snowfinch-collector 0.5.0

data/.gitignore

@@ -0,0 +1,4 @@
+*.gem
+.bundle
+Gemfile.lock
+pkg/*

data/.rspec

@@ -0,0 +1 @@
+--color

data/Gemfile

@@ -0,0 +1,11 @@
+source "http://rubygems.org"
+
+gemspec
+
+group :test do
+  gem "autotest-standalone"
+  gem "rack-test", :require => "rack/test"
+  gem "rspec"
+  gem "steak"
+  gem "timecop"
+end

data/README.md

@@ -0,0 +1,2 @@
+Snowfinch Collector
+===================

data/Rakefile

@@ -0,0 +1,5 @@
+require "bundler"
+Bundler::GemHelper.install_tasks
+
+require "rspec/core/rake_task"
+RSpec::Core::RakeTask.new

data/lib/snowfinch/collector.rb

@@ -0,0 +1,59 @@
+require "base64"
+require "mongo"
+require "rack"
+require "rack/request"
+require "uri"
+require "digest/sha1"
+require "radix62"
+require "snowfinch/collector/click"
+
+module Snowfinch
+  module Collector
+    
+    EMPTY_GIF = "R0lGODlhAQABAIABAP///wAAACH5BAEKAAEALAAAAAABAAEAAAICTAEAOw=="
+    RESPONSE  = [Base64.decode64(EMPTY_GIF)]
+    HEADERS   = { "Content-Type" => "image/gif" }
+
+    OK          = [200, HEADERS, RESPONSE]
+    BAD_REQUEST = [400, {}, []]
+
+    def self.call(env)
+      params = Rack::Request.new(env).params
+
+      click = Click.new :token => params["token"],
+                        :uri => params["uri"],
+                        :uuid => params["uuid"],
+                        :referrer => params["referrer"]
+      
+      if click.save
+        OK
+      else
+        BAD_REQUEST
+      end
+    #rescue
+      #BAD_REQUEST
+    end
+
+    def self.db
+      @db ||= Mongo::Connection.new.db("snowfinch")
+    end
+
+    def self.db=(database)
+      @db = database
+    end
+
+    def self.sanitize_uri(uri)
+      uri = uri.sub(/^https?:\/\/(www\.)?/, "http://")
+      uri = URI.parse(uri)
+      uri.path = uri.path.sub(/(.)\/$/, '\1')
+      uri.query = nil
+      uri.fragment = nil
+      uri = uri.to_s
+    end
+
+    def self.hash_uri(uri)
+      Digest::SHA1.hexdigest(uri).to_i(16).encode62
+    end
+
+  end
+end

data/lib/snowfinch/collector/click.rb

@@ -0,0 +1,168 @@
+require "bson"
+require "cgi"
+require "time"
+require "tzinfo"
+require "uri"
+
+module Snowfinch
+  module Collector
+    class Click
+
+      def initialize(attributes={})
+        @attributes = attributes
+      end
+
+      def save
+        if uri && uuid
+          update_site_count
+          update_page_count
+          update_visit
+          update_visitor
+          update_sensors
+          true
+        else
+          false
+        end
+      end
+
+      private
+
+      def site_id
+        @site_id ||= BSON::ObjectId(@attributes[:token])
+      end
+
+      def uuid
+        @uuid ||= @attributes[:uuid]
+      end
+
+      def uri
+        @uri ||= begin
+          uri = @attributes[:uri]
+          uri && Snowfinch::Collector.sanitize_uri(uri)
+        end
+      end
+
+      def uri_hash
+        @uri_hash ||= Snowfinch::Collector.hash_uri(uri)
+      end
+
+      def referrer
+        @referrer ||= @attributes[:referrer]
+      end
+
+      def site
+        @site ||= Snowfinch::Collector.db["sites"].find_one(site_id)
+      end
+
+      def time
+        @time ||= TZInfo::Timezone.get(site["tz"]).current_period_and_time.first
+      end
+
+      def sensors
+        @sensors ||= site["sensors"]
+      end
+
+      def matching_sensors
+        matching_query_sensors + matching_host_sensors
+      end
+
+      def matching_query_sensors
+        query_string = URI.parse(@attributes[:uri]).query
+
+        if query_string && sensors
+          query_parts = CGI.parse(query_string)
+
+          matches = sensors.find_all do |sensor|
+            if sensor["type"] == "query"
+              query_parts.any? do |key, value|
+                sensor["key"] == key && value.include?(sensor["value"])
+              end
+            end
+          end
+
+          matches.map { |sensor| sensor["id"] }
+        else
+          []
+        end
+      end
+
+      def matching_host_sensors
+        if referrer && !referrer.empty? && sensors
+          referrer_host = URI.parse(referrer).host
+
+          matches = sensors.find_all do |sensor|
+            if sensor["type"] == "referrer"
+              sensor["hosts"].any? do |sensor_host|
+                referrer_host =~ /^(\S+\.)?#{sensor_host}$/
+              end
+            end
+          end
+
+          matches.map { |sensor| sensor["id"] }
+        else
+          []
+        end
+      end
+
+      def hourly_increment
+        @hourly_increment ||= { 
+          "c" => 1,
+          "#{time.mon}.c" => 1,
+          "#{time.mon}.#{time.day}.c" => 1,
+          "#{time.mon}.#{time.day}.#{time.hour}.c" => 1
+        }
+      end
+
+      def update_site_count
+        Snowfinch::Collector.db["site_counts"].update(
+          { "s" => site_id, "y" => time.year },
+          { :$inc => hourly_increment },
+          { :upsert => true }
+        )
+      end
+
+      def update_page_count
+        Snowfinch::Collector.db["page_counts"].update(
+          { "s" => site_id, "u" => uri, "y" => time.year, "h" => uri_hash },
+          { :$inc => hourly_increment },
+          { :upsert => true }
+        )
+      end
+
+      def update_visit
+        Snowfinch::Collector.db["visits"].update(
+          {
+            "s" => site_id,
+            "v" => uuid,
+            "h" => { :$gt => (Time.now.to_i - 15 * 60) }
+          },
+          {
+            :$addToSet => { "p" => uri_hash },
+            :$set => { "h" => Time.now.to_i },
+            :$inc => { "c" => 1 }
+          },
+          { :upsert => true }
+        )
+      end
+
+      def update_visitor
+        Snowfinch::Collector.db["visitors"].update(
+          { "s" => site_id, "u" => uuid, "d" => time.to_date.to_s },
+          { :$inc => { "c" => 1 } },
+          { :upsert => 1 }
+        )
+      end
+
+      def update_sensors
+        matching_sensors.each do |id|
+          Snowfinch::Collector.db["sensor_counts"].update(
+            { "s" => site_id, "y" => time.year, "id" => id },
+            { :$inc => hourly_increment },
+            { :upsert => true }
+          )
+        end
+      end
+
+    end
+  end
+end

data/lib/snowfinch/collector/version.rb

@@ -0,0 +1,5 @@
+module Snowfinch
+  module Collector
+    VERSION = "0.5.0"
+  end
+end

data/snowfinch-collector.gemspec

@@ -0,0 +1,27 @@
+# -*- encoding: utf-8 -*-
+$:.push File.expand_path("../lib", __FILE__)
+require "snowfinch/collector/version"
+
+Gem::Specification.new do |s|
+  s.name        = "snowfinch-collector"
+  s.version     = Snowfinch::Collector::VERSION
+  s.platform    = Gem::Platform::RUBY
+  s.authors     = ["Joao Carlos"]
+  s.email       = ["mail@joao-carlos.com"]
+  s.homepage    = "https://github.com/jcxplorer/snowfinch"
+  s.summary     = %q{Snowfinch collector}
+  s.description = %q{Collector gem for snowfinch.}
+
+  s.rubyforge_project = "snowfinch-collector"
+
+  s.files         = `git ls-files`.split("\n")
+  s.test_files    = `git ls-files -- {test,spec,features}/*`.split("\n")
+  s.executables   = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
+  s.require_paths = ["lib"]
+
+  s.add_dependency "mongo"
+  s.add_dependency "bson_ext"
+  s.add_dependency "rack"
+  s.add_dependency "radix62"
+  s.add_dependency "tzinfo"
+end

data/spec/acceptance/data_collection_spec.rb

@@ -0,0 +1,304 @@
+require "spec_helper"
+
+feature "Data collection" do
+
+  let(:homepage) { "http://snowfinch.net/" }
+
+  let :sites do
+    Snowfinch::Collector.db["sites"].find.to_a
+  end
+  
+  let :site_counts do
+    Snowfinch::Collector.db["site_counts"].find.to_a
+  end
+
+  let :page_counts do
+    Snowfinch::Collector.db["page_counts"].find({}, :sort => "_id").to_a
+  end
+
+  let :sensor_counts do
+    Snowfinch::Collector.db["sensor_counts"].find({}, :sort => "_id").to_a
+  end
+
+  let :visits do
+    Snowfinch::Collector.db["visits"].find({}, :sort => "_id").to_a
+  end
+
+  let :visitors do
+    Snowfinch::Collector.db["visitors"].find({}, :sort => "_id").to_a
+  end
+
+  scenario "Multiple pageviews at different times" do
+    freeze_utc_time(2011, 2, 12, 7)
+    get path(:token => token, :uri => "http://snowfinch.net/posts")
+
+    freeze_utc_time(2011, 6, 4, 10)
+    get path(:token => token, :uri => "http://snowfinch.net/archive")
+
+    freeze_utc_time(2011, 6, 4, 15)
+    get path(:token => token, :uri => "http://snowfinch.net/")
+
+    freeze_utc_time(2011, 6, 4, 15)
+    get path(:token => token, :uri => "http://snowfinch.net/posts")
+
+    freeze_utc_time(2011, 6, 4, 15)
+    get path(:token => token, :uri => "http://snowfinch.net/posts")
+
+    freeze_utc_time(2012, 1, 1, 4)
+    get path(:token => token, :uri => "http://snowfinch.net/")
+
+    site_counts.count.should == 2
+    page_counts.count.should == 4
+
+    (site_counts + page_counts).each do |doc|
+      doc["s"].should == BSON::ObjectId(token)
+    end
+
+    site_counts[0]["y"].should == 2011
+    site_counts[0]["c"].should == 5
+    site_counts[0]["2"]["c"].should == 1
+    site_counts[0]["2"]["12"]["c"].should == 1
+    site_counts[0]["2"]["12"]["9"]["c"].should == 1
+    site_counts[0]["6"]["c"].should == 4
+    site_counts[0]["6"]["4"]["c"].should == 4
+    site_counts[0]["6"]["4"]["13"]["c"].should == 1
+    site_counts[0]["6"]["4"]["18"]["c"].should == 3
+
+    site_counts[1]["y"].should == 2012
+    site_counts[1]["c"].should == 1
+    site_counts[1]["1"]["c"].should == 1
+    site_counts[1]["1"]["1"]["c"].should == 1
+    site_counts[1]["1"]["1"]["6"]["c"].should == 1
+
+    page_counts[0]["u"].should == "http://snowfinch.net/posts"
+    page_counts[0]["h"].should == "rmT7mgGiXq6Hw8d6oApVW1AohTW"
+    page_counts[0]["y"].should == 2011
+    page_counts[0]["c"].should == 3
+    page_counts[0]["2"]["c"].should == 1
+    page_counts[0]["2"]["12"]["c"].should == 1
+    page_counts[0]["2"]["12"]["9"]["c"].should == 1
+    page_counts[0]["6"]["c"].should == 2
+    page_counts[0]["6"]["4"]["c"].should == 2
+    page_counts[0]["6"]["4"]["18"]["c"].should == 2
+
+    page_counts[1]["u"].should == "http://snowfinch.net/archive"
+    page_counts[1]["h"].should == "61EDJAzzvZOSNlIsLEaD3GRau2K"
+    page_counts[1]["y"].should == 2011
+    page_counts[1]["c"].should == 1
+    page_counts[1]["6"]["c"].should == 1
+    page_counts[1]["6"]["4"]["c"].should == 1
+    page_counts[1]["6"]["4"]
+    page_counts[1]["6"]["4"]["13"]["c"].should == 1
+
+    page_counts[2]["u"].should == "http://snowfinch.net/"
+    page_counts[2]["h"].should == "acrfzPFTC4qJH0SLjgo4611dj2h"
+    page_counts[2]["y"].should == 2011
+    page_counts[2]["c"].should == 1
+    page_counts[2]["6"]["c"].should == 1
+    page_counts[2]["6"]["4"]["c"].should == 1
+    page_counts[2]["6"]["4"]["18"]["c"].should == 1
+
+    page_counts[3]["u"].should == "http://snowfinch.net/"
+    page_counts[3]["h"].should == "acrfzPFTC4qJH0SLjgo4611dj2h"
+    page_counts[3]["y"].should == 2012
+    page_counts[3]["c"].should == 1
+    page_counts[3]["1"]["c"].should == 1
+    page_counts[3]["1"]["1"]["c"].should == 1
+    page_counts[3]["1"]["1"]["6"]["c"].should == 1
+  end
+
+  scenario "Multiple visits" do
+    archive  = "http://snowfinch.net/archive"
+
+    freeze_utc_time(2011, 1, 1, 10, 0)
+    get path(:uuid => "A", :token => token, :uri => homepage)
+    get path(:uuid => "B", :token => token, :uri => homepage)
+
+    freeze_utc_time(2011, 1, 1, 10, 10)
+    get path(:uuid => "A", :token => token, :uri => homepage)
+
+    freeze_utc_time(2011, 1, 1, 10, 15)
+    get path(:uuid => "B", :token => token, :uri => homepage)
+
+    freeze_utc_time(2011, 1, 1, 10, 30)
+    get path(:uuid => "C", :token => token, :uri => homepage)
+
+    freeze_utc_time(2011, 1, 1, 10, 44, 59)
+    get path(:uuid => "C", :token => token, :uri => archive)
+
+    freeze_utc_time(2011, 1, 1, 10, 55)
+    get path(:uuid => "A", :token => token, :uri => homepage)
+
+    freeze_utc_time(2011, 1, 1, 11, 5)
+    get path(:uuid => "A", :token => token, :uri => homepage)
+
+    visits.count.should == 5
+    visits.each { |doc| doc["s"].should == BSON::ObjectId(token) }
+
+    visits[0]["p"].should == [Snowfinch::Collector.hash_uri(homepage)]
+    visits[0]["v"].should == "A"
+    visits[0]["h"].should == Time.utc(2011, 1, 1, 10, 10).to_i
+    visits[0]["c"].should == 2
+
+    visits[1]["p"].should == [Snowfinch::Collector.hash_uri(homepage)]
+    visits[1]["v"].should == "B"
+    visits[1]["h"].should == Time.utc(2011, 1, 1, 10, 0).to_i
+    visits[1]["c"].should == 1
+
+    visits[2]["p"].should == [Snowfinch::Collector.hash_uri(homepage)]
+    visits[2]["v"].should == "B"
+    visits[2]["h"].should == Time.utc(2011, 1, 1, 10, 15).to_i
+    visits[2]["c"].should == 1
+
+    pages = [homepage, archive].map { |uri| Snowfinch::Collector.hash_uri(uri) }
+    visits[3]["p"].should == pages
+    visits[3]["v"].should == "C"
+    visits[3]["h"].should == Time.utc(2011, 1, 1, 10, 44, 59).to_i
+    visits[3]["c"].should == 2
+
+    visits[4]["p"].should == [Snowfinch::Collector.hash_uri(homepage)]
+    visits[4]["v"].should == "A"
+    visits[4]["h"].should == Time.utc(2011, 1, 1, 11, 5).to_i
+    visits[4]["c"].should == 2
+  end
+
+  scenario "Multiple visitors" do
+    freeze_utc_time(2011, 1, 1, 23, 0)
+    get path(:token => token, :uuid => "A", :uri => homepage)
+
+    freeze_utc_time(2011, 1, 2)
+    get path(:token => token, :uuid => "A", :uri => homepage)
+
+    freeze_utc_time(2011, 1, 2)
+    get path(:token => token, :uuid => "B", :uri => homepage)
+
+    freeze_utc_time(2011, 1, 3)
+    get path(:token => token, :uuid => "A", :uri => homepage)
+
+    visitors.count.should == 3
+    visitors
+
+    visitors[0]["d"].should == "2011-01-02"
+    visitors[0]["u"].should == "A"
+    visitors[0]["c"].should == 2
+
+    visitors[1]["d"].should == "2011-01-02"
+    visitors[1]["u"].should == "B"
+    visitors[1]["c"].should == 1
+
+    visitors[2]["d"].should == "2011-01-03"
+    visitors[2]["u"].should == "A"
+    visitors[2]["c"].should == 1
+  end
+
+  scenario "Entries matching a query based sensor" do
+    campaign_uri     = "http://snowfinch.net/?campaign=rr"
+    both_sensors_uri = "http://snowfinch.net/?campaign=rr&from=email"
+
+    campaign_sensor = {
+      "id" => 12,
+      "type" => "query",
+      "key" => "campaign",
+      "value" => "rr"
+    }
+
+    email_sensor = {
+      "id" => 24,
+      "type" => "query",
+      "key" => "from",
+      "value" => "email"
+    }
+
+    Snowfinch::Collector.db["sites"].update(
+      { "_id" => BSON::ObjectId(token) },
+      { :$set => { "sensors" => [campaign_sensor, email_sensor] } }
+    )
+
+    freeze_utc_time(2011, 11, 11, 20)
+    get path(:token => token, :uri => campaign_uri)
+
+    freeze_utc_time(2011, 11, 11, 20)
+    get path(:token => token, :uri => campaign_uri)
+    
+    freeze_utc_time(2011, 11, 11, 21)
+    get path(:token => token, :uri => both_sensors_uri)
+
+    freeze_utc_time(2011, 11, 11, 21)
+    get path(:token => token, :uri => homepage)
+
+    sensor_counts.count.should == 2
+
+    sensor_counts[0]["s"].should == BSON::ObjectId(token)
+    sensor_counts[0]["id"].should == 12
+    sensor_counts[0]["y"].should == 2011
+    sensor_counts[0]["c"].should == 3
+    sensor_counts[0]["11"]["c"].should == 3
+    sensor_counts[0]["11"]["11"]["c"].should == 3
+    sensor_counts[0]["11"]["11"]["22"]["c"].should == 2
+    sensor_counts[0]["11"]["11"]["23"]["c"].should == 1
+
+    sensor_counts[1]["s"].should == BSON::ObjectId(token)
+    sensor_counts[1]["id"].should == 24
+    sensor_counts[1]["y"].should == 2011
+    sensor_counts[1]["c"].should == 1
+    sensor_counts[1]["11"]["c"].should == 1
+    sensor_counts[1]["11"]["11"]["c"].should == 1
+    sensor_counts[1]["11"]["11"]["23"]["c"].should == 1
+  end
+
+  scenario "Entries matching a referrer based sensor" do
+    facebook_referrer = "http://www.facebook.com/l.php"
+    twitter_referrer = "http://twitter.com/jcxplorer"
+    search_referrer = "http://duckduckgo.com/post.html"
+
+    social_sensor = {
+      "id" => 33,
+      "type" => "referrer",
+      "hosts" => ["facebook.com", "twitter.com"]
+    }
+
+    facebook_sensor = {
+      "id" => 46,
+      "type" => "referrer",
+      "hosts" => ["facebook.com"]
+    }
+
+    Snowfinch::Collector.db["sites"].update(
+      { "_id" => BSON::ObjectId(token) },
+      { :$set => { "sensors" => [social_sensor, facebook_sensor] } }
+    )
+
+    freeze_utc_time(2011, 8, 2, 5)
+    get path(:token => token, :uri => homepage, :referrer => twitter_referrer)
+
+    freeze_utc_time(2011, 8, 2, 5)
+    get path(:token => token, :uri => homepage, :referrer => search_referrer)
+
+    freeze_utc_time(2011, 8, 10, 12)
+    get path(:token => token, :uri => homepage, :referrer => facebook_referrer)
+
+    freeze_utc_time(2011, 8, 10, 12)
+    get path(:token => token, :uri => homepage, :referrer => twitter_referrer)
+
+    sensor_counts.count.should == 2
+
+    sensor_counts[0]["s"].should == BSON::ObjectId(token)
+    sensor_counts[0]["id"].should == 33
+    sensor_counts[0]["y"].should == 2011
+    sensor_counts[0]["c"].should == 3
+    sensor_counts[0]["8"]["c"].should == 3
+    sensor_counts[0]["8"]["2"]["c"].should == 1
+    sensor_counts[0]["8"]["2"]["8"]["c"].should == 1
+    sensor_counts[0]["8"]["10"]["c"].should == 2
+    sensor_counts[0]["8"]["10"]["15"]["c"].should == 2
+
+    sensor_counts[1]["s"].should == BSON::ObjectId(token)
+    sensor_counts[1]["id"].should == 46
+    sensor_counts[1]["y"].should == 2011
+    sensor_counts[1]["c"].should == 1
+    sensor_counts[1]["8"]["c"].should == 1
+    sensor_counts[1]["8"]["10"]["c"].should == 1
+    sensor_counts[1]["8"]["10"]["15"]["c"].should == 1
+  end
+
+end

data/spec/acceptance/response_spec.rb

@@ -0,0 +1,30 @@
+require "spec_helper"
+
+feature "Response" do
+
+  scenario "GET request" do
+    get path(:token => token, :uri => "http://snowfinch.net/", :uuid => "CAFE")
+    
+    empty_gif = "R0lGODlhAQABAIABAP///wAAACH5BAEKAAEALAAAAAABAAEAAAICTAEAOw=="
+
+    last_response.status.should == 200
+    last_response.headers["Content-Type"].should == "image/gif"
+    Base64.encode64(last_response.body).strip.should == empty_gif
+  end
+
+  scenario "Invalid requests" do
+    get path_without_defaults
+    last_response.status.should == 400
+
+    get path_without_defaults(:token => token)
+    last_response.status.should == 400
+
+    get path_without_defaults(:token => token, :uri => "http://snowfinch.net/")
+    last_response.status.should == 400
+
+    get path_without_defaults(:token => token,
+                              :uuid => "c2f6b003-e7e3-4bac-b69d-8b3d54ebab62")
+    last_response.status.should == 400
+  end
+
+end

data/spec/snowfinch/collector_spec.rb

@@ -0,0 +1,76 @@
+require "spec_helper"
+
+describe Snowfinch::Collector do
+
+  describe ".db", :database => false do
+    context "default" do
+      it "returns a database 'snowfinch' with a default connection" do
+        connection = mock("Mongo::Connection")
+        database = mock("Mongo::Database")
+        Mongo::Connection.should_receive(:new).with(no_args).
+          and_return(connection)
+        connection.should_receive(:db).with("snowfinch").and_return(database)
+
+        Snowfinch::Collector.db.should == database
+      end
+
+      it "returns the same object accross calls" do
+        first_id  = Snowfinch::Collector.db.object_id
+        second_id = Snowfinch::Collector.db.object_id
+
+        first_id.should == second_id
+      end
+    end
+  end
+
+  describe ".db=", :database => false do
+    it "sets the Mongo::Database object to be used" do
+      database = Mongo::Connection.new.db("snowfinch")
+      Snowfinch::Collector.db = database
+      Snowfinch::Collector.db.should == database
+    end
+  end
+
+  describe ".sanitize_uri" do
+    it "turns https into http" do
+      original_uri = "https://snowfinch.net/posts"
+      expected_uri = "http://snowfinch.net/posts"
+      Snowfinch::Collector.sanitize_uri(original_uri).should == expected_uri
+    end
+
+    it "removes www." do
+      original_uri = "http://www.snowfinch.net/archive"
+      expected_uri = "http://snowfinch.net/archive"
+      Snowfinch::Collector.sanitize_uri(original_uri).should == expected_uri
+    end
+
+    it "removes a slash at the end of the path" do
+      original_uri = "http://snowfinch.net/archive/"
+      expected_uri = "http://snowfinch.net/archive"
+      Snowfinch::Collector.sanitize_uri(original_uri).should == expected_uri
+    end
+
+    it "removes the query part" do
+      original_uri = "http://snowfinch.net/?source=google"
+      expected_uri = "http://snowfinch.net/"
+      Snowfinch::Collector.sanitize_uri(original_uri).should == expected_uri
+    end
+
+    it "removes the fragment part" do
+      original_uri = "http://snowfinch.net/about#contact"
+      expected_uri = "http://snowfinch.net/about"
+      Snowfinch::Collector.sanitize_uri(original_uri).should == expected_uri
+    end
+  end
+
+  describe ".hash_uri" do
+    it "returns a SHA1 hash of the URI in base 62" do
+      uri = "http://snowfinch.net/about"
+      Snowfinch::Collector.hash_uri(uri).should == "jjvMHRNTpBvTWe5Nm0YIjHufcdA"
+
+      uri = "http://snowfinch.net/"
+      Snowfinch::Collector.hash_uri(uri).should == "acrfzPFTC4qJH0SLjgo4611dj2h"
+    end
+  end
+
+end

data/spec/spec_helper.rb

@@ -0,0 +1,27 @@
+require "bundler"
+Bundler.require(:test)
+
+require "snowfinch/collector"
+
+Dir[File.expand_path("../support/**/*.rb", __FILE__)].each { |f| require f }
+
+RSpec.configure do |config|
+  config.include Rack::Test::Methods
+
+  config.before(:each) do
+    Snowfinch::Collector.db = nil
+
+    unless example.metadata[:database] == false
+      Snowfinch::Collector.db = Mongo::Connection.new.db("snowfinch_test")
+      Snowfinch::Collector.db.collections.each do |collection|
+        collection.drop unless collection.name.match(/^system\./)
+      end
+
+      Snowfinch::Collector.db["sites"].insert({ "tz" => "Europe/Helsinki" })
+    end
+  end
+
+  config.after(:suite) do
+    Timecop.return
+  end
+end

data/spec/support/helpers.rb

@@ -0,0 +1,24 @@
+require "cgi"
+
+def app
+  Snowfinch::Collector
+end
+
+def path_without_defaults(parts={})
+  "/?" + parts.each.map { |k,v| k.to_s + "=" + CGI.escape(v) }.join("&")
+end
+
+def path(parts={})
+  parts[:token] ||= token
+  parts[:uri] ||= "http://snowfinch.net/"
+  parts[:uuid] ||= "8e41cb1f-72f1-4ed5-bb29-84151737cc0a"
+  path_without_defaults(parts)
+end
+
+def token
+  Snowfinch::Collector.db["sites"].find_one["_id"].to_s
+end
+
+def freeze_utc_time(*args)
+  Timecop.freeze(Time.utc(*args))
+end

data/spec/support/mongo_extensions.rb

@@ -0,0 +1,7 @@
+class Mongo::Collection
+
+  def last
+    find_one({}, { :sort => [:$natural, :desc] })
+  end
+
+end

metadata

@@ -0,0 +1,121 @@
+--- !ruby/object:Gem::Specification
+name: snowfinch-collector
+version: !ruby/object:Gem::Version
+  version: 0.5.0
+  prerelease: 
+platform: ruby
+authors:
+- Joao Carlos
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2011-05-05 00:00:00.000000000Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: mongo
+  requirement: &2158673220 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: *2158673220
+- !ruby/object:Gem::Dependency
+  name: bson_ext
+  requirement: &2158672800 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: *2158672800
+- !ruby/object:Gem::Dependency
+  name: rack
+  requirement: &2158672380 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: *2158672380
+- !ruby/object:Gem::Dependency
+  name: radix62
+  requirement: &2158671940 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: *2158671940
+- !ruby/object:Gem::Dependency
+  name: tzinfo
+  requirement: &2158671480 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: *2158671480
+description: Collector gem for snowfinch.
+email:
+- mail@joao-carlos.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- .rspec
+- Gemfile
+- README.md
+- Rakefile
+- lib/snowfinch/collector.rb
+- lib/snowfinch/collector/click.rb
+- lib/snowfinch/collector/version.rb
+- snowfinch-collector.gemspec
+- spec/acceptance/data_collection_spec.rb
+- spec/acceptance/response_spec.rb
+- spec/snowfinch/collector_spec.rb
+- spec/spec_helper.rb
+- spec/support/helpers.rb
+- spec/support/mongo_extensions.rb
+homepage: https://github.com/jcxplorer/snowfinch
+licenses: []
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: snowfinch-collector
+rubygems_version: 1.8.0
+signing_key: 
+specification_version: 3
+summary: Snowfinch collector
+test_files:
+- spec/acceptance/data_collection_spec.rb
+- spec/acceptance/response_spec.rb
+- spec/snowfinch/collector_spec.rb
+- spec/spec_helper.rb
+- spec/support/helpers.rb
+- spec/support/mongo_extensions.rb