link-checker 0.0.0 → 0.1.0

data/Gemfile

@@ -7,6 +7,6 @@ group(:test, :development) do
   gem "rspec", "~> 2.11.0"
   gem "jeweler", "~> 1.8.4"
   gem "simplecov", "~> 0.6.4"
-  gem "ruby-debug19", "~> 0.11.6"
   gem "fakeweb", "~> 1.3.0"
+  gem "debugger"
 end

data/Gemfile.lock

@@ -1,9 +1,15 @@
 GEM
   remote: http://rubygems.org/
   specs:
-    archive-tar-minitar (0.5.2)
     colorize (0.5.8)
     columnize (0.3.6)
+    debugger (1.2.0)
+      columnize (>= 0.3.1)
+      debugger-linecache (~> 1.1.1)
+      debugger-ruby_core_source (~> 1.1.3)
+    debugger-linecache (1.1.2)
+      debugger-ruby_core_source (>= 1.1.1)
+    debugger-ruby_core_source (1.1.3)
     diff-lcs (1.1.3)
     fakeweb (1.3.0)
     git (1.2.5)
@@ -13,8 +19,6 @@ GEM
       rake
       rdoc
     json (1.7.5)
-    linecache19 (0.5.12)
-      ruby_core_source (>= 0.1.4)
     multi_json (1.3.6)
     nokogiri (1.5.5)
     rake (0.9.2.2)
@@ -28,16 +32,6 @@ GEM
     rspec-expectations (2.11.3)
       diff-lcs (~> 1.1.3)
     rspec-mocks (2.11.3)
-    ruby-debug-base19 (0.11.25)
-      columnize (>= 0.3.1)
-      linecache19 (>= 0.5.11)
-      ruby_core_source (>= 0.1.4)
-    ruby-debug19 (0.11.6)
-      columnize (>= 0.3.1)
-      linecache19 (>= 0.5.11)
-      ruby-debug-base19 (>= 0.11.19)
-    ruby_core_source (0.1.5)
-      archive-tar-minitar (>= 0.5.2)
     simplecov (0.6.4)
       multi_json (~> 1.0)
       simplecov-html (~> 0.5.3)
@@ -48,9 +42,9 @@ PLATFORMS
 
 DEPENDENCIES
   colorize (~> 0.5.8)
+  debugger
   fakeweb (~> 1.3.0)
   jeweler (~> 1.8.4)
   nokogiri (~> 1.5.5)
   rspec (~> 2.11.0)
-  ruby-debug19 (~> 0.11.6)
   simplecov (~> 0.6.4)

data/README.md

@@ -4,12 +4,24 @@ This Ruby gem allows you to easily check the links in your Octopress web site.
 
 ## Installation
 
-*coming soon*
+Add the ```link-checker``` gem to your project's ```Gemfile```:
+
+    gem "link-checker"
+
+Then ```bundle install``` to install the gem.
 
 ## Usage
 
-*coming soon*
+You can use the ```check-links``` command to specify any directory to scan for HTML files.  It will scan each ```.html``` or ```.htm``` file and then check each link within each file.
+
+For example, to check the links for a Jekyll or Octopress site:
+
+    check-links 'public'
 
 ## Testing
 
-````rake spec````
+The ```link-checker``` gem uses [RSpec](http://rspec.info) for testing and has 100% test coverage, verified using [simplecov](https://github.com/colszowka/simplecov).
+
+Run the specs with:
+
+    rake spec

data/VERSION

@@ -1 +1 @@
-0.0.0
+0.1.0

data/bin/check-links

@@ -5,4 +5,4 @@ require 'link_checker'
 # Assume the 'public' directory is the site unless otherwise specified.
 site_path = ARGV[0] || 'public'
 
-Link::Checker.new(site_path).check_links
+LinkChecker.new(site_path).check_links

data/lib/link_checker.rb

@@ -5,69 +5,90 @@ require 'net/https'
 require 'uri'
 require 'colorize'
 
-module Link
+class LinkChecker
 
-  class Checker
-
-    def initialize(target_path)
-      @target_path = target_path
-    end
+  def initialize(target_path)
+    @target_path = target_path
+  end
 
-    def find_html_files
-      Find.find(@target_path).map {|path|
-        FileTest.file?(path) && (path =~ /\.html?$/) ? path : nil
-      }.reject{|path| path.nil?}
-    end
+  def find_html_files
+    Find.find(@target_path).map {|path|
+      FileTest.file?(path) && (path =~ /\.html?$/) ? path : nil
+    }.reject{|path| path.nil?}
+  end
 
-    def self.find_external_links(file_path)
-      Nokogiri::HTML(open(file_path)).css('a').
-        select{|link| link.attribute('href').value =~ /^https?\:\/\// }
-    end
+  def self.find_external_links(file_path)
+    Nokogiri::HTML(open(file_path)).css('a').
+      select{|link| link.attribute('href').value =~ /^https?\:\/\// }
+  end
 
-    def self.check_link(uri)
-      uri = URI.parse(uri)
-      http = Net::HTTP.new(uri.host, uri.port)
-      http.use_ssl = true if uri.scheme == "https"
-      http.start do
-        path = (uri.path.empty?) ? '/' : uri.path
-        http.request_get(path) do |response|
-          case response
-          when Net::HTTPSuccess then
-            return true
-          when Net::HTTPRedirection then
-            return self.check_link(response['location'])
+  def self.check_link(uri, redirected=false)
+    uri = URI.parse(uri)
+    http = Net::HTTP.new(uri.host, uri.port)
+    http.use_ssl = true if uri.scheme == "https"
+    http.start do
+      path = (uri.path.empty?) ? '/' : uri.path
+      http.request_get(path) do |response|
+        case response
+        when Net::HTTPSuccess then
+          if redirected
+            return Redirect.new(uri)
           else
-            raise Error.new(response)
+            return Good.new
           end
+        when Net::HTTPRedirection then
+          return self.check_link(response['location'], true)
+        else
+          raise Error.new(response)
         end
       end
     end
+  end
 
-    def check_links
-      find_html_files.each do |file|
-        bad_checks = []  
+  def check_links
+    find_html_files.each do |file|
+      bad_checks = []
+      warnings = []
 
-        self.class.find_external_links(file).each do |link|
-          uri = link.attribute('href').value
-          begin
-            self.class.check_link(uri)
-          rescue => error
-            bad_checks << { :link => link, :error => error }
+      self.class.find_external_links(file).each do |link|
+        uri = link.attribute('href').value
+        begin
+          response = self.class.check_link(uri)
+          if response.class.eql? Redirect
+            warnings << { :link => link, :response => response }
           end
+        rescue => error
+          bad_checks << { :link => link, :response => error }
         end
-        
-        if bad_checks.empty?
+      end
+      
+      if bad_checks.empty?
+        if warnings.empty?
           puts "Checked: #{file}".green
         else
-          puts "Problem: #{file}".red
-          bad_checks.each do |check|
-            puts "   Link: #{check[:link].attribute('href').value}".red
-            puts "     Response: #{check[:error].response.inspect}".red
-          end
+          puts "Checked: #{file}".yellow
+        end
+        warnings.each do |warning|
+          puts "   Warning: #{warning[:link].attribute('href').value}".yellow
+          puts "     Redirected to: #{warning[:response].final_destination.to_s}".yellow
+        end
+      else
+        puts "Problem: #{file}".red
+        bad_checks.each do |check|
+          puts "   Link: #{check[:link].attribute('href').value}".red
+          puts "     Response: #{check[:response].response.inspect}".red
         end
       end
     end
+  end
 
+  class Good; end
+
+  class Redirect
+    attr_reader :final_destination
+    def initialize(final_destination)
+      @final_destination = final_destination
+    end
   end
 
   class Error < StandardError

data/link-checker.gemspec

@@ -5,11 +5,11 @@
 
 Gem::Specification.new do |s|
   s.name = "link-checker"
-  s.version = "0.0.0"
+  s.version = "0.1.0"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["Ryan Alyn Porter"]
-  s.date = "2012-10-03"
+  s.date = "2012-10-04"
   s.description = "Check the links in a web site before deploying, using Nokogiri."
   s.executables = ["check-links"]
   s.extra_rdoc_files = [
@@ -368,7 +368,7 @@ Gem::Specification.new do |s|
   s.homepage = "https://github.com/endymion/link-checker"
   s.licenses = ["MIT"]
   s.require_paths = ["lib"]
-  s.rubygems_version = "1.8.15"
+  s.rubygems_version = "1.8.24"
   s.summary = "Check the links in a web site before deploying."
 
   if s.respond_to? :specification_version then
@@ -380,16 +380,16 @@ Gem::Specification.new do |s|
       s.add_development_dependency(%q<rspec>, ["~> 2.11.0"])
       s.add_development_dependency(%q<jeweler>, ["~> 1.8.4"])
       s.add_development_dependency(%q<simplecov>, ["~> 0.6.4"])
-      s.add_development_dependency(%q<ruby-debug19>, ["~> 0.11.6"])
       s.add_development_dependency(%q<fakeweb>, ["~> 1.3.0"])
+      s.add_development_dependency(%q<debugger>, [">= 0"])
     else
       s.add_dependency(%q<nokogiri>, ["~> 1.5.5"])
       s.add_dependency(%q<colorize>, ["~> 0.5.8"])
       s.add_dependency(%q<rspec>, ["~> 2.11.0"])
       s.add_dependency(%q<jeweler>, ["~> 1.8.4"])
       s.add_dependency(%q<simplecov>, ["~> 0.6.4"])
-      s.add_dependency(%q<ruby-debug19>, ["~> 0.11.6"])
       s.add_dependency(%q<fakeweb>, ["~> 1.3.0"])
+      s.add_dependency(%q<debugger>, [">= 0"])
     end
   else
     s.add_dependency(%q<nokogiri>, ["~> 1.5.5"])
@@ -397,8 +397,8 @@ Gem::Specification.new do |s|
     s.add_dependency(%q<rspec>, ["~> 2.11.0"])
     s.add_dependency(%q<jeweler>, ["~> 1.8.4"])
     s.add_dependency(%q<simplecov>, ["~> 0.6.4"])
-    s.add_dependency(%q<ruby-debug19>, ["~> 0.11.6"])
     s.add_dependency(%q<fakeweb>, ["~> 1.3.0"])
+    s.add_dependency(%q<debugger>, [">= 0"])
   end
 end
 

data/spec/link-checker_spec.rb

@@ -1,20 +1,19 @@
 require 'spec_helper'
 require 'link_checker'
 
-describe Link::Checker do
+describe LinkChecker do
 
   before(:all) do
     @site_path = 'spec/test-site/public/'
   end
 
   it "finds all of the HTML files in the target path." do
-    checker = Link::Checker.new(@site_path)
-    files = checker.find_html_files
+    files = LinkChecker.new(@site_path).find_html_files
     files.size.should == 3
   end
 
   it "finds all of the external links in an HTML file." do
-    links = Link::Checker.find_external_links(
+    links = LinkChecker.find_external_links(
       'spec/test-site/public/blog/2012/10/02/a-list-of-links/index.html')
     links.size.should == 4
   end
@@ -33,12 +32,12 @@ describe Link::Checker do
     end
 
     it "declares good links to be good." do
-      Link::Checker.check_link(@good_uri).should be true
+      LinkChecker.check_link(@good_uri).class.should be LinkChecker::Good
     end
 
     it "declares bad links to be bad." do
-      expect { Link::Checker.check_link(@bad_uri) }.to(
-        raise_error(Link::Error))
+      expect { LinkChecker.check_link(@bad_uri) }.to(
+        raise_error(LinkChecker::Error))
     end
 
     describe "follows redirects to the destination and" do
@@ -46,14 +45,16 @@ describe Link::Checker do
       it "declares good redirect targets to be good." do
         FakeWeb.register_uri(:get, @redirect_uri,
           :location => @good_uri, :status => ["302", "Moved"])
-        Link::Checker.check_link(@redirect_uri).should be true
+        result = LinkChecker.check_link(@redirect_uri)
+        result.class.should be LinkChecker::Redirect
+        result.final_destination.to_s.should == @good_uri
       end
 
       it "declares bad redirect targets to be bad." do
         FakeWeb.register_uri(:get, @redirect_uri,
           :location => @bad_uri, :status => ["302", "Moved"])
-        expect { Link::Checker.check_link(@redirect_uri) }.to(
-          raise_error(Link::Error))
+        expect { LinkChecker.check_link(@redirect_uri) }.to(
+          raise_error(LinkChecker::Error))
       end
 
     end
@@ -62,31 +63,20 @@ describe Link::Checker do
 
   describe "prints output" do
 
-    before(:all) do
-      @uris =
-        %w{
-          http://goodlink.com
-          http://brokenlink.com
-          http://twitter.com/share
-          http://octopress.org
-        }
-    end
-
     it "prints green when the links are all good." do
-      Link::Checker.stub(:check_link) { true }
+      LinkChecker.stub(:check_link) { true }
       $stdout.should_receive(:puts).with(/Checked/i).exactly(3).times
-      Link::Checker.new(@site_path).check_links
+      LinkChecker.new(@site_path).check_links
     end
 
     it "prints green when the links are all bad." do
-      Link::Checker.stub(:check_link).and_raise Link::Error.new('blah')
+      LinkChecker.stub(:check_link).and_raise LinkChecker::Error.new('blah')
       $stdout.should_receive(:puts).with(/Problem/i).exactly(3).times
       $stdout.should_receive(:puts).with(/Link/i).at_least(3).times
       $stdout.should_receive(:puts).with(/Response/i).at_least(3).times
-      Link::Checker.new(@site_path).check_links
+      LinkChecker.new(@site_path).check_links
     end
 
-
   end
 
 end

data/spec/spec_helper.rb

@@ -1,3 +1,4 @@
+require 'debugger'
 require 'fakeweb'
 
 require 'simplecov'

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: link-checker
 version: !ruby/object:Gem::Version
-  version: 0.0.0
+  version: 0.1.0
   prerelease: 
 platform: ruby
 authors:
@@ -9,11 +9,11 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-10-03 00:00:00.000000000 Z
+date: 2012-10-04 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
-  requirement: &70228592620540 !ruby/object:Gem::Requirement
+  requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -21,10 +21,15 @@ dependencies:
         version: 1.5.5
   type: :runtime
   prerelease: false
-  version_requirements: *70228592620540
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 1.5.5
 - !ruby/object:Gem::Dependency
   name: colorize
-  requirement: &70228592619700 !ruby/object:Gem::Requirement
+  requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -32,10 +37,15 @@ dependencies:
         version: 0.5.8
   type: :runtime
   prerelease: false
-  version_requirements: *70228592619700
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 0.5.8
 - !ruby/object:Gem::Dependency
   name: rspec
-  requirement: &70228592619120 !ruby/object:Gem::Requirement
+  requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -43,10 +53,15 @@ dependencies:
         version: 2.11.0
   type: :development
   prerelease: false
-  version_requirements: *70228592619120
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 2.11.0
 - !ruby/object:Gem::Dependency
   name: jeweler
-  requirement: &70228592618580 !ruby/object:Gem::Requirement
+  requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -54,10 +69,15 @@ dependencies:
         version: 1.8.4
   type: :development
   prerelease: false
-  version_requirements: *70228592618580
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 1.8.4
 - !ruby/object:Gem::Dependency
   name: simplecov
-  requirement: &70228592617740 !ruby/object:Gem::Requirement
+  requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -65,29 +85,44 @@ dependencies:
         version: 0.6.4
   type: :development
   prerelease: false
-  version_requirements: *70228592617740
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 0.6.4
 - !ruby/object:Gem::Dependency
-  name: ruby-debug19
-  requirement: &70228592617140 !ruby/object:Gem::Requirement
+  name: fakeweb
+  requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
-        version: 0.11.6
+        version: 1.3.0
   type: :development
   prerelease: false
-  version_requirements: *70228592617140
-- !ruby/object:Gem::Dependency
-  name: fakeweb
-  requirement: &70228592616280 !ruby/object:Gem::Requirement
+  version_requirements: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
         version: 1.3.0
+- !ruby/object:Gem::Dependency
+  name: debugger
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
   type: :development
   prerelease: false
-  version_requirements: *70228592616280
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
 description: Check the links in a web site before deploying, using Nokogiri.
 email: 
 executables:
@@ -459,7 +494,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
       version: '0'
       segments:
       - 0
-      hash: 3077015528124566736
+      hash: 3227380414018538119
 required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
   requirements:
@@ -468,7 +503,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 1.8.15
+rubygems_version: 1.8.24
 signing_key: 
 specification_version: 3
 summary: Check the links in a web site before deploying.