CharsetDetector.cs 4.0 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125
  1. /* ***** BEGIN LICENSE BLOCK *****
  2. * Version: MPL 1.1/GPL 2.0/LGPL 2.1
  3. *
  4. * The contents of this file are subject to the Mozilla Public License Version
  5. * 1.1 (the "License"); you may not use this file except in compliance with
  6. * the License. You may obtain a copy of the License at
  7. * http://www.mozilla.org/MPL/
  8. *
  9. * Software distributed under the License is distributed on an "AS IS" basis,
  10. * WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
  11. * for the specific language governing rights and limitations under the
  12. * License.
  13. *
  14. * The Original Code is Mozilla Universal charset detector code.
  15. *
  16. * The Initial Developer of the Original Code is
  17. * Netscape Communications Corporation.
  18. * Portions created by the Initial Developer are Copyright (C) 2001
  19. * the Initial Developer. All Rights Reserved.
  20. *
  21. * Contributor(s):
  22. * Shy Shalom <shooshX@gmail.com>
  23. * Rudi Pettazzi <rudi.pettazzi@gmail.com> (C# port)
  24. *
  25. * Alternatively, the contents of this file may be used under the terms of
  26. * either the GNU General Public License Version 2 or later (the "GPL"), or
  27. * the GNU Lesser General Public License Version 2.1 or later (the "LGPL"),
  28. * in which case the provisions of the GPL or the LGPL are applicable instead
  29. * of those above. If you wish to allow use of your version of this file only
  30. * under the terms of either the GPL or the LGPL, and not to allow others to
  31. * use your version of this file under the terms of the MPL, indicate your
  32. * decision by deleting the provisions above and replace them with the notice
  33. * and other provisions required by the GPL or the LGPL. If you do not delete
  34. * the provisions above, a recipient may use your version of this file under
  35. * the terms of any one of the MPL, the GPL or the LGPL.
  36. *
  37. * ***** END LICENSE BLOCK ***** */
  38. using System.IO;
  39. namespace UniversalDetector
  40. {
  41. /// <summary>
  42. /// Default implementation of charset detection interface.
  43. /// The detector can be fed by a System.IO.Stream:
  44. /// <example>
  45. /// <code>
  46. /// using (FileStream fs = File.OpenRead(filename)) {
  47. /// CharsetDetector cdet = new CharsetDetector();
  48. /// cdet.Feed(fs);
  49. /// cdet.DataEnd();
  50. /// Console.WriteLine("{0}, {1}", cdet.Charset, cdet.Confidence);
  51. /// </code>
  52. /// </example>
  53. ///
  54. /// or by a byte a array:
  55. ///
  56. /// <example>
  57. /// <code>
  58. /// byte[] buff = new byte[1024];
  59. /// int read;
  60. /// while ((read = stream.Read(buff, 0, buff.Length)) > 0 && !done)
  61. /// Feed(buff, 0, read);
  62. /// cdet.DataEnd();
  63. /// Console.WriteLine("{0}, {1}", cdet.Charset, cdet.Confidence);
  64. /// </code>
  65. /// </example>
  66. /// </summary>
  67. public class CharsetDetector : Core.UniversalDetector, ICharsetDetector
  68. {
  69. private string charset;
  70. private float confidence;
  71. //public event DetectorFinished Finished;
  72. public CharsetDetector() : base(FILTER_ALL)
  73. {
  74. }
  75. public void Feed(Stream stream)
  76. {
  77. byte[] buff = new byte[1024];
  78. int read;
  79. while ((read = stream.Read(buff, 0, buff.Length)) > 0 && !done)
  80. {
  81. Feed(buff, 0, read);
  82. }
  83. }
  84. public bool IsDone()
  85. {
  86. return done;
  87. }
  88. public override void Reset()
  89. {
  90. this.charset = null;
  91. this.confidence = 0.0f;
  92. base.Reset();
  93. }
  94. public string Charset {
  95. get { return charset; }
  96. }
  97. public float Confidence {
  98. get { return confidence; }
  99. }
  100. protected override void Report(string charset, float confidence)
  101. {
  102. this.charset = charset;
  103. this.confidence = confidence;
  104. // if (Finished != null) {
  105. // Finished(charset, confidence);
  106. // }
  107. }
  108. }
  109. //public delegate void DetectorFinished(string charset, float confidence);
  110. }