class Repos::StackOverflow

Public Class Methods

new(gem_name, stackoverflow_token) click to toggle source
# File lib/repocrawler/crawler.rb, line 378
def initialize(gem_name, stackoverflow_token)
  @STACKOVERFLOW_API = "https://api.stackexchange.com/2.2/search/advanced?order=desc&sort=creation&q=#{gem_name}&site=stackoverflow&key=#{stackoverflow_token}"
end

Public Instance Methods

get_questions() click to toggle source

get questions from stackexchange

# File lib/repocrawler/crawler.rb, line 383
def get_questions

  stop_words = []
  File.open(File.expand_path("../../public/stop_words.txt",  File.dirname(__FILE__)), "r") do |f|
    f.each_line do |line|
      stop_words << line.gsub(/\n/,"")
    end
  end

  questions = []
  fetch_questions = HTTParty.get(@STACKOVERFLOW_API)
  fetch_questions['items'].each do |q|
    #don't store stop words
    good_words = []
    q['title'].split(' ').map do |word|
      if !stop_words.include?(word.downcase)
        good_words << word
      end
    end

    questions << {
      'creation_date' => q['creation_date'],
      'title' => good_words,
      'views' => q['view_count']
    }
  end

  questions_word_count = Hash.new(0)
  questions.each do |question|
    question['title'].each do |word|
      questions_word_count[word] += 1
    end
  end

  questions_word_count = questions_word_count.sort_by { |word, freq| freq }.reverse!
  [questions, questions_word_count]
end