Created
August 27, 2014 16:06
-
-
Save ololobus/11f222d1fc48f2efef56 to your computer and use it in GitHub Desktop.
XLS file dict (word, transcription, translation) to js object
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
require 'roo' | |
require 'optparse' | |
require 'json' | |
options = {} | |
dict = {} | |
OptionParser.new do |opts| | |
opts.on('-f File', '--file File', String, 'Input file') do |f| | |
options[:file] = f | |
end | |
opts.on('-o OutputFile', '--output OutputFile', String, 'Output file') do |o| | |
options[:output] = o | |
end | |
end.parse! | |
if !options[:file] || !options[:output] then | |
puts 'Please scpecify input file using -f key and output file using -o' | |
else | |
sheet = Roo::Excel.new(options[:file]) | |
for l in sheet.first_row..sheet.last_row | |
word = sheet.cell('A', l) | |
transcript = sheet.cell('B', l) | |
trans = sheet.cell('C', l) | |
if word && word != '' && transcript && transcript != '' && word.scan(/\ /).count < 3 && word.scan(/[\-\.\,]+/).count == 0 && trans | |
trans = trans.strip.gsub(/\(.*\)/, '').gsub(';', '').split(',').first(2).map{ |w| w.strip }.join(', ') | |
if trans.scan(/\ /).count < 3 && trans.scan(/[\=\"\(\)]+/).count == 0 && trans != '' | |
dict[word] = [transcript, trans] | |
end | |
end | |
end | |
output_content = "{\n" | |
dict.each do |k,v| | |
output_content += " \"#{k}\": [\"#{v[0]}\", \"#{v[1]}\"],\n" | |
end | |
output_content += '}' | |
File.open(options[:output], 'w') { |file| file.write(output_content) } | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment