Method: PDF::Reader::Turtletext#fuzzed_y

Defined in:
lib/pdf/reader/turtletext.rb

#fuzzed_y(input) ⇒ Object

Returns an Array with fuzzed positioning, ordered by decreasing y position. Row content order by x position.

[ fuzzed_y_position, [[x_position,content]] ]

Given input as a hash:

{ y_position: { x_position: content}}

Fuzz factors: y_precision



51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
 
# File 'lib/pdf/reader/turtletext.rb', line 51

def fuzzed_y(input)
  output = []
  input.keys.sort.reverse.each do |precise_y|
    matching_y = output.map(&:first).select{|new_y| (new_y - precise_y).abs < y_precision }.first || precise_y
    y_index = output.index{|y| y.first == matching_y }
    new_row_content = input[precise_y].to_a
    if y_index
      row_content = output[y_index].last
      row_content += new_row_content
      output[y_index] = [matching_y,row_content.sort{|a,b| a.first <=> b.first }]
    else
      output << [matching_y,new_row_content.sort{|a,b| a.first <=> b.first }]
    end
  end
  output
end