beagled/GoogleDriver.cs

   1 //
   2 // GoogleDriver.cs
   3 //
   4 // Copyright (C) 2004 Novell, Inc.
   5 //
   6 // Google is a trademark of Google.  But you already knew that.
   7 //
   8
   9 //
  10 // Permission is hereby granted, free of charge, to any person obtaining a
  11 // copy of this software and associated documentation files (the "Software"),
  12 // to deal in the Software without restriction, including without limitation
  13 // the rights to use, copy, modify, merge, publish, distribute, sublicense,
  14 // and/or sell copies of the Software, and to permit persons to whom the
  15 // Software is furnished to do so, subject to the following conditions:
  16 //
  17 // The above copyright notice and this permission notice shall be included in
  18 // all copies or substantial portions of the Software.
  19 //
  20 // THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
  21 // IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
  22 // FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
  23 // AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
  24 // LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
  25 // FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
  26 // DEALINGS IN THE SOFTWARE.
  27 //
  28
  29
  30 using System;
  31 using System.Collections;
  32 using Beagle.Util;
  33
  34 namespace Beagle.Daemon {
  35
  36         [QueryableFlavor (Name="Google", Domain=QueryDomain.Global, RequireInotify=false)]
  37         public class GoogleDriver : IQueryable {
  38
  39                 int maxResults = 5;
  40
  41                 GoogleSearchService gss = new GoogleSearchService ();
  42                 string googleKey;
  43
  44                 public GoogleDriver ()
  45                 {
  46                         googleKey = Environment.GetEnvironmentVariable ("GOOGLE_WEB_API_KEY");
  47                 }
  48
  49                 public string Name {
  50                         get { return "Google"; }
  51                 }
  52
  53                 public void Start ()
  54                 {
  55                 }
  56
  57                 Hit FromGoogleResultElement (ResultElement res, int rank)
  58                 {
  59                         Hit hit = new Hit ();
  60
  61                         hit.Uri      = new Uri (res.URL, true);
  62                         hit.Type     = "Google";
  63                         hit.MimeType = "text/html"; // FIXME
  64                         hit.Source   = "Google";
  65
  66                         // FIXME: We don't get scoring information from Google
  67                         // other than the ranks.  This is a hack.
  68                         hit.ScoreRaw    = 0.2f / (1 + rank);
  69
  70                         hit ["Summary"]        = res.summary;
  71                         hit ["Snippet"]        = res.snippet;
  72                         hit ["Title"]          = res.title;
  73                         hit ["CachedSize"]     = res.cachedSize;
  74                         hit ["HostName"]       = res.hostName;
  75                         hit ["DirectoryTitle"] = res.directoryTitle;
  76
  77                         return hit;
  78                 }
  79
  80                 static bool showNoKeyMessage = true;
  81
  82                 public bool AcceptQuery (Query query)
  83                 {
  84                         if (query.IsEmpty)
  85                                 return false;
  86
  87                         if (! query.AllowsDomain (QueryDomain.Global))
  88                                 return false;
  89
  90                         // FIXME: This is a meta-FIXME, since this is a bad assumption
  91                         // because the mime-type setting FIXME above.
  92                         if (! query.AllowsMimeType ("text/html"))
  93                                 return false;
  94
  95                         // Reject queries if the key isn't set.
  96                         if (googleKey == null || googleKey == "") {
  97                                 if (showNoKeyMessage) {
  98                                         Logger.Log.Warn ("To query Google, put your Google key into the GOOGLE_WEB_API_KEY environment variable.");
  99                                         Logger.Log.Warn ("To get a Google key, go to http://api.google.com/createkey");
 100                                         showNoKeyMessage = false;
 101                                 }
 102                                 return false;
 103                         }
 104
 105                         return true;
 106                 }
 107
 108
 109                 public void DoQuery (Query query,
 110                                      IQueryResult result,
 111                                      IQueryableChangeData changeData)
 112                 {
 113                         GoogleSearchResult gsr = gss.doGoogleSearch (googleKey,
 114                                                                      query.QuotedText,
 115                                                                      0, maxResults,
 116                                                                      false, "", false, "", "", "");
 117
 118                         ArrayList hits = new ArrayList ();
 119                         int rank = 0;
 120                         foreach (ResultElement elt in gsr.resultElements) {
 121                                 Hit hit = FromGoogleResultElement (elt, rank);
 122                                 hits.Add (hit);
 123                                 ++rank;
 124                         }
 125                         result.Add (hits);
 126                 }
 127
 128                 public string GetSnippet (string[] query_terms, Hit hit)
 129                 {
 130                         return hit ["Snippet"];
 131                 }
 132
 133                 public int GetItemCount ()
 134                 {
 135                         // Is there a way to get the # of indexed pages from
 136                         // google via the web services api?
 137                         return -1;
 138                 }
 139
 140         }
 141
 142 }