Class: PdfProcessor::Abstract

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

Instance Method Summary collapse

Constructor Details

#initialize(pdf_processor) ⇒ Abstract

attr_accessor :reader



41
42
43
44
45
46
47
 
# File 'lib/pdf_processor.rb', line 41

def initialize(pdf_processor)
  @pdf_processor=pdf_processor
  @reader=pdf_processor.reader
  @mode=:pre
  @abstract_lines=[]
  @empty_lines=0
end

Instance Method Details

#parse ⇒ Object 



63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
 
# File 'lib/pdf_processor.rb', line 63

def parse
  # First, we locate the page on which is located the abstract
  page_for_abstract=@reader.pages[0..1].index {|page_n| page_n.text=~/Abstract/}
  return nil if page_for_abstract.nil?

  @pdf_processor.page(page_for_abstract).text.each_line do |r|
    line=r.chomp.lstrip
    if @mode==:pre and line=~/Abstract/ # We must include other languages
      @mode=:abstract
      # There is more information on this line?
      if (line_wo_abstract=(line.gsub(/(?:Abstract):?/,"")).lstrip)!=""
        @abstract_lines.push(line_wo_abstract)
      end

    elsif @mode==:abstract
      break if !parse_line_abstract(line)
    end

  end
  @abstract_lines.join("")
end