Logo Search packages:      
Sourcecode: codeblocks version File versions  Download package


Go to the documentation of this file.
// Name:        pdfparser.h
// Purpose:
// Author:      Ulrich Telle
// Modified by:
// Created:     2006-05-15
// Copyright:   (c) Ulrich Telle
// Licence:     wxWindows licence

/// \file pdfparser.h Interface of the wxPdfParser classes

#ifndef _PDFPARSER_H_
#define _PDFPARSER_H_

// wxWidgets headers
#include <wx/dynarray.h>

#include "wx/pdfdocdef.h"
#include "wx/pdfobjects.h"

/// Permissions required for import of a document
// Permission bit  3: Print
// Permission bit  5: Copy or extract text and graphics
// Permission bit 10: Extract text and graphics
00027 #define REQUIRED_PERMISSIONS 0x0214

/// Token types
00030 #define TOKEN_COMMENT           1
#define TOKEN_BOOLEAN           2
#define TOKEN_NUMBER            3
#define TOKEN_STRING            4
#define TOKEN_NAME              5
#define TOKEN_START_ARRAY       6
#define TOKEN_END_ARRAY         7
#define TOKEN_REFERENCE        10
#define TOKEN_NULL             12
#define TOKEN_OTHER            13

/// Class representing a tokenizer for parsing PDF documenst.
00044 class WXDLLIMPEXP_PDFDOC wxPdfTokenizer
  /// Constructor
  wxPdfTokenizer(wxInputStream* inputStream);

  /// Destructor
  virtual ~wxPdfTokenizer();

  /// Set current offset position in stream
  off_t Seek(off_t pos);

  /// Get current offset position in stream
  off_t Tell();

  /// Go back one position in the stream
  void BackOnePosition(int ch);

  /// Get length of stream
  off_t GetLength();

  /// Read one byte from stream
  int ReadChar();

  /// Read size bytes from stream
  wxMemoryOutputStream* ReadBuffer(size_t size);

  /// Find the offset of the startxref tag
  off_t GetStartXRef();

  /// Read a string
  wxString ReadString(int size);

  /// Check the header of the document stream
  wxString CheckPdfHeader();

  /// Get the next token
  bool NextToken();

  /// Get the next valid token
  void NextValidToken();

  /// Get the type of the last token
  int GetTokenType();

  /// Get the token value as a string
  wxString GetStringValue();

  /// Get the token value as an integer
  int GetIntValue();

  /// Check whether the token is a hexadecimal string
00096   bool IsHexString() { return m_hexString; }

  /// Get object reference
  int GetReference();

  /// Get object generation
  int GetGeneration();

  /// Check byte whether it represents a white space character
  static bool IsWhitespace(int ch);

  /// Check byte whether it is a delimiter
  static bool IsDelimiter(int ch);

  /// Check byte whether it is a delimiter or a whitespace character
  static bool IsDelimiterOrWhitespace(int ch);

  /// Get hexadecimal character
  static int GetHex(int v);

00117   wxInputStream* m_inputStream; ///< Stream of document data
00118   int            m_type;        ///< Type of last token
00119   wxString       m_stringValue; ///< Value of last token
00120   int            m_reference;   ///< Reference number of object
00121   int            m_generation;  ///< Generation number of object
00122   bool           m_hexString;   ///< Flag for hexadeciaml strings


/// Class representing an XRef entry (for internal use only)
00127 class WXDLLIMPEXP_PDFDOC wxPdfXRefEntry
  /// Constructor

  /// Destructor
  virtual ~wxPdfXRefEntry();

00136   int m_type;    ///< Type of XRef entry
00137   int m_ofs_idx; ///< Offset or index of object
00138   int m_gen_ref; ///< Generation of object or reference of object stream containing the object


/// Class representing a PDF parser. (For internal use only)
00144 class WXDLLIMPEXP_PDFDOC wxPdfParser
  /// Constructor
  wxPdfParser(const wxString& filename,
              const wxString& password = wxEmptyString);

  /// Destructor
  virtual ~wxPdfParser();

  /// Check whether the PDF document to be parsed is valid
  bool IsOk();

  /// Get PDF version of parsed document
00158   wxString GetPdfVersion() { return m_pdfVersion; }

  /// Get number of pages in the parsed document
  int GetPageCount();

  /// Get the document information dictionary
  bool GetSourceInfo(wxPdfInfo& info);

  /// Get the queue of referenced objects
00167   wxPdfObjectQueue* GetObjectQueue() { return m_objectQueue; }

  /// Get the map of referenced objects
00170   wxPdfObjectMap* GetObjectMap() { return m_objectMap; }

  /// Append a referenced object to the queue
  void AppendObject(int originalObjectId, int actualObjectId, wxPdfObject* obj);

  /// Get the resources of a specific page
  wxPdfObject* GetPageResources(int pageno);

  /// Get the content stream collection of a specific page
  void GetContent(int pageno, wxArrayPtrVoid& contents);

  /// Get the media box of a specific page
  wxPdfArrayDouble* GetPageMediaBox(int pageno);

  /// Get the crop box of a specific page
  wxPdfArrayDouble* GetPageCropBox(int pageno);

  /// Get the bleed box of a specific page
  wxPdfArrayDouble* GetPageBleedBox(int pageno);

  /// Get the trim box of a specific page
  wxPdfArrayDouble* GetPageTrimBox(int pageno);

  /// Get the art box of a specific page
  wxPdfArrayDouble* GetPageArtBox(int pageno);

  /// Resolve an object
  wxPdfObject* ResolveObject(wxPdfObject* obj);

  /// Set flag whether a stream should be decoded or not
00200   void SetUseRawStream(bool useRawStream) { m_useRawStream = useRawStream; }

  /// Get flag whether a stream should be decoded or not
00203   bool GetUseRawStream() { return m_useRawStream; }

  /// Get the resources of a specific page identified by a page object
  wxPdfObject* GetPageResources(wxPdfObject* page);

  /// Get the content stream collection of a specific page
  void GetPageContent(wxPdfObject* contentRef, wxArrayPtrVoid& contents);

  /// Get a page box
  wxPdfArrayDouble* GetPageBox(wxPdfDictionary* page, const wxString& boxIndex);

  /// Parse PDF document
  bool ParseDocument();

  bool SetupDecryptor();

  /// Parse the cross reference
  bool ParseXRef();

  /// Parse the page tree of the PDF document
  bool ParsePageTree(wxPdfDictionary* pages);

  /// Parse a cross reference section
  wxPdfDictionary* ParseXRefSection();

  /// Parse a cross reference stream
  bool ParseXRefStream(int ptr, bool setTrailer);

  /// Parse an object
  wxPdfObject* ParseObject();

  /// Parse a dictionary
  wxPdfDictionary* ParseDictionary();

  /// Parse an array
  wxPdfArray* ParseArray();

  /// Parse a specific object
  wxPdfObject* ParseSpecificObject(int idx);

  /// Parse a direct object
  wxPdfObject* ParseDirectObject(int k);

  /// Parse an object from an object stream
  wxPdfObject* ParseObjectStream(wxPdfStream* stream, int idx);

  /// Parse the content of a stream object
  void GetStreamBytes(wxPdfStream* stream);

  /// Parse the raw content of a stream object
  void GetStreamBytesRaw(wxPdfStream* stream);

  /// Decode a stream predictor
  wxMemoryOutputStream* DecodePredictor(wxMemoryOutputStream* in, wxPdfObject* dicPar);

  /// Decode a stream that has the FlateDecode filter.
   * \param osIn the input data
   * \return the decoded data
  wxMemoryOutputStream* FlateDecode(wxMemoryOutputStream* osIn);

  /// Decode a stream that has the ASCIIHexDecode filter.
   * \param osIn the input data
   * \return the decoded data
  wxMemoryOutputStream* ASCIIHexDecode(wxMemoryOutputStream* osIn);

  /// Decode a stream that has the ASCII85Decode filter.
   * \param osIn the input data
   * \return the decoded data
  wxMemoryOutputStream* ASCII85Decode(wxMemoryOutputStream* osIn);

  /// Decode a stream that has the ASCII85Decode filter.
   * \param osIn the input data
   * \return the decoded data
  wxMemoryOutputStream* LZWDecode(wxMemoryOutputStream* osIn);

  /// Get wxWidgets file system
  static wxFileSystem* GetFileSystem();

  /// Reserve at least count cross reference entries
  void ReserveXRef(size_t count);

00295   bool              m_initialized;     ///< Flag whether parser is properly initialized
00296   int               m_fileSize;        ///< File size
00297   wxString          m_filename;        ///< File name of PDF document
  wxString          m_password;        ///<
00299   wxString          m_pdfVersion;      ///< Version of PDF document
00300   wxFSFile*         m_pdfFile;         ///< File system file object of PDF document
00301   wxPdfTokenizer*   m_tokens;          ///< Tokenizer
00302   wxPdfDictionary*  m_trailer;         ///< Trailer dictionary
00303   wxPdfDictionary*  m_root;            ///< Root object
00304   wxArrayPtrVoid    m_pages;           ///< Array of page objects
00305   int               m_currentPage;     ///< Number of current page
00306   bool              m_useRawStream;    ///< Flag whether to use raw stream data (without decoding)

00308   bool              m_encrypted;       ///< Flag whether the document is encrypted
00309   wxPdfEncrypt*     m_decryptor;       ///< decryptor instance
00310   wxPdfDictionary*  m_encryption;      ///< Encryption dictionary

00312   wxPdfObjectQueue* m_objectQueue;     ///< Queue of referenced objects
00313   wxPdfObjectQueue* m_objectQueueLast; ///< Pointer to last queue element
00314   wxPdfObjectMap*   m_objectMap;       ///< Map for object queue elements
00315   wxPdfObjStmMap*   m_objStmCache;     ///< Cache for object streams
00316   bool              m_cacheObjects;    ///< Flag whether object streams should be cached

00318   int               m_objNum;          ///< Number of current object
00319   int               m_objGen;          ///< Generation of current object

//  wxArrayInt        m_xref;            ///< Cross reference
00322   wxPdfXRef         m_xref;            ///< Cross reference

00324   static wxFileSystem* ms_fileSystem; ///< wxWidgets file system


/// Class representing an LZW decoder. (For internal use only)
00330 class WXDLLIMPEXP_PDFDOC wxPdfLzwDecoder
  /// Constructor

  /// Destructor
  virtual ~wxPdfLzwDecoder();

  /// Get next code
  int GetNextCode();

  /// Decode a byte stream
  bool Decode(wxMemoryInputStream* dataIn, wxMemoryOutputStream* dataOut);

  /// Initialize the string table
  void InitializeStringTable();

  /// Write decoded string into output buffer
  void WriteString(int code);

  /// Add string to string table
  void AddStringToTable(int oldCode, char newString);

00355   wxMemoryInputStream*  m_dataIn;       ///< Encoded data stream
00356   wxMemoryOutputStream* m_dataOut;      ///< Decoded data stream
00357   size_t                m_dataSize;     ///< Length of encoded data stream
00358   wxArrayInt            m_stringTable[WXPDF_LZW_STRINGTABLE_SIZE]; ///< Table of decoded strings

00360   int                   m_tableIndex;   ///< Current string table index
00361   int                   m_bitsToGet;    ///< Number of bits to get from stream
00362   int                   m_bytePointer;  ///< Offset in encoded data stream
00363   int                   m_bitPointer;   ///< Bit offset
00364   int                   m_nextData;     ///< Next data item
00365   int                   m_nextBits;     ///< Next bits

00367   static int            ms_andTable[4]; ///< Static array of string table offsets


Generated by  Doxygen 1.6.0   Back to index