gojee-sunspot 2.0.3 → 2.0.4

data/lib/sunspot/schema.rb

@@ -0,0 +1,151 @@
+require 'erb'
+
+module Sunspot
+  # 
+  # Object that encapsulates schema information for building a Solr schema.xml
+  # file. This class is used by the schema:compile task as well as the
+  # sunspot-configure-solr executable.
+  #
+  class Schema #:nodoc:all
+    FieldType = Struct.new(:name, :class_name, :suffix)
+    FieldVariant = Struct.new(:attribute, :suffix)
+
+    DEFAULT_TOKENIZER = 'solr.StandardTokenizerFactory'
+    DEFAULT_FILTERS = %w(solr.StandardFilterFactory solr.LowerCaseFilterFactory)
+
+    FIELD_TYPES = [
+      FieldType.new('boolean', 'Bool', 'b'),
+      FieldType.new('sfloat', 'SortableFloat', 'f'),
+      FieldType.new('date', 'Date', 'd'),
+      FieldType.new('sint', 'SortableInt', 'i'),
+      FieldType.new('string', 'Str', 's'),
+      FieldType.new('sdouble', 'SortableDouble', 'e'),
+      FieldType.new('slong', 'SortableLong', 'l'),
+      FieldType.new('tint', 'TrieInteger', 'it'),
+      FieldType.new('tfloat', 'TrieFloat', 'ft'),
+      FieldType.new('tdate', 'TrieInt', 'dt')
+
+    ]
+
+    FIELD_VARIANTS = [
+      FieldVariant.new('multiValued', 'm'),
+      FieldVariant.new('stored', 's')
+    ]
+
+    attr_reader :tokenizer, :filters
+
+    def initialize
+      @tokenizer = DEFAULT_TOKENIZER
+      @filters = DEFAULT_FILTERS.dup
+    end
+
+    # 
+    # Attribute field types defined in the schema
+    #
+    def types
+      FIELD_TYPES
+    end
+
+    # 
+    # DynamicField instances representing all the available types and variants
+    #
+    def dynamic_fields
+      fields = []
+      variant_combinations.each do |field_variants|
+        FIELD_TYPES.each do |type|
+          fields << DynamicField.new(type, field_variants)
+        end
+      end
+      fields
+    end
+
+    # 
+    # Which tokenizer to use for text fields
+    #
+    def tokenizer=(tokenizer)
+      @tokenizer = 
+        if tokenizer =~ /\./
+          tokenizer
+        else
+          "solr.#{tokenizer}TokenizerFactory"
+        end
+    end
+
+    # 
+    # Add a filter for text field tokenization
+    #
+    def add_filter(filter)
+      @filters <<
+        if filter =~ /\./
+          filter
+        else
+          "solr.#{filter}FilterFactory"
+        end
+    end
+
+    # 
+    # Return an XML representation of this schema using the ERB template
+    #
+    def to_xml
+      template = File.join(File.dirname(__FILE__), '..', '..', 'templates', 'schema.xml.erb')
+      ERB.new(File.read(template), nil, '-').result(binding)
+    end
+
+    private
+
+    #
+    # All of the possible combinations of variants
+    #
+    def variant_combinations
+      combinations = []
+      0.upto(2 ** FIELD_VARIANTS.length - 1) do |b|
+        combinations << combination = []
+        FIELD_VARIANTS.each_with_index do |variant, i|
+          combination << variant if b & 1<<i > 0
+        end
+      end
+      combinations
+    end
+
+    # 
+    # Represents a dynamic field (in the Solr schema sense, not the Sunspot
+    # sense).
+    #
+    class DynamicField
+      def initialize(type, field_variants)
+        @type, @field_variants = type, field_variants
+      end
+
+      # 
+      # Name of the field in the schema
+      #
+      def name
+        variant_suffixes = @field_variants.map { |variant| variant.suffix }.join
+        "*_#{@type.suffix}#{variant_suffixes}"
+      end
+
+      # 
+      # Name of the type as defined in the schema
+      #
+      def type
+        @type.name
+      end
+
+      # 
+      # Implement magic methods to ask if a field is of a particular variant.
+      # Returns "true" if the field is of that variant and "false" otherwise.
+      #
+      def method_missing(name, *args, &block)
+        if name.to_s =~ /\?$/ && args.empty?
+          if @field_variants.any? { |variant| "#{variant.attribute}?" == name.to_s }
+            'true'
+          else
+            'false'
+          end
+        else
+          super(name.to_sym, *args, &block)
+        end
+      end
+    end
+  end
+end

data/lib/sunspot/search/abstract_search.rb

@@ -0,0 +1,281 @@
+require 'sunspot/search/paginated_collection'
+require 'sunspot/search/hit_enumerable'
+
+module Sunspot
+  module Search #:nodoc:
+    
+    # 
+    # This class encapsulates the results of a Solr search. It provides access
+    # to search results, total result count, facets, and pagination information.
+    # Instances of Search are returned by the Sunspot.search and
+    # Sunspot.new_search methods.
+    #
+    class AbstractSearch
+      # 
+      # Retrieve all facet objects defined for this search, in order they were
+      # defined. To retrieve an individual facet by name, use #facet()
+      #
+      attr_reader :facets, :groups
+      attr_reader :query #:nodoc:
+      attr_accessor :request_handler
+
+      include HitEnumerable
+  
+      def initialize(connection, setup, query, configuration) #:nodoc:
+        @connection, @setup, @query = connection, setup, query
+        @query.paginate(1, configuration.pagination.default_per_page)
+
+        @facets = []
+        @facets_by_name = {}
+
+        @groups_by_name = {}
+        @groups = []
+      end
+  
+      #
+      # Execute the search on the Solr instance and store the results. If you
+      # use Sunspot#search() to construct your searches, there is no need to call
+      # this method as it has already been called. If you use
+      # Sunspot#new_search(), you will need to call this method after building the
+      # query.
+      #
+      def execute
+        reset
+        params = @query.to_params
+        @solr_result = @connection.post "#{request_handler}", :data => params
+        self
+      end
+
+      def execute! #:nodoc: deprecated
+        execute
+      end
+  
+      # 
+      # Get the collection of results as instantiated objects. If WillPaginate is
+      # available, the results will be a WillPaginate::Collection instance; if
+      # not, it will be a vanilla Array.
+      #
+      # If not all of the results referenced by the Solr hits actually exist in
+      # the data store, Sunspot will only return the results that do exist.
+      #
+      # ==== Returns
+      #
+      # WillPaginate::Collection or Array:: Instantiated result objects
+      #
+      def results
+        @results ||= paginate_collection(verified_hits.map { |hit| hit.instance })
+      end
+  
+      # 
+      # Access raw Solr result information. Returns a collection of Hit objects
+      # that contain the class name, primary key, keyword relevance score (if
+      # applicable), and any stored fields.
+      #
+      # ==== Options (options)
+      #
+      # :verify::
+      #   Only return hits that reference objects that actually exist in the data
+      #   store. This causes results to be eager-loaded from the data store,
+      #   unlike the normal behavior of this method, which only loads the
+      #   referenced results when Hit#result is first called.
+      #
+      # ==== Returns
+      #
+      # Array:: Ordered collection of Hit objects
+      #
+      def hits(options = {})
+        if options[:verify]
+          super
+        else
+          @hits ||= paginate_collection(super)
+        end
+      end
+      alias_method :raw_results, :hits
+
+      # 
+      # The total number of documents matching the query parameters
+      #
+      # ==== Returns
+      #
+      # Integer:: Total matching documents
+      #
+      def total
+        @total ||= solr_response['numFound'] || 0
+      end
+  
+      # 
+      # The time elapsed to generate the Solr response
+      #
+      # ==== Returns
+      #
+      # Integer:: Query runtime in milliseconds
+      #
+      def query_time
+        @query_time ||= solr_response_header['QTime']
+      end
+  
+      # 
+      # Get the facet object for the given name. `name` can either be the name
+      # given to a query facet, or the field name of a field facet. Returns a
+      # Sunspot::Facet object.
+      #
+      # ==== Parameters
+      #
+      # name<Symbol>::
+      #   Name of the field to return the facet for, or the name given to the
+      #   query facet when the search was constructed.
+      # dynamic_name<Symbol>::
+      #   If faceting on a dynamic field, this is the dynamic portion of the field
+      #   name.
+      #
+      # ==== Example:
+      #
+      #   search = Sunspot.search(Post) do
+      #     facet :category_ids
+      #     dynamic :custom do
+      #       facet :cuisine
+      #     end
+      #     facet :age do
+      #       row 'Less than a month' do
+      #         with(:published_at).greater_than(1.month.ago)
+      #       end
+      #       row 'Less than a year' do
+      #         with(:published_at, 1.year.ago..1.month.ago)
+      #       end
+      #       row 'More than a year' do
+      #         with(:published_at).less_than(1.year.ago)
+      #       end
+      #     end
+      #   end
+      #   search.facet(:category_ids)
+      #     #=> Facet for :category_ids field
+      #   search.facet(:custom, :cuisine)
+      #     #=> Facet for the dynamic field :cuisine in the :custom field definition
+      #   search.facet(:age)
+      #     #=> Facet for the query facet named :age
+      #
+      def facet(name, dynamic_name = nil)
+        if name
+          if dynamic_name
+            @facets_by_name[:"#{name}:#{dynamic_name}"]
+          else
+            @facets_by_name[name.to_sym]
+          end
+        end
+      end
+
+      def group(name)
+        if name
+          @groups_by_name[name.to_sym]
+        end
+      end
+  
+      # 
+      # Deprecated in favor of optional second argument to #facet
+      #
+      def dynamic_facet(base_name, dynamic_name) #:nodoc:
+        facet(base_name, dynamic_name)
+      end
+  
+      def facet_response #:nodoc:
+        @solr_result['facet_counts']
+      end
+
+      def group_response #:nodoc:
+        @solr_result['grouped']
+      end
+  
+      # 
+      # Build this search using a DSL block. This method can be called more than
+      # once on an unexecuted search (e.g., Sunspot.new_search) in order to build
+      # a search incrementally.
+      #
+      # === Example
+      #
+      #   search = Sunspot.new_search(Post)
+      #   search.build do
+      #     with(:published_at).less_than Time.now
+      #   end
+      #   search.execute
+      #
+      def build(&block)
+        Util.instance_eval_or_call(dsl, &block)
+        self
+      end
+  
+  
+      def inspect #:nodoc:
+        "<Sunspot::Search:#{query.to_params.inspect}>"
+      end
+
+      def add_field_group(field, options = {}) #:nodoc:
+        add_group(field.name, FieldGroup.new(field, self, options))
+      end
+  
+      def add_field_facet(field, options = {}) #:nodoc:
+        name = (options[:name] || field.name)
+        add_facet(name, FieldFacet.new(field, self, options))
+      end
+  
+      def add_query_facet(name, options) #:nodoc:
+        add_facet(name, QueryFacet.new(name, self, options))
+      end
+  
+      def add_date_facet(field, options) #:nodoc:
+        name = (options[:name] || field.name)
+        add_facet(name, DateFacet.new(field, self, options))
+      end
+
+      def highlights_for(doc) #:nodoc:
+        if @solr_result['highlighting']
+          @solr_result['highlighting'][doc['id']]
+        end
+      end
+  
+      private
+  
+      def dsl
+        raise NotImplementedError 
+      end
+  
+      def execute_request(params)
+        raise NotImplementedError
+      end
+  
+      def solr_response
+        @solr_response ||= @solr_result['response'] || {}
+      end
+  
+      def solr_response_header
+        @solr_response_header ||= @solr_result['responseHeader'] || {}
+      end
+
+      def solr_docs
+        solr_response['docs']
+      end
+  
+      def verified_hits
+        @verified_hits ||= paginate_collection(super)
+      end
+  
+      def paginate_collection(collection)
+        PaginatedCollection.new(collection, @query.page, @query.per_page, total)
+      end
+  
+      def add_facet(name, facet)
+        @facets << facet
+        @facets_by_name[name.to_sym] = facet
+      end
+
+      def add_group(name, group)
+        @groups << group
+        @groups_by_name[name.to_sym] = group
+      end
+      
+      # Clear out all the cached ivars so the search can be called again.
+      def reset
+        @results = @hits = @verified_hits = @total = @solr_response = @doc_ids = nil
+      end
+    end
+  end
+end

data/lib/sunspot/search/date_facet.rb

@@ -0,0 +1,35 @@
+module Sunspot
+  module Search
+    class DateFacet
+      def initialize(field, search, options)
+        @field, @search, @options = field, search, options
+      end
+
+      def field_name
+        @field.name
+      end
+
+      def rows
+        @rows ||=
+          begin
+            data = @search.facet_response['facet_dates'][@field.indexed_name]
+            gap = (@options[:time_interval] || 86400).to_i
+            rows = []
+            data.each_pair do |value, count|
+              if value =~ /^\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}Z$/
+                start_time = @field.cast(value)
+                end_time = start_time + gap
+                rows << FacetRow.new(start_time..end_time, count, self)
+              end
+            end
+            if @options[:sort] == :count
+              rows.sort! { |lrow, rrow| rrow.count <=> lrow.count }
+            else
+              rows.sort! { |lrow, rrow| lrow.value.first <=> rrow.value.first }
+            end
+            rows
+          end
+      end
+    end
+  end
+end

data/lib/sunspot/search/facet_row.rb

@@ -0,0 +1,27 @@
+module Sunspot
+  module Search
+    class FacetRow
+      attr_reader :value, :count
+      attr_writer :instance #:nodoc:
+
+      def initialize(value, count, facet) #:nodoc:
+        @value, @count, @facet = value, count, facet
+      end
+
+      # 
+      # Return the instance referenced by this facet row. Only valid for field
+      # facets whose fields are defined with the :references key.
+      #
+      def instance
+        if !defined?(@instance)
+          @facet.populate_instances
+        end
+        @instance
+      end
+
+      def inspect
+        "<Sunspot::Search::FacetRow:#{value.inspect} (#{count})>"
+      end
+    end
+  end
+end

data/lib/sunspot/search/field_facet.rb

@@ -0,0 +1,88 @@
+module Sunspot
+  module Search
+    # 
+    # A FieldFacet is a facet whose rows are all values for a certain field, in
+    # contrast to a QueryFacet, whose rows represent arbitrary queries.
+    #
+    class FieldFacet < QueryFacet
+      def initialize(field, search, options) #:nodoc:
+        super((options[:name] || field.name).to_sym, search, options)
+        @field = field
+      end
+
+      def field_name
+        @field.name
+      end
+
+      # 
+      # Get the rows returned for this facet.
+      #
+      # ==== Options (options)
+      #
+      # :verify::
+      #   Only return rows for which the referenced object exists in the data
+      #   store. This option is ignored unless the field associated with this
+      #   facet is configured with a :references argument.
+      #
+      # ==== Returns
+      #
+      # Array:: Array of FacetRow objects
+      #
+      def rows(options = {})
+        if options[:verify]
+          verified_rows
+        else
+          @rows ||=
+            begin
+              rows = super
+              has_query_facets = !rows.empty?
+              if @search.facet_response['facet_fields']
+                if data = @search.facet_response['facet_fields'][key]
+                  data.each_slice(2) do |value, count|
+                    row = FacetRow.new(@field.cast(value), count, self)
+                    rows << row
+                  end
+                end
+              end
+              sort_rows!(rows) if has_query_facets
+              rows
+            end
+        end
+      end
+
+      # 
+      # If this facet references a model class, populate the rows with instances
+      # of the model class by loading them out of the appropriate adapter.
+      #
+      def populate_instances #:nodoc:
+        if reference = @field.reference
+          values_hash = rows.inject({}) do |hash, row|
+            hash[row.value] = row
+            hash
+          end
+          instances = Adapters::DataAccessor.create(Sunspot::Util.full_const_get(reference)).load_all(
+            values_hash.keys
+          )
+          instances.each do |instance|
+            values_hash[Adapters::InstanceAdapter.adapt(instance).id].instance = instance
+          end
+          true
+        end
+      end
+
+      private
+
+      def verified_rows
+        if @field.reference
+          @verified_rows ||= rows.select { |row| row.instance }
+        else
+          rows
+        end
+      end
+      
+      def key
+        @key ||= (@options[:name] || @field.indexed_name).to_s
+      end
+    end
+  end
+end

data/lib/sunspot/search/field_group.rb

@@ -0,0 +1,32 @@
+module Sunspot
+  module Search
+    class FieldGroup
+      def initialize(field, search, options) #:nodoc:
+        @field, @search, @options = field, search, options
+      end
+
+      def groups
+        @groups ||=
+          begin
+            if solr_response
+              solr_response['groups'].map do |group|
+                Group.new(group['groupValue'], group['doclist'], @search)
+              end
+            end
+          end
+      end
+
+      def matches
+        if solr_response
+          solr_response['matches'].to_i
+        end
+      end
+
+      private
+
+      def solr_response
+        @search.group_response[@field.indexed_name.to_s]
+      end
+    end
+  end
+end

data/lib/sunspot/search/group.rb

@@ -0,0 +1,50 @@
+require 'sunspot/search/hit_enumerable'
+
+module Sunspot
+  module Search
+    class Group
+      attr_reader :value
+
+      include HitEnumerable
+
+      def initialize(value, doclist, search)
+        @value, @doclist, @search = value, doclist, search
+      end
+
+      def hits(options = {})
+        if options[:verify]
+          super
+        else
+          @hits ||= super
+        end
+      end
+
+      def verified_hits
+        @verified_hits ||= super
+      end
+
+      def results
+        @results ||= verified_hits.map { |hit| hit.instance }
+      end
+
+      def highlights_for(doc)
+        @search.highlights_for(doc)
+      end
+
+      def solr_docs
+        @doclist['docs']
+      end
+      
+      #
+      # The total number of documents matching the query for this group
+      #
+      # ==== Returns
+      #
+      # Integer:: Total matching documents
+      # 
+      def total
+        @doclist['numFound']
+      end      
+    end
+  end
+end

data/lib/sunspot/search/highlight.rb

@@ -0,0 +1,38 @@
+module Sunspot
+  module Search
+    # 
+    # A Highlight represents a single highlighted fragment of text from a
+    # document. Depending on the highlighting parameters used for search, there
+    # may be more than one Highlight object for a given field in a given result.
+    #
+    class Highlight
+      HIGHLIGHT_MATCHER = /@@@hl@@@(.*?)@@@endhl@@@/ #:nodoc:
+      
+      #
+      # The name of the field in which the highlight appeared.
+      #
+      attr_reader :field_name
+            
+      def initialize(field_name, highlight) #:nodoc:
+        @field_name = field_name.to_sym
+        @highlight = highlight.to_s.strip
+      end
+      
+      #
+      # Returns the highlighted text with formatting according to the template given in &block.
+      # When no block is given, <em> and </em> are used to surround the highlight.
+      #
+      # ==== Example
+      #
+      #   search.highlights(:body).first.format { |word| "<strong>#{word}</strong>" }
+      #
+      def format(&block)
+        block ||= proc { |word| "<em>#{word}</em>" }
+        @highlight.gsub(HIGHLIGHT_MATCHER) do
+          block.call(Regexp.last_match[1])
+        end
+      end
+      alias_method :formatted, :format
+    end
+  end
+end