searchkick 4.0.0 → 5.0.0

data/lib/searchkick/indexer.rb

@@ -1,3 +1,5 @@
+# thread-local (technically fiber-local) indexer
+# used to aggregate bulk callbacks across models
 module Searchkick
   class Indexer
     attr_reader :queued_items
@@ -14,15 +16,20 @@ module Searchkick
     def perform
       items = @queued_items
       @queued_items = []
-      if items.any?
-        response = Searchkick.client.bulk(body: items)
-        if response["errors"]
-          first_with_error = response["items"].map do |item|
-            (item["index"] || item["delete"] || item["update"])
-          end.find { |item| item["error"] }
-          raise Searchkick::ImportError, "#{first_with_error["error"]} on item with id '#{first_with_error["_id"]}'"
-        end
+
+      return if items.empty?
+
+      response = Searchkick.client.bulk(body: items)
+      if response["errors"]
+        # note: delete does not set error when item not found
+        first_with_error = response["items"].map do |item|
+          (item["index"] || item["delete"] || item["update"])
+        end.find { |item| item["error"] }
+        raise ImportError, "#{first_with_error["error"]} on item with id '#{first_with_error["_id"]}'"
       end
+
+      # maybe return response in future
+      nil
     end
   end
 end

data/lib/searchkick/log_subscriber.rb

@@ -0,0 +1,57 @@
+# based on https://gist.github.com/mnutt/566725
+module Searchkick
+  class LogSubscriber < ActiveSupport::LogSubscriber
+    def self.runtime=(value)
+      Thread.current[:searchkick_runtime] = value
+    end
+
+    def self.runtime
+      Thread.current[:searchkick_runtime] ||= 0
+    end
+
+    def self.reset_runtime
+      rt = runtime
+      self.runtime = 0
+      rt
+    end
+
+    def search(event)
+      self.class.runtime += event.duration
+      return unless logger.debug?
+
+      payload = event.payload
+      name = "#{payload[:name]} (#{event.duration.round(1)}ms)"
+
+      index = payload[:query][:index].is_a?(Array) ? payload[:query][:index].join(",") : payload[:query][:index]
+      type = payload[:query][:type]
+      request_params = payload[:query].except(:index, :type, :body)
+
+      params = []
+      request_params.each do |k, v|
+        params << "#{CGI.escape(k.to_s)}=#{CGI.escape(v.to_s)}"
+      end
+
+      debug "  #{color(name, YELLOW, true)}  #{index}#{type ? "/#{type.join(',')}" : ''}/_search#{params.any? ? '?' + params.join('&') : nil} #{payload[:query][:body].to_json}"
+    end
+
+    def request(event)
+      self.class.runtime += event.duration
+      return unless logger.debug?
+
+      payload = event.payload
+      name = "#{payload[:name]} (#{event.duration.round(1)}ms)"
+
+      debug "  #{color(name, YELLOW, true)}  #{payload.except(:name).to_json}"
+    end
+
+    def multi_search(event)
+      self.class.runtime += event.duration
+      return unless logger.debug?
+
+      payload = event.payload
+      name = "#{payload[:name]} (#{event.duration.round(1)}ms)"
+
+      debug "  #{color(name, YELLOW, true)}  _msearch #{payload[:body]}"
+    end
+  end
+end

data/lib/searchkick/middleware.rb

@@ -1,4 +1,4 @@
-require "faraday/middleware"
+require "faraday"
 
 module Searchkick
   class Middleware < Faraday::Middleware

data/lib/searchkick/model.rb

@@ -3,11 +3,11 @@ module Searchkick
     def searchkick(**options)
       options = Searchkick.model_options.merge(options)
 
-      unknown_keywords = options.keys - [:_all, :_type, :batch_size, :callbacks, :case_sensitive, :conversions, :default_fields,
+      unknown_keywords = options.keys - [:_all, :_type, :batch_size, :callbacks, :case_sensitive, :conversions, :deep_paging, :default_fields,
         :filterable, :geo_shape, :highlight, :ignore_above, :index_name, :index_prefix, :inheritance, :language,
-        :locations, :mappings, :match, :merge_mappings, :routing, :searchable, :settings, :similarity,
-        :special_characters, :stem, :stem_conversions, :suggest, :synonyms, :text_end,
-        :text_middle, :text_start, :word, :wordnet, :word_end, :word_middle, :word_start]
+        :locations, :mappings, :match, :merge_mappings, :routing, :searchable, :search_synonyms, :settings, :similarity,
+        :special_characters, :stem, :stemmer, :stem_conversions, :stem_exclusion, :stemmer_override, :suggest, :synonyms, :text_end,
+        :text_middle, :text_start, :unscope, :word, :word_end, :word_middle, :word_start]
       raise ArgumentError, "unknown keywords: #{unknown_keywords.join(", ")}" if unknown_keywords.any?
 
       raise "Only call searchkick once per model" if respond_to?(:searchkick_index)
@@ -15,54 +15,83 @@ module Searchkick
       Searchkick.models << self
 
       options[:_type] ||= -> { searchkick_index.klass_document_type(self, true) }
+      options[:class_name] = model_name.name
 
       callbacks = options.key?(:callbacks) ? options[:callbacks] : :inline
       unless [:inline, true, false, :async, :queue].include?(callbacks)
         raise ArgumentError, "Invalid value for callbacks"
       end
 
-      index_name =
-        if options[:index_name]
-          options[:index_name]
-        elsif options[:index_prefix].respond_to?(:call)
-          -> { [options[:index_prefix].call, model_name.plural, Searchkick.env, Searchkick.index_suffix].compact.join("_") }
-        else
-          [options.key?(:index_prefix) ? options[:index_prefix] : Searchkick.index_prefix, model_name.plural, Searchkick.env, Searchkick.index_suffix].compact.join("_")
+      mod = Module.new
+      include(mod)
+      mod.module_eval do
+        def reindex(method_name = nil, mode: nil, refresh: false)
+          self.class.searchkick_index.reindex([self], method_name: method_name, mode: mode, refresh: refresh, single: true)
         end
 
+        def similar(**options)
+          self.class.searchkick_index.similar_record(self, **options)
+        end
+
+        def search_data
+          data = respond_to?(:to_hash) ? to_hash : serializable_hash
+          data.delete("id")
+          data.delete("_id")
+          data.delete("_type")
+          data
+        end
+
+        def should_index?
+          true
+        end
+      end
+
       class_eval do
-        cattr_reader :searchkick_options, :searchkick_klass
+        cattr_reader :searchkick_options, :searchkick_klass, instance_reader: false
 
         class_variable_set :@@searchkick_options, options.dup
         class_variable_set :@@searchkick_klass, self
-        class_variable_set :@@searchkick_index, index_name
-        class_variable_set :@@searchkick_index_cache, {}
+        class_variable_set :@@searchkick_index_cache, Searchkick::IndexCache.new
 
         class << self
           def searchkick_search(term = "*", **options, &block)
-            Searchkick.search(term, {model: self}.merge(options), &block)
+            if Searchkick.relation?(self)
+              raise Searchkick::Error, "search must be called on model, not relation"
+            end
+
+            Searchkick.search(term, model: self, **options, &block)
           end
           alias_method Searchkick.search_method_name, :searchkick_search if Searchkick.search_method_name
 
-          def searchkick_index
-            index = class_variable_get(:@@searchkick_index)
+          def searchkick_index(name: nil)
+            index = name || searchkick_index_name
             index = index.call if index.respond_to?(:call)
             index_cache = class_variable_get(:@@searchkick_index_cache)
-            index_cache[index] ||= Searchkick::Index.new(index, searchkick_options)
+            index_cache.fetch(index) { Searchkick::Index.new(index, searchkick_options) }
           end
           alias_method :search_index, :searchkick_index unless method_defined?(:search_index)
 
           def searchkick_reindex(method_name = nil, **options)
-            scoped = (respond_to?(:current_scope) && respond_to?(:default_scoped) && current_scope && current_scope.to_sql != default_scoped.to_sql) ||
-              (respond_to?(:queryable) && queryable != unscoped.with_default_scope)
-
-            searchkick_index.reindex(searchkick_klass, method_name, scoped: scoped, **options)
+            searchkick_index.reindex(self, method_name: method_name, **options)
           end
           alias_method :reindex, :searchkick_reindex unless method_defined?(:reindex)
 
           def searchkick_index_options
             searchkick_index.index_options
           end
+
+          def searchkick_index_name
+            @searchkick_index_name ||= begin
+              options = class_variable_get(:@@searchkick_options)
+              if options[:index_name]
+                options[:index_name]
+              elsif options[:index_prefix].respond_to?(:call)
+                -> { [options[:index_prefix].call, model_name.plural, Searchkick.env, Searchkick.index_suffix].compact.join("_") }
+              else
+                [options.key?(:index_prefix) ? options[:index_prefix] : Searchkick.index_prefix, model_name.plural, Searchkick.env, Searchkick.index_suffix].compact.join("_")
+              end
+            end
+          end
         end
 
         # always add callbacks, even when callbacks is false
@@ -73,32 +102,6 @@ module Searchkick
           after_save :reindex, if: -> { Searchkick.callbacks?(default: callbacks) }
           after_destroy :reindex, if: -> { Searchkick.callbacks?(default: callbacks) }
         end
-
-        def reindex(method_name = nil, **options)
-          RecordIndexer.new(self).reindex(method_name, **options)
-        end unless method_defined?(:reindex)
-
-        def similar(options = {})
-          self.class.searchkick_index.similar_record(self, options)
-        end unless method_defined?(:similar)
-
-        def search_data
-          data = respond_to?(:to_hash) ? to_hash : serializable_hash
-          data.delete("id")
-          data.delete("_id")
-          data.delete("_type")
-          data
-        end unless method_defined?(:search_data)
-
-        def should_index?
-          true
-        end unless method_defined?(:should_index?)
-
-        if defined?(Cequel) && self < Cequel::Record && !method_defined?(:destroyed?)
-          def destroyed?
-            transient?
-          end
-        end
       end
     end
   end

data/lib/searchkick/process_batch_job.rb

@@ -2,35 +2,19 @@ module Searchkick
   class ProcessBatchJob < ActiveJob::Base
     queue_as { Searchkick.queue_name }
 
-    def perform(class_name:, record_ids:)
-      # separate routing from id
-      routing = Hash[record_ids.map { |r| r.split(/(?<!\|)\|(?!\|)/, 2).map { |v| v.gsub("||", "|") } }]
-      record_ids = routing.keys
+    def perform(class_name:, record_ids:, index_name: nil)
+      model = Searchkick.load_model(class_name)
+      index = model.searchkick_index(name: index_name)
 
-      klass = class_name.constantize
-      scope = Searchkick.load_records(klass, record_ids)
-      scope = scope.search_import if scope.respond_to?(:search_import)
-      records = scope.select(&:should_index?)
-
-      # determine which records to delete
-      delete_ids = record_ids - records.map { |r| r.id.to_s }
-      delete_records = delete_ids.map do |id|
-        m = klass.new
-        m.id = id
-        if routing[id]
-          m.define_singleton_method(:search_routing) do
-            routing[id]
-          end
+      items =
+        record_ids.map do |r|
+          parts = r.split(/(?<!\|)\|(?!\|)/, 2)
+            .map { |v| v.gsub("||", "|") }
+          {id: parts[0], routing: parts[1]}
         end
-        m
-      end
 
-      # bulk reindex
-      index = klass.searchkick_index
-      Searchkick.callbacks(:bulk) do
-        index.bulk_index(records) if records.any?
-        index.bulk_delete(delete_records) if delete_records.any?
-      end
+      relation = Searchkick.scope(model)
+      RecordIndexer.new(index).reindex_items(relation, items, method_name: nil)
     end
   end
 end

data/lib/searchkick/process_queue_job.rb

@@ -2,21 +2,30 @@ module Searchkick
   class ProcessQueueJob < ActiveJob::Base
     queue_as { Searchkick.queue_name }
 
-    def perform(class_name:)
-      model = class_name.constantize
+    def perform(class_name:, index_name: nil, inline: false)
+      model = Searchkick.load_model(class_name)
+      index = model.searchkick_index(name: index_name)
+      limit = model.searchkick_options[:batch_size] || 1000
 
-      limit = model.searchkick_index.options[:batch_size] || 1000
-      record_ids = model.searchkick_index.reindex_queue.reserve(limit: limit)
-      if record_ids.any?
-        Searchkick::ProcessBatchJob.perform_later(
-          class_name: model.name,
-          record_ids: record_ids
-        )
-        # TODO when moving to reliable queuing, mark as complete
+      loop do
+        record_ids = index.reindex_queue.reserve(limit: limit)
+        if record_ids.any?
+          batch_options = {
+            class_name: class_name,
+            record_ids: record_ids.uniq,
+            index_name: index_name
+          }
 
-        if record_ids.size == limit
-          Searchkick::ProcessQueueJob.perform_later(class_name: class_name)
+          if inline
+            # use new.perform to avoid excessive logging
+            Searchkick::ProcessBatchJob.new.perform(**batch_options)
+          else
+            Searchkick::ProcessBatchJob.perform_later(**batch_options)
+          end
+
+          # TODO when moving to reliable queuing, mark as complete
         end
+        break unless record_ids.size == limit
       end
     end
   end