outoftime-sunspot 0.0.1 → 0.0.2

data/History.txt

@@ -1,7 +1,10 @@
-== 0.0.1 2008-12-11
+== 0.0.2 2009-02-14
+* Run sunspot's built-in Solr instance using
+  sunspot-solr executable
+* Search hash interpretation delegated to
+  Builder object
 
-* 1 major enhancement:
-  * Initial release
-  * Define indexing for any class using DSL
-  * Search indexed classes using DSL
-  
+== 0.0.1 2008-12-11
+* Initial release
+* Define indexing for any class using DSL
+* Search indexed classes using DSL

data/README.rdoc

@@ -33,6 +33,22 @@ Sunspot is currently under active development and is not feature-complete.
 * Access search parameters as hash or object attributes, for easy integration with form helpers or query string builders
 * Plugins for drop-in integration with Merb and Rails
 
+== Installation
+
+  gem sources -a http://gems.github.com
+  gem install outoftime-sunspot
+
+In order to start the packaged Solr installation, run:
+
+  sunspot-solr start -- [-d /path/to/data/directory] [-p port]
+
+If you don't specify a data directory, your Solr index will be stored in your operating system's temporary directory.
+
+You can also run your own instance of Solr wherever you'd like; just copy the solr/config/schema.xml file out of the gem's solr into your installation.
+You can change the URL at which Sunspot accesses Solr with:
+
+  Sunspot.config.solr.url = 'http://solr.my.host:9818/solr'
+
 == Using Sunspot
 
 === Define an index:
@@ -55,40 +71,56 @@ Sunspot is currently under active development and is not feature-complete.
 
 === Search for objects:
   
-  search = Sunspot.search Post, :conditions => { :average_rating => 3.0 } do
+  search = Sunspot.search Post do
     keywords 'great pizza'
     with.author_name 'Mark Twain'
     with.blog_id.any_of [2, 14]
     with.category_ids.all_of [4, 10]
     with.published_at.less_than Time.now
 
-    conditions.interpret :average_rating, :greater_than
-    conditions.default :average_rating, 4.0
-
     paginate :page => 3, :per_page => 15
     order_by :average_rating, :desc
   end
 
-=== Get data and parameters from search:
+=== Get data from search:
 
   search.results
   search.total
   search.page
   search.per_page
-  search.keywords
-  search.conditions.average_rating
-  search.attributes[:conditions]
 
-== REQUIREMENTS:
+=== Build search from a hash (e.g., params) and retrieve them later:
+
+  search = Sunspot.search Post, :keywords => 'great pizza',
+                                :conditions => { :author_name => 'Mark Twain',
+                                                 :blog_id => [4, 10] },
+                                :order => 'published_at desc'
+  search.builder.keywords
+    #=> "great pizza"
+  search.builder.conditions.author_name
+    #=> "Mark Twain"
+  search.builder.params[:conditions][:blog_id]
+    #=> [4, 10]
+
+This functionality is great for building a search from user input; if you're
+building a search using business logic in your application, the block DSL
+is the way to go. Note you can mix-and-match the two:
+
+  search = Sunspot.search Post, :keywords => 'great pizza' do
+    with.blog_id 1
+  end
+
+  search.builder.keywords
+    #=> "great pizza"
+  search.builder.blog_id
+    #=> nil
+
+== Requirements
 
 1. extlib
 2. solr-ruby
 3. Java
 
-== INSTALL:
-
-* FIX (sudo gem install, anything else)
-
 == LICENSE:
 
 (The MIT License)

data/Rakefile

@@ -1,27 +1,11 @@
-%w[rubygems rake rake/clean fileutils newgem rubigen].each { |f| require f }
-require File.dirname(__FILE__) + '/lib/sunspot'
+require 'rubygems'
 
 ENV['RUBYOPT'] = '-W1'
 
-# Generate all the Rake tasks
-# Run 'rake -T' to see list of generated tasks (from gem root directory)
-$hoe = Hoe.new('sunspot', Sunspot::VERSION) do |p|
-  p.developer('Mat Brown', 'mat@patch.com')
-  p.changes              = p.paragraphs_of("History.txt", 0..1).join("\n\n")
-  p.post_install_message = 'PostInstall.txt' # TODO remove if post-install message not required
-  p.rubyforge_name       = p.name # TODO this is default value
-  # p.extra_deps         = [
-  #   ['activesupport','>= 2.0.2'],
-  # ]
-  p.extra_dev_deps = [
-    ['newgem', ">= #{::Newgem::VERSION}"]
-  ]
-  
-  p.clean_globs |= %w[**/.DS_Store tmp *.log]
-  path = (p.rubyforge_name == p.name) ? p.rubyforge_name : "\#{p.rubyforge_name}/\#{p.name}"
-  p.remote_rdoc_dir = File.join(path.gsub(/^#{p.rubyforge_name}\/?/,''), 'rdoc')
-  p.rsync_args = '-av --delete --ignore-errors'
+task :environment do
+  require File.dirname(__FILE__) + '/lib/sunspot'
 end
 
-require 'newgem/tasks' # load /tasks/*.rake
 Dir['tasks/**/*.rake'].each { |t| load t }
+
+task :default => :spec

data/VERSION.yml

@@ -0,0 +1,4 @@
+--- 
+:major: 0
+:minor: 0
+:patch: 2

data/bin/sunspot-solr

@@ -0,0 +1,39 @@
+#!/usr/bin/env ruby
+require 'rubygems'
+gem 'daemons', '~> 1.0'
+gem 'optiflag', '~> 0.6.5'
+require 'fileutils'
+require 'tmpdir'
+require 'daemons'
+require 'optiflag'
+
+working_directory = FileUtils.pwd
+solr_home = File.join(File.dirname(__FILE__), '..', 'solr')
+
+module SolrFlags extend OptiFlagSet
+  optional_flag 'p' do
+    description 'Port on which to run Solr (default 8983)'
+    long_form 'port'
+  end
+
+  optional_flag 'd' do
+    description 'Solr data directory'
+  end
+
+  and_process!
+end
+
+port = ARGV.flags.p || '8983'
+data_dir = File.expand_path(ARGV.flags.d || File.join(Dir.tmpdir, 'solr_data'))
+
+Daemons.run_proc('sunspot-solr') do
+  FileUtils.cd(working_directory) do
+    FileUtils.cd(solr_home) do
+      args = ['java']
+      args << "-Djetty.port=#{port}" if port
+      args << "-Dsolr.data.dir=#{data_dir}" if data_dir
+      args << '-jar' << 'start.jar'
+      Kernel.exec(*args)
+    end
+  end
+end

data/lib/sunspot/builder.rb

@@ -0,0 +1,78 @@
+module Sunspot
+  module Builder
+    class AbstractBuilder
+      attr_reader :search, :types, :field_names
+
+      def initialize(query_dsl, types, field_names)
+        @search, @types, @field_names = query_dsl, types, field_names
+      end
+    end
+
+    class ParamsBuilder < AbstractBuilder
+      attr_reader :params
+
+      def initialize(query_dsl, types, field_names, params = {})
+        super(query_dsl, types, field_names)
+        @params = params
+        params.each_pair do |field_name, value|
+          self.send("#{field_name}=", value)
+        end
+      end
+    end
+
+    class StandardBuilder < ParamsBuilder
+      def initialize(query_dsl, types, field_names, params = {})
+        params = { :keywords => nil, :conditions => {}, :order => nil, :page => nil, :per_page => nil }.merge(params)
+        field_names.each { |field_name| params[:conditions][field_name.to_sym] = nil unless params[:conditions].has_key?(field_name.to_sym) }
+        super(query_dsl, types, field_names, params)
+      end
+
+      def keywords=(keywords)
+        search.keywords(keywords) if keywords
+      end
+
+      def conditions=(conditions)
+        conditions.each_pair do |field_name, value|
+          unless value.nil?
+            unless value.is_a?(Array)
+              search.with.send(field_name, value) if field_names.include?(field_name.to_s)
+            else
+              search.with.send(field_name).any_of(value)
+            end
+          end
+        end
+      end
+
+      def order=(order_string)
+        search.order_by(*order_string.split(' ')) if order_string
+      end
+
+      def page=(page)
+        search.paginate(:page => page, :per_page => params[:per_page]) if page
+      end
+
+      def per_page=(per_page) # ugly
+      end
+
+      def keywords
+        params[:keywords]
+      end
+
+      def conditions
+        ::Sunspot::Util::ClosedStruct.new(params[:conditions])
+      end
+      
+      def order
+        params[:order]
+      end
+
+      def page
+        params[:page]
+      end
+
+      def per_page
+        params[:per_page]
+      end
+    end
+  end
+end

data/lib/sunspot/dsl/fields.rb

@@ -0,0 +1,39 @@
+module Sunspot
+  module DSL
+    class Fields
+      def initialize(clazz)
+        @clazz = clazz
+      end
+
+      def text(*names, &block)
+        for name in names
+          ::Sunspot::Field.register_text clazz, build_field(name, ::Sunspot::Type::TextType, &block)
+        end
+      end
+
+      def method_missing(method, *args, &block)
+        begin
+          type = ::Sunspot::Type.const_get "#{method.to_s.camel_case}Type"
+        rescue(NameError)
+          super(method.to_sym, *args, &block) and return
+        end
+        name = args.shift
+        ::Sunspot::Field.register clazz, build_field(name, type, *args, &block)
+      end
+
+      protected
+      attr_reader :clazz
+
+      private
+
+      def build_field(name, type, *args, &block)
+        options = args.shift if args.first.is_a?(Hash)
+        unless block
+          ::Sunspot::Field::AttributeField.new(name, type, options || {})
+        else
+          ::Sunspot::Field::VirtualField.new(name, type, options || {}, &block)
+        end
+      end
+    end
+  end
+end

data/lib/sunspot/dsl/query.rb

@@ -0,0 +1,32 @@
+module Sunspot
+  module DSL
+    class Query
+      def initialize(query)
+        @query = query 
+      end
+
+      def keywords(keywords)
+        @query.keywords = keywords
+      end
+
+      def with
+        @conditions_builder ||= ::Sunspot::DSL::Scope.new(@query)
+      end
+
+      def conditions
+        @query.conditions
+      end
+
+      def paginate(options = {})
+        page = options.delete(:page) || raise(ArgumentError, "paginate requires a :page argument")
+        per_page = options.delete(:per_page)
+        raise ArgumentError, "unknown argument #{options.keys.first.inspect} passed to paginate" unless options.empty?
+        @query.paginate(page, per_page)
+      end
+
+      def order_by(field_name, direction = nil)
+        @query.order_by(field_name, direction)
+      end
+    end
+  end
+end

data/lib/sunspot/dsl/scope.rb

@@ -0,0 +1,35 @@
+module Sunspot
+  module DSL
+    class Scope
+      def initialize(query)
+        @query = query
+      end
+
+      def method_missing(field_name, *args)
+        if args.length == 0 then RestrictionBuilder.new(field_name, @query)
+        elsif args.length == 1 then @query.add_scope @query.build_condition(field_name, ::Sunspot::Restriction::EqualTo, args.first)
+        else super(field_name.to_sym, *args)
+        end
+      end
+
+      class RestrictionBuilder
+        def initialize(field_name, query)
+          @field_name, @query = field_name, query
+        end
+
+        def method_missing(condition_name, *args)
+          clazz = begin
+                    ::Sunspot::Restriction.const_get(condition_name.to_s.camel_case)
+                  rescue(NameError)
+                    super(condition_name.to_sym, *args)
+                  end
+          if value = args.first
+            @query.add_scope @query.build_condition(@field_name, clazz, args.first)
+          else
+            @query.interpret_condition @field_name, clazz
+          end
+        end
+      end
+    end
+  end
+end

data/lib/sunspot/dsl.rb

@@ -0,0 +1,3 @@
+%w(fields query scope).each do |file|
+  require File.join(File.dirname(__FILE__), 'dsl', file)
+end

data/lib/sunspot/query.rb

@@ -3,14 +3,8 @@ module Sunspot
     attr_accessor :keywords, :conditions, :rows, :start, :sort
 
     def initialize(types, params, configuration)
-      @keywords, @types, @configuration = params[:keywords], types, configuration
-      @conditions = Sunspot::Conditions.new(self, params[:conditions] || {})
-      paginate(params[:page], params[:per_page])
-      self.order = params[:order] if params[:order]
-      attributes[:keywords] = @keywords
-      params[:conditions].each_pair do |field_name, value|
-        attributes[:conditions][field_name.to_sym] = value
-      end if params[:conditions]
+      @types, @configuration = types, configuration
+      paginate
     end
 
     def to_solr
@@ -21,7 +15,7 @@ module Sunspot
     end
 
     def filter_queries
-      scope_queries + condition_queries
+      scope_queries
     end
 
     def add_scope(condition)
@@ -37,7 +31,6 @@ module Sunspot
       per_page ||= configuration.pagination.default_per_page
       @start = (page - 1) * per_page
       @rows = per_page
-      attributes[:page], attributes[:per_page] = page, per_page
     end
 
     def order=(order)
@@ -47,7 +40,6 @@ module Sunspot
     def order_by(field_name, direction = nil)
       direction ||= :asc
       @sort = [{ field(field_name).indexed_name.to_sym => (direction.to_s == 'asc' ? :ascending : :descending) }] #TODO should support multiple order columns
-      attributes[:order] = "#{field_name} #{direction}"
     end
 
     def page
@@ -55,11 +47,12 @@ module Sunspot
       start / rows + 1
     end
 
-    def attributes
-      @attributes ||= {
-        :order => nil,
-        :conditions => fields_hash.keys.inject({}) { |conditions, key| conditions[key.to_sym] = nil; conditions }
-      }
+    def dsl
+      @dsl ||= ::Sunspot::DSL::Query.new(self)
+    end
+
+    def build_with(builder_class, *args)
+      builder_class.new(dsl, types, fields_hash.keys, *args)
     end
 
     alias_method :per_page, :rows
@@ -77,10 +70,6 @@ module Sunspot
       scope.map { |condition| condition.to_solr_query }
     end
 
-    def condition_queries
-      conditions.restrictions.map { |condition| condition.to_solr_query }
-    end
-
     def types_query
       if types.nil? || types.empty? then "type:[* TO *]"
       elsif types.length == 1 then "type:#{types.first}"

data/lib/sunspot/search.rb

@@ -1,13 +1,20 @@
 module Sunspot
   class Search
+    attr_reader :builder
+
     def initialize(connection, configuration, *types, &block)
       @connection = connection
       params = types.last.is_a?(Hash) ? types.pop : {}
       @query = Sunspot::Query.new(types, params, configuration)
-      QueryBuilder.new(@query).instance_eval(&block) if block
+      @builder = build_with(::Sunspot::Builder::StandardBuilder, params)
+      @query.dsl.instance_eval(&block) if block
       @types = types
     end
 
+    def build_with(builder_class, *args)
+      @query.build_with(builder_class, *args)
+    end
+
     def execute!
       query_options = {}
       query_options[:filter_queries] = query.filter_queries
@@ -32,30 +39,6 @@ module Sunspot
       @total ||= @solr_result.total_hits
     end
 
-    def attributes
-      @query.attributes
-    end
-
-    def order
-      @query.attributes[:order]
-    end
-
-    def page
-      @query.attributes[:page]
-    end
-
-    def per_page
-      @query.attributes[:per_page]
-    end
-
-    def keywords
-      @query.attributes[:keywords]
-    end
-
-    def conditions
-      ::Sunspot::Util::ClosedStruct.new(@query.attributes[:conditions])
-    end
-
     protected
     attr_reader :query, :types, :connection
 

data/lib/sunspot.rb

@@ -1,11 +1,10 @@
-require 'rubygems'
 gem 'solr-ruby'
 gem 'extlib'
 require 'solr'
 require 'extlib'
 require File.join(File.dirname(__FILE__), 'light_config')
 
-%w(adapters restriction conditions configuration field field_builder indexer query query_builder scope_builder search session type util).each do |filename|
+%w(adapters builder restriction configuration field indexer query search session type util dsl).each do |filename|
   require File.join(File.dirname(__FILE__), 'sunspot', filename)
 end
 
@@ -15,7 +14,7 @@ end
 
 class <<Sunspot
   def setup(clazz, &block)
-    ::Sunspot::FieldBuilder.new(clazz).instance_eval(&block) if block
+    ::Sunspot::DSL::Fields.new(clazz).instance_eval(&block) if block
   end
 
   def index(*objects)

data/solr/etc/jetty.xml

@@ -12,6 +12,12 @@
 
 <Configure id="Server" class="org.mortbay.jetty.Server">
 
+    <!-- Increase the maximum POST size to 1 MB to be able to handle large shard requests -->
+    <Call class="java.lang.System" name="setProperty">
+      <Arg>org.mortbay.jetty.Request.maxFormContentSize</Arg>
+      <Arg>1000000</Arg>
+    </Call>
+
     <!-- =========================================================== -->
     <!-- Server Thread Pool                                          -->
     <!-- =========================================================== -->
@@ -21,7 +27,7 @@
       <New class="org.mortbay.thread.BoundedThreadPool">
         <Set name="minThreads">10</Set>
         <Set name="lowThreads">50</Set>
-        <Set name="maxThreads">250</Set>
+        <Set name="maxThreads">10000</Set>
       </New>
 
       <!-- Optional Java 5 bounded threadpool with job queue 
@@ -64,7 +70,7 @@
     <Call name="addConnector">
       <Arg>
           <New class="org.mortbay.jetty.bio.SocketConnector">
-            <Set name="port">8983</Set>
+            <Set name="port"><SystemProperty name="jetty.port" default="8983"/></Set>
             <Set name="maxIdleTime">50000</Set>
             <Set name="lowResourceMaxIdleTime">1500</Set>
           </New>
@@ -185,13 +191,13 @@
     <!-- =========================================================== -->
     <Ref id="RequestLog">
       <Set name="requestLog">
-        <New id="RequestLogImpl" class="org.mortbay.jetty.NCSARequestLog">
+        <!-- New id="RequestLogImpl" class="org.mortbay.jetty.NCSARequestLog">
           <Arg><SystemProperty name="jetty.logs" default="./logs"/>/yyyy_mm_dd.request.log</Arg>
           <Set name="retainDays">90</Set>
           <Set name="append">true</Set>
           <Set name="extended">false</Set>
           <Set name="LogTimeZone">GMT</Set>
-        </New>
+        </New -->
       </Set>
     </Ref>
 

data/solr/solr/conf/{admin-extra.html → elevate.xml}

@@ -1,3 +1,4 @@
+<?xml version="1.0" encoding="UTF-8" ?>
 <!--
  Licensed to the Apache Software Foundation (ASF) under one or more
  contributor license agreements.  See the NOTICE file distributed with
@@ -15,17 +16,21 @@
  limitations under the License.
 -->
 
-<!-- The content of this page will be statically included into the top
-of the admin page.  Uncomment this as an example to see there the content
-will show up.
-
-<hr>
-<i>This line will appear before the first table</i>
-<tr>
-<td colspan="2">
-This row will be appended to the end of the first table
-</td>
-</tr>
-<hr>
-
+<!-- If this file is found in the config directory, it will only be
+     loaded once at startup.  If it is found in Solr's data
+     directory, it will be re-loaded every commit.
 -->
+
+<elevate>
+ <query text="foo bar">
+  <doc id="1" />
+  <doc id="2" />
+  <doc id="3" />
+ </query>
+ 
+ <query text="ipod">
+   <doc id="MA147LL/A" />  <!-- put the actual ipod at the top -->
+   <doc id="IW-02" exclude="true" /> <!-- exclude this cable -->
+ </query>
+ 
+</elevate>