Class: Honyomi::Pdf

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

Instance Method Summary collapse

Constructor Details

#initialize(filename) ⇒ Pdf

Returns a new instance of Pdf.



8
9
10
# File 'lib/honyomi/pdf.rb', line 8

def initialize(filename)
  @filename = filename
end

Instance Method Details

#generate_images(output_dir) ⇒ Object



25
26
27
28
# File 'lib/honyomi/pdf.rb', line 25

def generate_images(output_dir)
  FileUtils.mkdir_p output_dir
  system("pdftoppm", "-jpeg", @filename, File.join(output_dir, "book"))
end

#pagesObject



12
13
14
15
16
17
18
19
20
21
22
23
# File 'lib/honyomi/pdf.rb', line 12

def pages
  Dir.mktmpdir do |dir|
    outfile = File.join(dir, "pdf.txt")
    system("pdftotext", @filename, outfile) # Need pdftotext (poppler, xpdf)
    @text = File.read(outfile, encoding: Encoding::UTF_8)
    if String.method_defined? :scrub
      @text = @text.scrub('?')
    end
  end

  @text.split("\f")
end