iconoclasm 1.0.0

data/.document

@@ -0,0 +1,5 @@
+README.rdoc
+lib/**/*.rb
+bin/*
+features/**/*.feature
+LICENSE

data/.gitignore

@@ -0,0 +1,22 @@
+## MAC OS
+.DS_Store
+
+## TEXTMATE
+*.tmproj
+tmtags
+
+## EMACS
+*~
+\#*
+.\#*
+
+## VIM
+*.swp
+
+## PROJECT::GENERAL
+coverage
+rdoc
+pkg
+
+## PROJECT::SPECIFIC
+*.gemspec

data/LICENSE

@@ -0,0 +1,20 @@
+Copyright (c) 2009 Sander Hartlage
+
+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.markdown

@@ -0,0 +1,24 @@
+# iconoclasm
+
+Finds favorites icons for web pages on the world wide internets by checking the HTML head or the standard favicon location. Then, do with them what you will.
+
+Called "iconoclasm" because there was already a gem on gemcutter called "iconoclast". Boo! Hiss!
+
+### Usage
+
+To get the favicon for a page, do:
+
+`favicon = Iconoclasm.extract('www.website.com')`
+
+This will go and do a bunch of GETs (two or three, actually) on the url given. If you've already got the content and want to skip one of the GETs, you can pass the content in as the second argument.
+
+`content = get_some_content('www.website.com')`<br/>
+`favicon = Iconoclasm.extract('www.website.com', content)`
+
+`Iconoclasm.extract` returns an `Iconoclasm::Favicon` instance, from which you can get the URL, content type, size, or access the binary image data. By calling `valid?`, you can check if the favicon is valid based on whatever my standards were when I wrote this (basically, whether or not it's actually an image).
+
+You can save the image to a tempfile using `favicon.save`, or more usefully, to a file at `favicon.save('path/to/file')`. Fun times had by all.
+
+## Copyright
+
+Copyright (c) 2009 Sander Hartlage. See LICENSE for details.

data/Rakefile

@@ -0,0 +1,52 @@
+require 'rubygems'
+require 'rake'
+
+begin
+  require 'jeweler'
+  Jeweler::Tasks.new do |gem|
+    gem.name = "iconoclasm"
+    gem.summary = %Q{Finds favicons and DESTROYS THEM (well, not really, but it will download and save them)}
+    gem.description = %Q{Finds favorites icons for web pages on the world wide internets by checking the HTML head or the standard favicon location. Then, do with them what you will.}
+    gem.email = "sander.hartlage@gmail.com"
+    gem.homepage = "http://github.com/sander6/iconoclasm"
+    gem.authors = ["Sander Hartlage"]
+    # gem is a Gem::Specification... see http://www.rubygems.org/read/chapter/20 for additional settings
+  end
+  Jeweler::GemcutterTasks.new
+rescue LoadError
+  puts "Jeweler (or a dependency) not available. Install it with: gem install jeweler"
+end
+
+require 'rake/testtask'
+Rake::TestTask.new(:test) do |test|
+  test.libs << 'lib' << 'test'
+  test.pattern = 'test/**/test_*.rb'
+  test.verbose = true
+end
+
+begin
+  require 'rcov/rcovtask'
+  Rcov::RcovTask.new do |test|
+    test.libs << 'test'
+    test.pattern = 'test/**/test_*.rb'
+    test.verbose = true
+  end
+rescue LoadError
+  task :rcov do
+    abort "RCov is not available. In order to run rcov, you must: sudo gem install spicycode-rcov"
+  end
+end
+
+task :test => :check_dependencies
+
+task :default => :test
+
+require 'rake/rdoctask'
+Rake::RDocTask.new do |rdoc|
+  version = File.exist?('VERSION') ? File.read('VERSION') : ""
+
+  rdoc.rdoc_dir = 'rdoc'
+  rdoc.title = "iconoclast #{version}"
+  rdoc.rdoc_files.include('README*')
+  rdoc.rdoc_files.include('lib/**/*.rb')
+end

data/VERSION

@@ -0,0 +1 @@
+1.0.0

data/lib/iconoclasm/downloader.rb

@@ -0,0 +1,30 @@
+require 'curl'
+
+module Iconoclasm
+  module Downloader
+
+    @@user_agent = 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'
+    
+    def self.user_agent=(agent)
+      @@user_agent = agent
+    end
+    
+    def self.user_agent
+      @@user_agent
+    end
+    
+    def get(url)
+      Curl::Easy.http_get(url) do |curl|
+        curl.headers['User-Agent']  = Iconoclasm::Downloader.user_agent
+        curl.follow_location        = true
+      end
+    end
+    
+    def head(url)
+      Curl::Easy.http_head(url) do |curl|
+        curl.headers['User-Agent']  = Iconoclasm::Downloader.user_agent
+      end
+    end
+    
+  end
+end

data/lib/iconoclasm/errors.rb

@@ -0,0 +1,61 @@
+module Iconoclasm
+
+  class Error < StandardError
+    def initialize(url)
+      @url = url
+    end
+  end
+
+  class MissingFavicon < Iconoclasm::Error
+    def message
+      "#{@url} doesn't seem to have a favicon"
+    end
+  end
+  
+  class HTTPError < Iconoclasm::Error
+    def initialize(url, response)
+      super(url)
+      @response = response
+    end
+    
+    def message
+      msg = ""
+      msg += "There was a problem getting #{@url} " if @url
+      msg += "(#{http_error_reason})"
+      msg
+    end
+
+    def code
+      @response.respond_to?(:response_code) ? @response.response_code : @response[/\d{3}/]
+    end
+
+    def http_error_reason
+      @response.respond_to?(:header_str) ? @response.header_str[/(?<=\d{3}\s)(.*)$/].chomp : @response
+    end    
+
+    def http_error_message
+      "#{@code}: #{http_error_reason}"
+    end    
+  end
+  
+  class RTFMError < Iconoclasm::Error
+    def initialize(reason)
+      @reason = reason
+    end
+    
+    def message
+      "Iconoclasm doesn't work that way (#{@reason})"
+    end
+  end
+  
+  class InvalidFavicon < Iconoclasm::Error
+    def initialize(url, content_type)
+      super(url)
+      @content_type = content_type
+    end
+    
+    def message
+      "The favicon from #{@url} is invalid (content type is #{@content_type})"
+    end
+  end
+end

data/lib/iconoclasm/extractor.rb

@@ -0,0 +1,82 @@
+require 'nokogiri'
+require 'uri'
+
+module Iconoclasm
+  module Extractor
+    
+    def self.included(base)
+      base.class_eval { include Iconoclasm::Downloader }
+    end
+    
+    def extract_favicon_from(url, content = nil)
+      catch(:done) do
+        base_url  = base_url_of(url)
+        extract_favicon_from_head_of(base_url, content)
+        extract_favicon_from_naive_guess(base_url)
+        raise Iconoclasm::MissingFavicon.new(base_url)
+      end
+    end
+    
+    private
+    
+    def extract_favicon_from_head_of(base_url, content = nil)
+      if document = document_from(base_url, content)
+        favicon_links = find_favicon_links_in(document)
+        throw(:done, {
+          :url          => href_of(favicon_links.first),
+          :content_type => type_of(favicon_links.first)
+        }) unless favicon_links.empty?
+      end
+    end
+
+    def document_from(base_url, content = nil)
+      if content
+        Nokogiri::XML(content)
+      else
+        response = get(base_url)
+        Nokogiri::XML(response.body_str) if response.response_code == 200
+      end
+    end
+    
+    def extract_favicon_from_naive_guess(base_url)
+      naive_url = "#{base_url}/favicon.ico"
+      response  = get(naive_url)
+      headers   = Iconoclasm::Headers.new(response.header_str)
+      if response.response_code == 200
+        throw(:done, {
+          :url            => naive_url,
+          :content_length => header.content_length,
+          :content_type   => headers.content_type,
+          :data           => response.body_str
+        })
+      end
+    end
+    
+    def find_favicon_links_in(document)
+      document.xpath('//link[favicon_link(.)]', Class.new {
+        def favicon_link(node_set)
+          node_set.find_all { |node| node['rel'] && node['rel'] =~ /^(?:shortcut\s)?icon$/i }
+        end
+      }.new)
+    end
+    
+    def base_url_of(url)
+      uri = URI.parse(url)
+      "#{uri.scheme}://#{uri.host}"
+    end
+    
+    def href_of(node)
+      href = normal_node_attributes(node)['href']
+      href.value if href
+    end
+    
+    def type_of(node)
+      type = normal_node_attributes(node)['type']
+      type.value if type
+    end
+    
+    def normal_node_attributes(node)
+      node.attributes.inject({}) { |hash, (key, value)| hash.merge(key.downcase => value) }
+    end
+  end
+end

data/lib/iconoclasm/favicon.rb

@@ -0,0 +1,104 @@
+require 'tempfile'
+require 'mime/types'
+require 'uri'
+
+module Iconoclasm
+  class Favicon
+    include Iconoclasm::Downloader
+    
+    attr_reader :content_type, :url, :save_path
+    attr_accessor :name
+
+    def initialize(attributes = {})
+      @url          = attributes[:url]
+      @data         = attributes[:data]
+      @name         = attributes[:name]           || parse_name_from(@url)
+      headers       = attributes[:headers]
+      @content_type = attributes[:content_type]   || headers ? headers.content_type : nil
+      @size         = attributes[:content_length] || headers ? headers.content_length : nil
+      @save_path    = nil
+    end
+    
+    def inspect
+      "#<Iconoclasm::Favicon @url=#{url}, @name=#{name}, @content_type=#{content_type}, @size=#{size}, @save_path=#{save_path ? save_path : "nil"}>"
+    end
+    
+    def size
+      @size ||= data.size
+    end
+    alias_method :content_length, :size
+    
+    def data
+      @data ||= fetch_data
+    end
+    
+    def content_type
+      if @content_type
+        @content_type
+      else
+        mime = MIME::Types.of(name).first
+        @content_type = mime.content_type if mime
+      end
+    end
+    
+    def valid?
+      @valid ||= if size > 0
+        case content_type
+        when /^(?:x-)?image/ then true
+        when /^text\/html/ then false
+        when NilClass then false
+        else
+          # check the file type using filemagic, maybe?
+          false
+        end
+      else
+        false
+      end
+    end
+    
+    def fetch_data
+      response = get(url)
+      if response.response_code == 200
+        response.body_str
+      else
+        raise Iconoclasm::HTTPError.new(url, response)
+      end
+    end
+    
+    def save(path_or_storage = nil, force = false)
+      if valid? && !force
+        warn("Saving an invalid favicon.") if !valid? && force
+        @save_path = if path_or_storage.nil?
+          save_to_tempfile
+        elsif path_or_storage.is_a?(String)
+          save_to_file(path_or_storage)
+        else
+          raise Iconoclasm::RTFMError.new("invalid storage type")
+        end
+      else
+        raise Iconoclasm::InvalidFavicon.new(url, content_type)
+      end
+    end
+    
+    def save_to_tempfile
+      tfile = dump_data(Tempfile.new(name))
+      @save_path = tfile.path
+    end
+
+    def save_to_file(path)
+      path = File.expand_path(File.join(path, name))
+      dump_data(File.new(path, File::CREAT|File::TRUNC|File::WRONLY))
+      @save_path = path
+    end
+    
+    def parse_name_from(url)
+      URI.parse(url).path.split('/').last
+    end
+    
+    def dump_data(file)
+      file.write(data)
+      file.close
+      file
+    end
+  end
+end

data/lib/iconoclasm/headers.rb

@@ -0,0 +1,59 @@
+module Iconoclasm
+  class Headers
+
+    attr_reader :version, :code, :message
+    
+    def initialize(header_string)
+      parse_http_response(header_string.lines.first.chomp)
+      @header_hash    = parse_header_string(header_string)
+    end
+    
+    def [](header)
+      @header_hash[convert_header_key(header.to_s)]
+    end
+    
+    def content_type
+      @content_type ||= self['content_type']
+    end
+    alias_method :type, :content_type
+    
+    def content_length
+      @content_length ||= self['content_length']
+    end
+    alias_method :length, :content_length
+    
+    def location
+      @location ||= self['location']
+    end
+    
+    private
+    
+    def parse_header_string(header_string)
+      header_string.scan(/^([^:]+):(.*)$/).inject({}) do |hash, (key, value)|
+        hash.merge(convert_header_key(key) => convert_header_value(value))
+      end
+    end
+    
+    def convert_header_key(key)
+      key.gsub(/-/, '_').downcase
+    end
+    
+    def convert_header_value(value)
+      if value =~ /^\s*\d+\s*$/
+        value.to_i
+      else
+        value.strip
+      end
+    end
+    
+    def parse_http_response(response)
+      if response.match(/HTTP\/(\d\.\d)\s*(\d{3})\s*(.*)/)
+        @version  = $1
+        @code     = $2.to_i
+        @message  = $3.strip
+      else
+        raise Iconoclasm::HTTPError.new(nil, response)
+      end
+    end
+  end
+end

data/lib/iconoclasm.rb

@@ -0,0 +1,18 @@
+$:.unshift(File.dirname(__FILE__))
+require 'iconoclasm/downloader'
+require 'iconoclasm/errors'
+require 'iconoclasm/extractor'
+require 'iconoclasm/favicon'
+require 'iconoclasm/headers'
+
+module Iconoclasm
+  
+  class << self
+    include Iconoclasm::Extractor
+    
+    def extract(url, content = nil)
+      Iconoclasm::Favicon.new(extract_favicon_from(url, content))
+    end
+  end
+  
+end

data/spec/helper.rb

@@ -0,0 +1,34 @@
+require 'rubygems'
+require 'spec'
+require 'mocha'
+
+$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
+$LOAD_PATH.unshift(File.dirname(__FILE__))
+require 'iconoclasm'
+
+Spec::Runner.configure do |config|
+  config.mock_with :mocha
+end
+
+# It bothers me that mocha doesn't have this built-in.
+# It also bothers me that I forked mocha but didn't add this.
+# We are all at fault.
+module Mocha
+  class Expectation
+    def throws(symbol, object = nil)
+      @return_values += ReturnValues.new(SymbolThrower.new(symbol, object))
+      self
+    end
+  end
+  
+  class SymbolThrower
+    def initialize(symbol, object)
+      @symbol = symbol
+      @object = object
+    end
+    
+    def evaluate
+      @object ? throw(@symbol, @object) : throw(@symbol)
+    end
+  end
+end

data/spec/iconoclasm/downloader_spec.rb

@@ -0,0 +1,49 @@
+require File.expand_path(File.dirname(__FILE__) + '/../helper')
+
+describe Iconoclasm::Downloader do
+
+  before do
+    class Thing; include Iconoclasm::Downloader; end
+    @thing  = Thing.new
+    @url    = 'http://www.website.com'
+    @curl   = mock('curl')
+  end
+  
+  describe "GETting a url" do
+    it "should GET the url using curl easy" do
+      Curl::Easy.expects(:http_get).with(@url)
+      @thing.get(@url)
+    end
+    
+    it "should set the user agent to the default user agent" do
+      @curl.stubs(:follow_location=)
+      headers = mock('headers')
+      Curl::Easy.stubs(:http_get).yields(@curl)
+      @curl.expects(:headers).returns(headers)
+      headers.expects(:[]=).with('User-Agent', Iconoclasm::Downloader.user_agent)
+      @thing.get(@url)
+    end
+    
+    it "should follow redirects" do
+      @curl.stubs(:headers).returns({})
+      Curl::Easy.stubs(:http_get).yields(@curl)
+      @curl.expects(:follow_location=).with(true)
+      @thing.get(@url)
+    end
+  end
+  
+  describe "HEADing a url" do
+    it "should HEAD the url using curl easy" do
+      Curl::Easy.expects(:http_head).with(@url)
+      @thing.head(@url)
+    end
+    
+    it "should set the user agent to the default user agent" do
+      headers = mock('headers')
+      Curl::Easy.stubs(:http_head).yields(@curl)
+      @curl.expects(:headers).returns(headers)
+      headers.expects(:[]=).with('User-Agent', Iconoclasm::Downloader.user_agent)
+      @thing.head(@url)
+    end
+  end
+end

data/spec/iconoclasm/errors_spec.rb

@@ -0,0 +1,5 @@
+require File.expand_path(File.dirname(__FILE__) + '/../helper')
+
+describe "Errors" do
+  
+end

data/spec/iconoclasm/extractor_spec.rb

@@ -0,0 +1,121 @@
+require File.expand_path(File.dirname(__FILE__) + '/../helper')
+
+describe Iconoclasm::Extractor do
+  
+  before do
+    class Thing; include Iconoclasm::Extractor; end
+    @thing = Thing.new
+  end
+  
+  describe "requiring the module" do
+    it "should also require the Downloader module" do
+      Thing.included_modules.should include(Iconoclasm::Downloader)
+    end
+  end
+  
+  describe "extracting a favicon from a url" do
+    before do
+      @url      = "http://www.website.com/page.html"
+      @base_url = "http://www.website.com"
+    end
+    
+    it "should try to find the favicon path in the head of the content" do
+      @thing.expects(:extract_favicon_from_head_of).with(@base_url, nil).throws(:done)
+      @thing.extract_favicon_from(@url)
+    end
+    
+    describe "when the favicon path isn't in the head of the content" do
+      before do
+        @thing.stubs(:extract_favicon_from_head_of)
+      end
+      
+      it "should naively guess where the favicon is" do
+        @thing.expects(:extract_favicon_from_naive_guess).with(@base_url).throws(:done)
+        @thing.extract_favicon_from(@url)
+      end
+    end
+    
+    describe "when the favicon isn't mentioned in the content or in the default place" do
+      before do
+        @thing.stubs(:extract_favicon_from_head_of)
+        @thing.stubs(:extract_favicon_from_naive_guess)
+      end
+      
+      it "should raise an error" do
+        lambda { @thing.extract_favicon_from(@url) }.should raise_error(Iconoclasm::MissingFavicon)
+      end
+    end
+  end
+  
+  describe "extracting a favicon from the head of some HTML content" do
+    before do
+      # stubbing this to make sure we're not calling it accidentally without
+      # having to deal with expectations within a catch/throw pile
+      @thing.stubs(:extract_favicon_from_naive_guess)
+      @url      = "http://www.website.com/page.html"
+      @base_url = "http://www.website.com"
+      @content = <<-HTML
+        <html>
+          <head>
+            <link rel="stylesheet" type="text/css" href="/stylesuponstyles.css" />
+            <link rel="shortcut icon" type="image/vnd.microsoft.icon" href="/images/favicon.ico" />
+          </head>
+          <body>
+            <p>This is the most interesting website ever.</p>
+          </body>
+        </html>
+      HTML
+    end
+    
+    describe "when content isn't already provided" do
+      before do
+        @response = mock('http response', :response_code => 200, :body_str => "")
+      end
+      
+      it "should go get the content" do
+        @thing.expects(:get).returns(@response)
+        catch(:done) { @thing.__send__(:extract_favicon_from_head_of, @url) }
+      end
+    end
+
+    describe "when content is provided" do
+      describe "when there are no favicon links in the HTML content" do
+        before do
+          @thing.stubs(:find_favicon_links_in).returns([])
+        end
+        
+        it "should return nil" do
+          catch(:done) { @thing.__send__(:extract_favicon_from_head_of, @url, @content) }.should be_nil     
+        end
+      end
+      
+      describe "when there are some favicon links in the HTML content" do
+        before do
+          @link   = stub('favicon link')
+          @links  = stub('favicon links', :empty? => false, :first => @link)
+          @thing.stubs(:find_favicon_links_in).returns(@links)
+        end
+        
+        describe "the return value" do
+          before do
+            @href = 'http://www.website.com/images/favicon.ico'
+            @type = 'image/vnd.microsoft.icon'
+            @thing.expects(:href_of).with(@link).returns(@href)
+            @thing.expects(:type_of).with(@link).returns(@type)
+            @hash = catch(:done) { @thing.__send__(:extract_favicon_from_head_of, @url, @content) } 
+          end
+
+          it "should contain the href from the first link" do
+            @hash.should have_key(:url)
+            @hash[:url].should == @href
+          end
+          
+          it "should contain the content type from the first link" do
+            @hash.should have_key(:content_type)
+            @hash[:content_type].should == @type
+          end
+        end
+      end
+    end
+  end
+end

data/spec/iconoclasm/favicon_spec.rb

@@ -0,0 +1,304 @@
+require File.expand_path(File.dirname(__FILE__) + '/../helper')
+
+describe Iconoclasm::Favicon do
+
+  before do
+    @size       = 100
+    @headers    = stub('headers', :content_type => 'image/vnd.microsoft.icon', :content_length => @size)
+    @name       = 'favicon.ico'
+    @url        = "http://www.website.com/#{@name}"
+    @attributes = {
+      :url      => @url,
+      :headers  => @headers
+    }
+  end
+  
+  describe "initialization" do
+    before do
+      @favicon = Iconoclasm::Favicon.new(@attributes)
+    end
+    
+    it "should set the content type to the content type supplied in the headers" do
+      @favicon.content_type.should == @headers.content_type
+    end
+    
+    it "should set the size to the content length supplied in the headers" do
+      @favicon.size.should == @headers.content_length
+    end
+    
+    it "should parse the name from the url supplied in the headers" do
+      @favicon.name.should == @name
+    end
+    
+    it "should not have a save path" do
+      @favicon.save_path.should be_nil
+    end    
+  end
+  
+  describe "accessing the data attribute" do
+    before do
+      @data = "THIS IS TOTALLY SOME IMAGE DATA!"
+    end
+    
+    describe "when the data was supplied on intialization" do
+      before do
+        @favicon = Iconoclasm::Favicon.new(@attributes.merge({:data => @data}))
+      end
+      
+      it "should return the supplied data" do
+        @favicon.data.should == @data
+      end
+    
+      it "should not try to fetch the data from the internets" do
+        @favicon.expects(:fetch_data).never
+        @favicon.data
+      end    
+    end
+    
+    describe "when data was not supplied on initialization" do
+      before do
+        @favicon = Iconoclasm::Favicon.new(@attributes.merge({:data => nil}))
+      end
+      
+      it "should fetch the data from the internets and return it" do
+        @favicon.expects(:fetch_data).returns(@data)
+        @favicon.data.should == @data
+      end
+      
+      it "should not fetch the data from the internets on subsequent calls" do
+        @favicon.expects(:fetch_data).once.returns(@data)
+        @favicon.data
+        @favicon.data
+      end
+    end
+  end
+  
+  describe "accessing the size attribute" do
+    before do
+      @data = "THIS IS SOME DATA!"
+      @size = 100
+    end
+    
+    describe "when the size was supplied on initialization" do
+      before do
+        @favicon = Iconoclasm::Favicon.new(@attributes.merge({:data => @data, :content_length => @size}))
+      end
+      
+      it "should return the supplied size" do
+        @favicon.size.should == @size
+      end
+      
+      it "should not check the length of the data" do
+        @favicon.data.expects(:size).never
+        @favicon.size
+      end
+    end
+    
+    describe "when the size was not supplied on initialization" do
+      before do
+        @headers.stubs(:content_length).returns(nil)
+        @favicon = Iconoclasm::Favicon.new(@attributes.merge({:data => @data, :content_length => nil}))
+        @favicon.instance_variable_get(:@size).should be_nil
+      end
+      
+      it "should return the size of the data" do
+        @favicon.size.should == @data.size
+      end      
+    end
+  end
+  
+  describe "accessing the content type attribute" do
+    before do
+      @content_type = 'image/vnd.microsoft.icon'
+    end
+    
+    describe "when the content type was supplied on initialization" do
+      before do
+        @favicon = Iconoclasm::Favicon.new(@attributes.merge({:content_type => @content_type}))
+      end
+      
+      it "should return the supplied content_type" do
+        @favicon.content_type.should == @content_type
+      end
+      
+      it "should not try to check it" do
+        ::MIME::Types.expects(:of).never
+        @favicon.content_type
+      end
+    end
+    
+    describe "when the content type was not supplied on initialization" do
+      before do
+        @headers.stubs(:content_type).returns(nil)
+        @favicon  = Iconoclasm::Favicon.new(@attributes.merge({:content_type => nil}))
+        @mime     = mock('mime type', :content_type => @content_type)
+      end
+      
+      it "should check the content type of the file name using the mime types library and return the first" do
+        ::MIME::Types.expects(:of).with(@favicon.name).returns([@mime])
+        @favicon.content_type.should == @content_type
+      end
+    end
+  end
+  
+  describe "fetching the image data" do
+    before do
+      @favicon  = Iconoclasm::Favicon.new(@attributes)
+      @response = mock('http response')
+    end
+    
+    it "should request the icon image" do
+      @favicon.expects(:get).returns(@response)
+      @response.stubs(:response_code => 200, :body_str => "IMAGE DATA!")
+      @favicon.fetch_data      
+    end
+    
+    describe "when the HTTP request is successsful" do
+      before do
+        @favicon.stubs(:get).returns(@response)
+        @data = "THIS IS ALSO TOTALLY SOME IMAGE DATA HAR HAR HAR!"
+        @response.expects(:response_code).returns(200)
+      end
+      
+      it "should return the content of the request (the binary image data)" do
+        @response.expects(:body_str).returns(@data)
+        @favicon.fetch_data.should == @data
+      end
+    end
+    
+    describe "when the HTTP request is not successful" do
+      before do
+        @favicon.stubs(:get).returns(@response)
+        @response.expects(:response_code).returns(400)
+      end
+      
+      it "should raise an HTTP error" do
+        lambda { @favicon.fetch_data }.should raise_error(Iconoclasm::HTTPError)
+      end
+    end
+  end
+  
+  describe "determining the validity of the favicon" do
+    before do
+      @favicon = Iconoclasm::Favicon.new(@attributes.merge({:data => "IMAGE DATA!"}))
+    end
+    
+    describe "when the content is zero-length" do
+      before do
+        @favicon.stubs(:size).returns(0)
+      end
+      
+      it "should not be valid" do
+        @favicon.should_not be_valid
+      end
+    end
+    
+    describe "when the content type is a image" do
+      before do
+        @favicon.stubs(:content_type).returns('image/png')
+      end
+      
+      it "should be valid" do
+        @favicon.should be_valid
+      end
+    end
+    
+    describe "when the content type is HTML" do
+      before do
+        # This will happen when some jerkface puts a webpage where the favicon
+        # should be. People on the internet are the worst.
+        @favicon.stubs(:content_type).returns('text/html')
+      end
+      
+      it "should not be valid" do
+        @favicon.should_not be_valid
+      end
+    end
+    
+    describe "when the content type is nil" do
+      before do
+        @favicon.stubs(:content_type).returns(nil)
+      end
+      
+      it "should not be valid" do
+        @favicon.should_not be_valid
+      end
+    end
+    
+    describe "when the content type is something else" do
+      before do
+        @favicon.stubs(:content_type).returns('something/else')
+        # eventually, maybe, I'll try harder to see if it's a valid image of some sort.
+      end
+      
+      it "should not be valid" do
+        @favicon.should_not be_valid
+      end
+    end
+  end
+  
+  describe "saving the favicon" do
+    before do
+      @favicon = Iconoclasm::Favicon.new(@attributes.merge({:data => "IMAGE DATA!"}))
+    end
+    
+    describe "to a tempfile" do
+      before do
+        @path = '/tmp/favicon.ico'
+        @tempfile = stub('tempfile!', :path => @path)
+      end
+      
+      it "should happen when there are no arguments to save" do
+        @favicon.expects(:save_to_tempfile)
+        @favicon.save
+      end
+      
+      it "should dump its data to a tempfile named after the favicon" do
+        Tempfile.expects(:new).with(@favicon.name).returns(@tempfile)
+        @favicon.expects(:dump_data).with(@tempfile).returns(@tempfile)
+        @favicon.save_to_tempfile
+      end
+      
+      it "should set the save_path to the path to the tempfile" do
+        Tempfile.stubs(:new).returns(@tempfile)
+        @favicon.stubs(:dump_data).returns(@tempfile)
+        @favicon.save
+        @favicon.save_path.should == @path
+      end
+    end
+    
+    describe "to a file" do
+      before do
+        @file = stub('file')
+        @path = '/var/stuff/favicons'
+      end
+      
+      it "should happen when providing a path to save" do
+        @favicon.expects(:save_to_file)
+        @favicon.save(@path)
+      end
+      
+      it "should dump its data to a file at the given path" do
+        File.expects(:new).with("#{@path}/#{@favicon.name}", anything).returns(@file)
+        @favicon.expects(:dump_data).with(@file)
+        @favicon.save_to_file(@path)
+      end
+      
+      it "should set the save_path to the path to the new file" do
+        File.stubs(:new).returns(stub_everything)
+        @favicon.save_to_file(@path)
+        @favicon.save_path.should == "#{@path}/#{@favicon.name}"
+      end
+    end
+        
+    describe "to some other kind of storage" do
+      before do
+        @storage = Object.new
+      end
+      
+      it "should raise an error" do
+        lambda { @favicon.save(@storage) }.should raise_error(Iconoclasm::RTFMError)
+      end
+    end
+  end
+end

data/spec/iconoclasm/headers_spec.rb

@@ -0,0 +1,43 @@
+require File.expand_path(File.dirname(__FILE__) + '/../helper')
+
+describe Iconoclasm::Headers do
+  
+  before do
+    @http_response  = "HTTP/1.1 200 OK"
+    @server         = "Apache/2.2.11 (Unix) mod_ssl/2.2.11 OpenSSL/0.9.7e"
+    @last_modified  = "Wed, 13 Jun 2007 19:15:36 GMT"
+    @content_type   = "image/x-icon"
+    @content_length = 3638
+    @header_string  = "#{@http_response}\r\nDate: Tue, 22 Dec 2009 21:15:31 GMT\r\nServer: #{@server}\r\nVary: Host,User-Agent\r\nLast-Modified: #{@last_modified}\r\nETag: \"e36-432ce70534600\"\r\nAccept-Ranges: bytes\r\nContent-Length: #{@content_length}\r\nContent-Type: #{@content_type}\r\n\r\n"
+    @headers = Iconoclasm::Headers.new(@header_string)
+  end
+  
+  describe "parsing the HTTP response" do
+    
+    it "should extract the HTTP version from the headers" do
+      @headers.version.should == "1.1"
+    end
+    
+    it "should extract the HTTP response code from the headers" do
+      @headers.code.should == 200
+    end
+    
+    it "should extract the HTTP response message from the headers" do
+      @headers.message.should == "OK"
+    end
+  end
+  
+  describe "hashifying the headers" do
+    it "should allow headers to be accessible by name" do
+      @headers['Server'].should == @server
+    end
+    
+    it "should allow headers to be accessible by their normalized (lowercase and underscored) names" do
+      @headers[:last_modified].should == @last_modified
+    end
+    
+    it "should convert numeric values to actual numbers" do
+      @headers[:content_length].should be_a_kind_of(Numeric)
+    end
+  end  
+end

data/spec/iconoclasm_spec.rb

@@ -0,0 +1,24 @@
+require File.expand_path(File.dirname(__FILE__) + '/helper')
+
+describe Iconoclasm do
+  
+  describe "#extract" do
+    before do
+      @url = 'http://www.website.com/some-crappy-blog-post'
+    end
+    
+    it "should extract the favicon for the given url" do
+      Iconoclasm.expects(:extract_favicon_from).with(@url, nil)
+      Iconoclasm::Favicon.stubs(:new)
+      Iconoclasm.extract(@url)
+    end
+    
+    it "should make a new Favicon instance" do
+      favicon = stub('favicon')
+      Iconoclasm.stubs(:extract_favicon_from).returns(favicon)
+      Iconoclasm::Favicon.expects(:new).with(favicon)
+      Iconoclasm.extract(@url)
+    end
+  end
+  
+end

metadata

@@ -0,0 +1,80 @@
+--- !ruby/object:Gem::Specification 
+name: iconoclasm
+version: !ruby/object:Gem::Version 
+  version: 1.0.0
+platform: ruby
+authors: 
+- Sander Hartlage
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2009-12-28 00:00:00 -05:00
+default_executable: 
+dependencies: []
+
+description: Finds favorites icons for web pages on the world wide internets by checking the HTML head or the standard favicon location. Then, do with them what you will.
+email: sander.hartlage@gmail.com
+executables: []
+
+extensions: []
+
+extra_rdoc_files: 
+- LICENSE
+- README.markdown
+files: 
+- .document
+- .gitignore
+- LICENSE
+- README.markdown
+- Rakefile
+- VERSION
+- lib/iconoclasm.rb
+- lib/iconoclasm/downloader.rb
+- lib/iconoclasm/errors.rb
+- lib/iconoclasm/extractor.rb
+- lib/iconoclasm/favicon.rb
+- lib/iconoclasm/headers.rb
+- spec/helper.rb
+- spec/iconoclasm/downloader_spec.rb
+- spec/iconoclasm/errors_spec.rb
+- spec/iconoclasm/extractor_spec.rb
+- spec/iconoclasm/favicon_spec.rb
+- spec/iconoclasm/headers_spec.rb
+- spec/iconoclasm_spec.rb
+has_rdoc: true
+homepage: http://github.com/sander6/iconoclasm
+licenses: []
+
+post_install_message: 
+rdoc_options: 
+- --charset=UTF-8
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+  version: 
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+  version: 
+requirements: []
+
+rubyforge_project: 
+rubygems_version: 1.3.5
+signing_key: 
+specification_version: 3
+summary: Finds favicons and DESTROYS THEM (well, not really, but it will download and save them)
+test_files: 
+- spec/helper.rb
+- spec/iconoclasm/downloader_spec.rb
+- spec/iconoclasm/errors_spec.rb
+- spec/iconoclasm/extractor_spec.rb
+- spec/iconoclasm/favicon_spec.rb
+- spec/iconoclasm/headers_spec.rb
+- spec/iconoclasm_spec.rb