Class: Jetel::Modules::Alexa
- Inherits:
-
Module
- Object
- Module
- Jetel::Modules::Alexa
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, target_dir, #target_dir, #transform_dir, transform_dir, transformed_file, #transformed_file, #unzip
Class Method Details
.sources ⇒ Object
13
14
15
16
17
18
19
20
21
22
23
|
# File 'lib/jetel/modules/alexa/alexa.rb', line 13
def sources
[
{
name: 'alexa',
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
26
27
28
29
30
|
# File 'lib/jetel/modules/alexa/alexa.rb', line 26
def download(global_options, options, args)
self.class.sources.pmap do |source|
download_source(source, global_options.merge(options))
end
end
|
32
33
34
35
36
|
# File 'lib/jetel/modules/alexa/alexa.rb', line 32
def (global_options, options, args)
self.class.sources.pmap do |source|
unzip(source, global_options.merge(options))
end
end
|
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
|
# File 'lib/jetel/modules/alexa/alexa.rb', line 38
def transform(global_options, options, args)
self.class.sources.pmap do |source|
= (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 #{}"
FileUtils.mkdir_p(dest_dir)
File.open(, '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
|