summaryrefslogtreecommitdiffstats
path: root/kpdf/xpdf/xpdf/Parser.cc
blob: 65a43d947409eec0ac750a1920fc9b761ff934d7 (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
224
225
226
227
//========================================================================
//
// Parser.cc
//
// Copyright 1996-2003 Glyph & Cog, LLC
//
//========================================================================

#include <aconf.h>

#ifdef USE_GCC_PRAGMAS
#pragma implementation
#endif

#include <stddef.h>
#include "Object.h"
#include "Array.h"
#include "Dict.h"
#include "Decrypt.h"
#include "Parser.h"
#include "XRef.h"
#include "Error.h"

Parser::Parser(XRef *xrefA, Lexer *lexerA, GBool allowStreamsA) {
  xref = xrefA;
  lexer = lexerA;
  inlineImg = 0;
  allowStreams = allowStreamsA;
  lexer->getObj(&buf1);
  lexer->getObj(&buf2);
}

Parser::~Parser() {
  buf1.free();
  buf2.free();
  delete lexer;
}

Object *Parser::getObj(Object *obj, Guchar *fileKey,
		       CryptAlgorithm encAlgorithm, int keyLength,
		       int objNum, int objGen) {
  char *key;
  Stream *str;
  Object obj2;
  int num;
  DecryptStream *decrypt;
  GString *s, *s2;
  int c;

  // refill buffer after inline image data
  if (inlineImg == 2) {
    buf1.free();
    buf2.free();
    lexer->getObj(&buf1);
    lexer->getObj(&buf2);
    inlineImg = 0;
  }

  // array
  if (buf1.isCmd("[")) {
    shift();
    obj->initArray(xref);
    while (!buf1.isCmd("]") && !buf1.isEOF())
      obj->arrayAdd(getObj(&obj2, fileKey, encAlgorithm, keyLength,
			   objNum, objGen));
    if (buf1.isEOF())
      error(getPos(), "End of file inside array");
    shift();

  // dictionary or stream
  } else if (buf1.isCmd("<<")) {
    shift(objNum);
    obj->initDict(xref);
    while (!buf1.isCmd(">>") && !buf1.isEOF()) {
      if (!buf1.isName()) {
	error(getPos(), "Dictionary key must be a name object");
	shift();
      } else {
	key = copyString(buf1.getName());
	shift();
	if (buf1.isEOF() || buf1.isError()) {
	  gfree(key);
	  break;
	}
	obj->dictAdd(key, getObj(&obj2, fileKey, encAlgorithm, keyLength,
				 objNum, objGen));
      }
    }
    if (buf1.isEOF())
      error(getPos(), "End of file inside dictionary");
    // stream objects are not allowed inside content streams or
    // object streams
    if (allowStreams && buf2.isCmd("stream")) {
      if ((str = makeStream(obj, fileKey, encAlgorithm, keyLength,
			    objNum, objGen))) {
	obj->initStream(str);
      } else {
	obj->free();
	obj->initError();
      }
    } else {
      shift();
    }

  // indirect reference or integer
  } else if (buf1.isInt()) {
    num = buf1.getInt();
    shift();
    if (buf1.isInt() && buf2.isCmd("R")) {
      obj->initRef(num, buf1.getInt());
      shift();
      shift();
    } else {
      obj->initInt(num);
    }

  // string
  } else if (buf1.isString() && fileKey) {
    s = buf1.getString();
    s2 = new GString();
    obj2.initNull();
    decrypt = new DecryptStream(new MemStream(s->getCString(), 0,
					      s->getLength(), &obj2),
				fileKey, encAlgorithm, keyLength,
				objNum, objGen);
    decrypt->reset();
    while ((c = decrypt->getChar()) != EOF) {
      s2->append((char)c);
    }
    delete decrypt;
    obj->initString(s2);
    shift();

  // simple object
  } else {
    buf1.copy(obj);
    shift();
  }

  return obj;
}

Stream *Parser::makeStream(Object *dict, Guchar *fileKey,
			   CryptAlgorithm encAlgorithm, int keyLength,
			   int objNum, int objGen) {
  Object obj;
  BaseStream *baseStr;
  Stream *str;
  Guint pos, endPos, length;

  // get stream start position
  lexer->skipToNextLine();
  pos = lexer->getPos();

  // get length
  dict->dictLookup("Length", &obj);
  if (obj.isInt()) {
    length = (Guint)obj.getInt();
    obj.free();
  } else {
    error(getPos(), "Bad 'Length' attribute in stream");
    obj.free();
    return NULL;
  }

  // check for length in damaged file
  if (xref && xref->getStreamEnd(pos, &endPos)) {
    length = endPos - pos;
  }

  // in badly damaged PDF files, we can run off the end of the input
  // stream immediately after the "stream" token
  if (!lexer->getStream()) {
    return NULL;
  }
  baseStr = lexer->getStream()->getBaseStream();

  // skip over stream data
  lexer->setPos(pos + length);

  // refill token buffers and check for 'endstream'
  shift();  // kill '>>'
  shift();  // kill 'stream'
  if (buf1.isCmd("endstream")) {
    shift();
  } else {
    error(getPos(), "Missing 'endstream'");
    // kludge for broken PDF files: just add 5k to the length, and
    // hope its enough
    length += 5000;
  }

  // make base stream
  str = baseStr->makeSubStream(pos, gTrue, length, dict);

  // handle decryption
  if (fileKey) {
    str = new DecryptStream(str, fileKey, encAlgorithm, keyLength,
			    objNum, objGen);
  }

  // get filters
  str = str->addFilters(dict);

  return str;
}

void Parser::shift(int objNum) {
  if (inlineImg > 0) {
    if (inlineImg < 2) {
      ++inlineImg;
    } else {
      // in a damaged content stream, if 'ID' shows up in the middle
      // of a dictionary, we need to reset
      inlineImg = 0;
    }
  } else if (buf2.isCmd("ID")) {
    lexer->skipChar();		// skip char after 'ID' command
    inlineImg = 1;
  }
  buf1.free();
  buf1 = buf2;
  if (inlineImg > 0)		// don't buffer inline image data
    buf2.initNull();
  else
    lexer->getObj(&buf2, objNum);
}