Created
September 22, 2009 08:27
-
-
Save rtanglao/190923 to your computer and use it in GitHub Desktop.
getTop5.rb
This file contains hidden or 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
#!/usr/bin/env ruby | |
require 'json' | |
require 'net/http' | |
require 'pp' | |
require 'Time' | |
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 getResponse(url) | |
http = Net::HTTP.new("api.getsatisfaction.com",80) | |
url = "/" + url | |
resp, data = http.get(url, nil) | |
if resp.code != "200" | |
puts "Error: #{resp.code}" | |
return "" | |
end | |
result = JSON.parse(data) | |
return result | |
end | |
if ARGV.length < 6 | |
puts "usage: #{$0} yyyy mm dd yyyy mmm dd" | |
exit | |
end | |
metrics_start = Time.utc(ARGV[0], ARGV[1], ARGV[2], 0, 0) | |
metrics_start -= 1 | |
metrics_stop = Time.utc(ARGV[3], ARGV[4], ARGV[5], 23, 59) | |
metrics_stop += 1 | |
topic_page = 1 | |
end_program = false | |
spreadsheet = {} | |
while true | |
topic_url = "products/mozilla_thunderbird/topics.json?sort=recently_created&page=" << "%d" % topic_page << "&limit=30" | |
printf(STDERR, "topic_url") | |
topics = getResponse(topic_url) | |
topics["data"].each do|topic| | |
created_at = Time.parse(topic["created_at"]) | |
created_at = created_at.utc | |
printf(STDERR, "TOPIC created_at:%s\n", created_at) | |
if (created_at <=> (metrics_start + 1)) == -1 | |
printf(STDERR, "topic created before start date at:%s so ending program\n", created_at) | |
end_program = true | |
break | |
end | |
if (created_at <=> metrics_stop) == 1 | |
printf(STDERR, "topic created after end at:%s, so breaking\n", created_at) | |
break | |
end | |
printf(STDERR, "START*** of topic\n") | |
PP::pp(topic,$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) | |
if tags["total"] != 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 | |
end | |
end | |
if !tag_is_stop_word | |
if spreadsheet.has_key?(tag_name) | |
spreadsheet[tag_name] += 1 | |
else | |
spreadsheet[tag_name] = 1 | |
end | |
end | |
end | |
end | |
end | |
topic_page += 1 | |
if end_program | |
break | |
end | |
end | |
spreadsheet.sort{|tag,count| tag[1]<=>count[1]}.each { |row| | |
puts "#{row[0]}, #{row[1]}" | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment