url_scrubber 0.7.3 → 0.7.4

data/.rvmrc

@@ -1,48 +1 @@
-#!/usr/bin/env bash
-
-# This is an RVM Project .rvmrc file, used to automatically load the ruby
-# development environment upon cd'ing into the directory
-
-# First we specify our desired <ruby>[@<gemset>], the @gemset name is optional,
-# Only full ruby name is supported here, for short names use:
-#     echo "rvm use 1.9.3" > .rvmrc
-environment_id="ruby-1.9.3-p194@url_scrubber"
-
-# Uncomment the following lines if you want to verify rvm version per project
-# rvmrc_rvm_version="1.16.19 (stable)" # 1.10.1 seams as a safe start
-# eval "$(echo ${rvm_version}.${rvmrc_rvm_version} | awk -F. '{print "[[ "$1*65536+$2*256+$3" -ge "$4*65536+$5*256+$6" ]]"}' )" || {
-#   echo "This .rvmrc file requires at least RVM ${rvmrc_rvm_version}, aborting loading."
-#   return 1
-# }
-
-# First we attempt to load the desired environment directly from the environment
-# file. This is very fast and efficient compared to running through the entire
-# CLI and selector. If you want feedback on which environment was used then
-# insert the word 'use' after --create as this triggers verbose mode.
-if [[ -d "${rvm_path:-$HOME/.rvm}/environments"
-  && -s "${rvm_path:-$HOME/.rvm}/environments/$environment_id" ]]
-then
-  \. "${rvm_path:-$HOME/.rvm}/environments/$environment_id"
-  [[ -s "${rvm_path:-$HOME/.rvm}/hooks/after_use" ]] &&
-    \. "${rvm_path:-$HOME/.rvm}/hooks/after_use" || true
-else
-  # If the environment file has not yet been created, use the RVM CLI to select.
-  rvm --create  "$environment_id" || {
-    echo "Failed to create RVM environment '${environment_id}'."
-    return 1
-  }
-fi
-
-# If you use bundler, this might be useful to you:
-# if [[ -s Gemfile ]] && {
-#   ! builtin command -v bundle >/dev/null ||
-#   builtin command -v bundle | GREP_OPTIONS= \grep $rvm_path/bin/bundle >/dev/null
-# }
-# then
-#   printf "%b" "The rubygem 'bundler' is not installed. Installing it now.\n"
-#   gem install bundler
-# fi
-# if [[ -s Gemfile ]] && builtin command -v bundle >/dev/null
-# then
-#   bundle install | GREP_OPTIONS= \grep -vE '^Using|Your bundle is complete'
-# fi
+rvm use 1.9.3@url_scrubber --create

data/lib/url_scrubber.rb

@@ -16,10 +16,21 @@ module UrlScrubber
   end
 
   def self.service_of(url)
+    
     domain_match = url.match(%r{https?://([^/]+)})
     
     if domain_match
-      domain = domain_match[1]
+      domain = domain_match[1] 
+      first_dot = domain.index(".")
+      
+  	  #first_dot_position = domain.index(".")
+  	  #first_dot_position += 1 if first_dot_position
+  	  
+  	  #Rails.logger.debug "domain = #{domain}, first dot = #{first_dot ? first_dot : 'none'}, first dot 1= #{first_dot ? domain[first_dot+1..domain.size] : 'NIL'}"
+  	  if first_dot
+        # tumblr is a unique format
+        return :tumblr if domain[first_dot+1..domain.size].index("tumblr.com") == 0
+      end
 
       case domain
       when /\byoutube\.com$/      then return :youtube
@@ -31,8 +42,11 @@ module UrlScrubber
       when /\bflickr\.com$/       then return :flickr
       when /\bpinterest\.com$/    then return :pinterest
       when /\bvimeo\.com$/        then return :vimeo
+      when /\binstagram\.com$/    then return :instagram
       when /\byelp\.com$/         then return :yelp
       end
+    else
+  	  Rails.logger.debug "No Domain Match"
     end
 
     :other
@@ -63,6 +77,11 @@ module UrlScrubber
       !!url.match(%r{^http://yelp\.com/[\w_-]+$})
     when :vimeo
       !!url.match(%r{^http://vimeo\.com/[\w_-]+$}) && !url.match(%r{/\d+$})
+    when :instagram
+      !!url.match(%r{^http://instagram\.com/[\w_]+$})
+    when :tumblr
+      #Rails.logger.debug "CCC  Tumblr - url=#{url}, ideal=#{!!url.match(%r{^http://[\w_]+\.tumblr\.com$})}, www=#{url.index("://www.") ? url.index("://www.") : 'NIL'}"
+      !!url.match(%r{^http://[\w_]+\.tumblr\.com$}) && !url.index("://www.")
     else
       true
     end

data/lib/url_scrubber/version.rb

@@ -1,3 +1,3 @@
 module UrlScrubber
-  VERSION = "0.7.3"
+  VERSION = "0.7.4"
 end

data/spec/spec_helper.rb

@@ -0,0 +1,2 @@
+require 'rspec'
+require_relative '../lib/url_scrubber'

data/spec/url_scrubber_spec.rb

@@ -1,5 +1,4 @@
-require 'rspec'
-require 'url_scrubber'
+require 'spec_helper'
 
 describe UrlScrubber do
   describe '.scrub' do
@@ -177,6 +176,19 @@ describe UrlScrubber do
     describe 'with vimeo urls' do
       pending
     end
+    
+    describe 'with instagram urls' do
+      it 'should drop www. from the beginning' do
+        UrlScrubber.scrub('http://www.instagram.com/username').should eq('http://instagram.com/username')
+      end
+    end
+
+    describe 'with tumblr urls' do
+      it 'should drop www. from the beginning' do
+        UrlScrubber.scrub('http://www.cisco.tumblr.com').should eq('http://cisco.tumblr.com')
+      end
+    end
+
   end
 
   describe '.service_of' do
@@ -192,6 +204,11 @@ describe UrlScrubber do
       UrlScrubber.service_of('http://facebook.com/person.name').should eq :facebook
     end
 
+    it 'does not return :facebook for a non-facebook url with facebook in the name' do
+      UrlScrubber.service_of('http://foofacebook.com/').should_not eq :facebook
+      UrlScrubber.service_of('http://facebookfoo.com/').should_not eq :facebook
+    end
+
     it 'returns :linkedin for LinkedIn urls' do
       UrlScrubber.service_of('http://linkedin.com/company/1337').should eq :linkedin
     end
@@ -220,6 +237,14 @@ describe UrlScrubber do
       UrlScrubber.service_of('http://vimeo.com/absolutely').should eq :vimeo
     end
     
+    it 'returns :instagram for Instagram urls' do
+      UrlScrubber.service_of('http://instagram.com/absolutely').should eq :instagram
+    end
+    
+    it 'returns :tumblr for Tumblr urls' do
+      UrlScrubber.service_of('http://cisco.tumblr.com).should eq :tumblr
+    end
+    
     it 'returns :other for other urls' do
       UrlScrubber.service_of('http://example.com/page').should eq :other
     end
@@ -336,6 +361,26 @@ describe UrlScrubber do
       end
     end
 
+    describe 'for instagram' do
+      it 'returns true for apparent user urls' do
+        UrlScrubber.ideal_form?('http://instagram.com/username').should be_true
+      end
+
+      it 'returns false for other urls' do
+        UrlScrubber.ideal_form?('http://instagram.com/532513451524').should be_false
+      end
+    end
+
+    describe 'for tumblr' do
+      it 'returns true for apparent business urls' do
+        UrlScrubber.ideal_form?('http://cisco.tumblr.com').should be_true
+      end
+
+      it 'returns false for user urls' do
+        UrlScrubber.ideal_form?('http://tumblr.com/joe').should be_false
+      end
+    end
+
     describe 'for other sites' do
       it 'returns true for any other site, really' do
         UrlScrubber.ideal_form?('http://example.com/absolutely/anything').should be_true

data/url_scrubber.gemspec

@@ -2,8 +2,8 @@
 require File.expand_path('../lib/url_scrubber/version', __FILE__)
 
 Gem::Specification.new do |gem|
-  gem.authors       = ["Colin Langton", "Christopher Maujean"]
-  gem.email         = ["colin@hoteldelta.net", "cmaujean@brandle.net"]
+  gem.authors       = ["Colin Langton", "Christopher Maujean", "David Hillard"]
+  gem.email         = ["colin@hoteldelta.net", "cmaujean@brandle.net", "dhillard@brandle.net"]
   gem.description   = %q{Remove extraneous bits from URLs, follow redirects, identify social media urls, etc.}
   gem.summary       = %q{Clean up URLs.}
   gem.homepage      = "http://brandle.net"

metadata

@@ -1,20 +1,21 @@
 --- !ruby/object:Gem::Specification
 name: url_scrubber
 version: !ruby/object:Gem::Version
-  version: 0.7.3
+  version: 0.7.4
   prerelease: 
 platform: ruby
 authors:
 - Colin Langton
 - Christopher Maujean
+- David Hillard
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-06-06 00:00:00.000000000 Z
+date: 2013-08-28 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rspec
-  requirement: &2152156960 !ruby/object:Gem::Requirement
+  requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -22,10 +23,15 @@ dependencies:
         version: 2.11.0
   type: :development
   prerelease: false
-  version_requirements: *2152156960
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 2.11.0
 - !ruby/object:Gem::Dependency
   name: guard-bundler
-  requirement: &2152155880 !ruby/object:Gem::Requirement
+  requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -33,10 +39,15 @@ dependencies:
         version: 0.1.3
   type: :development
   prerelease: false
-  version_requirements: *2152155880
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 0.1.3
 - !ruby/object:Gem::Dependency
   name: guard-rspec
-  requirement: &2152154720 !ruby/object:Gem::Requirement
+  requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -44,10 +55,15 @@ dependencies:
         version: 0.4.3
   type: :development
   prerelease: false
-  version_requirements: *2152154720
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 0.4.3
 - !ruby/object:Gem::Dependency
   name: terminal-notifier-guard
-  requirement: &2152153980 !ruby/object:Gem::Requirement
+  requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -55,10 +71,15 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *2152153980
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: rb-fsevent
-  requirement: &2152153300 !ruby/object:Gem::Requirement
+  requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -66,12 +87,18 @@ dependencies:
         version: 0.9.1
   type: :development
   prerelease: false
-  version_requirements: *2152153300
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 0.9.1
 description: Remove extraneous bits from URLs, follow redirects, identify social media
   urls, etc.
 email:
 - colin@hoteldelta.net
 - cmaujean@brandle.net
+- dhillard@brandle.net
 executables: []
 extensions: []
 extra_rdoc_files: []
@@ -84,6 +111,7 @@ files:
 - Rakefile
 - lib/url_scrubber.rb
 - lib/url_scrubber/version.rb
+- spec/spec_helper.rb
 - spec/url_scrubber_spec.rb
 - url_scrubber.gemspec
 homepage: http://brandle.net
@@ -106,9 +134,10 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 1.8.16
+rubygems_version: 1.8.21
 signing_key: 
 specification_version: 3
 summary: Clean up URLs.
 test_files:
+- spec/spec_helper.rb
 - spec/url_scrubber_spec.rb