sitemap_generator 4.0.alpha → 4.0

data/VERSION

@@ -1 +1 @@
-4.0.alpha
+4.0

data/lib/sitemap_generator/builder/sitemap_file.rb

@@ -83,20 +83,20 @@ module SitemapGenerator
       # Call with:
       #   sitemap_url - a SitemapUrl instance
       #   sitemap, options - a Sitemap instance and options hash
-      #   path, options - a path for the URL and options hash
+      #   path, options - a path for the URL and options hash.  For supported options
+      #                   see the SitemapGenerator::Builder::SitemapUrl class.
       #
-      # KJV: We should be using the host from the Location object if no host is
-      # specified in the call to add().  The issue is noticeable when we add links
-      # to a sitemap direct as in the following example:
-      #   ls = SitemapGenerator::LinkSet.new(:default_host => 'http://abc.com')
-      #   ls.sitemap_index.add('/link')
-      # This raises a RuntimeError: Cannot generate a url without a host
-      # Expected: the link added to the sitemap should use the host from its
-      # location object if no host has been specified.
+      # The link added to the sitemap will use the host from its location object
+      # if no host has been specified.
       def add(link, options={})
         raise SitemapGenerator::SitemapFinalizedError if finalized?
 
-        sitemap_url = (link.is_a?(SitemapUrl) ? link : SitemapUrl.new(link, options) )
+        sitemap_url = if link.is_a?(SitemapUrl)
+          link
+        else
+          options[:host] ||= @location.host
+          SitemapUrl.new(link, options)
+        end
 
         xml = sitemap_url.to_xml
         raise SitemapGenerator::SitemapFullError if !file_can_fit?(xml)
@@ -178,8 +178,8 @@ module SitemapGenerator
       # Replace the last 3 characters of string with ... if the string is as big
       # or bigger than max.
       def ellipsis(string, max)
-        if string.size >= max
-          string[0, max - 3] + '...'
+        if string.size > max
+          (string[0, max - 3] || '') + '...'
         else
           string
         end

data/lib/sitemap_generator/builder/sitemap_index_file.rb

@@ -36,6 +36,10 @@ module SitemapGenerator
       # index, and go and write out the first sitemap.  If it's the third or
       # greater sitemap, just finalize and write it out as usual, nothing more
       # needs to be done.
+      #
+      # If a link is being added to the index manually as a string, then we
+      # can assume that the index is required (unless create_index is false of course).
+      # This seems like the logical thing to do.
       alias_method :super_add, :add
       def add(link, options={})
         if file = link.is_a?(SitemapFile) && link
@@ -51,17 +55,24 @@ module SitemapGenerator
           # for there to be an index.
           if @link_count == 0
             @first_sitemap = SitemapGenerator::Builder::LinkHolder.new(file, options)
-            @link_count += 1      # pretend it's added
-          elsif @link_count == 1  # adding second link, need an index so reserve names & write out first sitemap
-            reserve_name unless @location.create_index == false # index gets first name
-            write_first_sitemap
-            file.write
-            super(SitemapGenerator::Builder::SitemapIndexUrl.new(file, options))
+            @link_count += 1     # pretend it's added, but don't add it yet
           else
+            # need an index so make sure name is reserved and first sitemap is written out
+            reserve_name unless @location.create_index == false
+            write_first_sitemap
             file.write
             super(SitemapGenerator::Builder::SitemapIndexUrl.new(file, options))
           end
         else
+          # A link is being added manually.  Obviously the user wants an index.
+          # This overrides the create_index setting.
+          unless @location.create_index == false
+            @create_index = true
+            reserve_name
+          end
+
+          # Use the host from the location if none provided
+          options[:host] ||= @location.host
           super(SitemapGenerator::Builder::SitemapIndexUrl.new(link, options))
         end
       end
@@ -104,9 +115,12 @@ module SitemapGenerator
         super if create_index?
       end
 
-      # Whether or not we need to create an index file.
+      # Whether or not we need to create an index file.  True if create_index is true
+      # or if create_index is :auto and we have more than one link in the index.
+      # If a link is added manually and create_index is not false, we force index
+      # creation because they obviously intend for there to be an index.  False otherwise.
       def create_index?
-        @location.create_index == true || @location.create_index == :auto && @link_count > 1
+        @create_index || @location.create_index == true || @location.create_index == :auto && @link_count > 1
       end
 
       protected

data/lib/sitemap_generator/builder/sitemap_url.rb

@@ -19,6 +19,7 @@ module SitemapGenerator
       # Requires a host to be set.  If passing a sitemap, the sitemap must have a +default_host+
       # configured.  If calling with a path and options, you must include the <tt>:host</tt> option.
       #
+      # * +host+
       # * +priority+
       # * +changefreq+
       # * +lastmod+
@@ -81,7 +82,7 @@ module SitemapGenerator
 
               builder.news :access, news_data[:access] if news_data[:access]
               builder.news :genres, news_data[:genres] if news_data[:genres]
-              builder.news :publication_date, news_data[:publication_date] if news_data[:publication_date]
+              builder.news :publication_date, w3c_date(news_data[:publication_date]) if news_data[:publication_date]
               builder.news :title, news_data[:title] if news_data[:title]
               builder.news :keywords, news_data[:keywords] if news_data[:keywords]
               builder.news :stock_tickers, news_data[:stock_tickers] if news_data[:stock_tickers]
@@ -126,7 +127,8 @@ module SitemapGenerator
           end
 
           self[:alternates].each do |alternate|
-            builder.xhtml :link, :rel => 'alternate', :hreflang => alternate[:lang], :href => alternate[:href]
+            rel = alternate[:nofollow] ? 'alternate nofollow' : 'alternate'
+            builder.xhtml :link, :rel => rel, :hreflang => alternate[:lang], :href => alternate[:href]
           end
 
           unless SitemapGenerator::Utilities.blank?(self[:geo])

data/lib/sitemap_generator/link_set.rb

@@ -4,13 +4,13 @@ require 'builder'
 # which lists all the sitemap files written.
 module SitemapGenerator
   class LinkSet
-    @@requires_finalization_opts = [:filename, :sitemaps_path, :sitemaps_namer, :sitemaps_host]
-    @@new_location_opts = [:filename, :sitemaps_path, :sitemaps_namer]
+    @@requires_finalization_opts = [:filename, :sitemaps_path, :sitemaps_namer, :sitemaps_host, :namer]
+    @@new_location_opts = [:filename, :sitemaps_path, :sitemaps_namer, :namer]
 
-    attr_reader :default_host, :sitemaps_path, :filename
-    attr_accessor :verbose, :yahoo_app_id, :include_root, :include_index, :sitemaps_host, :adapter, :yield_sitemap, :create_index
+    attr_reader :default_host, :sitemaps_path, :filename, :create_index
+    attr_accessor :verbose, :yahoo_app_id, :include_root, :include_index, :sitemaps_host, :adapter, :yield_sitemap
 
-    # Create a new sitemap index and sitemap files.  Pass a block calls to the following
+    # Create a new sitemap index and sitemap files.  Pass a block with calls to the following
     # methods:
     # * +add+   - Add a link to the current sitemap
     # * +group+ - Start a new group of sitemaps
@@ -81,15 +81,15 @@ module SitemapGenerator
     #   to e.g. 'en/'.  Sitemaps are written to <tt>public_path</tt> + <tt>sitemaps_path</tt>
     #
     # * <tt>:filename</tt> - symbol giving the base name for files (default <tt>:sitemap</tt>).
-    #   The sitemap names are generated like "#{filename}1.xml.gz", "#{filename}2.xml.gz"
-    #   and the index name is like "#{filename}_index.xml.gz".
+    #   The names are generated like "#{filename}.xml.gz", "#{filename}1.xml.gz", "#{filename}2.xml.gz"
+    #   with the first file being the index if you have more than one sitemap file.
     #
-    # * <tt>:sitemaps_namer</tt> - A +SitemapNamer+ instance for generating the sitemap names.
-    #
-    # * <tt>:include_index</tt> - Boolean.  Whether to <b>add a link to the sitemap index<b>
+    # * <tt>:include_index</tt> - Boolean.  Whether to <b>add a link pointing to the sitemap index<b>
     #   to the current sitemap.  This points search engines to your Sitemap Index to
     #   include it in the indexing of your site.  Default is `false`.  Turned off when
-    #  `sitemaps_host` is set or within a `group()` block.
+    #  `sitemaps_host` is set or within a `group()` block.  Turned off because Google can complain
+    #   about nested indexing and because if a robot is already reading your sitemap, they
+    #   probably know about the index.
     #
     # * <tt>:include_root</tt> - Boolean.  Whether to **add the root** url i.e. '/' to the
     #   current sitemap.  Default is `true`.  Turned off within a `group()` block.
@@ -100,11 +100,20 @@ module SitemapGenerator
     # * <tt>:verbose</tt> - If +true+, output a summary line for each sitemap and sitemap
     #   index that is created.  Default is +false+.
     #
-    # * <tt>:create_index</tt> - Supported values: `true`, `false`, `:auto`.  Default: `true`.
+    # * <tt>:create_index</tt> - Supported values: `true`, `false`, `:auto`.  Default: `:auto`.
     #   Whether to create a sitemap index file.  If `true` an index file is always created,
     #   regardless of how many links are in your sitemap.  If `false` an index file is never
     #   created.  If `:auto` an index file is created only if your sitemap has more than
-    #   50,000 (or SitemapGenerator::MAX_SITEMAP_LINKS) links.
+    #   one sitemap file.
+    #
+    # * <tt>:namer</tt> - A <tt>SitemapGenerator::SimpleNamer</tt> instance for generating the sitemap
+    #   and index file names.  See <tt>:filename</tt> if you don't need to do anything fancy, and can
+    #   accept the default naming conventions.
+    #
+    # === Deprecated
+    #
+    # * <tt>:sitemaps_namer</tt> - Deprecated, use <tt>:namer</tt>.  A <tt>SitemapGenerator::SitemapNamer</tt> instance for generating the sitemap names.
+    # * <tt>:sitemap_index_namer</tt> - Deprecated, use <tt>:namer</tt>.  A <tt>SitemapGenerator::SitemapIndexNamer</tt> instance for generating the sitemap index name.
     #
     # KJV: When adding a new option be sure to include it in `options_for_group()` if
     # the option should be inherited by groups.
@@ -118,7 +127,7 @@ module SitemapGenerator
           :bing           => "http://www.bing.com/webmaster/ping.aspx?siteMap=%s",
           :sitemap_writer => "http://www.sitemapwriter.com/notify.php?crawler=all&url=%s"
         },
-        :create_index => true
+        :create_index => :auto
       )
       options.each_pair { |k, v| instance_variable_set("@#{k}".to_sym, v) }
 
@@ -172,10 +181,13 @@ module SitemapGenerator
     # be finalized when the block returns.
     #
     # If you are not changing any of the location settings like <tt>filename<tt>,
-    # <tt>sitemaps_path</tt>, <tt>sitemaps_host</tt> or <tt>sitemaps_namer</tt>
-    # links you add within the group will be added to the current sitemap file (e.g. sitemap1.xml).
-    # If one of these options is specified, the current sitemap file is finalized
-    # and a new sitemap file started.
+    # <tt>sitemaps_path</tt>, <tt>sitemaps_host</tt> or <tt>namer</tt>,
+    # links you add within the group will be added to the current sitemap.
+    # Otherwise the current sitemap file is finalized and a new sitemap file started,
+    # using the options you specified.
+    #
+    # Most commonly, you'll want to give the group's files a distinct name using
+    # the <tt>filename</tt> option.
     #
     # Options like <tt>:default_host</tt> can be used and it will only affect the links
     # within the group.  Links added outside of the group will revert to the previous
@@ -187,15 +199,15 @@ module SitemapGenerator
       if (@@requires_finalization_opts & original_opts.keys).empty?
         # If no new filename or path is specified reuse the default sitemap file.
         # A new location object will be set on it for the duration of the group.
-        opts[:sitemap] = sitemap
+        original_opts[:sitemap] = sitemap
       elsif original_opts.key?(:sitemaps_host) && (@@new_location_opts & original_opts.keys).empty?
         # If no location options are provided we are creating the next sitemap in the
         # current series, so finalize and inherit the namer.
         finalize_sitemap!
-        opts[:sitemaps_namer] = sitemaps_namer
+        original_opts[:namer] = namer
       end
 
-      opts = options_for_group(opts)
+      opts = options_for_group(original_opts)
       @group = SitemapGenerator::LinkSet.new(opts)
       if opts.key?(:sitemap)
         # If the group is sharing the current sitemap, set the
@@ -206,9 +218,24 @@ module SitemapGenerator
           @group.interpreter.eval(:yield_sitemap => @yield_sitemap || SitemapGenerator.yield_sitemap?, &block)
           @sitemap.location.merge!(@original_location)
         end
-      elsif block_given?
-        @group.interpreter.eval(:yield_sitemap => @yield_sitemap || SitemapGenerator.yield_sitemap?, &block)
-        @group.finalize_sitemap!
+      else
+        # Handle the case where a user only has one group, and it's being written
+        # to a new sitemap file.  They would expect there to be an index.  So force
+        # index creation.  If there is more than one group, we would have an index anyways,
+        # so it's safe to force index creation in these other cases.  In the case that
+        # the groups reuse the current sitemap, don't force index creation because
+        # we want the default behaviour i.e. only an index if more than one sitemap file.
+        # Don't force index creation if the user specifically requested no index.  This
+        # unfortunately means that if they set it to :auto they may be getting an index
+        # when they didn't expect one, but you shouldn't be using groups if you only have
+        # one sitemap and don't want an index.  Rather, just add the links directly in the create()
+        # block.
+        @group.send(:create_index=, true, true) if @group.create_index != false
+
+        if block_given?
+          @group.interpreter.eval(:yield_sitemap => @yield_sitemap || SitemapGenerator.yield_sitemap?, &block)
+          @group.finalize_sitemap!
+        end
       end
       @group
     end
@@ -234,20 +261,20 @@ module SitemapGenerator
     # a string interpolation that will be replaced by the CGI escaped sitemap
     # index URL.  If you have any literal percent characters in your URL you
     # need to escape them with `%%`.  For example if your sitemap index URL
-    # is `http://example.com/sitemap_index.xml.gz` and your
+    # is `http://example.com/sitemap.xml.gz` and your
     # ping url is `http://example.com/100%%/ping?url=%s`
-    # then the final URL that is pinged will be `http://example.com/100%/ping?url=http%3A%2F%2Fexample.com%2Fsitemap_index.xml.gz`
+    # then the final URL that is pinged will be `http://example.com/100%/ping?url=http%3A%2F%2Fexample.com%2Fsitemap.xml.gz`
     #
     # == Examples
     #
-    # Both of these examples will ping the default search engines in addition to `http://superengine.com/ping?url=http%3A%2F%2Fexample.com%2Fsitemap_index.xml.gz`
+    # Both of these examples will ping the default search engines in addition to `http://superengine.com/ping?url=http%3A%2F%2Fexample.com%2Fsitemap.xml.gz`
     #
     #   SitemapGenerator::Sitemap.host('http://example.com/')
     #   SitemapGenerator::Sitemap.ping_search_engines(:super_engine => 'http://superengine.com/ping?url=%s')
     #
     # Is equivalent to:
     #
-    #   SitemapGenerator::Sitemap.ping_search_engines('http://example.com/sitemap_index.xml.gz', :super_engine => 'http://superengine.com/ping?url=%s')
+    #   SitemapGenerator::Sitemap.ping_search_engines('http://example.com/sitemap.xml.gz', :super_engine => 'http://superengine.com/ping?url=%s')
     def ping_search_engines(*args)
       require 'cgi/session'
       require 'open-uri'
@@ -341,11 +368,11 @@ module SitemapGenerator
     # Set each option on this instance using accessor methods.  This will affect
     # both the sitemap and the sitemap index.
     #
-    # If both `filename` and `sitemaps_namer` are passed, set filename first so it
+    # If both `filename` and `namer` are passed, set filename first so it
     # doesn't override the latter.
     def set_options(opts={})
       opts = opts.dup
-      %w(filename sitemaps_namer).each do |key|
+      %w(filename namer sitemaps_namer).each do |key|
         if value = opts.delete(key.to_sym)
           send("#{key}=", value)
         end
@@ -355,7 +382,7 @@ module SitemapGenerator
       end
     end
 
-    # Given +opts+, return a hash of options prepped for creating a new group from this LinkSet.
+    # Given +opts+, modify it and return it prepped for creating a new group from this LinkSet.
     # If <tt>:public_path</tt> is present in +opts+ it is removed because groups cannot
     # change the public path.
     def options_for_group(opts)
@@ -405,8 +432,7 @@ module SitemapGenerator
     # Finalize a sitemap by including it in the index and outputting a summary line.
     # Do nothing if it has already been finalized.
     #
-    # Don't finalize if the sitemap is empty and a group has been created.  The reason
-    # being that the group will have written out its sitemap.
+    # Don't finalize if the sitemap is empty.
     #
     # Add the default links if they have not been added yet and no groups have been created.
     # If the default links haven't been added we know that the sitemap is empty,
@@ -420,7 +446,7 @@ module SitemapGenerator
       # the index keeps track of how many links are in our sitemaps and we need this info
       # for the summary line.  Also the index determines which file gets the first name
       # so everything has to go via the index.
-      add_to_index(sitemap)
+      add_to_index(sitemap) unless sitemap.empty?
     end
 
     # Finalize a sitemap index and output a summary line.  Do nothing if it has already
@@ -438,11 +464,12 @@ module SitemapGenerator
     end
 
     # Reset this instance.  Keep the same options, but return to the same state
-    # as before an sitemaps were created.
+    # as before any sitemaps were created.
     def reset!
       @sitemap_index = nil if @sitemap_index && @sitemap_index.finalized? && !@protect_index
       @sitemap = nil if @sitemap && @sitemap.finalized?
-      self.sitemaps_namer.reset # start from 1
+      self.namer.reset
+      self.sitemaps_namer.reset if self.sitemaps_namer
       @added_default_links = false
     end
 
@@ -502,14 +529,16 @@ module SitemapGenerator
         update_location_info(:host, value)
       end
 
-      # Set the filename base to use when generating sitemaps and sitemap indexes.
-      # The index name will be +value+ with <tt>_index.xml.gz</tt> appended.
+      # Set the filename base to use when generating sitemaps (and the sitemap index).
+      #
       # === Example
       # <tt>filename = :sitemap</tt>
+      #
+      # === Generates
+      # <tt>sitemap.xml.gz, sitemap1.xml.gz, sitemap2.xml.gz, ...</tt>
       def filename=(value)
         @filename = value
-        self.sitemaps_namer = SitemapGenerator::SitemapNamer.new(@filename)
-        self.sitemap_index_namer = SitemapGenerator::SitemapIndexNamer.new("#{@filename}_index")
+        self.namer = SitemapGenerator::SimpleNamer.new(@filename)
       end
 
       # Set the search engines hash to a new hash of search engine names mapped to
@@ -526,36 +555,11 @@ module SitemapGenerator
         @search_engines || {}
       end
 
-      # Set the namer to use when generating SitemapFiles (does not apply to the
-      # SitemapIndexFile)
-      def sitemaps_namer=(value)
-        @sitemaps_namer = value
-        @sitemap.location[:namer] = value if @sitemap && !@sitemap.finalized?
-      end
-
-      # Return the current sitemaps namer object.  If it not set, looks for it on
-      # the current sitemap and if there is no sitemap, creates a new one using
-      # the current filename.
-      def sitemaps_namer
-        @sitemaps_namer ||= @sitemap && @sitemap.location.namer || SitemapGenerator::SitemapNamer.new(@filename)
-      end
-
-      # Set the namer to use when generating SitemapFiles (does not apply to the
-      # SitemapIndexFile)
-      def sitemap_index_namer=(value)
-        @sitemap_index_namer = value
-        @sitemap_index.location[:namer] = value if @sitemap_index && !@sitemap_index.finalized? && !@protect_index
-      end
-
-      def sitemap_index_namer
-        @sitemap_index_namer ||= @sitemap_index && @sitemap_index.location.namer || SitemapGenerator::SitemapIndexNamer.new("#{@filename}_index")
-      end
-
       # Return a new +SitemapLocation+ instance with the current options included
       def sitemap_location
         SitemapGenerator::SitemapLocation.new(
           :host => sitemaps_host,
-          :namer => sitemaps_namer,
+          :namer => sitemaps_namer || namer,  # sitemaps_namer is deprecated
           :public_path => public_path,
           :sitemaps_path => @sitemaps_path,
           :adapter => @adapter,
@@ -567,7 +571,7 @@ module SitemapGenerator
       def sitemap_index_location
         SitemapGenerator::SitemapLocation.new(
           :host => sitemaps_host,
-          :namer => sitemap_index_namer,
+          :namer => sitemap_index_namer || namer,  # sitemap_index_namer is deprecated
           :public_path => public_path,
           :sitemaps_path => @sitemaps_path,
           :adapter => @adapter,
@@ -576,6 +580,31 @@ module SitemapGenerator
         )
       end
 
+      # Set the value of +create_index+ on the SitemapIndexLocation object of the
+      # SitemapIndexFile.
+      def create_index=(value, force=false)
+        @create_index = value
+        # Allow overriding the protected status of the index when we are creating a group.
+        # Because sometimes we need to force an index in that case.  But generally we don't
+        # want to allow people to mess with this value if the index is protected.
+        @sitemap_index.location[:create_index] = value if @sitemap_index && ((!@sitemap_index.finalized? && !@protect_index) || force)
+      end
+
+      # Set the namer to use to generate the sitemap (and index) file names.
+      # This should be an instance of <tt>SitemapGenerator::SimpleNamer</tt>
+      def namer=(value)
+        @namer = value
+        @sitemap.location[:namer] = value if @sitemap && !@sitemap.finalized?
+        @sitemap_index.location[:namer] = value if @sitemap_index && !@sitemap_index.finalized? && !@protect_index
+      end
+
+      # Return the namer object.  If it is not set, looks for it on
+      # the current sitemap and if there is no sitemap, creates a new one using
+      # the current filename.
+      def namer
+        @namer ||= @sitemap && @sitemap.location.namer || SitemapGenerator::SimpleNamer.new(@filename)
+      end
+
       protected
 
       # Update the given attribute on the current sitemap index and sitemap file location objects.
@@ -587,5 +616,48 @@ module SitemapGenerator
       end
     end
     include LocationHelpers
+
+    module Deprecated
+      # *Deprecated*
+      #
+      # Set the namer to use when generating SitemapFiles (does not apply to the
+      # SitemapIndexFile)
+      #
+      # As of version 4, use the <tt>namer<tt> option.
+      def sitemaps_namer=(value)
+        @sitemaps_namer = value
+        @sitemap.location[:namer] = value if @sitemap && !@sitemap.finalized?
+      end
+
+      # *Deprecated*
+      #
+      # Return the current sitemaps namer object.  If it not set, looks for it on
+      # the current sitemap and if there is no sitemap, creates a new one using
+      # the current filename.
+      #
+      # As of version 4, use the <tt>namer<tt> option.
+      def sitemaps_namer
+        @sitemaps_namer ||= @sitemap && @sitemap.location.namer
+      end
+
+      # *Deprecated*
+      #
+      # Set the namer to use when generating the index file.
+      # The namer should be a <tt>SitemapGenerator::SitemapIndexNamer</tt> instance.
+      #
+      # As of version 4, use the <tt>namer<tt> option.
+      def sitemap_index_namer=(value)
+        @sitemap_index_namer = value
+        @sitemap_index.location[:namer] = value if @sitemap_index && !@sitemap_index.finalized? && !@protect_index
+      end
+
+      # *Deprecated*
+      #
+      # As of version 4, use the <tt>namer<tt> option.
+      def sitemap_index_namer
+        @sitemap_index_namer ||= @sitemap_index && @sitemap_index.location.namer
+      end
+    end
+    include Deprecated
   end
 end