByteStringC& bstr) {
int size = bstr.GetLength();
const FX_CHAR* pSrc = bstr.GetCStr();
if (!FXSYS_memchr(pSrc, '#', size)) {
return bstr;
}
CFX_ByteString result;
FX_CHAR* pDestStart = result.GetBuffer(size);
FX_CHAR* pDest = pDestStart;
for (int i = 0; i < size; i++) {
if (pSrc[i] == '#' && i < size - 2) {
*pDest++ =
FXSYS_toHexDigit(pSrc[i + 1]) * 16 + FXSYS_toHexDigit(pSrc[i + 2]);
i += 2;
} else {
*pDest++ = pSrc[i];
}
}
result.ReleaseBuffer((FX_STRSIZE)(pDest - pDestStart));
return result;
}
CFX_ByteString PDF_NameDecode(const CFX_ByteString& orig) {
if (!FXSYS_memchr(orig.c_str(), '#', orig.GetLength())) {
return orig;
}
return PDF_NameDecode(CFX_ByteStringC(orig));
}
CFX_ByteString PDF_NameEncode(const CFX_ByteString& orig) {
uint8_t* src_buf = (uint8_t*)orig.c_str();
int src_len = orig.GetLength();
int dest_len = 0;
int i;
for (i = 0; i < src_len; i++) {
uint8_t ch = src_buf[i];
if (ch >= 0x80 || PDFCharIsWhitespace(ch) || ch == '#' ||
PDFCharIsDelimiter(ch)) {
dest_len += 3;
} else {
dest_len++;
}
}
if (dest_len == src_len)
return orig;
CFX_ByteString res;
FX_CHAR* dest_buf = res.GetBuffer(dest_len);
dest_len = 0;
for (i = 0; i < src_len; i++) {
uint8_t ch = src_buf[i];
if (ch >= 0x80 || PDFCharIsWhitespace(ch) || ch == '#' ||
PDFCharIsDelimiter(ch)) {
dest_buf[dest_len++] = '#';
dest_buf[dest_len++] = "0123456789ABCDEF"[ch / 16];
dest_buf[dest_len++] = "0123456789ABCDEF"[ch % 16];
} else {
dest_buf[dest_len++] = ch;
}
}
dest_buf[dest_len] = 0;
res.ReleaseBuffer();
return res;
}
CFX_ByteTextBuf& operator<<(CFX_ByteTextBuf& buf, const CPDF_Object* pObj) {
if (!pObj) {
buf << " null";
return buf;
}
switch (pObj->GetType()) {
case CPDF_Object::NULLOBJ:
buf << " null";
break;
case CPDF_Object::BOOLEAN:
case CPDF_Object::NUMBER:
buf << " " << pObj->GetString();
break;
case CPDF_Object::STRING:
buf << PDF_EncodeString(pObj->GetString(), pObj->AsString()->IsHex());
break;
case CPDF_Object::NAME: {
CFX_ByteString str = pObj->GetString();
buf << "/" << PDF_NameEncode(str);
break;
}
case CPDF_Object::REFERENCE: {
buf << " " << pObj->AsReference()->GetRefObjNum() << " 0 R ";
break;
}
case CPDF_Object::ARRAY: {
const CPDF_Array* p = pObj->AsArray();
buf << "[";
for (FX_DWORD i = 0; i < p->GetCount(); i++) {
CPDF_Object* pElement = p->GetElement(i);
if (pElement->GetObjNum()) {
buf << " " << pElement->GetObjNum() << " 0 R";
} else {
buf << pElement;
}
}
buf << "]";
break;
}
case CPDF_Object::DICTIONARY: {
const CPDF_Dictionary* p = pObj->AsDictionary();
buf << "<<";
for (const auto& it : *p) {
const CFX_ByteString& key = it.first;
CPDF_Object* pValue = it.second;
buf << "/" << PDF_NameEncode(key);
if (pValue && pValue->GetObjNum()) {
buf << " " << pValue->GetObjNum() << " 0 R ";
} else {
buf << pValue;
}
}
buf << ">>";
break;
}
case CPDF_Object::STREAM: {
const CPDF_Stream* p = pObj->AsStream();
buf << p->GetDict() << "stream\r\n";
CPDF_StreamAcc acc;
acc.LoadAllData(p, TRUE);
buf.AppendBlock(acc.GetData(), acc.GetSize());
buf << "\r\nendstream";
break;
}
default:
ASSERT(FALSE);
break;
}
return buf;
}
|
