Small ruby script that will rank all Github issues in a repo according to which is the most popular

github_issue_rankings.rb

#!/usr/bin/ruby -w
#
# This script will analyze a Github repo and try to rank all open issues with regard to popularity.
# WARNING: This script will run quite a few HTTP requests against Github to do this analysis. At least 1 pr. issue.
# The current limit on Github is 5000 requests pr. hour: https://developer.github.com/v3/rate_limit/
#
# Usage: ./ruby github-issue-rankings.rb <github_user/repo> <github_api_access_token>
# Example: ruby github_issue_rankings.rb realm/realm-java $GITHUB_ISSUE_RANKINGS_ACCESS_TOKEN
#
# The algorithm for ranking issues are the following:
#
# 1. Search all comments for a positive reaction (see list of keywords). Each comment can only be counted once.
# 2. Count all positive reactions across all comments.
# 3. Negative reactions are ignored.
#
# Output: CSV file '<repo>-issues.csv'
# - <Title>, <Url>, <totalReactions>, <biggestSingleComment>, <reactions/day>
#
# Rationale:
# - Github does not have a similar concept to "Google stars", so it is relatively hard to rank issues with respect to
#   popularity.
# - Reactions are still a relative new concept, so a lot of older issues are littered with "+1" comments. Only counting
#   reactions will thus favour new issues.
# - If a single post is getting a lot of votes, it most likely describe a solution people want.
# - Reactions/Day is an attempt to capture new issues that might have strictly less up votes, but seem to acquire them
#   faster, which would indicate they are more popular.
#
# Known errors:
# - When folding issues into other issues we sometimes do something like "+15 from other issue". These will not be
#   counted, mainly because it is fairly difficult to tell the difference between "+1000000 for awesome idea vs. +15 from other
#   issue"
#
# Author: Christian Melchior <[email protected]>
#
require 'octokit'
require 'json'
require 'date'
require 'csv'

# Validate input
if ARGV.length <= 0 || ARGV.length > 2
  puts "Usage: ruby ./github-issue-rankings.rb <github_user/repo-name> <github_api_access_token>"
  exit
end
$repo = ARGV[0]
if ARGV[1]
  $access_token = ARGV[1]
elsif ENV['GITHUB_ISSUE_RANKINGS_ACCESS_TOKEN']
  $access_token = ENV['GITHUB_ISSUE_RANKINGS_ACCESS_TOKEN']
else
  puts "Usage: ruby ./github-issue-rankings.rb <github_user/repo-name> <github_api_access_token>"
  exit
end

#
# Internal class for keeping track of issues and their stats.
#
class GithubIssuesRankingModel
  class GithubIssue
    attr_accessor :positive_reactions, :biggest_comment

    def initialize(name, url, timestamp)
      @name = name
      @url = url
      @date = timestamp
      @days = (Time.now.to_date - timestamp.to_date).round
      @positive_reactions = 0
      @biggest_comment = 0
    end

    def values
      return [ @name, @url, @positive_reactions, @biggest_comment, @days > 0 ? @positive_reactions/@days.to_f : 0 ]
    end
  end

  def initialize
    @issues = Array.new
    @positive_reactions = ["+1", ":tada:", ":heart:"] # :+1: included in +1
    @body_regexp = @positive_reactions.map {|n| Regexp.escape(n) }.join('|')
  end

  #
  # Add a single issue + comments to the model.
  # Input should match the Github API v3 output: https://developer.github.com/v3/issues/
  #
  def add(issue, comments)
    github_issue = GithubIssue.new(issue.title, issue.html_url, issue.created_at)
    issue_total = 0

    # Issue description
    if /#{@body_regexp}/.match(issue.body)
      issue_total += 1
    end
    issue_total += count_positive_reactions(issue)
    biggest_comment = issue_total

    # Comments
    comments.each do |comment|
      comment_total = 0
      if /#{@body_regexp}/.match(comment.body)
        comment_total += 1
      end
      comment_total += count_positive_reactions(comment)
      issue_total += comment_total
      biggest_comment = [biggest_comment, comment_total].max
    end

    github_issue.positive_reactions = issue_total
    github_issue.biggest_comment = biggest_comment
    @issues.push(github_issue)
  end

  #
  # Count all positive reactions
  #
  def count_positive_reactions(response)
    reactions = 0
    reactions += response.reactions.heart
    reactions += response.reactions['+1']
    reactions += response.reactions.hooray
    return reactions
  end

  #
  # Save the result of the analysis to a csv file
  #
  def save_results
    CSV.open("#{ $repo.split('/').last }-issues.csv", "wb") do |csv|
      csv << ['Name', 'URL', 'PositiveReactions', 'SingleBiggestComment', 'Reactions/Day']
      @issues.sort { |left, right| right.positive_reactions <=> left.positive_reactions }.map { |x| csv << x.values }
    end
  end
end

# Provide authentication credentials
# See https://help.github.com/articles/creating-an-access-token-for-command-line-use/
client = Octokit::Client.new(access_token: $access_token, auto_paginate: true, per_page: 100)
model = GithubIssuesRankingModel.new

# Load and process all open issues from Github
gh_issues = client.list_issues($repo, :state => 'open', :accept => 'application/vnd.github.squirrel-girl-preview')
puts "No. of issues: #{gh_issues.size}"
gh_issues.map do |gh_issue|
  print "."
  unless gh_issue.pull_request
    comments = client.get(gh_issue['comments_url'], :accept => 'application/vnd.github.squirrel-girl-preview')
    model.add(gh_issue, comments)
  end
end
model.save_results