Class: LineStateMachine

Inherits:
Object
  • Object
show all
Defined in:
lib/data/line_state_machine.rb

Overview

First pass at state machine for converting sequence of formatted lines into a different

set of word values, in this case "<N>, blank, |, blank, <footer title>" get converted
into [ "END_OF_PAGE", "<page number>", "<title as a single word>"]

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize ⇒ LineStateMachine

Returns a new instance of LineStateMachine.



11
12
13
14
15
16
 
# File 'lib/data/line_state_machine.rb', line 11

def initialize
  @bucket = "Page 0"
  @pages = {}
  @dataQueue = []
  super
end

Instance Attribute Details

#bucket ⇒ Object

Returns the value of attribute bucket.



9
10
11
 
# File 'lib/data/line_state_machine.rb', line 9

def bucket
  @bucket
end

#pages ⇒ Object

Returns the value of attribute pages.



9
10
11
 
# File 'lib/data/line_state_machine.rb', line 9

def pages
  @pages
end

Instance Method Details

#process(line, wordIndex) ⇒ Object 



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
 
# File 'lib/data/line_state_machine.rb', line 27

def process(line, wordIndex)
  data = line.split

  # we are looking for a blank, a pipe, or a page number
  if (data.length == 0) then
    if (self.foundBlank) then
      return []
    end
  end
  if (data.length == 1) then
    if (data[0] == "|") then
      if (self.foundPipe) then
        return []
      end
    end
    ival = data[0].to_i
    if (ival > 0) then
      if (self.foundN) then
        @potentialPageNumber = ival
        @dataQueue << data  # in case this really isn't it
        return []
      end
    end
  end

  # if we are looking for the title, the entire line is the title
  if (data.length > 0) then
    if (self.foundTitle) then
      @dataQueue = []
      @bucket = "Page #{@potentialPageNumber}"
      @pages[@bucket] = wordIndex
      return []
    end
  end

  resetState(data)
end

#resetState(data) ⇒ Object 



18
19
20
21
22
23
24
25
 
# File 'lib/data/line_state_machine.rb', line 18

def resetState(data)
  self.reset
  result = []
  result << @dataQueue
  result << data
  @dataQueue = []
  return result.flatten
end