Class: Konjak::TmxSegmentor::BaseStrategy

Inherits:
Object
  • Object
show all
Includes:
Mem
Defined in:
lib/konjak/tmx_segmentor/base_strategy.rb

Direct Known Subclasses

GttHtmlStrategy, TextStrategy

Defined Under Namespace

Classes: Edge, Node

Instance Method Summary collapse

Constructor Details

#initialize(tmx, lang, text, options = {}) ⇒ BaseStrategy



24
25
26
27
28
29
# File 'lib/konjak/tmx_segmentor/base_strategy.rb', line 24

def initialize(tmx, lang, text, options = {})
  @tmx     = tmx
  @lang    = lang
  @text    = text
  @options = default_options.merge(options)
end

Instance Method Details

#max_cost_pathObject



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
# File 'lib/konjak/tmx_segmentor/base_strategy.rb', line 56

def max_cost_path
  prev_nodes = nodes.map {|node| [node, Node::None] }.to_h
  costs      = nodes.map {|node| [node, node.range.size] }.to_h

  edges.each do |edge|
    node, node2    = edge.prev, edge.current
    node2_cost     = costs[node2]
    new_node2_cost = costs[node] + calc_edge_cost(edge)

    if node2_cost < new_node2_cost
      costs[node2] = new_node2_cost
      prev_nodes[node2] = node
    end
  end

  node, _ = costs.max_by {|_, cost| cost }

  Enumerator.new {|y|
    loop do
      break if node == Node::None
      y << node
      node = prev_nodes[node]
    end
  }.to_a.reverse
end

#segmentsObject



31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
# File 'lib/konjak/tmx_segmentor/base_strategy.rb', line 31

def segments
  # Can't split text
  return [@text] if nodes.empty?

  segments = []
  prev_text_end = 0
  prev_segment = nil
  max_cost_path.each do |node|
    range     = node.range
    segment   = select_next_segment(prev_segment, node)
    prev_text = @text[prev_text_end...range.begin]

    segments << prev_text unless prev_text.empty?

    segments << SegmentString.new(@text[range.begin, range.size], segment)

    prev_segment    = segment
    prev_text_end = range.end
  end
  after_text = @text[prev_text_end..-1]
  segments << after_text unless after_text.empty?
  segments
end