sunspot 2.0.0 → 2.5.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 179de5f5261bdb69d21038a0b2e36fbd2812e1fc71ef4c1efd77979a03e58179
+  data.tar.gz: 1f7f40d9737400cf61c23515c61ebde70140b1c1bf9df800d7e19ce27c3cbd0d
+SHA512:
+  metadata.gz: ad59d5868f3461648d29c77b6368d7c5145ef6247ecca38878bf4f03bb3d2ab73fea2decf629936d58282b8067345198f6bff82be1347bb0cc92cb4537722d28
+  data.tar.gz: 3c4fd67940331fbdacffd665ca624119038bf12da2aa2b041adbd8260aef3921660b83803a912cf81384c7269f6b46d3b7fad1c883c34e1a1ba2ccbade2fd6dc

data/.gitignore

@@ -11,3 +11,4 @@ pkg
 README.rdoc
 .bundle
 Gemfile.lock
+gemfiles/*.gemfile*

data/.rspec

@@ -0,0 +1,2 @@
+--color
+--format progress

data/Appraisals

@@ -0,0 +1,7 @@
+appraise 'rsolr-1.x' do
+  gem 'rsolr', '>= 1', '< 2'
+end
+
+appraise 'rsolr-2.x' do
+  gem 'rsolr', '>= 2', '< 3'
+end

data/Gemfile

@@ -1,5 +1,3 @@
 source "http://rubygems.org"
 
-gem 'sunspot_solr', :path => File.expand_path('../../sunspot_solr', __FILE__)
-
 gemspec

data/History.txt

@@ -1,3 +1,13 @@
+== 2.1.0
+* Dropped support for rails 2.x. Added support for Rails 4.
+* Bundled Solr installation (`sunspot_solr`) is version 4.2.0
+* Upgrade to Jetty 8 and changed solr config directory structure.
+* Removed interactive warning prompt from sunspot:reindex rake task.
+* Support Rails 4 custom primary keys i.e. UUID
+* Switch to EDismax query parser from dismax.
+* Extend Sunspot.remove! to accept a block, and enable .remove_by_id! to accept multiple ids.
+* add 'order_by_function' method to field queries. Allowing for Solr FunctionQuery, nesting, and literal constants.
+
 == 2.0.0
 * Adds support for field grouping (Andy Lindeman)
 * Adds support for native geospatial searches and ordering (Eric Tang, Bruno Miranda, Andy Lindeman)

data/lib/sunspot.rb

@@ -196,23 +196,61 @@ module Sunspot
       session.index!(*objects)
     end
 
-    # Commits the singleton session
+    # Atomic update object properties on the singleton session.
+    #
+    # ==== Parameters
+    #
+    # clazz<Class>:: the class of the objects to be updated
+    # updates<Hash>:: hash of updates where keys are model ids
+    #                 and values are hash with property name/values to be updated
+    #
+    # ==== Example
+    #
+    #   post1, post2 = new Array(2) { Post.create }
+    #   Sunspot.atomic_update(Post, post1.id => {title: 'New Title'}, post2.id => {description: 'new description'})
+    #
+    # Note that indexed objects won't be reflected in search until a commit is
+    # sent - see Sunspot.index! and Sunspot.commit
+    #
+    def atomic_update(clazz, updates = {})
+      session.atomic_update(clazz, updates)
+    end
+
+    # Atomic update object properties on the singleton session.
+    #
+    # See: Sunspot.atomic_update and Sunspot.commit
+    #
+    # ==== Parameters
+    #
+    # clazz<Class>:: the class of the objects to be updated
+    # updates<Hash>:: hash of updates where keys are model ids
+    #                 and values are hash with property name/values to be updated
+    #
+    def atomic_update!(clazz, updates = {})
+      session.atomic_update!(clazz, updates)
+    end
+
+    # Commits (soft or hard) the singleton session
     #
     # When documents are added to or removed from Solr, the changes are
     # initially stored in memory, and are not reflected in Solr's existing
-    # searcher instance. When a commit message is sent, the changes are written
+    # searcher instance. When a hard commit message is sent, the changes are written
     # to disk, and a new searcher is spawned. Commits are thus fairly
     # expensive, so if your application needs to index several documents as part
     # of a single operation, it is advisable to index them all and then call
     # commit at the end of the operation.
+    # Solr 4 introduced the concept of a soft commit which is much faster
+    # since it only makes index changes visible while not writing changes to disk.
+    # If Solr crashes or there is a loss of power, changes that occurred after
+    # the last hard commit will be lost.
     #
     # Note that Solr can also be configured to automatically perform a commit
     # after either a specified interval after the last change, or after a
     # specified number of documents are added. See
     # http://wiki.apache.org/solr/SolrConfigXml
     #
-    def commit
-      session.commit
+    def commit(soft_commit = false)
+      session.commit soft_commit
     end
 
     # Optimizes the index on the singletion session.
@@ -417,8 +455,8 @@ module Sunspot
     #
     # objects...<Object>:: Objects to remove from the index
     #
-    def remove!(*objects)
-      session.remove!(*objects)
+    def remove!(*objects, &block)
+      session.remove!(*objects, &block)
     end
 
     # 
@@ -433,16 +471,16 @@ module Sunspot
     #   Primary key of the object. This should be the same id that would be
     #   returned by the class's instance adapter.
     #
-    def remove_by_id(clazz, id)
-      session.remove_by_id(clazz, id)
+    def remove_by_id(clazz, *ids)
+      session.remove_by_id(clazz, ids)
     end
 
     # 
     # Remove an object by class name and primary key, and immediately commit.
     # See #remove_by_id and #commit
     #
-    def remove_by_id!(clazz, id)
-      session.remove_by_id!(clazz, id)
+    def remove_by_id!(clazz, *ids)
+      session.remove_by_id!(clazz, ids)
     end
 
     # Remove all objects of the given classes from the index. There isn't much
@@ -486,9 +524,9 @@ module Sunspot
     #
     #   Sunspot.batch do
     #     post = Post.new
-    #     Sunspot.add(post)
+    #     Sunspot.index(post)
     #     comment = Comment.new
-    #     Sunspot.add(comment)
+    #     Sunspot.index(comment)
     #   end
     #
     # Sunspot will send both the post and the comment in a single request.
@@ -510,10 +548,10 @@ module Sunspot
     end
 
     # 
-    # Sends a commit if the session is dirty (see #dirty?).
+    # Sends a commit (soft or hard) if the session is dirty (see #dirty?).
     #
-    def commit_if_dirty
-      session.commit_if_dirty
+    def commit_if_dirty(soft_commit = false)
+      session.commit_if_dirty soft_commit
     end
     
     #
@@ -530,8 +568,8 @@ module Sunspot
     # 
     # Sends a commit if the session has deletes since the last commit (see #delete_dirty?).
     #
-    def commit_if_delete_dirty
-      session.commit_if_delete_dirty
+    def commit_if_delete_dirty(soft_commit = false)
+      session.commit_if_delete_dirty soft_commit
     end
     
     # Returns the configuration associated with the singleton session. See

data/lib/sunspot/adapters.rb

@@ -1,3 +1,5 @@
+require 'forwardable'
+
 module Sunspot
   #
   # Sunspot works by saving references to the primary key (or natural ID) of
@@ -46,7 +48,7 @@ module Sunspot
     #   end
     #
     #   # then in your initializer
-    #   Sunspot::Adapters::InstanceAdapter.register(MyAdapter, File)
+    #   Sunspot::Adapters::InstanceAdapter.register(FileAdapter, File)
     #
     class InstanceAdapter
       def initialize(instance) #:nodoc:
@@ -61,7 +63,10 @@ module Sunspot
       # String:: ID for use in Solr
       #
       def index_id #:nodoc:
-        InstanceAdapter.index_id_for(@instance.class.name, id)
+        setup     = Sunspot::Setup.for(@instance.class)
+        id_prefix = setup ? setup.id_prefix_for(@instance) : nil
+
+        InstanceAdapter.index_id_for("#{id_prefix}#{@instance.class.name}", id)
       end
 
       class <<self
@@ -119,16 +124,28 @@ module Sunspot
         #
         # Sunspot::NoAdapterError:: If no adapter is registered for this class
         #
-        def for(clazz) #:nodoc:
-          original_class_name = clazz.name
-          clazz.ancestors.each do |ancestor_class|
-            next if ancestor_class.name.nil? || ancestor_class.name.empty?
-            class_name = ancestor_class.name.to_sym
-            return instance_adapters[class_name] if instance_adapters[class_name]
-          end
-
+        def for(clazz)
+          adapter = registered_adapter_for(clazz) || registered_adapter_for_ancestors_of(clazz)
+          return adapter if adapter
           raise(Sunspot::NoAdapterError,
-                "No adapter is configured for #{original_class_name} or its superclasses. See the documentation for Sunspot::Adapters")
+                "No adapter is configured for #{clazz.name} or its superclasses. See the documentation for Sunspot::Adapters")
+        end
+
+        # Returns the directly-registered adapter for the specified class,
+        # if one exists, without searching the class's ancestors.
+        #
+        # === Parameters
+        #
+        # clazz<Class>:: The model class to be checked for the registered
+        #   adapter
+        #
+        # === Returns
+        #
+        # Class:: Subclass of InstanceAdapter, or nil if none found
+        #
+        def registered_adapter_for(clazz)
+          return nil if clazz.name.nil? || clazz.name.empty?
+          instance_adapters[clazz.name.to_sym]
         end
 
         def index_id_for(class_name, id) #:nodoc:
@@ -146,6 +163,16 @@ module Sunspot
         def instance_adapters #:nodoc:
           @instance_adapters ||= {}
         end
+
+        def registered_adapter_for_ancestors_of(clazz) # :nodoc:
+          clazz.ancestors.each do |ancestor_class|
+            if adapter = registered_adapter_for(ancestor_class)
+              register(adapter, clazz)
+              return adapter
+            end
+          end
+          nil
+        end
       end
     end
 
@@ -247,14 +274,27 @@ module Sunspot
         # Sunspot::NoAdapterError:: If no data accessor exists for the given class
         #
         def for(clazz) #:nodoc:
-          original_class_name = clazz.name
-          clazz.ancestors.each do |ancestor_class|
-            next if ancestor_class.name.nil? || ancestor_class.name.empty?
-            class_name = ancestor_class.name.to_sym
-            return data_accessors[class_name] if data_accessors[class_name]
-          end
+          accessor = registered_accessor_for(clazz) || registered_accessor_for_ancestors_of(clazz)
+          return accessor if accessor
           raise(Sunspot::NoAdapterError,
-                "No data accessor is configured for #{original_class_name} or its superclasses. See the documentation for Sunspot::Adapters")
+                "No data accessor is configured for #{clazz.name} or its superclasses. See the documentation for Sunspot::Adapters")
+        end
+
+        # Returns the directly-registered accessor for the specified class, if
+        # one exists, without searching the class's ancestors.
+        #
+        # === Parameters
+        #
+        # clazz<Class>:: The model class to be checked for the registered
+        #   data accessor
+        #
+        # === Returns
+        #
+        # Class:: Subclass of DataAccessor, or nil if none found
+        #
+        def registered_accessor_for(clazz)
+          return nil if clazz.name.nil? || clazz.name.empty?
+          data_accessors[clazz.name.to_sym]
         end
 
         protected
@@ -268,6 +308,16 @@ module Sunspot
         def data_accessors #:nodoc:
           @adapters ||= {}
         end
+
+        def registered_accessor_for_ancestors_of(clazz) # :nodoc:
+          clazz.ancestors.each do |ancestor_class|
+            if accessor = registered_accessor_for(ancestor_class)
+              register(accessor, clazz)
+              return accessor
+            end
+          end
+          nil
+        end
       end
     end
 

data/lib/sunspot/batcher.rb

@@ -12,7 +12,7 @@ module Sunspot
   #   end
   #
   # it is the Batcher's job to keep track of these nestings. The inner will
-  # be sent of to be indexed first.
+  # be sent off to be indexed first.
   #
   class Batcher
     include Enumerable

data/lib/sunspot/configuration.rb

@@ -22,9 +22,11 @@ module Sunspot
       def build #:nodoc:
         LightConfig.build do
           solr do
-            url 'http://127.0.0.1:8983/solr'
+            url 'http://127.0.0.1:8983/solr/default'
             read_timeout nil
             open_timeout nil
+            proxy nil
+            update_format :xml
           end
           master_solr do
             url nil
@@ -37,7 +39,7 @@ module Sunspot
           end
         end
       end
-      
+
       # Location for the default solr configuration files,
       # required for bootstrapping a new solr installation
       #

data/lib/sunspot/data_extractor.rb

@@ -5,16 +5,46 @@ module Sunspot
   # method, which takes an object and returns the value extracted from it.
   #
   module DataExtractor #:nodoc: all
+    #
+    # Abstract extractor to perform common actions on extracted values
+    #
+    class AbstractExtractor
+      BLACKLIST_REGEXP = /[\x0-\x8\xB\xC\xE-\x1F\x7f]/
+
+      def value_for(object)
+        extract_value_from(object)
+      end
+
+      private
+
+      def extract_value_from(object)
+        case object
+          when String
+            remove_blacklisted_chars(object)
+          when Array
+            object.map { |o| extract_value_from(o) }
+          when Hash
+            object.inject({}) { |h, (k, v)| h.merge(extract_value_from(k) => extract_value_from(v)) }
+          else
+            object
+        end
+      end
+
+      def remove_blacklisted_chars(object)
+        object.gsub(BLACKLIST_REGEXP, '')
+      end
+    end
+
     # 
     # AttributeExtractors extract data by simply calling a method on the block.
     #
-    class AttributeExtractor
+    class AttributeExtractor < AbstractExtractor
       def initialize(attribute_name)
         @attribute_name = attribute_name
       end
 
       def value_for(object)
-        object.send(@attribute_name)
+        super object.send(@attribute_name)
       end
     end
 
@@ -24,26 +54,26 @@ module Sunspot
     # as the argument to the block. Either way, the return value of the block is
     # the value returned by the extractor.
     #
-    class BlockExtractor
+    class BlockExtractor < AbstractExtractor
       def initialize(&block)
         @block = block
       end
 
       def value_for(object)
-        Util.instance_eval_or_call(object, &@block)
+        super Util.instance_eval_or_call(object, &@block)
       end
     end
 
     # 
     # Constant data extractors simply return the same value for every object.
     #
-    class Constant
+    class Constant < AbstractExtractor
       def initialize(value)
         @value = value
       end
 
       def value_for(object)
-        @value
+        super @value
       end
     end
   end

data/lib/sunspot/dsl.rb

@@ -1,5 +1,6 @@
-%w(fields scope paginatable adjustable field_query standard_query query_facet
-   functional fulltext restriction restriction_with_near search
-   more_like_this_query function field_group).each do |file|
+%w(spellcheckable fields scope paginatable adjustable field_query
+   standard_query query_facet functional fulltext restriction
+   restriction_with_near search more_like_this_query function
+   group field_stats).each do |file|
   require File.join(File.dirname(__FILE__), 'dsl', file)
 end

data/lib/sunspot/dsl/adjustable.rb

@@ -26,9 +26,9 @@ module Sunspot
       #       params["mlt.match.include"] = true
       #     end
       #   end
-      # 
+      #
       def adjust_solr_params( &block )
-        @query.solr_parameter_adjustment = block
+        @query.add_parameter_adjustment(block)
       end
 
       #