beagled/FileSystemQueryable/CrawlTask.cs

   1 //
   2 // CrawlTask.cs
   3 //
   4 // Copyright (C) 2005 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 using System;
  28 using System.IO;
  29
  30 using Beagle.Util;
  31 using Beagle.Daemon;
  32
  33 namespace Beagle.Daemon.FileSystemQueryable {
  34
  35         public class CrawlTask : Scheduler.Task {
  36
  37                 FileSystemQueryable queryable;
  38                 IIndexableGenerator current_generator;
  39
  40                 private bool active = true;
  41                 public bool Active {
  42                         get { return active; }
  43                 }
  44
  45                 public CrawlTask (FileSystemQueryable queryable)
  46                 {
  47                         this.queryable = queryable;
  48                         this.Tag = "File System Crawler";
  49                         this.Priority = Scheduler.Priority.Generator;
  50                 }
  51
  52                 private class PostCrawlClosure {
  53                         public FileSystemModel Model;
  54                         public FileSystemModel.Directory Directory;
  55                         public DateTime CrawlTime;
  56
  57                         public void Hook ()
  58                         {
  59                                 Model.MarkAsCrawled (Directory, CrawlTime);
  60                         }
  61                 }
  62
  63
  64                 protected override void DoTaskReal ()
  65                 {
  66                         // If our last generator is still doing stuff, just reschedule
  67                         // and return.  This keeps us from generating more tasks until
  68                         // the last one we started runs to completion.
  69                         if (current_generator != null && current_generator.HasNextIndexable ()) {
  70                                 Reschedule = true;
  71                                 return;
  72                         }
  73
  74                         FileSystemModel model = queryable.Model;
  75
  76                         current_generator = null;
  77
  78                         FileSystemModel.Directory next_dir = model.GetNextDirectoryToCrawl ();
  79                         if (next_dir == null) {
  80                                 this.active = false;
  81                                 return;
  82                         }
  83
  84                         int uncrawled = model.GetUncrawledCounts ();
  85                         this.Description = String.Format ("last={0}, uncrawled={1}",
  86                                                           next_dir.FullName, uncrawled);
  87
  88                         Logger.Log.Debug ("Crawl Task Scheduling {0} (state={1})", next_dir.FullName, next_dir.State);
  89
  90                         if (! model.ScanSubdirs (next_dir))
  91                                 next_dir = null;
  92
  93                         // We want this task to get re-scheduled after it is run.
  94                         Reschedule = true;
  95
  96                         // ...but if we are crawling a possibly-clean directory,
  97                         // maybe wait a little bit extra.
  98                         if (Environment.GetEnvironmentVariable ("BEAGLE_EXERCISE_THE_DOG") == null)
  99                                 TriggerTime = DateTime.Now.AddSeconds (5);
 100
 101                         if (next_dir == null)
 102                                 return;
 103
 104                         // We no longer care about the Open event
 105                         model.DropOpenWatch (next_dir);
 106
 107                         // Set up a task group to mark the time on the directory
 108                         // after we finish crawling it.
 109                         PostCrawlClosure closure = new PostCrawlClosure ();
 110                         closure.Model = model;
 111                         closure.Directory = next_dir;
 112                         closure.CrawlTime = DateTime.Now;
 113                         Scheduler.TaskGroup group = Scheduler.NewTaskGroup ("Crawl " + next_dir.FullName, null,
 114                                                                             new Scheduler.Hook (closure.Hook));
 115
 116                         // Construct an indexable generator and add it to the scheduler
 117                         current_generator = new DirectoryIndexableGenerator (queryable, next_dir);
 118                         Scheduler.Task task = queryable.NewAddTask (current_generator);
 119                         task.AddTaskGroup (group);
 120                         ThisScheduler.Add (task, Scheduler.AddType.OptionallyReplaceExisting);
 121                 }
 122         }
 123 }