tweetly 0.0.1

data/.gitignore

@@ -0,0 +1,19 @@
+*.gem
+*.rbc
+.bundle
+.config
+.yardoc
+Gemfile.lock
+InstalledFiles
+_yardoc
+coverage
+doc/
+lib/bundler/man
+pkg
+rdoc
+spec/reports
+test/tmp
+test/version_tmp
+tmp
+*.sublime-project
+*.sublime-workspace

data/.rspec

@@ -0,0 +1,2 @@
+--color
+--format progress

data/Gemfile

@@ -0,0 +1,4 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in tweetly.gemspec
+gemspec

data/LICENSE

@@ -0,0 +1,22 @@
+Copyright (c) 2012 Jico Baligod
+
+MIT License
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.md

@@ -0,0 +1,105 @@
+# Tweetly
+
+Generate nifty word frequency distributions from your Twitter statuses.
+
+Written and tested in __Ruby 1.9.3__.
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+    gem 'tweetly'
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install tweetly
+
+## Usage
+
+First, let's create a new user.
+
+```ruby
+require 'tweetly'
+user = Tweetly::User.new('jicooo')
+```
+
+Now we can print a word frequency distribution list from the last _tweets_ tweets and limit it to _count_ words like so:
+
+```ruby
+user.print_word_freq(tweets: 20, count: 5)
+```
+
+which prints:
+
+		for (5)
+		$10 (3)
+		@julioz2 (3)
+		my (3)
+		post: (2)
+
+By default, Tweetly pulls the last 1000 tweets from the user's timeline and displays the entire list of words.
+
+```ruby
+user.print_word_freq
+```
+
+which prints:
+
+		the (262)
+		to (179)
+		a (165)
+		@Sualehh (161)
+		my (112)
+		RT (107)
+		I (105)
+		of (100)
+		# and so on...
+
+Well, that's not a very interesting list. Let's ignore retweets as well as a few common words. Additionally, let's constrain our list to words of at least length 5, only word characters (i.e. letters, digits, underscores), and case insensitive:
+
+```ruby
+		options = {
+			include_rts: false, 
+			ignore: ['the', 'to', 'a', 'I'], 
+			min_length: 5, 
+			words_only: true, 
+			case_sensitive: false
+		}
+		user.print_word_freq(options)
+```
+
+The above prints out:
+
+		sualehh (206)
+		foursquare (31)
+		julioz2 (30)
+		mlacitation (24)
+		compywiz (24)
+		right (21)
+		think (20)
+		pretty (20)
+
+Awesome! That's a great looking list.
+
+If you strictly want the words and not the frequency counts printed, you can pass in the option `print_count: false`. For the above, we would just have
+
+		sualehh
+		foursquare
+		julioz2
+		mlacitation
+		compywiz
+		right
+		think
+		pretty
+
+## Contributing
+
+1. Fork it
+2. Create your feature branch (`git checkout -b my-new-feature`)
+3. Commit your changes (`git commit -am 'Added some feature'`)
+4. Push to the branch (`git push origin my-new-feature`)
+5. Create new Pull Request

data/Rakefile

@@ -0,0 +1,2 @@
+#!/usr/bin/env rake
+require "bundler/gem_tasks"

data/lib/tweetly.rb

@@ -0,0 +1,7 @@
+require "tweetly/version"
+require "twitter"
+require "tweetly/user"
+
+module Tweetly
+  # Your code goes here...
+end

data/lib/tweetly/user.rb

@@ -0,0 +1,142 @@
+module Tweetly
+	
+	class User
+		attr_accessor :name, :screen_name, :protected, :statuses_count, :timeline
+
+		def initialize(name)
+			user = Twitter.user(name)
+			unless user.protected?
+				@name = user.name
+				@screen_name = user.screen_name
+				@protected = user.protected?
+				@statuses_count = user.statuses_count
+				@timeline = []
+			end
+		end
+
+		# Builds a word frequency array from recent tweets.
+		#
+		# @param [Hash] options frequency distribution options
+		# @option [Integer] :tweets number of tweets to consider (max 3200)
+		# @option [Boolean] :words_only consider only word characers 
+		# 	i.e. (letters, symbols, underscores)
+		# @option [Boolean] :case_sensitive whether to consider word case
+		# @option [Boolean] :include_rts whether to consider retweeted statuses
+		# @option [Array<String>] :ignore list of words to ignore
+		# @return [Array<Array<String, Integer>>] list of word frequencies in descending order
+		def word_freq(options={})
+			# Default parameters
+			params = {
+				tweets: 1000,
+				words_only: false,
+				case_sensitive: true,
+				include_rts: true,
+				min_length: nil,
+				ignore: []
+			}
+			params.merge!(options)
+
+			# Fetch Tweets if necessary
+			fetch_timeline(params[:tweets]) if @timeline.count < params[:tweets]
+
+			freqDist = {}
+
+			@timeline.each_with_index do |tweet, i|
+				# :include_rts option
+				next if !params[:include_rts] && tweet.retweeted_status
+
+				tweet.text.split.each do |word|
+					# :ignore option
+					next if params[:ignore].include? word
+
+					# :case_sensitive option
+					word.downcase! if !params[:case_sensitive]
+
+					# :words_only option
+					if params[:words_only]
+						word = word.match(/\w+/)
+						next unless word
+						word = word[0]
+					end
+
+					# :min_length option
+					next if params[:min_length] && word.length < params[:min_length]
+
+					if freqDist.has_key? word
+						freqDist[word] += 1
+					else
+						freqDist[word] = 1
+					end
+				end
+
+				break if i == params[:tweets]
+			end
+			freqDist.sort_by { |k,v| -v }
+		end
+
+		# Prints word frequency distribution list.
+		#
+		# @param [Hash] options printing options
+		# @option [Integer] :tweets number of tweets to consider (default: 100, max: 3200)
+		# @option [Integer] :count prints top count of frequency distribution list
+		# @option [Boolean] :print_count whether to print count next to each word
+		def print_word_freq(options={})
+			opts = {
+				tweets: 1000,
+				print_count: true
+			}
+			opts.merge!(options)
+			dist = word_freq(opts)
+			opts[:count] ||= dist.count
+			dist[0,opts[:count]].each do |k,v| 
+				line = "#{k}"
+				line += " (#{v})" if opts[:print_count]
+				puts line
+			end
+			return
+		end
+
+		# Fetches user timeline and caches it in the @timeline field.
+		#
+		# @todo Duplicate tweets due to max_id
+		#
+		# @param [Integer] count the number of Tweets to fetch
+		# @return [Boolean] Success or failure (amount already cached)
+		def fetch_timeline(count=1000)
+			# Twitter API limits to 3200 tweets
+			count = [count, 3200].min
+
+			if @timeline.count < count
+				opts = { 
+					trim_user: 1,
+					include_rts: 1
+				}
+
+				while @timeline.length < count
+					# Fetch only what we don't have
+					opts[:max_id] = @timeline.last.id unless @timeline.empty?
+
+					# Max step count is 200 by API
+					# We may need less depending on what's already fetched
+					opts[:count] = [200, count - @timeline.count].min
+
+					# Fetch an extra since max_id is included
+					opts[:count] += 1 if opts[:max_id]
+
+					resp = Twitter.user_timeline(@screen_name, opts)
+
+					# Avoid reinserting max_id tweet
+					resp.delete_at(0) if opts[:max_id]
+
+					resp.each { |tweet| @timeline << tweet }
+				end
+
+				return true
+			else
+				# We've pulled this amount or more already
+				return false
+			end
+		end
+
+	end
+end

data/lib/tweetly/version.rb

@@ -0,0 +1,3 @@
+module Tweetly
+  VERSION = "0.0.1"
+end

data/spec/spec_helper.rb

@@ -0,0 +1,14 @@
+# This file was generated by the `rspec --init` command. Conventionally, all
+# specs live under a `spec` directory, which RSpec adds to the `$LOAD_PATH`.
+# Require this file using `require "spec_helper.rb"` to ensure that it is only
+# loaded once.
+#
+# See http://rubydoc.info/gems/rspec-core/RSpec/Core/Configuration
+
+require_relative "../lib/tweetly"
+
+RSpec.configure do |config|
+  config.treat_symbols_as_metadata_keys_with_true_values = true
+  config.run_all_when_everything_filtered = true
+  config.filter_run :focus
+end

data/spec/user_spec.rb

@@ -0,0 +1,50 @@
+require 'spec_helper'
+
+describe Tweetly::User do
+	context "Initializing a new user" do
+		before do
+			@user = Tweetly::User.new('jicooo')
+		end
+
+		it "should be created successfully" do
+      @user.should be_an_instance_of Tweetly::User
+    end
+	end
+
+	context "Fetching a user timeline" do
+		before do
+			@user = Tweetly::User.new('jicooo')
+		end
+
+		it "should fetch 1000 tweets by default" do
+			@user.fetch_timeline
+			@user.timeline.count.should == 1000
+		end
+
+		it "should be able to fetch less than 1000" do
+			@user.fetch_timeline(10)
+			@user.timeline.count.should == 10
+		end
+
+		it "should be able to fetch more than 1000" do
+			@user.fetch_timeline(1001)
+			@user.timeline.count.should == 1001
+		end
+
+		it "should not fetch duplicate tweets" do
+			seen = {}
+			duplicate = false
+			@user.timeline.each do |t|
+				if seen.has_key? t.id
+					duplicate = true
+					break
+				else
+					seen[t.id] = 1
+				end
+			end 
+			duplicate.should be_false
+		end
+	end
+
+
+end

data/tweetly.gemspec

@@ -0,0 +1,22 @@
+# -*- encoding: utf-8 -*-
+require File.expand_path('../lib/tweetly/version', __FILE__)
+
+Gem::Specification.new do |gem|
+  gem.authors       = ["Jico Baligod"]
+  gem.email         = ["jico@baligod.com"]
+  gem.description   = %q{Twitter user timeline stats.}
+  gem.summary       = %q{Generate word frequency distributions from your Twitter statuses.}
+  gem.homepage      = "https://github.com/jico/tweetly"
+
+  gem.executables   = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
+  gem.files         = `git ls-files`.split("\n")
+  gem.test_files    = `git ls-files -- {test,spec,features}/*`.split("\n")
+  gem.name          = "tweetly"
+  gem.require_paths = ["lib"]
+  gem.version       = Tweetly::VERSION
+
+  gem.add_development_dependency "rake"
+  gem.add_development_dependency "rspec", "~> 2.9.0"
+
+  gem.add_dependency "twitter"
+end

metadata

@@ -0,0 +1,98 @@
+--- !ruby/object:Gem::Specification
+name: tweetly
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+  prerelease: 
+platform: ruby
+authors:
+- Jico Baligod
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2012-05-15 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: &70128994114340 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: *70128994114340
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: &70128994113540 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 2.9.0
+  type: :development
+  prerelease: false
+  version_requirements: *70128994113540
+- !ruby/object:Gem::Dependency
+  name: twitter
+  requirement: &70128994113060 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: *70128994113060
+description: Twitter user timeline stats.
+email:
+- jico@baligod.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- .rspec
+- Gemfile
+- LICENSE
+- README.md
+- Rakefile
+- lib/tweetly.rb
+- lib/tweetly/user.rb
+- lib/tweetly/version.rb
+- spec/spec_helper.rb
+- spec/user_spec.rb
+- tweetly.gemspec
+homepage: https://github.com/jico/tweetly
+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'
+      segments:
+      - 0
+      hash: -4256241259014341675
+required_rubygems_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+      segments:
+      - 0
+      hash: -4256241259014341675
+requirements: []
+rubyforge_project: 
+rubygems_version: 1.8.17
+signing_key: 
+specification_version: 3
+summary: Generate word frequency distributions from your Twitter statuses.
+test_files:
+- spec/spec_helper.rb
+- spec/user_spec.rb