Filters/FilterText.cs

   1 //
   2 // FilterText.cs
   3 //
   4 // Copyright (C) 2004 Novell, Inc.
   5 //
   6
   7 //
   8 // Permission is hereby granted, free of charge, to any person obtaining a
   9 // copy of this software and associated documentation files (the "Software"),
  10 // to deal in the Software without restriction, including without limitation
  11 // the rights to use, copy, modify, merge, publish, distribute, sublicense,
  12 // and/or sell copies of the Software, and to permit persons to whom the
  13 // Software is furnished to do so, subject to the following conditions:
  14 //
  15 // The above copyright notice and this permission notice shall be included in
  16 // all copies or substantial portions of the Software.
  17 //
  18 // THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
  19 // IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
  20 // FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
  21 // AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
  22 // LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
  23 // FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
  24 // DEALINGS IN THE SOFTWARE.
  25 //
  26
  27
  28 using System;
  29 using System.IO;
  30
  31 namespace Beagle.Filters {
  32
  33         public class FilterText : Beagle.Daemon.Filter {
  34
  35                 public FilterText ()
  36                 {
  37                         AddSupportedMimeType ("text/plain");
  38                         SnippetMode = true;
  39                         OriginalIsText = true;
  40                 }
  41
  42                 const long LENGTH_CUTOFF = 1024 * 1024; // 1 Mb
  43
  44                 override protected void DoOpen (FileInfo file)
  45                 {
  46                         // Extremely large files of type text/plain are usually log files,
  47                         // data files, or other bits of not-particularly-human-readable junk
  48                         // that will tend to clog up our indexes.
  49                         if (file.Length > LENGTH_CUTOFF) {
  50                                 Beagle.Util.Logger.Log.Debug ("{0} is too large to filter!", file.FullName);
  51                                 Finished ();
  52                         }
  53                 }
  54
  55                 override protected void DoPull ()
  56                 {
  57                         string str = TextReader.ReadLine ();
  58                         if (str == null) {
  59                                 Finished ();
  60                         } else if (str.Length > 0) {
  61                                 AppendText (str);
  62                                 AppendStructuralBreak ();
  63                         }
  64                 }
  65         }
  66 }