Class: Jetel::Modules::Alexa

Inherits:
Module
  • Object
show all
Defined in:
lib/jetel/modules/alexa/alexa.rb

Instance Attribute Summary

Attributes inherited from Module

#downloader

Class Method Summary collapse

Instance Method Summary collapse

Methods inherited from Module

#download_dir, download_dir, #download_source, downloaded_file, #downloaded_file, extract_dir, #extract_dir, extracted_file, #extracted_file, #initialize, #load, #sources, target_dir, #target_dir, #transform_dir, transform_dir, transformed_file, #transformed_file, #unzip

Constructor Details

This class inherits a constructor from Jetel::Modules::Module

Class Method Details

.sourcesObject



32
33
34
35
36
37
38
39
40
41
42
# File 'lib/jetel/modules/alexa/alexa.rb', line 32

def sources
  [
    {
      name: 'alexa',
      # filename_downloaded: 'top-1m.csv.zip',
      filename_extracted: 'top-1m.csv',
      filename_transformed: 'top-1m.csv',
      url: 'http://s3.amazonaws.com/alexa-static/top-1m.csv.zip'
    }
  ]
end

Instance Method Details

#download(global_options, options, args) ⇒ Object



45
46
47
48
49
# File 'lib/jetel/modules/alexa/alexa.rb', line 45

def download(global_options, options, args)
  self.class.sources.pmap do |source|
    download_source(source, global_options.merge(options))
  end
end

#extract(global_options, options, args) ⇒ Object



51
52
53
54
55
# File 'lib/jetel/modules/alexa/alexa.rb', line 51

def extract(global_options, options, args)
  self.class.sources.pmap do |source|
    unzip(source, global_options.merge(options))
  end
end

#transform(global_options, options, args) ⇒ Object



57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
# File 'lib/jetel/modules/alexa/alexa.rb', line 57

def transform(global_options, options, args)
  self.class.sources.pmap do |source|
    extracted_file = extracted_file(source, global_options.merge(options))
    transformed_file = transformed_file(source, global_options.merge(options))
    dest_dir = transform_dir(source, global_options.merge(options))

    puts "Transforming #{extracted_file}"

    FileUtils.mkdir_p(dest_dir)
    File.open(extracted_file, 'rt') do |fin|
      File.open(transformed_file, 'wt') do |fout|
        fout.puts('rank,url')

        while buff = fin.read(4096)
          fout.write(buff)
        end
      end
    end
  end
end