PdfTextString.cs :  » PDF » PDF-Clown » it » stefanochizzolini » clown » objects » C# / CSharp Open Source

/*
  Copyright 2008 Stefano Chizzolini. http://clown.stefanochizzolini.it

  Contributors:
    * Stefano Chizzolini (original code developer, http://www.stefanochizzolini.it)

  This file should be part of the source code distribution of "PDF Clown library"
  (the Program): see the accompanying README files for more info.

  This Program is free software; you can redistribute it and/or modify it under
  the terms of the GNU 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, either expressed or implied; without even the implied warranty of
  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the License for more details.

  You should have received a copy of the GNU General Public License along with this
  Program (see README files); if not, go to the GNU website (http://www.gnu.org/).

  Redistribution and use, with or without modification, are permitted provided that such
  redistributions retain the above copyright notice, license and disclaimer, along with
  this list of conditions.
*/

using System;
using System.Text;
using System.Text.RegularExpressions;

namespace it.stefanochizzolini.clown.objects{
  /**
    <summary>PDF text string object [PDF:1.6:3.8.1].</summary>
    <remarks>Text strings are meaningful only as part of the document hierarchy;
    they cannot appear within content streams.
    They represent information that is intended to be human-readable.</remarks>
  */
  public class PdfTextString
    : PdfString
  {
    /*
      NOTE: Text strings are string objects encoded in either PDFDocEncoding
      or Unicode character encoding.
      PDFDocEncoding is a superset of the ISO Latin 1 encoding [PDF:1.6:D].
      Unicode is described in the Unicode Standard by the Unicode Consortium [UCS:4].
    */
    #region static
    #region fields
    private static readonly Encoding ISO88591Encoding = Encoding.GetEncoding("iso-8859-1");
    private static readonly Encoding UTF16BEEncoding = Encoding.BigEndianUnicode;
    #endregion
    #endregion

    #region dynamic
    #region fields
    private Encoding encoding;
    #endregion

    #region constructors
    public PdfTextString(
      )
    {}

    public PdfTextString(
      byte[] rawValue
      )
    {RawValue = rawValue;}

    public PdfTextString(
      string value
      )
    {Value = value;}
    #endregion

    #region interface
    #region public
    public override object Clone(
      files.File context
      )
    {
      // Shallow copy.
      return this.MemberwiseClone();
    }

    public Encoding Encoding
    {get{return encoding;}}

    public override object Value
    {
      get
      {
        byte[] valueBytes = RawValue;
        byte[] buffer;
        if(encoding == UTF16BEEncoding)
        {
          // Excluding UTF marker...
          buffer = new byte[valueBytes.Length - 2];
          Array.Copy(valueBytes,2,buffer,0,buffer.Length);
        }
        else
        {buffer = valueBytes;}

        return encoding.GetString(buffer);
      }
      set
      {
        // Prepending UTF marker...
        byte[] valueBytes = UTF16BEEncoding.GetBytes((string)value);
        byte[] buffer = new byte[valueBytes.Length + 2];
        buffer[0] = (byte)254; buffer[1] = (byte)255;
        Array.Copy(valueBytes,0,buffer,2,valueBytes.Length);

        RawValue = buffer;
      }
    }

    public override byte[] RawValue
    {
      set
      {
        if(value.Length > 2
          && value[0] == (byte)254
          && value[1] == (byte)255) // Multi-byte (Unicode).
        {encoding = UTF16BEEncoding;}
        else // Single byte (PDFDocEncoding).
        {encoding = ISO88591Encoding;}

        base.RawValue = value;
      }
    }

    public override string ToString(
      )
    {return (string)Value;}
    #endregion
    #endregion
    #endregion
  }
}