Deveaud Romain / mirimiri

Blame view

lib/mirimiri/ttagger.rb 2.57 KB
edit raw normal view history
cd7432252   Romain Deveaud   adding missing files 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
 
  #!/usr/bin/env ruby
  
  #--
  # This file is a part of the mirimiri library
  #
  # Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com>
  #
  # This program is free software: you can redistribute it and/or modify
  # it under the terms of the GNU General Public License as published by
  # the Free Software Foundation, either version 3 of the License, or
  # (at your option) any later version.
  #
  # This program is distributed in the hope that it will be useful,
  # but WITHOUT ANY WARRANTY; without even the implied warranty of
  # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  # GNU General Public License for more details.
  #
  # You should have received a copy of the GNU General Public License
  # along with this program.  If not, see <http://www.gnu.org/licenses/>.
  #++
  
  
  # TreeTagger-related stuff module.
  #
  # See http://www.ims.uni-stuttgart.de/projekte/corplex/TreeTagger/DecisionTreeTagger.html
  module TreeTagger
    
    # This class handles generic parsing of tagger-chunker outputs.
    class TaggerChunker
      attr_reader :chunks, :file
  
  
      # Parses a tagger-chunker output and returns an Array of Chunk.
      def self.parse chunk_lines
        open = false
        tag  = nil
  
        chunks = []
        words  = []
  
        chunk_lines.each do |l|
          l.chomp!
          if l =~ /^<\w+>$/
            open = true
            tag  = l
          elsif l =~ /^<\/\w+>$/
            if !words.empty? && open && l == tag.sub(/</, '</')
              open = false
              chunks.push Chunk.new(words.join(" "), tag) 
              words.clear
            else
              next
            end
          else
            words.push(l.split.first)
          end
        end
  
        chunks
      end
  
      # Initializes parsing. +chunk_file+ is the output of +tagger-chunker-+ and must
      # be a valid path to the file.
      #
      #   TaggerChunker.new("ttout/2010020") #=> #<RIR::TreeTagger::TaggerChunker:0x92fd088 @chunks=[#<RIR::TreeTagger::Chunk:0x8ec5a10 @words=["robert", "schumann"], @tag="NC">, ...] ...>
      def initialize chunk_file
        @chunks = TaggerChunker.parse File.open(chunk_file).readlines
      end
  
    end
  
    class TaggerChunkerEnglish < TaggerChunker
    end
  
    class TaggerChunkerFrench  < TaggerChunker
    end
  
    class TaggerChunkerGerman  < TaggerChunker
    end
  
    # Represents a Chunk extracted when parsing a TaggerChunker file.
    class Chunk
      attr_reader :words, :tag
  
      # Creates a Chunk.
      #
      # * +str+ are whitespace-separated terms.
      # * +tag+ see : ftp://ftp.ims.uni-stuttgart.de/pub/corpora/chunker-tagset-english.txt
      def initialize str,tag
        @words = str.split
        @tag   = tag[1..-2]
      end
    end
  
  end