sitemap_generator 4.1.0 → 4.1.1

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: ./
   specs:
-    sitemap_generator (4.1.0)
+    sitemap_generator (4.1.1)
       builder
 
 GEM

data/README.md

@@ -9,7 +9,7 @@ Sitemaps adhere to the [Sitemap 0.9 protocol][sitemap_protocol] specification.
 * Framework agnostic
 * Supports [News sitemaps][sitemap_news], [Video sitemaps][sitemap_video], [Image sitemaps][sitemap_images], [Geo sitemaps][sitemap_geo], [Mobile sitemaps][sitemap_mobile], [PageMap sitemaps][sitemap_pagemap] and [Alternate Links][alternate_links]
 * Supports read-only filesystems like Heroku via uploading to a remote host like Amazon S3
-* Compatible with Rails 2 & 3 and tested with Ruby REE, 1.9.2 & 1.9.3
+* Compatible with Rails 2, 3 & 4 and tested with Ruby REE, 1.9.2 & 1.9.3
 * Adheres to the [Sitemap 0.9 protocol][sitemap_protocol]
 * Handles millions of links
 * Automatically compresses your sitemaps
@@ -20,6 +20,8 @@ Sitemaps adhere to the [Sitemap 0.9 protocol][sitemap_protocol] specification.
 
 ### Show Me
 
+This is a simple standalone example.  For Rails installation see the Install section.
+
 Install:
 
 ```
@@ -37,7 +39,7 @@ SitemapGenerator::Sitemap.create do
   add '/home', :changefreq => 'daily', :priority => 0.9
   add '/contact_us', :changefreq => 'weekly'
 end
-SitemapGenerator::Sitemap.ping_search_engines # called for you when you use the rake task
+SitemapGenerator::Sitemap.ping_search_engines # Not needed if you use the rake tasks
 ```
 
 Run it:
@@ -103,7 +105,8 @@ That's it!  Welcome to the future!
 
 ## Changelog
 
-* v4.1.0: [PageMap sitemap][using_pagemaps] support.
+* v4.1.1: Support setting the S3 region.  Fixed bug where incorrect URL was being used in the ping to search engines - only affected sites with a single sitemap file and no index file.  Output the URL being pinged in the verbose output.  Test in Rails 4.
+* v4.1.0: [PageMap sitemap][using_pagemaps] support.  Tested with Rails 4 pre-release.
 * v4.0.1: Add a post install message regarding the naming convention change.
 * **v4.0: NEW, NON-BACKWARDS COMPATIBLE CHANGES.**  See above for more info. `create_index` defaults to `:auto`.  Define `SitemapGenerator::SimpleNamer` class for simpler custom namers compatible with the new naming conventions.  Deprecate `sitemaps_namer`, `sitemap_index_namer` and their respective namer classes.  It's more just that their usage is discouraged.  Support `nofollow` option on alternate links.  Fix formatting of `publication_date` in News sitemaps.
 * v3.4: Support [alternate links][alternate_links] for urls; Support configurable options in the `SitemapGenerator::S3Adapter`
@@ -165,6 +168,8 @@ The Rake tasks expect your sitemap to be at `config/sitemap.rb` but if you need
 
 ### Rails
 
+SitemapGenerator works will all versions of Rails and has been tested in Rails 2, 3 and 4.
+
 Add the gem to your `Gemfile`:
 
 ```ruby

data/VERSION

@@ -1 +1 @@
-4.1.0
+4.1.1

data/lib/sitemap_generator/adapters/s3_adapter.rb

@@ -8,6 +8,7 @@ module SitemapGenerator
       @aws_secret_access_key = opts[:aws_secret_access_key] || ENV['AWS_SECRET_ACCESS_KEY']
       @fog_provider = opts[:fog_provider] || ENV['FOG_PROVIDER']
       @fog_directory = opts[:fog_directory] || ENV['FOG_DIRECTORY']
+      @fog_region = opts[:fog_region] || ENV['FOG_REGION']
     end
 
     # Call with a SitemapLocation and string data
@@ -19,6 +20,7 @@ module SitemapGenerator
         :aws_secret_access_key => @aws_secret_access_key,
         :provider              => @fog_provider,
       }
+      credentials[:region] = @fog_region if @fog_region
 
       storage   = Fog::Storage.new(credentials)
       directory = storage.directories.get(@fog_directory)

data/lib/sitemap_generator/builder/sitemap_index_file.rb

@@ -27,6 +27,9 @@ module SitemapGenerator
         @reserved_name = nil # holds the name reserved from the namer
         @frozen = false      # rather than actually freeze, use this boolean
         @first_sitemap = nil # reference to the first thing added to this index
+        # Store the URL of the first sitemap added because if create_index is
+        # false this is the "index" URL
+        @first_sitemap_url = nil
       end
 
       # Finalize sitemaps as they are added to the index.
@@ -123,6 +126,18 @@ module SitemapGenerator
         @create_index || @location.create_index == true || @location.create_index == :auto && @link_count > 1
       end
 
+      # Return the index file URL.  If create_index is true, this is the URL
+      # of the actual index file.  If create_index is false, this is the URL
+      # of the first sitemap that was written out.  Only call this method
+      # *after* the files have been finalized.
+      def index_url
+        if create_index? || !@first_sitemap_url
+          @location.url
+        else
+          @first_sitemap_url
+        end
+      end
+
       protected
 
       # Make sure the first sitemap has been written out and added to the index
@@ -131,6 +146,9 @@ module SitemapGenerator
           @first_sitemap.link.write unless @first_sitemap.link.written?
           super_add(SitemapGenerator::Builder::SitemapIndexUrl.new(@first_sitemap.link, @first_sitemap.options))
           @link_count -= 1   # we already counted it, don't count it twice
+          # Store the URL because if create_index is false, this is the
+          # "index" URL
+          @first_sitemap_url = @first_sitemap.link.location.url
           @first_sitemap = nil
         end
       end

data/lib/sitemap_generator/link_set.rb

@@ -281,9 +281,11 @@ module SitemapGenerator
       require 'timeout'
 
       engines = args.last.is_a?(Hash) ? args.pop : {}
-      index_url = CGI.escape(args.shift || sitemap_index_url)
+      unescaped_url = args.shift || sitemap_index_url
+      index_url = CGI.escape(unescaped_url)
 
       output("\n")
+      output("Pinging with URL #{unescaped_url}:")
       search_engines.merge(engines).each do |engine, link|
         link = link % index_url
         name = Utilities.titleize(engine.to_s)
@@ -291,7 +293,7 @@ module SitemapGenerator
           Timeout::timeout(10) {
             open(link)
           }
-          output("Successful ping of #{name}")
+          output("  Successful ping of #{name}")
         rescue Timeout::Error, StandardError => e
           output("Ping failed for #{name}: #{e.inspect} (URL #{link})")
         end
@@ -319,9 +321,14 @@ module SitemapGenerator
       @sitemap_index ||= SitemapGenerator::Builder::SitemapIndexFile.new(sitemap_index_location)
     end
 
-    # Return the full url to the sitemap index file.
+    # Return the full url to the sitemap index file.  When `create_index` is `false`
+    # the first sitemap is technically the index, so this will be its URL.  It's important
+    # to use this method to get the index url because `sitemap_index.location.url`  will
+    # not be correct in such situations.
+    #
+    # KJV: This is somewhat confusing.
     def sitemap_index_url
-      sitemap_index.location.url
+      sitemap_index.index_url
     end
 
     # All done.  Write out remaining files.

data/spec/sitemap_generator/builder/sitemap_index_file_spec.rb

@@ -98,4 +98,27 @@ describe 'SitemapGenerator::Builder::SitemapIndexFile' do
       end
     end
   end
+
+  describe "index_url" do
+    it "when not creating an index, should be the first sitemap url" do
+      index.instance_variable_set(:@create_index, false)
+      index.instance_variable_set(:@first_sitemap_url, 'http://test.com/index.xml')
+      index.create_index?.should be_false
+      index.index_url.should == 'http://test.com/index.xml'
+    end
+
+    it "if there's no first sitemap url, should default to the index location url" do
+      index.instance_variable_set(:@create_index, false)
+      index.instance_variable_set(:@first_sitemap_url, nil)
+      index.create_index?.should be_false
+      index.index_url.should == index.location.url
+      index.index_url.should == 'http://example.com/test/sitemap.xml.gz'
+    end
+
+    it "when creating an index, should be the index location url" do
+      index.instance_variable_set(:@create_index, true)
+      index.index_url.should == index.location.url
+      index.index_url.should == 'http://example.com/test/sitemap.xml.gz'
+    end
+  end
 end

data/spec/sitemap_generator/link_set_spec.rb

@@ -152,7 +152,7 @@ describe SitemapGenerator::LinkSet do
         :search_engines => { :google => 'http://google.com/?url=%s' })
       index_url = ls.sitemap_index_url
       ls.expects(:open).with("http://google.com/?url=#{CGI.escape(index_url)}")
-      ls.ping_search_engines(index_url)
+      ls.ping_search_engines
     end
 
     it "should include the given search engines" do
@@ -777,6 +777,9 @@ describe SitemapGenerator::LinkSet do
         ls.sitemap_index.empty?.should be_false
         ls.send(:finalize_sitemap_index!)
         ls.sitemap_index.written?.should be_true
+
+        # Test that the index url is reported correctly
+        ls.sitemap_index.index_url.should == 'http://example.com/sitemap.xml.gz'
       end
 
       it "should not write the index when only one sitemap is added (considered internal usage)" do
@@ -784,6 +787,9 @@ describe SitemapGenerator::LinkSet do
         ls.sitemap_index.empty?.should be_false
         ls.send(:finalize_sitemap_index!)
         ls.sitemap_index.written?.should be_false
+
+        # Test that the index url is reported correctly
+        ls.sitemap_index.index_url.should == sitemap.location.url
       end
 
       it "should write the index when more than one sitemap is added (considered internal usage)" do
@@ -791,6 +797,10 @@ describe SitemapGenerator::LinkSet do
         ls.sitemap_index.add sitemap.new
         ls.send(:finalize_sitemap_index!)
         ls.sitemap_index.written?.should be_true
+
+        # Test that the index url is reported correctly
+        ls.sitemap_index.index_url.should == ls.sitemap_index.location.url
+        ls.sitemap_index.index_url.should == 'http://example.com/sitemap.xml.gz'
       end
 
       it "should write the index when it has more than one link" do
@@ -798,21 +808,24 @@ describe SitemapGenerator::LinkSet do
         ls.sitemap_index.add '/test2'
         ls.send(:finalize_sitemap_index!)
         ls.sitemap_index.written?.should be_true
+
+        # Test that the index url is reported correctly
+        ls.sitemap_index.index_url.should == 'http://example.com/sitemap.xml.gz'
       end
     end
   end
-      
+
   describe "when sitemap empty" do
     before :each do
       ls.include_root = false
     end
-    
+
     it "should not be written" do
       ls.sitemap.empty?.should be_true
       ls.expects(:add_to_index).never
       ls.send(:finalize_sitemap!)
     end
-    
+
     it "should be written" do
       ls.sitemap.add '/test'
       ls.sitemap.empty?.should be_false

data/spec/sitemap_generator/sitemap_generator_spec.rb

@@ -1,4 +1,5 @@
 require 'spec_helper'
+require 'cgi'
 
 class Holder
   class << self
@@ -351,32 +352,51 @@ describe "SitemapGenerator" do
     end
 
     describe "when true" do
-      let(:ls) { SitemapGenerator::LinkSet.new(:include_root => false, :default_host => 'http://example.com', :create_index => true) }
+      let(:ls) {
+        SitemapGenerator::LinkSet.new(
+          :include_root => false,
+          :default_host => 'http://example.com',
+          :create_index => true)
+      }
 
       it "should always create index" do
         with_max_links(1) do
           ls.create { add('/one') }
         end
+        ls.sitemap_index.link_count.should == 1 # one sitemap
         file_should_exist(rails_path('public/sitemap.xml.gz'))
         file_should_exist(rails_path('public/sitemap1.xml.gz'))
         file_should_not_exist(rails_path('public/sitemap2.xml.gz'))
         gzipped_xml_file_should_validate_against_schema rails_path('public/sitemap.xml.gz'), 'siteindex'
         gzipped_xml_file_should_validate_against_schema rails_path('public/sitemap1.xml.gz'), 'sitemap'
+
+        # Test that the index url is reported correctly
+        ls.search_engines = { :google => 'http://google.com/?url=%s' }
+        ls.expects(:open).with("http://google.com/?url=#{CGI.escape('http://example.com/sitemap.xml.gz')}")
+        ls.ping_search_engines
       end
 
       it "should always create index" do
         with_max_links(1) do
           ls.create { add('/one'); add('/two') }
         end
+        ls.sitemap_index.link_count.should == 2 # two sitemaps
         file_should_exist(rails_path('public/sitemap.xml.gz'))
         file_should_exist(rails_path('public/sitemap1.xml.gz'))
         file_should_exist(rails_path('public/sitemap2.xml.gz'))
         gzipped_xml_file_should_validate_against_schema rails_path('public/sitemap.xml.gz'), 'siteindex'
         gzipped_xml_file_should_validate_against_schema rails_path('public/sitemap1.xml.gz'), 'sitemap'
         gzipped_xml_file_should_validate_against_schema rails_path('public/sitemap2.xml.gz'), 'sitemap'
+
+        # Test that the index url is reported correctly
+        ls.search_engines = { :google => 'http://google.com/?url=%s' }
+        ls.expects(:open).with("http://google.com/?url=#{CGI.escape('http://example.com/sitemap.xml.gz')}")
+        ls.ping_search_engines
       end
     end
 
+    # Technically when there's no index, the first sitemap is the "index"
+    # regardless of how many sitemaps were created, or if create_index is false.
     describe "when false" do
       let(:ls) { SitemapGenerator::LinkSet.new(:include_root => false, :default_host => 'http://example.com', :create_index => false) }
 
@@ -384,20 +404,32 @@ describe "SitemapGenerator" do
         with_max_links(1) do
           ls.create { add('/one') }
         end
+        ls.sitemap_index.link_count.should == 1 # one sitemap
         file_should_exist(rails_path('public/sitemap.xml.gz'))
         file_should_not_exist(rails_path('public/sitemap1.xml.gz'))
         gzipped_xml_file_should_validate_against_schema rails_path('public/sitemap.xml.gz'), 'sitemap'
+
+        # Test that the index url is reported correctly
+        ls.search_engines = { :google => 'http://google.com/?url=%s' }
+        ls.expects(:open).with("http://google.com/?url=#{CGI.escape('http://example.com/sitemap.xml.gz')}")
+        ls.ping_search_engines
       end
 
       it "should never create index" do
         with_max_links(1) do
           ls.create { add('/one'); add('/two') }
         end
+        ls.sitemap_index.link_count.should == 2 # two sitemaps
         file_should_exist(rails_path('public/sitemap.xml.gz'))
         file_should_exist(rails_path('public/sitemap1.xml.gz'))
         file_should_not_exist(rails_path('public/sitemap2.xml.gz'))
         gzipped_xml_file_should_validate_against_schema rails_path('public/sitemap.xml.gz'), 'sitemap'
         gzipped_xml_file_should_validate_against_schema rails_path('public/sitemap1.xml.gz'), 'sitemap'
+
+        # Test that the index url is reported correctly
+        ls.search_engines = { :google => 'http://google.com/?url=%s' }
+        ls.expects(:open).with("http://google.com/?url=#{CGI.escape('http://example.com/sitemap.xml.gz')}")
+        ls.ping_search_engines
       end
     end
 
@@ -408,15 +440,22 @@ describe "SitemapGenerator" do
         with_max_links(1) do
           ls.create { add('/one') }
         end
+        ls.sitemap_index.link_count.should == 1 # one sitemap
         file_should_exist(rails_path('public/sitemap.xml.gz'))
         file_should_not_exist(rails_path('public/sitemap1.xml.gz'))
         gzipped_xml_file_should_validate_against_schema rails_path('public/sitemap.xml.gz'), 'sitemap'
+
+        # Test that the index url is reported correctly
+        ls.search_engines = { :google => 'http://google.com/?url=%s' }
+        ls.expects(:open).with("http://google.com/?url=#{CGI.escape('http://example.com/sitemap.xml.gz')}")
+        ls.ping_search_engines
       end
 
       it "should create index if more than one sitemap file" do
         with_max_links(1) do
           ls.create { add('/one'); add('/two') }
         end
+        ls.sitemap_index.link_count.should == 2 # two sitemaps
         file_should_exist(rails_path('public/sitemap.xml.gz'))
         file_should_exist(rails_path('public/sitemap1.xml.gz'))
         file_should_exist(rails_path('public/sitemap2.xml.gz'))
@@ -424,6 +463,11 @@ describe "SitemapGenerator" do
         gzipped_xml_file_should_validate_against_schema rails_path('public/sitemap.xml.gz'), 'siteindex'
         gzipped_xml_file_should_validate_against_schema rails_path('public/sitemap1.xml.gz'), 'sitemap'
         gzipped_xml_file_should_validate_against_schema rails_path('public/sitemap2.xml.gz'), 'sitemap'
+
+        # Test that the index url is reported correctly
+        ls.search_engines = { :google => 'http://google.com/?url=%s' }
+        ls.expects(:open).with("http://google.com/?url=#{CGI.escape('http://example.com/sitemap.xml.gz')}")
+        ls.ping_search_engines
       end
 
       it "should create index if more than one group" do
@@ -433,12 +477,18 @@ describe "SitemapGenerator" do
             group(:filename => :group2) { add('/two') };
           end
         end
+        ls.sitemap_index.link_count.should == 2 # two sitemaps
         file_should_exist(rails_path('public/sitemap.xml.gz'))
         file_should_exist(rails_path('public/group1.xml.gz'))
         file_should_exist(rails_path('public/group2.xml.gz'))
         gzipped_xml_file_should_validate_against_schema rails_path('public/sitemap.xml.gz'), 'siteindex'
         gzipped_xml_file_should_validate_against_schema rails_path('public/group1.xml.gz'), 'sitemap'
         gzipped_xml_file_should_validate_against_schema rails_path('public/group2.xml.gz'), 'sitemap'
+
+        # Test that the index url is reported correctly
+        ls.search_engines = { :google => 'http://google.com/?url=%s' }
+        ls.expects(:open).with("http://google.com/?url=#{CGI.escape('http://example.com/sitemap.xml.gz')}")
+        ls.ping_search_engines
       end
     end
   end

metadata

@@ -1,20 +1,19 @@
 --- !ruby/object:Gem::Specification
 name: sitemap_generator
 version: !ruby/object:Gem::Version
-  version: 4.1.0
+  version: 4.1.1
   prerelease: 
 platform: ruby
 authors:
 - Karl Varga
-- Adam Salter
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-06-03 00:00:00.000000000Z
+date: 2013-07-13 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: mocha
-  requirement: &70338921097240 !ruby/object:Gem::Requirement
+  requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -22,10 +21,15 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *70338921097240
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: nokogiri
-  requirement: &70338921096640 !ruby/object:Gem::Requirement
+  requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -33,10 +37,15 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *70338921096640
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: rspec
-  requirement: &70338921096180 !ruby/object:Gem::Requirement
+  requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -44,10 +53,15 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *70338921096180
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: builder
-  requirement: &70338921095700 !ruby/object:Gem::Requirement
+  requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -55,10 +69,16 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *70338921095700
-description: SitemapGenerator is an XML Sitemap generator written in Ruby with automatic
-  Rails integration.  It supports Video, News, Image and Geo sitemaps and includes
-  Rake tasks for managing your sitemaps.
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+description: SitemapGenerator is a framework-agnostic XML Sitemap generator written
+  in Ruby with automatic Rails integration.  It supports Video, News, Image, Geo,
+  Mobile, PageMap and Alternate Links sitemap extensions and includes Rake tasks for
+  managing your sitemaps, as well as many other great features.
 email: kjvarga@gmail.com
 executables: []
 extensions: []
@@ -163,7 +183,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
       version: '0'
       segments:
       - 0
-      hash: -1019294574066130331
+      hash: -880166997178231543
 required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
   requirements:
@@ -172,10 +192,10 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
       segments:
       - 0
-      hash: -1019294574066130331
+      hash: -880166997178231543
 requirements: []
 rubyforge_project: 
-rubygems_version: 1.8.10
+rubygems_version: 1.8.25
 signing_key: 
 specification_version: 3
 summary: Easily generate XML Sitemaps