This file is indexed.

/usr/include/podofo/base/PdfParser.h is in libpodofo-dev 0.9.0-1.2+b2.

This file is owned by root:root, with mode 0o644.

The actual contents of the file can be viewed below.

  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
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
/***************************************************************************
 *   Copyright (C) 2005 by Dominik Seichter                                *
 *   domseichter@web.de                                                    *
 *                                                                         *
 *   This program 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.                       *
 *                                                                         *
 *   This program is distributed in the hope that it will be useful,       *
 *   but WITHOUT ANY WARRANTY; without even the implied warranty of        *
 *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the         *
 *   GNU General Public License for more details.                          *
 *                                                                         *
 *   You should have received a copy of the GNU Library General Public     *
 *   License along with this program; if not, write to the                 *
 *   Free Software Foundation, Inc.,                                       *
 *   59 Temple Place - Suite 330, Boston, MA  02111-1307, USA.             *
 ***************************************************************************/

#ifndef _PDF_PARSER_H_
#define _PDF_PARSER_H_

#include "PdfDefines.h"
#include "PdfTokenizer.h"
#include "PdfVecObjects.h"

#define W_ARRAY_SIZE 3
#define W_MAX_BYTES  4

namespace PoDoFo {

typedef std::map<int,PdfObject*>    TMapObjects;
typedef TMapObjects::iterator       TIMapObjects;
typedef TMapObjects::const_iterator TCIMapObjects;

class PdfEncrypt;
class PdfString;

/**
 * PdfParser reads a PDF file into memory. 
 * The file can be modified in memory and written back using
 * the PdfWriter class.
 * Most PDF features are supported
 */
class PODOFO_API PdfParser : public PdfTokenizer {
    friend class PdfDocument;
    friend class PdfWriter;

 public:
    struct TXRefEntry {
        inline TXRefEntry() : lOffset(0), lGeneration(0), cUsed('\x00'), bParsed(false) { }
        pdf_long lOffset;
        long lGeneration;
        char cUsed;
        bool bParsed;
    };

    typedef std::vector<TXRefEntry>      TVecOffsets;
    typedef TVecOffsets::iterator        TIVecOffsets;
    typedef TVecOffsets::const_iterator  TCIVecOffsets;

    /** Create a new PdfParser object
     *  You have to open a PDF file using ParseFile later.
     *  \param pVecObjects vector to write the parsed PdfObjects to
     *
     *  \see ParseFile  
     */
    PdfParser( PdfVecObjects* pVecObjects );

    /** Create a new PdfParser object and open a PDF file and parse
     *  it into memory.
     *
     *  \param pVecObjects vector to write the parsed PdfObjects to
     *  \param pszFilename filename of the file which is going to be parsed
     *  \param bLoadOnDemand If true all objects will be read from the file at
     *                       the time they are accesed first.
     *                       If false all objects will be read immediately.
     *                       This is faster if you do not need the complete PDF 
     *                       file in memory.
     *
     *  This might throw a PdfError( ePdfError_InvalidPassword ) exception
     *  if a password is required to read this PDF.
     *  Call SetPassword with the correct password in this case.
     *  
     *  \see SetPassword
     */
    PdfParser( PdfVecObjects* pVecObjects, const char* pszFilename, bool bLoadOnDemand = true );

#ifdef _WIN32
#if defined(_MSC_VER)  &&  _MSC_VER <= 1200			// nicht für Visualstudio 6
#else
    /** Create a new PdfParser object and open a PDF file and parse
     *  it into memory.
     *
     *  \param pVecObjects vector to write the parsed PdfObjects to
     *  \param pszFilename filename of the file which is going to be parsed
     *  \param bLoadOnDemand If true all objects will be read from the file at
     *                       the time they are accesed first.
     *                       If false all objects will be read immediately.
     *                       This is faster if you do not need the complete PDF 
     *                       file in memory.
     *
     *  This might throw a PdfError( ePdfError_InvalidPassword ) exception
     *  if a password is required to read this PDF.
     *  Call SetPassword with the correct password in this case.
     *  
     *  This is an overloaded member function to allow working
     *  with unicode characters. On Unix systes you can also path
     *  UTF-8 to the const char* overload.
     *
     *  \see SetPassword
     */
    PdfParser( PdfVecObjects* pVecObjects, const wchar_t* pszFilename, bool bLoadOnDemand = true );
#endif
#endif // _WIN32

    /** Create a new PdfParser object and open a PDF file and parse
     *  it into memory.
     *
     *  \param pVecObjects vector to write the parsed PdfObjects to
     *  \param pBuffer buffer containing a PDF file in memory
     *  \param lLen length of the buffer containing the PDF file
     *  \param bLoadOnDemand If true all objects will be read from the file at
     *                       the time they are accesed first.
     *                       If false all objects will be read immediately.
     *                       This is faster if you do not need the complete PDF 
     *                       file in memory.
     *
     *  This might throw a PdfError( ePdfError_InvalidPassword ) exception
     *  if a password is required to read this PDF.
     *  Call SetPassword with the correct password in this case.
     *  
     *  \see SetPassword
     */
    PdfParser( PdfVecObjects* pVecObjects, const char* pBuffer, long lLen, bool bLoadOnDemand = true );

    /** Create a new PdfParser object and open a PDF file and parse
     *  it into memory.
     *
     *  \param pVecObjects vector to write the parsed PdfObjects to
     *  \param rDevice read from this PdfRefCountedInputDevice
     *  \param bLoadOnDemand If true all objects will be read from the file at
     *                       the time they are accesed first.
     *                       If false all objects will be read immediately.
     *                       This is faster if you do not need the complete PDF 
     *                       file in memory.
     *
     *  This might throw a PdfError( ePdfError_InvalidPassword ) exception
     *  if a password is required to read this PDF.
     *  Call SetPassword with the correct password in this case.
     *  
     *  \see SetPassword
     */
    PdfParser( PdfVecObjects* pVecObjects, const PdfRefCountedInputDevice & rDevice, 
               bool bLoadOnDemand = true );

    /** Delete the PdfParser and all PdfObjects
     */
    virtual ~PdfParser();

    /** Open a PDF file and parse it.
     *
     *  \param pszFilename filename of the file which is going to be parsed
     *  \param bLoadOnDemand If true all objects will be read from the file at
     *                       the time they are accesed first.
     *                       If false all objects will be read immediately.
     *                       This is faster if you do not need the complete PDF 
     *                       file in memory.
     *
     *
     *  This might throw a PdfError( ePdfError_InvalidPassword ) exception
     *  if a password is required to read this PDF.
     *  Call SetPassword with the correct password in this case.
     *  
     *  \see SetPassword
     */
    void ParseFile( const char* pszFilename, bool bLoadOnDemand = true );

#ifdef _WIN32
    /** Open a PDF file and parse it.
     *
     *  \param pszFilename filename of the file which is going to be parsed
     *  \param bLoadOnDemand If true all objects will be read from the file at
     *                       the time they are accesed first.
     *                       If false all objects will be read immediately.
     *                       This is faster if you do not need the complete PDF 
     *                       file in memory.
     *
     *
     *  This might throw a PdfError( ePdfError_InvalidPassword ) exception
     *  if a password is required to read this PDF.
     *  Call SetPassword with the correct password in this case.
     *  
     *  This is an overloaded member function to allow working
     *  with unicode characters. On Unix systes you can also path
     *  UTF-8 to the const char* overload.
     *
     *  \see SetPassword
     */
    void ParseFile( const wchar_t* pszFilename, bool bLoadOnDemand = true );
#endif // _WIN32

    /** Open a PDF file and parse it.
     *
     *  \param pBuffer buffer containing a PDF file in memory
     *  \param lLen length of the buffer containing the PDF file
     *  \param bLoadOnDemand If true all objects will be read from the file at
     *                       the time they are accesed first.
     *                       If false all objects will be read immediately.
     *                       This is faster if you do not need the complete PDF 
     *                       file in memory.
     *
     *
     *  This might throw a PdfError( ePdfError_InvalidPassword ) exception
     *  if a password is required to read this PDF.
     *  Call SetPassword with the correct password in this case.
     *  
     *  \see SetPassword
     */
    void ParseFile( const char* pBuffer, long lLen, bool bLoadOnDemand = true );

    /** Open a PDF file and parse it.
     *
     *  \param rDevice the input device to read from
     *  \param bLoadOnDemand If true all objects will be read from the file at
     *                       the time they are accesed first.
     *                       If false all objects will be read immediately.
     *                       This is faster if you do not need the complete PDF 
     *                       file in memory.
     *
     *
     *  This might throw a PdfError( ePdfError_InvalidPassword ) exception
     *  if a password is required to read this PDF.
     *  Call SetPassword with the correct password in this case.
     *  
     *  \see SetPassword
     */
    void ParseFile( const PdfRefCountedInputDevice & rDevice, bool bLoadOnDemand = true );

    /** Quick method to detect secured PDF files, i.e.
     *  a PDF with an /Encrypt key in the trailer directory.
     *
     *  \returns true if document is secured, false otherwise
     */
    bool QuickEncryptedCheck( const char* pszFilename );

    /**
     * Retrieve the number of incremental updates that 
     * have been applied to the last parsed PDF file.
     *
     * 0 means no update has been applied.
     *
     * \returns the number of incremental updates to the parsed PDF.
     */
    inline int GetNumberOfIncrementalUpdates() const;

    /** Get a reference to the sorted internal objects vector.
     *  \returns the internal objects vector.
     */
    inline const PdfVecObjects* GetObjects() const;

    /** Get the file format version of the pdf
     *  \returns the file format version as enum
     */
    inline EPdfVersion GetPdfVersion() const;

    /** Get the file format version of the pdf
     *  \returns the file format version as string
     */
    const char* GetPdfVersionString() const;

    /** Get the trailer dictionary
     *  which can be written unmodified to a pdf file.
     */
    inline const PdfObject* GetTrailer() const;

    /** \returns true if this PdfParser loads all objects on demand at
     *                the time they are accessed for the first time.
     *                The default is to load all object immediately.
     *                In this case false is returned.
     */
    inline bool GetLoadOnDemand() const;

    /** \returns whether the parsed document contains linearization tables
     */
    bool IsLinearized() const { return m_pLinearization != NULL; }

    /** \returns the length of the file
     */
    size_t GetFileSize() const { return m_nFileSize; }

    /** 
     * \returns true if this PdfWriter creates an encrypted PDF file
     */
    bool GetEncrypted() const { return (m_pEncrypt != NULL); }

    /** 
     * \returns the parsers encryption object or NULL if the read PDF file was not encrypted
     */
    const PdfEncrypt* GetEncrypt() const { return m_pEncrypt; }

    /** 
     * Takes the encryption object fro mthe parser. The internal handle will be set
     * to NULL and the ownership of the object is given to the caller.
     *
     * Only call this if you need access to the encryption object
     * before deleting the parser.
     *
     * \returns the parsers encryption object or NULL if the read PDF file was not encrypted
     */
    inline PdfEncrypt* TakeEncrypt();
    

    /** If you try to open an encrypted PDF file, which requires
     *  a password to open, PoDoFo will throw a PdfError( ePdfError_InvalidPassword ) 
     *  exception. 
     *  
     *  If you got such an exception, you have to set a password
     *  which should be used for opening the PDF.
     *
     *  The usual way will be to ask the user for the password
     *  and set the password using this method.
     *
     *  PdfParser will immediately continue to read the PDF file.
     *
     *  \param sPassword a user or owner password which can be used to open an encrypted PDF file
     *                   If the password is invalid, a PdfError( ePdfError_InvalidPassword ) exception is thrown!
     */
    void SetPassword( const std::string & sPassword );

    /**
     * \returns true if strict parsing mode is enabled
     *
     * \see SetStringParsing
     */
    inline bool IsStrictParsing() const;

    /**
     * Enable/disable strict parsing mode.
     * Strict parsing is by default disabled.
     *
     * If you enable strict parsing, PoDoFo will fail
     * on a few more common PDF failures. Please not 
     * that PoDoFo's parser is by default very strict
     * already and does not recover from e.g. wrong XREF
     * tables.
     *
     * \param bStrict new setting for strict parsing mode.
     */
    inline void SetStrictParsing( bool bStrict );

    /**
     * \return if broken objects are ignored while parsing
     */
    inline bool GetIgnoreBrokenObjects();

    /**
     * Specify if the parser should ignore broken
     * objects, i.e. XRef entries that do not point
     * to valid objects.
     *
     * Default is to not ignore broken objects and
     * throw an exception if one is found.
     *
     * \param bBroken if true broken objects will be ignored
     */
    inline void SetIgnoreBrokenObjects( bool bBroken );

 protected:
    /** Searches backwards from the end of the file
     *  and tries to find a token.
     *  The current file is positioned right after the token.
     * 
     *  \param pszToken a token to find
     *  \param lRange range in bytes in which to search
     *                begining at the end of the file
     */
    void FindToken( const char* pszToken, const long lRange );

    // Peter Petrov 23 December 2008
    /** Searches backwards from the specified position of the file
     *  and tries to find a token.
     *  The current file is positioned right after the token.
     * 
     *  \param pszToken a token to find
     *  \param lRange range in bytes in which to search
     *                begining at the specified position of the file
     *  \param searchEnd specifies position 
     */
    void FindToken2( const char* pszToken, const long lRange, size_t searchEnd );

    /** Reads the xref sections and the trailers of the file
     *  in the correct order in the memory
     *  and takes care for linearized pdf files.
     */
    void ReadDocumentStructure();

    /** Checks wether this pdf is linearized or not.
     *  Initializes the linearization directory on sucess.
     */
    void HasLinearizationDict();

    /** Merge the information of this trailer object
     *  in the parsers main trailer object.
     *  \param pTrailer take the keys to merge from this dictionary.
     */
    void MergeTrailer( const PdfObject* pTrailer );

    /** Read the trailer directory at the end of the file.
     */
    void ReadTrailer();

    /** Looks for a startxref entry at the current file position
     *  and saves its byteoffset to pXRefOffset.
     *  \param pXRefOffset store the byte offset of the xref section into this variable.
     */
    void ReadXRef( pdf_long* pXRefOffset );

    /** Reads the xref table from a pdf file.
     *  If there is no xref table, ReadXRefStreamContents() is called.
     *  \param lOffset read the table from this offset
     *  \param bPositionAtEnd if true the xref table is not read, but the 
     *                        file stream is positioned directly 
     *                        after the table, which allows reading
     *                        a following trailer dictionary.
     */
    void ReadXRefContents( pdf_long lOffset, bool bPositionAtEnd = false );

    /** Read a xref subsection
     *  
     *  Throws ePdfError_NoXref if the number of objects read was not
     *  the number specified by the subsection header (as passed in
     *  `nNumObjects').
     *
     *  \param nFirstObject object number of the first object
     *  \param nNumObjects  how many objects should be read from this section
     */
    void ReadXRefSubsection( long long & nFirstObject, long long & nNumObjects );

    /** Reads a xref stream contens object
     *  \param lOffset read the stream from this offset
     *  \param bReadOnlyTrailer only the trailer is skipped over, the contents
     *         of the xref stream are not parsed
     */
    void ReadXRefStreamContents( pdf_long lOffset, bool bReadOnlyTrailer );

    /** Reads all objects from the pdf into memory
     *  from the offsets listed in m_vecOffsets.
     *
     *  If required an encryption object is setup first.
     *
     *  The actual reading happens in ReadObjectsInternal()
     *  either if no encryption is required or a correct
     *  encryption object was initialized from SetPassword.
     */
    void ReadObjects();

    /** Reads all objects from the pdf into memory
     *  from the offsets listed in m_vecOffsets.
     *
     *  Requires a correctly setup PdfEncrypt object
     *  with correct password.
     *
     *  This method is called from ReadObjects
     *  or SetPassword.
     *
     *  \see ReadObjects
     *  \see SetPassword
     */
    void ReadObjectsInternal();

    /** Read the object with index nIndex from the object stream nObjNo
     *  and push it on the objects vector m_vecOffsets.
     *
     *  All objects are read from this stream and the stream object
     *  is free'd from memory. Further calls who try to read from the
     *  same stream simply do nothing.
     *
     *  \param nObjNo object number of the stream object
     *  \param nIndex index of the object which should be parsed
     *
     */
    void ReadObjectFromStream( int nObjNo, int nIndex );

    /** Checks the magic number at the start of the pdf file
     *  and sets the m_ePdfVersion member to the correct version
     *  of the pdf file.
     *
     *  \returns true if this is a pdf file, otherwise false
     */
    bool    IsPdfFile();

    void ReadNextTrailer();


    /** Checks for the existence of the %%EOF marker at the end of the file
     *  When strict mode is off it will also attempt to setup the parser to ignore
     *  any garbage after the last %%EOF marker
     *  Simply raises an error if there is a problem with the marker
     *
     */
    void CheckEOFMarker();

 private:
    /** Free all internal data structures
     */
    void         Clear();

    /** Initializes all private members
     *  with their initial values.
     */
    void         Init();

    /** Small helper method to retrieve the document id from the trailer
     *
     *  \returns the document id of this PDF document
     */
    const PdfString & GetDocumentId();

    /** Determines the correct version of the PDF
     *  from the document catalog (if available).
     *  as, PDF > 1.4 allows updating the version.
     *
     *  If no catalog dictionary is present or no /Version
     *  key is available, the version from the file header will
     *  be used.
     */
    void         UpdateDocumentVersion();

 private:
    EPdfVersion   m_ePdfVersion;

    bool          m_bLoadOnDemand;

    pdf_long      m_nXRefOffset;
    long          m_nFirstObject;
    long          m_nNumObjects;
    pdf_long      m_nXRefLinearizedOffset;
    size_t        m_nFileSize;
    pdf_long      m_lLastEOFOffset;

    TVecOffsets   m_offsets;
    PdfVecObjects* m_vecObjects;

    PdfObject*    m_pTrailer;
    PdfObject*    m_pLinearization;
    PdfEncrypt*   m_pEncrypt;

    bool          m_xrefSizeUnknown;

    std::set<int> m_setObjectStreams;

    bool          m_bStrictParsing;
    bool          m_bIgnoreBrokenObjects;

    int           m_nIncrementalUpdates;
};

// -----------------------------------------------------
// 
// -----------------------------------------------------
bool PdfParser::GetLoadOnDemand() const
{
    return m_bLoadOnDemand;
}

// -----------------------------------------------------
// 
// -----------------------------------------------------
EPdfVersion PdfParser::GetPdfVersion() const
{
    return m_ePdfVersion;
}

// -----------------------------------------------------
// 
// -----------------------------------------------------
int PdfParser::GetNumberOfIncrementalUpdates() const
{
    return m_nIncrementalUpdates;
}

// -----------------------------------------------------
// 
// -----------------------------------------------------
const PdfVecObjects* PdfParser::GetObjects() const
{
    return m_vecObjects;
}

// -----------------------------------------------------
// 
// -----------------------------------------------------
const PdfObject* PdfParser::GetTrailer() const
{
    return m_pTrailer;
}

// -----------------------------------------------------
// 
// -----------------------------------------------------
PdfEncrypt* PdfParser::TakeEncrypt() 
{ 
    PdfEncrypt* pEncrypt = m_pEncrypt;
    m_pEncrypt = NULL; 
    return pEncrypt; 
}

// -----------------------------------------------------
// 
// -----------------------------------------------------
bool PdfParser::IsStrictParsing() const
{
    return m_bStrictParsing;
}

// -----------------------------------------------------
// 
// -----------------------------------------------------
void PdfParser::SetStrictParsing( bool bStrict )
{
    m_bStrictParsing = bStrict;
}

// -----------------------------------------------------
// 
// -----------------------------------------------------
bool PdfParser::GetIgnoreBrokenObjects()
{
    return m_bIgnoreBrokenObjects;
}

// -----------------------------------------------------
// 
// -----------------------------------------------------
void PdfParser::SetIgnoreBrokenObjects( bool bBroken )
{
    m_bIgnoreBrokenObjects = bBroken;
}

};

#endif // _PDF_PARSER_H_