sherpa99-thinking-sphinx 1.1.4

data/lib/thinking_sphinx/attribute.rb

@@ -0,0 +1,258 @@
+module ThinkingSphinx
+  # Attributes - eternally useful when it comes to filtering, sorting or
+  # grouping. This class isn't really useful to you unless you're hacking
+  # around with the internals of Thinking Sphinx - but hey, don't let that
+  # stop you.
+  #
+  # One key thing to remember - if you're using the attribute manually to
+  # generate SQL statements, you'll need to set the base model, and all the
+  # associations. Which can get messy. Use Index.link!, it really helps.
+  # 
+  class Attribute
+    attr_accessor :alias, :columns, :associations, :model, :faceted
+    
+    # To create a new attribute, you'll need to pass in either a single Column
+    # or an array of them, and some (optional) options.
+    #
+    # Valid options are:
+    # - :as   => :alias_name 
+    # - :type => :attribute_type
+    #
+    # Alias is only required in three circumstances: when there's
+    # another attribute or field with the same name, when the column name is
+    # 'id', or when there's more than one column.
+    # 
+    # Type is not required, unless you want to force a column to be a certain
+    # type (but keep in mind the value will not be CASTed in the SQL
+    # statements). The only time you really need to use this is when the type
+    # can't be figured out by the column - ie: when not actually using a
+    # database column as your source.
+    # 
+    # Example usage:
+    #
+    #   Attribute.new(
+    #     Column.new(:created_at)
+    #   )
+    #
+    #   Attribute.new(
+    #     Column.new(:posts, :id),
+    #     :as => :post_ids
+    #   )
+    #
+    #   Attribute.new(
+    #     [Column.new(:pages, :id), Column.new(:articles, :id)],
+    #     :as => :content_ids
+    #   )
+    #
+    #   Attribute.new(
+    #     Column.new("NOW()"),
+    #     :as   => :indexed_at,
+    #     :type => :datetime
+    #   )
+    #
+    # If you're creating attributes for latitude and longitude, don't forget
+    # that Sphinx expects these values to be in radians.
+    #  
+    def initialize(columns, options = {})
+      @columns      = Array(columns)
+      @associations = {}
+      
+      raise "Cannot define a field with no columns. Maybe you are trying to index a field with a reserved name (id, name). You can fix this error by using a symbol rather than a bare name (:id instead of id)." if @columns.empty? || @columns.any? { |column| !column.respond_to?(:__stack) }
+      
+      @alias    = options[:as]
+      @type     = options[:type]
+      @faceted  = options[:facet]
+    end
+    
+    # Get the part of the SELECT clause related to this attribute. Don't forget
+    # to set your model and associations first though.
+    #
+    # This will concatenate strings and arrays of integers, and convert
+    # datetimes to timestamps, as needed.
+    # 
+    def to_select_sql
+      clause = @columns.collect { |column|
+        column_with_prefix(column)
+      }.join(', ')
+      
+      separator = all_ints? ? ',' : ' '
+      
+      clause = adapter.concatenate(clause, separator)       if concat_ws?
+      clause = adapter.group_concatenate(clause, separator) if is_many?
+      clause = adapter.cast_to_datetime(clause)             if type == :datetime
+      clause = adapter.convert_nulls(clause)                if type == :string
+      
+      "#{clause} AS #{quote_column(unique_name)}"
+    end
+    
+    # Get the part of the GROUP BY clause related to this attribute - if one is
+    # needed. If not, all you'll get back is nil. The latter will happen if
+    # there isn't actually a real column to get data from, or if there's
+    # multiple data values (read: a has_many or has_and_belongs_to_many
+    # association).
+    # 
+    def to_group_sql
+      case
+      when is_many?, is_string?, ThinkingSphinx.use_group_by_shortcut?
+        nil
+      else
+        @columns.collect { |column|
+          column_with_prefix(column)
+        }
+      end
+    end
+    
+    def type_to_config
+      {
+        :multi    => :sql_attr_multi,
+        :datetime => :sql_attr_timestamp,
+        :string   => :sql_attr_str2ordinal,
+        :float    => :sql_attr_float,
+        :boolean  => :sql_attr_bool,
+        :integer  => :sql_attr_uint
+      }[type]
+    end
+    
+    def config_value
+      if type == :multi
+        "uint #{unique_name} from field"
+      else
+        unique_name
+      end
+    end
+    
+    # Returns the unique name of the attribute - which is either the alias of
+    # the attribute, or the name of the only column - if there is only one. If
+    # there isn't, there should be an alias. Else things probably won't work.
+    # Consider yourself warned.
+    # 
+    def unique_name
+      if @columns.length == 1
+        @alias || @columns.first.__name
+      else
+        @alias
+      end
+    end
+    
+    # Returns the type of the column. If that's not already set, it returns
+    # :multi if there's the possibility of more than one value, :string if
+    # there's more than one association, otherwise it figures out what the
+    # actual column's datatype is and returns that.
+    def type
+      @type ||= case
+      when is_many?, is_many_ints?
+        :multi
+      when @associations.values.flatten.length > 1
+        :string
+      else
+        translated_type_from_database
+      end
+    end
+    
+    def to_facet
+      return nil unless @faceted
+      
+      ThinkingSphinx::Facet.new(self)
+    end
+    
+    private
+    
+    def adapter
+      @adapter ||= @model.sphinx_database_adapter
+    end
+    
+    def quote_column(column)
+      @model.connection.quote_column_name(column)
+    end
+    
+    # Indication of whether the columns should be concatenated with a space
+    # between each value. True if there's either multiple sources or multiple
+    # associations.
+    # 
+    def concat_ws?
+      multiple_associations? || @columns.length > 1
+    end
+        
+    # Checks whether any column requires multiple associations (which only
+    # happens for polymorphic situations).
+    # 
+    def multiple_associations?
+      associations.any? { |col,assocs| assocs.length > 1 }
+    end
+    
+    # Builds a column reference tied to the appropriate associations. This
+    # dives into the associations hash and their corresponding joins to
+    # figure out how to correctly reference a column in SQL.
+    # 
+    def column_with_prefix(column)
+      if column.is_string?
+        column.__name
+      elsif associations[column].empty?
+        "#{@model.quoted_table_name}.#{quote_column(column.__name)}"
+      else
+        associations[column].collect { |assoc|
+          assoc.has_column?(column.__name) ?
+          "#{@model.connection.quote_table_name(assoc.join.aliased_table_name)}" + 
+          ".#{quote_column(column.__name)}" :
+          nil
+        }.compact.join(', ')
+      end
+    end
+    
+    # Could there be more than one value related to the parent record? If so,
+    # then this will return true. If not, false. It's that simple.
+    # 
+    def is_many?
+      associations.values.flatten.any? { |assoc| assoc.is_many? }
+    end
+    
+    def is_many_ints?
+      concat_ws? && all_ints?
+    end
+    
+    # Returns true if any of the columns are string values, instead of database
+    # column references.
+    def is_string?
+      columns.all? { |col| col.is_string? }
+    end
+    
+    def all_ints?
+      @columns.all? { |col|
+        klasses = @associations[col].empty? ? [@model] :
+          @associations[col].collect { |assoc| assoc.reflection.klass }
+        klasses.all? { |klass|
+          column = klass.columns.detect { |column| column.name == col.__name.to_s }
+          !column.nil? && column.type == :integer
+        }
+      }
+    end
+    
+    def type_from_database
+      klass = @associations.values.flatten.first ? 
+        @associations.values.flatten.first.reflection.klass : @model
+      
+      klass.columns.detect { |col|
+        @columns.collect { |c| c.__name.to_s }.include? col.name
+      }.type
+    end
+    
+    def translated_type_from_database
+      case type_from_db = type_from_database
+      when :datetime, :string, :float, :boolean, :integer
+        type_from_db
+      when :decimal
+        :float
+      when :timestamp, :date
+        :datetime
+      else
+        raise <<-MESSAGE
+
+Cannot automatically map column type #{type_from_db} to an equivalent Sphinx
+type (integer, float, boolean, datetime, string as ordinal). You could try to
+explicitly convert the column's value in your define_index block:
+  has "CAST(column AS INT)", :type => :integer, :as => :column
+        MESSAGE
+      end
+    end
+  end
+end

data/lib/thinking_sphinx/collection.rb

@@ -0,0 +1,142 @@
+module ThinkingSphinx
+  class Collection < ::Array
+    attr_reader :total_entries, :total_pages, :current_page, :per_page
+    attr_accessor :results
+
+    # Compatibility with older versions of will_paginate
+    alias_method :page_count, :total_pages
+    
+    def initialize(page, per_page, entries, total_entries)
+      @current_page, @per_page, @total_entries = page, per_page, total_entries
+      
+      @total_pages = (entries / @per_page.to_f).ceil
+    end
+    
+    def self.ids_from_results(results, page, limit, options)
+      collection = self.new(page, limit,
+        results[:total] || 0, results[:total_found] || 0
+      )
+      collection.results = results
+      collection.replace results[:matches].collect { |match|
+        match[:attributes]["sphinx_internal_id"]
+      }
+      return collection
+    end
+    
+    def self.create_from_results(results, page, limit, options)
+      collection = self.new(page, limit,
+        results[:total] || 0, results[:total_found] || 0
+      )
+      collection.results = results
+      collection.replace instances_from_matches(results[:matches], options)
+      return collection
+    end
+    
+    def self.instances_from_matches(matches, options = {})
+      if klass = options[:class]
+        instances_from_class klass, matches, options
+      else
+        instances_from_classes matches, options
+      end
+    end
+    
+    def self.instances_from_class(klass, matches, options = {})
+      index_options = klass.sphinx_index_options
+
+      ids = matches.collect { |match| match[:attributes]["sphinx_internal_id"] }
+      instances = ids.length > 0 ? klass.find(
+        :all,
+        :conditions => {klass.primary_key.to_sym => ids},
+        :include    => (options[:include] || index_options[:include]),
+        :select     => (options[:select]  || index_options[:select])
+      ) : []
+
+      # Raise an exception if we find records in Sphinx but not in the DB, so
+      # the search method can retry without them. See 
+      # ThinkingSphinx::Search.retry_search_on_stale_index.
+      if options[:raise_on_stale] && instances.length < ids.length
+        stale_ids = ids - instances.map {|i| i.id }
+        raise StaleIdsException, stale_ids
+      end
+
+      ids.collect { |obj_id|
+        instances.detect { |obj| obj.id == obj_id }
+      }
+    end
+    
+    # Group results by class and call #find(:all) once for each group to reduce
+    # the number of #find's in multi-model searches.
+    # 
+    def self.instances_from_classes(matches, options = {})
+      groups = matches.group_by { |match| match[:attributes]["class_crc"] }
+      groups.each do |crc, group|
+        group.replace(
+          instances_from_class(class_from_crc(crc), group, options)
+        )
+      end
+      
+      matches.collect do |match|
+        groups.detect { |crc, group|
+          crc == match[:attributes]["class_crc"]
+        }[1].detect { |obj|
+          obj.id == match[:attributes]["sphinx_internal_id"]
+        }
+      end
+    end
+    
+    def self.class_from_crc(crc)
+      @@models_by_crc ||= ThinkingSphinx.indexed_models.inject({}) do |hash, model|
+        hash[model.constantize.to_crc32] = model
+        model.constantize.subclasses.each { |subclass|
+          hash[subclass.to_crc32] = subclass.name
+        }
+        hash
+      end
+      @@models_by_crc[crc].constantize
+    end
+    
+    def previous_page
+      current_page > 1 ? (current_page - 1) : nil
+    end
+    
+    def next_page
+      current_page < total_pages ? (current_page + 1): nil
+    end
+    
+    def offset
+      (current_page - 1) * @per_page
+    end
+    
+    def method_missing(method, *args, &block)
+      super unless method.to_s[/^each_with_.*/]
+      
+      each_with_attribute method.to_s.gsub(/^each_with_/, ''), &block
+    end
+    
+    def each_with_groupby_and_count(&block)
+      results[:matches].each_with_index do |match, index|
+        yield self[index], match[:attributes]["@groupby"], match[:attributes]["@count"]
+      end
+    end
+    
+    def each_with_attribute(attribute, &block)
+      results[:matches].each_with_index do |match, index|
+        yield self[index], (match[:attributes][attribute] || match[:attributes]["@#{attribute}"])
+      end
+    end
+    
+    def each_with_weighting(&block)
+      results[:matches].each_with_index do |match, index|
+        yield self[index], match[:weight]
+      end
+    end
+    
+    def inject_with_groupby_and_count(initial = nil, &block)
+      index = -1
+      results[:matches].inject(initial) do |memo, match|
+        index += 1
+        yield memo, self[index], match[:attributes]["@groupby"], match[:attributes]["@count"]
+      end
+    end
+  end
+end

data/lib/thinking_sphinx/configuration.rb

@@ -0,0 +1,236 @@
+require 'erb'
+require 'singleton'
+
+module ThinkingSphinx
+  # This class both keeps track of the configuration settings for Sphinx and
+  # also generates the resulting file for Sphinx to use.
+  # 
+  # Here are the default settings, relative to RAILS_ROOT where relevant:
+  #
+  # config file::           config/#{environment}.sphinx.conf
+  # searchd log file::      log/searchd.log
+  # query log file::        log/searchd.query.log
+  # pid file::              log/searchd.#{environment}.pid
+  # searchd files::         db/sphinx/#{environment}/
+  # address::               127.0.0.1
+  # port::                  3312
+  # allow star::            false
+  # min prefix length::     1
+  # min infix length::      1
+  # mem limit::             64M
+  # max matches::           1000
+  # morphology::            stem_en
+  # charset type::          utf-8
+  # charset table::         nil
+  # ignore chars::          nil
+  # html strip::            false
+  # html remove elements::  ''
+  #
+  # If you want to change these settings, create a YAML file at
+  # config/sphinx.yml with settings for each environment, in a similar
+  # fashion to database.yml - using the following keys: config_file,
+  # searchd_log_file, query_log_file, pid_file, searchd_file_path, port,
+  # allow_star, enable_star, min_prefix_len, min_infix_len, mem_limit,
+  # max_matches, # morphology, charset_type, charset_table, ignore_chars,
+  # html_strip, # html_remove_elements. I think you've got the idea.
+  # 
+  # Each setting in the YAML file is optional - so only put in the ones you
+  # want to change.
+  #
+  # Keep in mind, if for some particular reason you're using a version of
+  # Sphinx older than 0.9.8 r871 (that's prior to the proper 0.9.8 release),
+  # don't set allow_star to true.
+  # 
+  class Configuration
+    include Singleton
+    
+    SourceOptions = %w( mysql_connect_flags sql_range_step sql_query_pre
+      sql_query_post sql_ranged_throttle sql_query_post_index )
+    
+    IndexOptions  = %w( charset_table charset_type docinfo enable_star
+      exceptions html_index_attrs html_remove_elements html_strip ignore_chars
+      min_infix_len min_prefix_len min_word_len mlock morphology ngram_chars
+      ngram_len phrase_boundary phrase_boundary_step preopen stopwords
+      wordforms )
+        
+    attr_accessor :config_file, :searchd_log_file, :query_log_file,
+      :pid_file, :searchd_file_path, :address, :port, :allow_star,
+      :database_yml_file, :app_root, :bin_path, :model_directories
+    
+    attr_accessor :source_options, :index_options
+    
+    attr_reader :environment, :configuration
+    
+    # Load in the configuration settings - this will look for config/sphinx.yml
+    # and parse it according to the current environment.
+    # 
+    def initialize(app_root = Dir.pwd)
+      self.reset
+    end
+    
+    def reset
+      self.app_root          = RAILS_ROOT if defined?(RAILS_ROOT)
+      self.app_root          = Merb.root  if defined?(Merb)
+      self.app_root        ||= app_root
+      
+      @configuration = Riddle::Configuration.new
+      @configuration.searchd.address    = "127.0.0.1"
+      @configuration.searchd.port       = 3312
+      @configuration.searchd.pid_file   = "#{self.app_root}/log/searchd.#{environment}.pid"
+      @configuration.searchd.log        = "#{self.app_root}/log/searchd.log"
+      @configuration.searchd.query_log  = "#{self.app_root}/log/searchd.query.log"
+      
+      self.database_yml_file    = "#{self.app_root}/config/database.yml"
+      self.config_file          = "#{self.app_root}/config/#{environment}.sphinx.conf"
+      self.searchd_file_path    = "#{self.app_root}/db/sphinx/#{environment}"
+      self.allow_star           = false
+      self.bin_path             = ""
+      self.model_directories    = ["#{app_root}/app/models/"]
+      
+      self.source_options  = {}
+      self.index_options   = {
+        :charset_type => "utf-8",
+        :morphology   => "stem_en"
+      }
+            
+      parse_config
+      
+      self
+    end
+    
+    def self.environment
+      @@environment ||= (
+        defined?(Merb) ? Merb.environment : ENV['RAILS_ENV']
+      ) || "development"
+    end
+    
+    def environment
+      self.class.environment
+    end
+    
+    def controller
+      @controller ||= Riddle::Controller.new(@configuration, self.config_file)
+    end
+    
+    # Generate the config file for Sphinx by using all the settings defined and
+    # looping through all the models with indexes to build the relevant
+    # indexer and searchd configuration, and sources and indexes details.
+    #
+    def build(file_path=nil)
+      load_models
+      file_path ||= "#{self.config_file}"
+      
+      @configuration.indexes.clear
+      
+      ThinkingSphinx.indexed_models.each_with_index do |model, model_index|
+        @configuration.indexes.concat model.constantize.to_riddle(model_index)
+      end
+      
+      open(file_path, "w") do |file|
+        file.write @configuration.render
+      end
+    end
+    
+    # Make sure all models are loaded - without reloading any that
+    # ActiveRecord::Base is already aware of (otherwise we start to hit some
+    # messy dependencies issues).
+    # 
+    def load_models
+      self.model_directories.each do |base|
+        Dir["#{base}**/*.rb"].each do |file|
+          model_name = file.gsub(/^#{base}([\w_\/\\]+)\.rb/, '\1')
+        
+          next if model_name.nil?
+          next if ::ActiveRecord::Base.send(:subclasses).detect { |model|
+            model.name == model_name
+          }
+        
+          begin
+            model_name.camelize.constantize
+          rescue LoadError
+            model_name.gsub!(/.*[\/\\]/, '').nil? ? next : retry
+          rescue NameError
+            next
+          end
+        end
+      end
+    end
+    
+    def address
+      @configuration.searchd.address
+    end
+    
+    def address=(address)
+      @configuration.searchd.address = address
+    end
+    
+    def port
+      @configuration.searchd.port
+    end
+    
+    def port=(port)
+      @configuration.searchd.port = port
+    end
+    
+    def pid_file
+      @configuration.searchd.pid_file
+    end
+    
+    def pid_file=(pid_file)
+      @configuration.searchd.pid_file = pid_file
+    end
+    
+    def searchd_log_file
+      @configuration.searchd.log
+    end
+    
+    def searchd_log_file=(file)
+      @configuration.searchd.log = file
+    end
+    
+    def query_log_file
+      @configuration.searchd.query_log
+    end
+    
+    def query_log_file=(file)
+      @configuration.searchd.query_log = file
+    end
+    
+    private
+    
+    # Parse the config/sphinx.yml file - if it exists - then use the attribute
+    # accessors to set the appropriate values. Nothing too clever.
+    # 
+    def parse_config
+      path = "#{app_root}/config/sphinx.yml"
+      return unless File.exists?(path)
+      
+      conf = YAML::load(ERB.new(IO.read(path)).result)[environment]
+      
+      conf.each do |key,value|
+        self.send("#{key}=", value) if self.methods.include?("#{key}=")
+        
+        set_sphinx_setting self.source_options, key, value, SourceOptions
+        set_sphinx_setting self.index_options,  key, value, IndexOptions
+        set_sphinx_setting @configuration.searchd, key, value
+        set_sphinx_setting @configuration.indexer, key, value
+      end unless conf.nil?
+      
+      self.bin_path += '/' unless self.bin_path.blank?
+      
+      if self.allow_star
+        self.index_options[:enable_star]    = true
+        self.index_options[:min_prefix_len] = 1
+      end
+    end
+    
+    def set_sphinx_setting(object, key, value, allowed = {})
+      if object.is_a?(Hash)
+        object[key.to_sym] = value if allowed.include?(key.to_s)
+      else
+        object.send("#{key}=", value) if object.methods.include?("#{key}")
+        send("#{key}=", value) if self.methods.include?("#{key}")
+      end
+    end
+  end
+end