gettags.rb

gettags.rb

#!/usr/bin/env ruby
require 'json'
require 'net/http'
require 'pp'
require 'Time'
require 'tempfile'

STOP_WORDS = ["thunderbird", "email", "e-mail", "mail", "thunderbird3", "tbird", "tbird3", "tb", "emails", "mails", 
"e-mails", "tb3", "tb2", "support", "help", "error", "support", "please", "new", "ok", "message", "messages", 
"thanks", "got", "page", "two", "etc", "etc", "e.g.", "i.e", "fix", "computer", "seems", "right", "like", 
"fine", "also", "first", "fix", "worked", "something", "trying", "even", "much", "every", 'client',
 "different", "may", "since", "default", "problem", "many", "hi", "mozilla", "bug", "feature", "already", 
"unable", "using", "use", "one", "anyone", "however", "anything", "wrong", "now", "think", "found", 
"see", "still", "want", "might", "answer", "going", "question", "else", "used", "user", "appears", 
"line", "problems", "questions", "works", "thank", "works", "really", "great", "good", "well", 
"everything", "mac", "lot", "nothing", "nothing", "correct", "firefox", "people", "just", "get", 
"set", "apple", "thunderbird 3", "bugzilla" ]

def randomFileNameSuffix (numberOfRandomchars)
  s = ""
  numberOfRandomchars.times { s << (65 + rand(26))  }
  s
end

def getResponse(url)

  http = Net::HTTP.new("api.getsatisfaction.com",80)

  url = "/" + url 

  resp, data = http.get(url, nil)
   
  if resp.code != "200"
    printf(STDERR,"Error:%d\n", resp.code)
    return ""
  end

  result = JSON.parse(data)
  return result
end

if ARGV.length < 6
  puts "usage: #{$0} yyyy mm dd yyyy mmm dd"
  exit
end

metrics_start = Time.utc(ARGV[0], ARGV[1], ARGV[2], 0, 0)
metrics_start -= 1
metrics_stop =  Time.utc(ARGV[3], ARGV[4], ARGV[5], 23, 59)
metrics_stop += 1
topic_page = 0
end_program = false
spreadsheet = {}

while true
  topic_page += 1
  skip = false
  topic_url = "products/mozilla_thunderbird/topics.json?sort=recently_active&page=" << "%d" % topic_page << "&limit=30"
  printf(STDERR, "topic_url")
  begin
    topics = getResponse(topic_url)
  rescue JSON::ParserError
    printf(STDERR, "Parser error in topic:%s\n", topic_url)
    skip = true
  end
  if skip
    skip = false
    next
  end
  topics["data"].each do|topic|

    last_active_at = Time.parse(topic["last_active_at"])
    last_active_at = last_active_at.utc
    printf(STDERR, "TOPIC last_active_at:%s\n", last_active_at)

    if (last_active_at <=> (metrics_start + 1)) == -1 
      printf(STDERR, "ending program\n")
      end_program = true
      break
    end

    printf(STDERR, "START*** of topic\n")
    PP::pp(topic,$stderr)
    printf(STDERR, "\nEND*** of topic\n")

    get_tags_str = "topics/" + topic["slug"] + "/tags.json"
    PP::pp(get_tags_str, $stderr)

    tags = getResponse(get_tags_str)

    num_tags = tags["total"]
    printf(STDERR, "#of tags:%d\n", num_tags)
    if num_tags != 0
      tags["data"].each do|tag|

        printf(STDERR, "START*** of tag\n")
        PP::pp(tag, $stderr)
        printf(STDERR, "\nEND*** of tag\n")

        tag_name = tag["name"]

        tag_is_stop_word = false
        STOP_WORDS.each do|stop_word|
          if stop_word == tag_name 
            tag_is_stop_word = true
            break
          end
        end
        if !tag_is_stop_word
          if spreadsheet.has_key?(tag_name)
            spreadsheet[tag_name] += 1
          else
            spreadsheet[tag_name] = 1
          end 
          printf(STDOUT, "%s ", tag_name.gsub(/ /, '~'))
        end # each tag
        printf(STDOUT, "\n")
      end # if num_tags = 0
    end
  end 
  if end_program
    break
  end
end

csv_file = File.new("gettags."+ARGV[0]+ARGV[1]+ARGV[2]+ARGV[3]+ARGV[4]+ARGV[5]+"."+randomFileNameSuffix(4) + ".csv", "w")

spreadsheet.sort{|tag,count| tag[1]<=>count[1]}.each { |row|
csv_file.puts "#{row[0]}, #{row[1]}"
}
csv_file.close