sequel-elasticsearch 0.4.8 → 0.4.9

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 7d297d1a447dae85be685cef2d12b2f38ba9734259318b1bb7b2bd2458b6325e
-  data.tar.gz: 61aef4399f9f5faeb8bcb37ac74dedf386277d533dfb75996d7744fa1a4ab0f4
+  metadata.gz: 181431ca4bddeae82a6126453bf9439679feeb08243cf6d8a3158438cf5aed40
+  data.tar.gz: 80660bb4500762573c1e1cfc60b0242fff8cbb4ba0cf2d5bc922084eabd15a4a
 SHA512:
-  metadata.gz: f6d774d669be05c6b1030df3ca8ba83a2ce0ee62e3685d9b8d8cb0163a3b542584fb10f09569046529dd5795de3b5efb5cd1f7079009e68df6d867324dc498bd
-  data.tar.gz: b18e6af022f73da17285030c2a7ff880eec87b8df183481efbb8e49915cdff03ad2d5e1294d1092fc8fc9a5c5590ede4649f6fe9c9f9f6e36d043fc6d12b52ef
+  metadata.gz: 31071ac5cbeab5900fb4f505bd7d4357b5c45823a839fb7fa25a7192ed4aaa76cd77d3400322acc2bd70aeb213ebd6d12671f99e97b7bb9986823ae1aefdf000
+  data.tar.gz: 5e326ca98cad26b326e169a87d550d6ebcf00a12f01b22c2906a4dae7af71570080e469e79d8446b969fe93fb64cdbab34a2bd1074f7704f7eb182b859eabc40

data/README.md

@@ -105,6 +105,22 @@ while (scroll = Document.es(scroll, scroll: '1m')) && scroll.empty? == false do
 end
 ```
 
+### Import
+
+You can import the whole dataset, or specify a dataset to be imported. This will create a new, timestamped index for your dataset, and import all the records from that dataset into the index. An alias will be created (or updated) to point to the newly created index.
+
+```ruby
+Document.import! # Import all the Document records. Use the default settings.
+
+Document.import!(dataset: Document.where(active: true)) # Import all the active Document records
+
+Document.import!(
+    index: 'active-documents', # Use the active-documents index
+    dataset: Document.where(active: true), # Only index active documents
+    batch_size: 20 # Send documents to Elasticsearch in batches of 20 records
+)
+```
+
 ## Development
 
 After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.

data/lib/sequel/plugins/elasticsearch.rb

@@ -16,17 +16,21 @@ module Sequel
     module Elasticsearch
       # Apply the plugin to the specified model
       def self.apply(model, _opts = OPTS)
-        model.instance_variable_set(:@elasticsearch_opts, {})
-        model.instance_variable_set(:@elasticsearch_index, nil)
-        model.instance_variable_set(:@elasticsearch_type, '_doc')
         model
       end
 
       # Configure the plugin
       def self.configure(model, opts = OPTS)
+        environment_scoped = if opts[:environment_scoped].nil?
+                               model.environment != 'test'
+                             else
+                               opts[:environment_scoped]
+                             end
+
         model.elasticsearch_opts = opts[:elasticsearch] || {}
         model.elasticsearch_index = (opts[:index] || model.table_name).to_sym
         model.elasticsearch_type = (opts[:type] || :_doc).to_sym
+        model.elasticsearch_environment_scoped = environment_scoped
         model
       end
 
@@ -35,9 +39,11 @@ module Sequel
         # The extra options that will be passed to the Elasticsearch client.
         attr_accessor :elasticsearch_opts
         # The Elasticsearch index to which the documents will be written.
-        attr_accessor :elasticsearch_index
+        attr_writer :elasticsearch_index
         # The Elasticsearch type to which the documents will be written.
         attr_accessor :elasticsearch_type
+        # If generated indices should include the environment name
+        attr_accessor :elasticsearch_environment_scoped
 
         # Return the Elasticsearch client used to communicate with the cluster.
         def es_client
@@ -137,22 +143,41 @@ module Sequel
           es_client.indices.get_alias(name: elasticsearch_index)&.keys&.sort&.first
         end
 
+        def elasticsearch_index
+          return @elasticsearch_index unless elasticsearch_environment_scoped
+
+          "#{@elasticsearch_index}-#{environment}".to_sym
+        end
+
         # Generate a timestamped index name according to the environment.
-        # This will use the +APP_ENV+ ENV variable and a timestamp to construct
-        # index names like this:
+        # This will use the +APP_ENV+ or +RACK_ENV+ ENV variable and a timestamp
+        # to construct index names like this:
         #
         #    base-name-staging-20191004.123456 # This is a staging index
-        #    base-name-20191005.171213 # This is a production index
+        #    base-name-production-20191005.171213 # This is a production index
         #
+        # The adding of the environment name to the index can be turned off by
+        # setting +elasticsearch_environment_scoped+ to false.
         def timestamped_index
           time_str = Time.now.strftime('%Y%m%d.%H%M%S')
-          env_str = ENV['APP_ENV'] == 'production' ? nil : ENV['APP_ENV']
-          [elasticsearch_index, env_str, time_str].compact.join('-')
+          "#{elasticsearch_index}-#{time_str}".to_sym
+        end
+
+        def environment
+          ENV['APP_ENV'] || ENV['RACK_ENV'] || 'development'
         end
       end
 
       # The instance methods that will be added to the Sequel::Model
       module InstanceMethods
+        def elasticsearch_index
+          self.class.elasticsearch_index
+        end
+
+        def elasticsearch_type
+          self.class.elasticsearch_type
+        end
+
         # Sequel::Model after_create hook to add the new record to the Elasticsearch index.
         # It's "safe" in that it won't raise an error if it fails.
         def after_create
@@ -210,8 +235,8 @@ module Sequel
         # Determine the complete path to a document (/index/type/id) in the Elasticsearch cluster.
         def document_path(opts = {})
           {
-            index: opts.delete(:index) || self.class.elasticsearch_index,
-            type: opts.delete(:type) || self.class.elasticsearch_type,
+            index: opts.delete(:index) || elasticsearch_index,
+            type: opts.delete(:type) || elasticsearch_type,
             id: opts.delete(:id) || document_id
           }
         end

data/lib/sequel/plugins/elasticsearch/version.rb

@@ -4,6 +4,6 @@ module Sequel
   # See https://jrgns.github.io/sequel-elasticsearch
   module Elasticsearch
     # The Gem's version.
-    VERSION = '0.4.8'.freeze
+    VERSION = '0.4.9'.freeze
   end
 end

data/sequel-elasticsearch.gemspec

@@ -30,4 +30,5 @@ Gem::Specification.new do |spec|
   spec.add_development_dependency 'rubocop', '~> 0.52'
   spec.add_development_dependency 'simplecov', '~> 0.15'
   spec.add_development_dependency 'webmock', '~> 3.2'
+  spec.add_development_dependency 'sqlite3', '~> 1.4'
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: sequel-elasticsearch
 version: !ruby/object:Gem::Version
-  version: 0.4.8
+  version: 0.4.9
 platform: ruby
 authors:
 - Jurgens du Toit
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2019-11-04 00:00:00.000000000 Z
+date: 2019-11-05 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: elasticsearch
@@ -122,6 +122,20 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '3.2'
+- !ruby/object:Gem::Dependency
+  name: sqlite3
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.4'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.4'
 description: A plugin for the Sequel gem to sync data to Elasticsearch.
 email:
 - jrgns@jadeit.co.za