Filters/FilterMan.cs

   1 //
   2 // Beagle
   3 //
   4 // FilterMan.cs : Trivial implementation of a man-page filter.
   5 //
   6 // Author :
   7 //      Michael Levy <mlevy@wardium.homeip.net>
   8 //
   9 // Copyright (C) 2004 Michael levy
  10 //
  11 //
  12 // Permission is hereby granted, free of charge, to any person obtaining a
  13 // copy of this software and associated documentation files (the "Software"),
  14 // to deal in the Software without restriction, including without limitation
  15 // the rights to use, copy, modify, merge, publish, distribute, sublicense,
  16 // and/or sell copies of the Software, and to permit persons to whom the
  17 // Software is furnished to do so, subject to the following conditions:
  18 //
  19 // The above copyright notice and this permission notice shall be included in
  20 // all copies or substantial portions of the Software.
  21 //
  22 // THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
  23 // IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
  24 // FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
  25 // AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
  26 // LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
  27 // FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
  28 // DEALINGS IN THE SOFTWARE.
  29 //
  30
  31 using System;
  32 using System.IO;
  33 using System.Text;
  34 using System.Text.RegularExpressions;
  35
  36 using Beagle.Daemon;
  37
  38 namespace Beagle.Filters {
  39
  40         public class FilterMan : Beagle.Daemon.Filter {
  41                 StreamReader reader;
  42
  43                 public FilterMan ()
  44                 {
  45                         // Make this a general troff filter.
  46                         AddSupportedFlavor (FilterFlavor.NewFromMimeType ("application/x-troff-man"));
  47                         AddSupportedFlavor (FilterFlavor.NewFromMimeType ("text/x-troff-man"));
  48                         AddSupportedFlavor (FilterFlavor.NewFromMimeType ("application/x-troff"));
  49                         AddSupportedFlavor (FilterFlavor.NewFromMimeType ("text/x-troff"));
  50                         AddSupportedFlavor (FilterFlavor.NewFromMimeType ("text/troff"));
  51
  52                         SnippetMode = true;
  53                 }
  54                 /*
  55                         FIXME:
  56                         Right now we don't handle pages with just one line like:
  57                                 .so man3/strcpy.3
  58                         Which is in strncpy.3.gz and points to strcpy.3.gz
  59                 */
  60                 protected void ParseManFile (StreamReader reader)
  61                 {
  62                         string str;
  63                         /*
  64                            The regular expression for a complete man header line is built to allow a suite of
  65                            non-spaces, or words separated by spaces which are encompassed in quotes
  66                            The regexp should be :
  67
  68                         Regex headerRE = new Regex (@"^\.TH\s+" +
  69                                                     @"(?<title>(\S+|(""(\S+\s*)+"")))\s+" +
  70                                                     @"(?<section>\d+)\s+" +
  71                                                     @"(?<date>(\S+|(""(\S+\s*)+"")))\s+" +
  72                                                     @"(?<source>(\S+|(""(\S+\s*)+"")))\s+" +
  73                                                     @"(?<manual>(\S+|(""(\S+\s*)+"")))\s*" +
  74                                                     "$");
  75
  76                          But there seem to be a number of broken man pages, and the current filter can be used
  77                          for general troff pages.
  78                         */
  79                         Regex headerRE = new Regex (@"^\.TH\s+" +
  80                                                     @"(?<title>(\S+|(""(\S+\s*)+"")))\s*");
  81
  82                         while ((str = reader.ReadLine ()) != null) {
  83                                 if (str.StartsWith (".\"")) {
  84                                         /* Comment in man page */
  85                                         continue;
  86                                 } else if (str.StartsWith (".TH ")) {
  87                                         MatchCollection matches = headerRE.Matches (str);
  88                                         if (matches.Count != 1) {
  89                                                 Console.Error.WriteLine ("In title Expected 1 match but found {0} matches in '{1}'",
  90                                                                           matches.Count, str);
  91                                                 continue;
  92                                         }
  93                                         foreach (Match theMatch in matches) {
  94                                                 AddProperty (Beagle.Property.New ("dc:title",
  95                                                                                   theMatch.Groups ["title"].ToString ()));
  96                                         }
  97                                 } else {
  98                                         // A "regular" string
  99
 100                                         // FIXME: We need to strip out other macros
 101                                         // (.SH for example)
 102                                         AppendText (str);
 103
 104                                 }
 105
 106                         }
 107                         Finished ();
 108                 }
 109
 110                 override protected void DoOpen (FileInfo info)
 111                 {
 112                         Stream stream;
 113                         stream = new FileStream (info.FullName,
 114                                                  FileMode.Open,
 115                                                  FileAccess.Read,
 116                                                  FileShare.Read);
 117                         reader = new StreamReader (stream);
 118                 }
 119                 override protected void DoPull ()
 120                 {
 121                         ParseManFile (reader);
 122                 }
 123         }
 124 }