extractors 0.1.0

data/.gitignore

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

data/Gemfile

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

data/README.markdown

@@ -0,0 +1,45 @@
+### Extract user accounts from different contexts...
+
+```ruby
+Extractors(:twitter).sanitize("http://twitter.com/#!/programmingshit") # => "programmingshit"
+Extractors(:twitter).sanitize("programmingshit") # => "programmingshit"
+```
+
+### ... and format them back
+
+```ruby
+Extractors(:twitter).format("programmingshit") # => "http://twitter.com/#!/programmingshit"
+```
+
+### Add your own extractors
+
+```ruby
+Extractors.add :lookatme do
+  username_regexp = '[a-zA-Z0-9_\\-]{3,20}'
+  sanitizer [
+    %r{^(?:http://)?(?:www\.)?lookatme\.ru/users/(#{username_regexp})},
+    %r{^(#{username_regexp})$}
+  ]
+  formatter 'http://lookatme.ru/users/%s'
+end
+```
+
+### List of available extractors
+
+* :facebook
+* :googleplus
+* :gtalk
+* :lastfm
+* :livejournal
+* :lookatme
+* :moikrug
+* :myspace
+* :skype
+* :tumblr
+* :twitter
+* :vkontakte
+* :youtube
+
+### Credits
+
+The code itself has been *extracted* from <http://github.com/toy/contacts> gem.

data/Rakefile

@@ -0,0 +1,9 @@
+require 'bundler/gem_tasks'
+require 'rake/testtask'
+
+task :default => :test
+Rake::TestTask.new do |t|
+  t.libs << 'lib' << 'specs'
+  t.test_files = FileList['specs/*_spec.rb']
+  t.verbose = true
+end

data/extractors.gemspec

@@ -0,0 +1,24 @@
+# -*- encoding: utf-8 -*-
+$:.push File.expand_path("../lib", __FILE__)
+require "extractors/version"
+
+Gem::Specification.new do |s|
+  s.name        = "extractors"
+  s.version     = Extractors::VERSION
+  s.authors     = ["macovsky"]
+  s.email       = ["robotector@gmail.com"]
+  s.homepage    = "http://github.com/macovsky/extractors"
+  s.summary     = %q{Extract user accounts from different urls: tumblr, facebook and others.}
+  s.description = %q{}
+
+  s.rubyforge_project = "extractors"
+
+  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"]
+
+  # specify any dependencies here; for example:
+  s.add_development_dependency "minitest"
+  s.add_development_dependency "rake"
+end

data/lib/extractors.rb

@@ -0,0 +1,174 @@
+require 'extractors/version'
+require 'extractors/extractor'
+
+def Extractors (name)
+  Extractors.extractors[name.to_sym]
+end
+
+module Extractors
+  class <<self
+    def add(name, &block)
+      extractor = Extractor.new
+      extractor.instance_eval(&block)
+      extractors[name.to_sym] = extractor
+    end
+
+    def extractors
+      @extractors ||= {}
+    end
+  end
+
+  add :facebook do
+    username_regexp = '[0-9]{1,25}'
+    literal_username_regexp = '[a-zA-Z.]{1,25}'
+    sanitizer [
+      %r{^(?:http://)?(?:www\.)?facebook\.com/(#{literal_username_regexp})},
+      %r{^(#{literal_username_regexp})$},
+      %r{^(?:http://)?(?:www\.)?facebook\.com/profile.php\?id=(#{username_regexp})},
+      %r{^(?:http://)?(?:www\.)?facebook\.com/group.php\?gid=(#{username_regexp})},
+      %r{^(#{username_regexp})$}
+    ]
+    formatter do |value|
+      if value[%r{^\d+$}]
+        "http://facebook.com/profile.php?id=#{value}"
+      else
+        "http://facebook.com/#{value}"
+      end
+    end
+  end
+
+  # add :flickr do
+  #   username_regexp = '[\\-a-zA-Z0-9_@]{1,50}'
+  #   sanitizer [
+  #     %r{^(?:http://)?(?:www\.)?flickr\.com/(?:photos|people)/(#{username_regexp})},
+  #     %r{^(#{username_regexp})$}
+  #   ]
+  #   formatter 'http://flickr.com/photos/%s'
+  # end
+
+  add :googleplus do
+    sanitizer %r{^(?:https?://)?plus.google.com/(?:u/\d/)?(\d+)}
+    formatter 'https://plus.google.com/%s/posts'
+  end
+
+  add :gtalk do
+    sanitizer do |value|
+      username_regexp = '[a-zA-Z0-9]+(\\.[a-zA-Z0-9]+)*'
+      if result = value[%r{^(#{username_regexp})(?:@gmail\.com)?$}, 1]
+        "#{result}@gmail.com" if result && 6..30 === result.length
+      elsif result = value[%r{^#{username_regexp}@[a-z0-9]+(\.[a-z0-9]+)+$}]
+        "#{result}" if result
+      end
+    end
+    formatter 'gtalk:chat?jid=%s'
+  end
+
+  # add :icq do
+  #   sanitizer %r{^\d+$}
+  #   formatter 'http://icq.com/%s'
+  # end
+
+  add :lastfm do
+    username_regexp = '[a-zA-Z][_a-zA-Z0-9\\-]{1,20}'
+    sanitizer [
+      %r{^(?:http://)?(?:www\.)?last\.fm/user/(#{username_regexp})},
+      %r{^(#{username_regexp})$}
+    ]
+    formatter 'http://last.fm/user/%s'
+  end
+
+  add :livejournal do
+    sanitizer do |value|
+      username_regexp = '[a-zA-Z0-9_\\-]{1,20}'
+      result = value_from_matching_regexp(value, [
+                                        %r{^(?:http://)?(?:users|community)\.livejournal\.com/(#{username_regexp})},
+                                        %r{^(?:http://)?(#{username_regexp})\.livejournal\.com},
+                                        %r{^(#{username_regexp})$}
+      ])
+      result.gsub('_', '-') if result && result != 'www'
+    end
+    formatter 'http://%s.livejournal.com/'
+  end
+
+  add :lookatme do
+    username_regexp = '[a-zA-Z0-9_\\-]{3,20}'
+    sanitizer [
+      %r{^(?:http://)?(?:www\.)?lookatme\.ru/users/(#{username_regexp})},
+      %r{^(#{username_regexp})$}
+    ]
+    formatter 'http://lookatme.ru/users/%s'
+  end
+
+  add :moikrug do
+    sanitizer do |value|
+      username_regexp = '[a-zA-Z0-9][a-zA-Z0-9_\\-]{1,20}'
+     result = value_from_matching_regexp(value, [
+                                        %r{^(?:http://)?(#{username_regexp})\.moikrug\.ru},
+                                        %r{^(#{username_regexp})$}
+      ])
+      result.gsub('_', '-') if result && result != 'www'
+    end
+    formatter 'http://%s.moikrug.ru/'
+  end
+
+  add :myspace do
+    username_regexp = '[a-zA-Z0-9_\\-]{1,25}'
+    sanitizer [
+      %r{^(?:http://)?(?:www\.)?myspace\.com/(#{username_regexp})},
+      %r{^(#{username_regexp})$}
+    ]
+    formatter 'http://myspace.com/%s'
+  end
+
+  add :skype do
+    sanitizer %r{^[a-z][a-z0-9_,.\-]{5,31}$}i
+    formatter 'skype:%s?userinfo'
+  end
+
+  add :tumblr do
+    username_regexp = '[a-zA-Z0-9_\\-]{1,25}'
+    sanitizer [
+      %r{^(?:http://)?(?:www\.)tumblr\.com/blog/(#{username_regexp})},
+      %r{^(?:http://)?(#{username_regexp})\.tumblr\.com},
+      %r{^(#{username_regexp})$}
+    ]
+    formatter 'http://%s.tumblr.com'
+  end
+
+  add :twitter do
+    username_regexp = '[a-zA-Z0-9_\\-]{1,25}'
+    sanitizer [
+      %r{^(?:https?://)?(?:www\.)?twitter\.com/(?:#!/)?(#{username_regexp})},
+      %r{^(#{username_regexp})$}
+    ]
+    formatter 'http://twitter.com/#!/%s'
+  end
+
+  add :vkontakte do
+    id_regexp = '[0-9]{1,25}'
+    username_regexp = '[a-zA-Z][a-zA-Z0-9_\.]{4,}'
+    sanitizer [
+      %r{^(?:http://)?(?:www\.)?vkontakte\.ru/id(#{id_regexp})},
+      %r{^(#{id_regexp})$},
+      %r{^(?:http://)?(?:www\.)?vkontakte\.ru/(#{username_regexp})},
+      %r{^(#{username_regexp})$},
+    ]
+    formatter do |value|
+      if value[/\D/]
+        "http://vkontakte.ru/#{value}"
+      else
+        "http://vkontakte.ru/id#{value}"
+      end
+    end
+  end
+
+  add :youtube do
+    username_regexp = '[a-zA-Z0-9_\\-]{1,20}'
+    sanitizer [
+      %r{^(?:http://)?(?:www\.)?youtube\.com/user/(#{username_regexp})},
+      %r{^(#{username_regexp})$}
+    ]
+    formatter 'http://youtube.com/user/%s'
+  end
+end
+

data/lib/extractors/extractor.rb

@@ -0,0 +1,45 @@
+module Extractors
+  class Extractor
+    def sanitizer(arg = nil, &block)
+      @sanitizer = arg || block
+    end
+
+    def sanitize(value)
+      case @sanitizer
+      when Regexp
+        value_from_matching_regexp(value, [@sanitizer])
+      when Array
+        value_from_matching_regexp(value, @sanitizer)
+      when Proc
+        @sanitizer.call(value)
+      when nil
+        value
+      else
+        raise "Unknown type of sanitizer: #{@sanitizer.inspect}"
+      end
+    end
+
+    def formatter(arg = nil, &block)
+      @formatter = arg || block
+    end
+
+    def format(value)
+      case @formatter
+      when String
+        @formatter % value
+      when Proc
+        @formatter.call(value)
+      when nil
+        value
+      else
+        raise "Unknown type of formatter: #{@formatter.inspect}"
+      end
+    end
+
+    private
+
+    def value_from_matching_regexp(value, regexps)
+      regexps.find{ |regexp| regexp === value } && $1 || $&
+    end
+  end
+end

data/lib/extractors/version.rb

@@ -0,0 +1,3 @@
+module Extractors
+  VERSION = "0.1.0"
+end

data/specs/extractors_spec.rb

@@ -0,0 +1,81 @@
+require 'spec_helper'
+
+describe Extractors do
+  it "can reach extractors by a shortcut" do
+    Extractors(:skype).must_be_instance_of Extractors::Extractor
+  end
+
+  it "should have default extractors" do
+    Extractors.extractors.wont_be_empty
+    Extractors.extractors.keys.each do |extractor|
+      Extractors.extractors[extractor].must_be_instance_of Extractors::Extractor
+    end
+  end
+
+  it "can add new extractors" do
+    Extractors.add :test do
+    end
+    extractor = Extractors(:test)
+    
+    extractor.wont_be_nil
+    extractor.must_respond_to(:sanitize)
+    extractor.must_respond_to(:format)
+  end
+
+  describe "existing extractors" do
+    {
+      :tumblr => {
+        :sanitize => {
+          "http://robotector.tumblr.com" => "robotector",
+          "http://www.tumblr.com/blog/robotector" => "robotector",
+          "robotector" => "robotector",
+        },
+        :format => {
+          "robotector" => "http://robotector.tumblr.com"
+        }
+      },
+      :lookatme => {
+        :sanitize => {
+          "lookatme.ru/users/macovsky" => "macovsky",
+          "macovsky" => "macovsky",
+        },
+        :format => {
+          "macovsky" => "http://lookatme.ru/users/macovsky"
+        }
+      },
+      :twitter => {
+        :sanitize => {
+          "twitter.com/robotector" => "robotector",
+          "https://twitter.com/#!/robotector" => "robotector",
+          "http://twitter.com/#!/robotector" => "robotector"
+        },
+        :format => {
+          "robotector" => "http://twitter.com/#!/robotector"
+        }
+      },
+      :googleplus => {
+        :sanitize => {
+          "https://plus.google.com/u/0/103751848505965231255/posts" => "103751848505965231255",
+          "https://plus.google.com/u/0/103751848505965231255" => "103751848505965231255",
+          "https://plus.google.com/103751848505965231255/posts" => "103751848505965231255",
+        },
+        :format => {
+          "103751848505965231255" => "https://plus.google.com/103751848505965231255/posts"
+        }
+      }
+    }.each do |name, sanitize_and_format|
+      (sanitize_and_format[:sanitize] || {}).merge(nil => nil).each do |k, v|
+        it "#{name} should sanitize properly" do
+          Extractors(name).sanitize(k).must_equal(v)
+        end
+      end
+
+      (sanitize_and_format[:format] || {}).each do |k, v|
+        it "#{name} should format properly" do
+          Extractors(name).format(k).must_equal(v)
+        end
+      end
+    end
+  end
+end
+

data/specs/spec_helper.rb

@@ -0,0 +1,3 @@
+require 'minitest/spec'
+require 'minitest/autorun'
+require 'extractors'

metadata

@@ -0,0 +1,77 @@
+--- !ruby/object:Gem::Specification
+name: extractors
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+  prerelease: 
+platform: ruby
+authors:
+- macovsky
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2012-02-22 00:00:00.000000000Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: minitest
+  requirement: &70126699361480 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: *70126699361480
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: &70126699357780 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: *70126699357780
+description: ''
+email:
+- robotector@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- Gemfile
+- README.markdown
+- Rakefile
+- extractors.gemspec
+- lib/extractors.rb
+- lib/extractors/extractor.rb
+- lib/extractors/version.rb
+- specs/extractors_spec.rb
+- specs/spec_helper.rb
+homepage: http://github.com/macovsky/extractors
+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: extractors
+rubygems_version: 1.8.10
+signing_key: 
+specification_version: 3
+summary: ! 'Extract user accounts from different urls: tumblr, facebook and others.'
+test_files: []