sunspot 0.9.8 → 0.10.0

data/lib/sunspot/setup.rb

@@ -57,6 +57,20 @@ module Sunspot
       @dynamic_field_factories_cache[field_factory.name] = field_factory
     end
 
+    # 
+    # The coordinates field factory is used for populating the coordinate fields
+    # of documents during index, but does not actually generate fields (since
+    # the field names used in search are static).
+    #
+    def set_coordinates_field(name)
+      @coordinates_field_factory = FieldFactory::Coordinates.new(name)
+    end
+
+    # 
+    # Add a document boost to documents at index time. Document boost can be
+    # static (the same for all documents of this class), or extracted on a per-
+    # document basis using either attribute or block extraction as per usual.
+    #
     def add_document_boost(attr_name, &block)
       @document_boost_extractor =
         if attr_name
@@ -77,6 +91,9 @@ module Sunspot
       @dsl.instance_eval(&block)
     end
 
+    # 
+    # Return the Field with the given (public-facing) name
+    #
     def field(field_name)
       if field_factory = @field_factories_cache[field_name.to_sym]
         field_factory.build
@@ -88,17 +105,27 @@ module Sunspot
       end
     end
 
-    def text_field(field_name)
-      if field_factory = @text_field_factories_cache[field_name.to_sym]
-        field_factory.build
-      else
-        raise(
-          UnrecognizedFieldError,
-          "No text field configured for #{@clazz.name} with name '#{field_name}'"
-        )
-      end
+    # 
+    # Return one or more text fields with the given public-facing name. This
+    # implementation will always return a single field (in an array), but
+    # CompositeSetup objects might return more than one.
+    #
+    def text_fields(field_name)
+      text_field = 
+        if field_factory = @text_field_factories_cache[field_name.to_sym]
+          field_factory.build
+        else
+          raise(
+            UnrecognizedFieldError,
+            "No text field configured for #{@clazz.name} with name '#{field_name}'"
+          )
+        end
+      [text_field]
     end
 
+    # 
+    # Return the DynamicFieldFactory with the given base name
+    #
     def dynamic_field_factory(field_name)
       @dynamic_field_factories_cache[field_name.to_sym] || raise(
         UnrecognizedFieldError,
@@ -106,11 +133,17 @@ module Sunspot
       )
     end
 
+    # 
+    # Return all attribute fields
+    #
     def fields
       field_factories.map { |field_factory| field_factory.build }
     end
 
-    def text_fields
+    # 
+    # Return all text fields
+    #
+    def all_text_fields
       text_field_factories.map { |text_field_factory| text_field_factory.build }
     end
 
@@ -148,6 +181,7 @@ module Sunspot
     def all_field_factories
       all_field_factories = []
       all_field_factories.concat(field_factories).concat(text_field_factories).concat(dynamic_field_factories)
+      all_field_factories << @coordinates_field_factory if @coordinates_field_factory
       all_field_factories
     end
 
@@ -173,6 +207,9 @@ module Sunspot
       Util.full_const_get(@class_name)
     end
 
+    # 
+    # Get the document boost for a given model
+    #
     def document_boost_for(model)
       if @document_boost_extractor
         @document_boost_extractor.value_for(model)

data/lib/sunspot/text_field_setup.rb

@@ -0,0 +1,29 @@
+module Sunspot
+  # 
+  # A TextFieldSetup encapsulates a regular (or composite) setup, and exposes
+  # the #field() method returning text fields instead of attribute fields.
+  #
+  class TextFieldSetup #:nodoc:
+    def initialize(setup)
+      @setup = setup
+    end
+
+    # 
+    # Return a text field with the given name. Duck-type compatible with
+    # Setup and CompositeSetup, but return text fields instead.
+    #
+    def field(name)
+      fields = @setup.text_fields(name)
+      if fields
+        if fields.length == 1
+          fields.first
+        else
+          raise(
+            Sunspot::UnrecognizedFieldError,
+            "The text field with name #{name} has incompatible configurations for the classes #{@setup.type_names.join(', ')}"
+          )
+        end
+      end
+    end
+  end
+end

data/lib/sunspot/type.rb

@@ -147,7 +147,7 @@ module Sunspot
           end
         end
 
-        def cast(string)
+        def cast(string) #:nodoc:
           time = Time.xmlschema(string)
           Date.civil(time.year, time.mon, time.mday)
         end
@@ -183,15 +183,15 @@ module Sunspot
 
     module ClassType
       class <<self
-        def indexed_name(name)
+        def indexed_name(name) #:nodoc:
           'class_name'
         end
 
-        def to_indexed(value)
+        def to_indexed(value) #:nodoc:
           value.name
         end
 
-        def cast(string)
+        def cast(string) #:nodoc:
           Sunspot::Util.full_const_get(string)
         end
       end

data/lib/sunspot/util.rb

@@ -66,7 +66,7 @@ module Sunspot
       #
       def full_const_get(string)
         string.split('::').inject(Object) do |context, const_name|
-          context.const_get(const_name)
+          context.const_defined?(const_name) ? context.const_get(const_name) : context.const_missing(const_name)
         end
       end
 
@@ -160,5 +160,31 @@ module Sunspot
         destination
       end
     end
+
+    class Coordinates #:nodoc:
+      def initialize(coords)
+        @coords = coords
+      end
+
+      def lat
+        if @coords.respond_to?(:[])
+          @coords[0]
+        else
+          @coords.lat
+        end.to_f
+      end
+
+      def lng
+        if @coords.respond_to?(:[])
+          @coords[1]
+        elsif @coords.respond_to?(:lng)
+          @coords.lng
+        elsif @coords.respond_to?(:lon)
+          @coords.lon
+        elsif @coords.respond_to?(:long)
+          @coords.long
+        end.to_f
+      end
+    end
   end
 end

data/lib/sunspot.rb

@@ -9,9 +9,10 @@ end
 
 require File.join(File.dirname(__FILE__), 'light_config')
 
-%w(util adapters configuration setup composite_setup field field_factory
-   data_extractor indexer query search facet facet_row instantiated_facet
-   instantiated_facet_row facet_data session type dsl).each do |filename|
+%w(util adapters configuration setup composite_setup text_field_setup field
+   field_factory data_extractor indexer query search facet facet_row
+   instantiated_facet instantiated_facet_row facet_data session type
+   dsl).each do |filename|
   require File.join(File.dirname(__FILE__), 'sunspot', filename)
 end
 
@@ -35,6 +36,7 @@ module Sunspot
   UnrecognizedRestrictionError = Class.new(Exception)
   NoAdapterError = Class.new(Exception)
   NoSetupError = Class.new(Exception)
+  IllegalSearchError = Class.new(Exception)
 
   class <<self
     # Configures indexing and search for a given class.
@@ -221,18 +223,6 @@ module Sunspot
     #   Zero, one, or more types to search for. If no types are passed, all
     #   configured types will be searched.
     #
-    # ==== Options (last argument, optional)
-    #
-    # :keywords<String>:: Fulltext search string
-    # :conditions<Hash>::
-    #   Hash of key-value pairs to be used as restrictions. Keys are field
-    #   names. Scalar values are used as equality restrictions; arrays are used
-    #   as "any of" restrictions; and Ranges are used as range restrictions.
-    # :order<String>:: order field and direction (e.g., 'updated_at desc')
-    # :page<Integer>:: Page to start on for pagination
-    # :per_page<Integer>::
-    #   Number of results to use per page. Ignored if :page is not specified.
-    #
     # ==== Returns
     #
     # Sunspot::Search:: Object containing results, facets, count, etc.
@@ -241,9 +231,10 @@ module Sunspot
     # the following criteria:
     #
     # * They are not of type +text+.
-    # * They are defined for all of the classes being searched
-    # * They have the same data type for all of the classes being searched
+    # * They are defined for at least one of the classes being searched
+    # * They have the same data type for all of the classes being searched.
     # * They have the same multiple flag for all of the classes being searched.
+    # * They have the same stored flag for all of the classes being searched.
     #
     # The restrictions available are the constants defined in the
     # Sunspot::Restriction class. The standard restrictions are:

data/solr/solr/conf/schema.xml

@@ -1,50 +1,64 @@
-<?xml version='1.0' encoding='utf-8' ?>
-<schema name='sunspot' version='0.9'>
+<?xml version="1.0" encoding="UTF-8"?>
+<schema version="0.9" name="sunspot">
   <types>
-    <fieldtype class='solr.TextField' name='text' positionIncrementGap='100'>
+    <fieldtype class="solr.TextField" positionIncrementGap="100" name="text">
       <analyzer>
-        <tokenizer class='solr.StandardTokenizerFactory' />
-        <filter class='solr.StandardFilterFactory' />
-        <filter class='solr.LowerCaseFilterFactory' />
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.StandardFilterFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
       </analyzer>
     </fieldtype>
-    <fieldtype class='solr.RandomSortField' name='rand'></fieldtype>
-    <fieldtype class='solr.BoolField' name='boolean' omitNorms='true' />
-    <fieldtype class='solr.SortableFloatField' name='sfloat' omitNorms='true' />
-    <fieldtype class='solr.DateField' name='date' omitNorms='true' />
-    <fieldtype class='solr.SortableIntField' name='sint' omitNorms='true' />
-    <fieldtype class='solr.StrField' name='string' omitNorms='true' />
+    <fieldtype class="solr.RandomSortField" name="rand"/>
+    <fieldtype name="boolean" class="solr.BoolField" omitNorms="true"/>
+    <fieldtype name="sfloat" class="solr.SortableFloatField" omitNorms="true"/>
+    <fieldtype name="date" class="solr.DateField" omitNorms="true"/>
+    <fieldtype name="sint" class="solr.SortableIntField" omitNorms="true"/>
+    <fieldtype name="string" class="solr.StrField" omitNorms="true"/>
+    <fieldtype name="sdouble" class="solr.SortableDoubleField" omitNorms="true"/>
+    <fieldtype name="slong" class="solr.SortableLongField" omitNorms="true"/>
   </types>
   <fields>
-    <field indexed='true' multiValued='false' name='id' stored='true' type='string' />
-    <field indexed='true' multiValued='true' name='type' stored='false' type='string' />
-    <field indexed='true' multiValued='false' name='class_name' stored='false' type='string' />
-    <field indexed='true' multiValued='true' name='text' stored='false' type='text' />
-    <dynamicField indexed='true' multiValued='true' name='*_text' stored='false' type='text' />
-    <dynamicField indexed='true' name='random_*' stored='false' type='rand' />
-    <dynamicField indexed='true' multiValued='false' name='*_b' stored='false' type='boolean' />
-    <dynamicField indexed='true' multiValued='false' name='*_f' stored='false' type='sfloat' />
-    <dynamicField indexed='true' multiValued='false' name='*_d' stored='false' type='date' />
-    <dynamicField indexed='true' multiValued='false' name='*_i' stored='false' type='sint' />
-    <dynamicField indexed='true' multiValued='false' name='*_s' stored='false' type='string' />
-    <dynamicField indexed='true' multiValued='true' name='*_bm' stored='false' type='boolean' />
-    <dynamicField indexed='true' multiValued='true' name='*_fm' stored='false' type='sfloat' />
-    <dynamicField indexed='true' multiValued='true' name='*_dm' stored='false' type='date' />
-    <dynamicField indexed='true' multiValued='true' name='*_im' stored='false' type='sint' />
-    <dynamicField indexed='true' multiValued='true' name='*_sm' stored='false' type='string' />
-    <dynamicField indexed='true' multiValued='false' name='*_bs' stored='true' type='boolean' />
-    <dynamicField indexed='true' multiValued='false' name='*_fs' stored='true' type='sfloat' />
-    <dynamicField indexed='true' multiValued='false' name='*_ds' stored='true' type='date' />
-    <dynamicField indexed='true' multiValued='false' name='*_is' stored='true' type='sint' />
-    <dynamicField indexed='true' multiValued='false' name='*_ss' stored='true' type='string' />
-    <dynamicField indexed='true' multiValued='true' name='*_bms' stored='true' type='boolean' />
-    <dynamicField indexed='true' multiValued='true' name='*_fms' stored='true' type='sfloat' />
-    <dynamicField indexed='true' multiValued='true' name='*_dms' stored='true' type='date' />
-    <dynamicField indexed='true' multiValued='true' name='*_ims' stored='true' type='sint' />
-    <dynamicField indexed='true' multiValued='true' name='*_sms' stored='true' type='string' />
+    <field name="id"         type="string"  indexed="true" stored="true"  multiValued="false" />
+    <field name="type"       type="string"  indexed="true" stored="false" multiValued="true" />
+    <field name="class_name" type="string"  indexed="true" stored="false" multiValued="false" />
+    <field name="text"       type="text"    indexed="true" stored="false" multiValued="true" />
+    <field name="lat"        type="sdouble" indexed="true" stored="true"  multiValued="false" />
+    <field name="long"       type="sdouble" indexed="true" stored="true"  multiValued="false" />
+    <dynamicField name="*_text"   type="text"    indexed="true" stored="false" multiValued="true" />
+    <dynamicField name="*_texts"  type="text"    indexed="true" stored="true"  multiValued="true" />
+    <dynamicField name="random_*" type="rand"    indexed="true" stored="false" multiValued="false" />
+    <dynamicField name="_local*" type="sdouble" indexed="true" stored="false" multiValued="false" />
+    <dynamicField name="*_b" type="boolean" indexed="true" stored="false" multiValued="false" />
+    <dynamicField name="*_f" type="sfloat" indexed="true" stored="false" multiValued="false" />
+    <dynamicField name="*_d" type="date" indexed="true" stored="false" multiValued="false" />
+    <dynamicField name="*_i" type="sint" indexed="true" stored="false" multiValued="false" />
+    <dynamicField name="*_s" type="string" indexed="true" stored="false" multiValued="false" />
+    <dynamicField name="*_e" type="sdouble" indexed="true" stored="false" multiValued="false" />
+    <dynamicField name="*_l" type="slong" indexed="true" stored="false" multiValued="false" />
+    <dynamicField name="*_bm" type="boolean" indexed="true" stored="false" multiValued="true" />
+    <dynamicField name="*_fm" type="sfloat" indexed="true" stored="false" multiValued="true" />
+    <dynamicField name="*_dm" type="date" indexed="true" stored="false" multiValued="true" />
+    <dynamicField name="*_im" type="sint" indexed="true" stored="false" multiValued="true" />
+    <dynamicField name="*_sm" type="string" indexed="true" stored="false" multiValued="true" />
+    <dynamicField name="*_em" type="sdouble" indexed="true" stored="false" multiValued="true" />
+    <dynamicField name="*_lm" type="slong" indexed="true" stored="false" multiValued="true" />
+    <dynamicField name="*_bs" type="boolean" indexed="true" stored="true" multiValued="false" />
+    <dynamicField name="*_fs" type="sfloat" indexed="true" stored="true" multiValued="false" />
+    <dynamicField name="*_ds" type="date" indexed="true" stored="true" multiValued="false" />
+    <dynamicField name="*_is" type="sint" indexed="true" stored="true" multiValued="false" />
+    <dynamicField name="*_ss" type="string" indexed="true" stored="true" multiValued="false" />
+    <dynamicField name="*_es" type="sdouble" indexed="true" stored="true" multiValued="false" />
+    <dynamicField name="*_ls" type="slong" indexed="true" stored="true" multiValued="false" />
+    <dynamicField name="*_bms" type="boolean" indexed="true" stored="true" multiValued="true" />
+    <dynamicField name="*_fms" type="sfloat" indexed="true" stored="true" multiValued="true" />
+    <dynamicField name="*_dms" type="date" indexed="true" stored="true" multiValued="true" />
+    <dynamicField name="*_ims" type="sint" indexed="true" stored="true" multiValued="true" />
+    <dynamicField name="*_sms" type="string" indexed="true" stored="true" multiValued="true" />
+    <dynamicField name="*_ems" type="sdouble" indexed="true" stored="true" multiValued="true" />
+    <dynamicField name="*_lms" type="slong" indexed="true" stored="true" multiValued="true" />
   </fields>
   <uniqueKey>id</uniqueKey>
   <defaultSearchField>text</defaultSearchField>
-  <solrQueryParser defaultOperator='AND' />
-  <copyField dest='text' source='*_text' />
+  <solrQueryParser defaultOperator="AND"/>
+  <copyField dest="text" source="*_text"/>
 </schema>

data/solr/solr/conf/solrconfig.xml

@@ -34,6 +34,12 @@
 
   <indexDefaults>
    <!-- Values here affect all index writers and act as a default unless overridden. -->
+    %arr{ :name => 'components' }
+      %str localsolr
+      %str facet
+      %str mlt
+      %str highlight
+      %str debug
     <useCompoundFile>false</useCompoundFile>
 
     <mergeFactor>10</mergeFactor>
@@ -693,4 +699,28 @@
     -->
   </admin>
 
+  <!-- configuration for LocalSolr -->
+  <updateRequestProcessorChain>
+    <processor class='com.pjaol.search.solr.update.LocalUpdateProcessorFactory'>
+      <str name='latField'>lat</str>
+      <str name='lngField'>long</str>
+      <int name='startTier'>9</int>
+      <int name='endTier'>16</int>
+    </processor>
+    <processor class='solr.RunUpdateProcessorFactory'></processor>
+    <processor class='solr.LogUpdateProcessorFactory'></processor>
+  </updateRequestProcessorChain>
+  <searchComponent class='com.pjaol.search.solr.component.LocalSolrQueryComponent' name='localsolr'>
+    <str name='latField'>lat</str>
+    <str name='lngField'>long</str>
+  </searchComponent>
+  <requestHandler class='org.apache.solr.handler.component.SearchHandler' name='geo'>
+    <arr name='components'>
+      <str>localsolr</str>
+      <str>facet</str>
+      <str>mlt</str>
+      <str>highlight</str>
+      <str>debug</str>
+    </arr>
+  </requestHandler>
 </config>

data/spec/api/indexer/attributes_spec.rb

@@ -0,0 +1,100 @@
+require File.join(File.dirname(__FILE__), 'spec_helper')
+
+describe 'indexing attribute fields', :type => :indexer do
+  it 'should correctly index a stored string attribute field' do
+    session.index(post(:title => 'A Title'))
+    connection.should have_add_with(:title_ss => 'A Title')
+  end
+
+  it 'should correctly index an integer attribute field' do
+    session.index(post(:blog_id => 4))
+    connection.should have_add_with(:blog_id_i => '4')
+  end
+
+  it 'should correctly index a float attribute field' do
+    session.index(post(:ratings_average => 2.23))
+    connection.should have_add_with(:average_rating_f => '2.23')
+  end
+
+  it 'should allow indexing by a multiple-value field' do
+    session.index(post(:category_ids => [3, 14]))
+    connection.should have_add_with(:category_ids_im => ['3', '14'])
+  end
+
+  it 'should correctly index a time field' do
+    session.index(
+      post(:published_at => Time.parse('1983-07-08 05:00:00 -0400'))
+    )
+    connection.should have_add_with(:published_at_d => '1983-07-08T09:00:00Z')
+  end
+
+  it 'should correctly index a date field' do
+    session.index(post(:expire_date => Date.new(2009, 07, 13)))
+    connection.should have_add_with(:expire_date_d => '2009-07-13T00:00:00Z')
+  end
+
+  it 'should correctly index a boolean field' do
+    session.index(post(:featured => true))
+    connection.should have_add_with(:featured_b => 'true')
+  end
+
+  it 'should correctly index a false boolean field' do
+    session.index(post(:featured => false))
+    connection.should have_add_with(:featured_b => 'false')
+  end
+
+  it 'should not index a nil boolean field' do
+    session.index(post)
+    connection.should_not have_add_with(:featured_b)
+  end
+
+  it 'should index latitude and longitude as a pair' do
+    session.index(post(:coordinates => [40.7, -73.5]))
+    connection.should have_add_with(:lat => 40.7, :long => -73.5)
+  end
+
+  [
+    [:lat, :lng],
+    [:lat, :lon],
+    [:lat, :long]
+  ].each do |lat_attr, lng_attr|
+    it "should index latitude and longitude from #{lat_attr.inspect}, #{lng_attr.inspect}" do
+      session.index(post(
+          :coordinates => OpenStruct.new(lat_attr => 40.7, lng_attr => -73.5)
+      ))
+      connection.should have_add_with(:lat => 40.7, :long => -73.5)
+    end
+  end
+
+  it 'should correctly index an attribute field with block access' do
+    session.index(post(:title => 'The Blog Post'))
+    connection.should have_add_with(:sort_title_s => 'blog post')
+  end
+
+  it 'should correctly index an attribute field with instance-external block access' do
+    session.index(post(:category_ids => [1, 2, 3]))
+    connection.should have_add_with(:primary_category_id_i => '1')
+  end
+
+  it 'should correctly index a field that is defined on a superclass' do
+    Sunspot.setup(SuperClass) { string :author_name }
+    session.index(post(:author_name => 'Mat Brown'))
+    connection.should have_add_with(:author_name_s => 'Mat Brown')
+  end
+
+  it 'should throw a NoMethodError only if a nonexistent type is defined' do
+    lambda { Sunspot.setup(Post) { string :author_name }}.should_not raise_error
+    lambda { Sunspot.setup(Post) { bogus :journey }}.should raise_error(NoMethodError)
+  end
+
+  it 'should throw a NoMethodError if a nonexistent field argument is passed' do
+    lambda { Sunspot.setup(Post) { string :author_name, :bogus => :argument }}.should raise_error(ArgumentError)
+  end
+
+  it 'should throw an ArgumentError if single-value field tries to index multiple values' do
+    lambda do
+      Sunspot.setup(Post) { string :author_name }
+      session.index(post(:author_name => ['Mat Brown', 'Matthew Brown']))
+    end.should raise_error(ArgumentError)
+  end
+end

data/spec/api/indexer/batch_spec.rb

@@ -0,0 +1,46 @@
+require File.join(File.dirname(__FILE__), 'spec_helper')
+
+describe 'batch indexing', :type => :indexer do
+  it 'should send all batched adds in a single request' do
+    posts = Array.new(2) { Post.new }
+    session.batch do
+      for post in posts
+        session.index(post)
+      end
+    end
+    connection.adds.length.should == 1
+  end
+
+  it 'should add all batched adds' do
+    posts = Array.new(2) { Post.new }
+    session.batch do
+      for post in posts
+        session.index(post)
+      end
+    end
+    add = connection.adds.last
+    connection.adds.first.map { |add| add.field_by_name(:id).value }.should ==
+      posts.map { |post| "Post #{post.id}" }
+  end
+
+  it 'should not index changes to models that happen after index call' do
+    post = Post.new
+    session.batch do
+      session.index(post)
+      post.title = 'Title'
+    end
+    connection.adds.first.first.field_by_name(:title_ss).should be_nil
+  end
+
+  it 'should batch an add and a delete' do
+    pending 'batching all operations'
+    connection.should_not_receive(:add)
+    connection.should_not_receive(:remove)
+    posts = Array.new(2) { Post.new }
+    session.batch do
+      session.index(posts[0])
+      session.remove(posts[1])
+    end
+    connection.adds
+  end
+end

data/spec/api/indexer/dynamic_fields_spec.rb

@@ -0,0 +1,33 @@
+require File.join(File.dirname(__FILE__), 'spec_helper')
+
+describe 'indexing dynamic fields' do
+  it 'indexes string data' do
+    session.index(post(:custom_string => { :test => 'string' }))
+    connection.should have_add_with(:"custom_string:test_s" => 'string')
+  end
+
+  it 'indexes integer data with virtual accessor' do
+    session.index(post(:category_ids => [1, 2]))
+    connection.should have_add_with(:"custom_integer:1_i" => '1', :"custom_integer:2_i" => '1')
+  end
+
+  it 'indexes float data' do
+    session.index(post(:custom_fl => { :test => 1.5 }))
+    connection.should have_add_with(:"custom_float:test_fm" => '1.5')
+  end
+
+  it 'indexes time data' do
+    session.index(post(:custom_time => { :test => Time.parse('2009-05-18 18:05:00 -0400') }))
+    connection.should have_add_with(:"custom_time:test_d" => '2009-05-18T22:05:00Z')
+  end
+
+  it 'indexes boolean data' do
+    session.index(post(:custom_boolean => { :test => false }))
+    connection.should have_add_with(:"custom_boolean:test_b" => 'false')
+  end
+
+  it 'indexes multiple values for a field' do
+    session.index(post(:custom_fl => { :test => [1.0, 2.1, 3.2] }))
+    connection.should have_add_with(:"custom_float:test_fm" => %w(1.0 2.1 3.2))
+  end
+end