chewy 0.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 1731bb408069ab82feb6979f9f70008a0977cb48
+  data.tar.gz: b676bfdc501aece147b1af8a915f99defd0f2eaa
+SHA512:
+  metadata.gz: 7ce0646699822d696680438f2be44d12b4a9829470362e841e357e059759474c4a54fdbed4c4b5ec6946b2d50800fd7e8be3a3f31d33e7ac987705fb5622266c
+  data.tar.gz: 5ede42795877994577c4aac44c5898dd7abacc7d922db0a1563b0e5e1564d8c02fec987eb4f01014f7fc46c4c20811aab5cc4f17280d734be6f7f5ba73fa8c0f

data/.gitignore

@@ -0,0 +1,17 @@
+*.gem
+*.rbc
+.bundle
+.config
+.yardoc
+Gemfile.lock
+InstalledFiles
+_yardoc
+coverage
+doc/
+lib/bundler/man
+pkg
+rdoc
+spec/reports
+test/tmp
+test/version_tmp
+tmp

data/.rspec

@@ -0,0 +1,3 @@
+--color
+--backtrace
+--order random

data/.rvmrc

@@ -0,0 +1 @@
+rvm use 1.9.3@chewy --create

data/.travis.yml

@@ -0,0 +1,7 @@
+language: ruby
+rvm:
+  - 1.9.3
+  - 2.0.0
+  - rbx
+services:
+  - elasticsearch

data/Gemfile

@@ -0,0 +1,12 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in chewy.gemspec
+gemspec
+
+group :test do
+  gem 'guard'
+  gem 'guard-rspec'
+  gem 'rb-inotify', require: false
+  gem 'rb-fsevent', require: false
+  gem 'rb-fchange', require: false
+end

data/Guardfile

@@ -0,0 +1,24 @@
+# A sample Guardfile
+# More info at https://github.com/guard/guard#readme
+
+guard :rspec do
+  watch(%r{^spec/.+_spec\.rb$})
+  watch(%r{^lib/(.+)\.rb$})     { |m| "spec/lib/#{m[1]}_spec.rb" }
+  watch('spec/spec_helper.rb')  { "spec" }
+
+  # Rails example
+  watch(%r{^app/(.+)\.rb$})                           { |m| "spec/#{m[1]}_spec.rb" }
+  watch(%r{^app/(.*)(\.erb|\.haml|\.slim)$})          { |m| "spec/#{m[1]}#{m[2]}_spec.rb" }
+  watch(%r{^app/controllers/(.+)_(controller)\.rb$})  { |m| ["spec/routing/#{m[1]}_routing_spec.rb", "spec/#{m[2]}s/#{m[1]}_#{m[2]}_spec.rb", "spec/acceptance/#{m[1]}_spec.rb"] }
+  watch(%r{^spec/support/(.+)\.rb$})                  { "spec" }
+  watch('config/routes.rb')                           { "spec/routing" }
+  watch('app/controllers/application_controller.rb')  { "spec/controllers" }
+
+  # Capybara features specs
+  watch(%r{^app/views/(.+)/.*\.(erb|haml|slim)$})     { |m| "spec/features/#{m[1]}_spec.rb" }
+
+  # Turnip features and steps
+  watch(%r{^spec/acceptance/(.+)\.feature$})
+  watch(%r{^spec/acceptance/steps/(.+)_steps\.rb$})   { |m| Dir[File.join("**/#{m[1]}.feature")][0] || 'spec/acceptance' }
+end
+

data/LICENSE.txt

@@ -0,0 +1,22 @@
+Copyright (c) 2013 pyromaniac
+
+MIT License
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.md

@@ -0,0 +1,208 @@
+# Chewy
+
+Chewy is ODM and wrapper for official elasticsearch client (https://github.com/elasticsearch/elasticsearch-ruby)
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+    gem 'chewy'
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install chewy
+
+## Usage
+
+### Index file
+
+1. Create `/app/chewy/users_index.rb`
+
+  ```ruby
+    class UsersIndex < Chewy::Index
+
+    end
+  ```
+
+2. Add one or more types mapping
+
+  ```ruby
+    class UsersIndex < Chewy::Index
+      define_type User.active # or just model instead_of scope: define_type User
+    end
+  ```
+
+  Newly-defined index type class is accessible via `UsersIndex.user` or `UsersIndex::User`
+
+3. Add some type mappings
+
+  ```ruby
+    class UsersIndex < Chewy::Index
+      define_type User.active.includes(:country, :bages, :projects) do
+        field :first_name, :last_name # multiple fields without additional options
+        field :email, analyzer: 'email' # elasticsearch-related options
+        field :country, value: ->(user) { user.country.name } # custom value proc
+        field :bages, value: ->(user) { user.bages.map(&:name) } # passing array values to index
+        field :projects, type: 'object' do # the same syntax for `multi_field`
+          field :title
+          field :description # default data type is `string`
+        end
+        field :rating, type: 'integer' # custom data type
+        field :created_at, type: 'date', include_in_all: false
+      end
+    end
+  ```
+
+  Mapping definitions - http://www.elasticsearch.org/guide/en/elasticsearch/reference/current/mapping.html
+
+4. Add some index- and type-related settings
+
+  ```ruby
+    class UsersIndex < Chewy::Index
+      settings analysis: {
+        analyzer: {
+          email: {
+            tokenizer: 'keyword',
+            filter: ['lowercase']
+          }
+        }
+      }
+
+      define_type User.active.includes(:country, :bages, :projects) do
+        root _boost: { name: :_boost, null_value: 1.0 } do # optional `root` object settings
+          field :first_name, :last_name # multiple fields without additional options
+          field :email, analyzer: 'email' # elasticsearch-related options
+          field :country, value: ->(user) { user.country.name } # custom value proc
+          field :bages, value: ->(user) { user.bages.map(&:name) } # passing array values to index
+          field :projects, type: 'object' do # the same syntax for `multi_field`
+            field :title
+            field :description # default data type is `string`
+          end
+          field :about_translations, type: 'object'
+          field :rating, type: 'integer' # custom data type
+          field :created_at, type: 'date', include_in_all: false
+        end
+      end
+    end
+  ```
+
+  Index settings - http://www.elasticsearch.org/guide/en/elasticsearch/reference/current/indices-update-settings.html
+  Root object settings - http://www.elasticsearch.org/guide/en/elasticsearch/reference/current/mapping-root-object-type.html
+
+5. Add model observing code
+
+  ```ruby
+    class User < ActiveRecord::Base
+      update_elasticsearch('users#user') { self } # specifying index, type and backreference
+                                                  # for updating after user save or destroy
+    end
+
+    class Country < ActiveRecord::Base
+      has_many :users
+
+      update_elasticsearch('users#user') { users } # return single object or collection
+    end
+
+    class Project < ActiveRecord::Base
+      update_elasticsearch('users#user') { user if user.active? } # you can return even `nil` from the backreference
+    end
+
+    class Bage < ActiveRecord::Base
+      has_and_belongs_to_many :users
+
+      update_elasticsearch('users') { users } # if index has only one type
+                                              # there is no need to specify updated type
+    end
+  ```
+
+### Index manipulation
+
+```ruby
+  UsersIndex.index_delete # destroy index if exists
+  UsersIndex.index_create! # use bang or non-bang methods
+  UsersIndex.import # import with 0 arguments process all the data specified in type definition
+                    # literally, User.active.includes(:country, :bages, :projects).find_in_batches
+
+  UsersIndex.import User.where('rating > 100') # or import specified users
+  UsersIndex.import [1, 2, 42] # pass even ids for import, it will be handled in the most effective way
+```
+
+Also if passed user is #destroyed? or specified id is not existing in the database, import will perform `delete` index for this it
+
+### Observing strategies
+
+There are 2 strategies for index updating: updating right after save and cummulative update. The first is by default. To perform the second one, use `Chewy.atomic`:
+
+```ruby
+  Chewy.atomic do
+    user.each { |user| user.update_attributes(name: user.name.strip) }
+  end
+```
+
+Index update will be performed once per Chewy.atomic block. This strategy is highly usable for rails actions:
+
+```ruby
+  class ApplicationController < ActionController::Base
+    around_action { |&block| Chewy.atomic(&block) }
+  end
+```
+
+### Index querying
+
+```ruby
+  scope = UsersIndex.search.query(term: {name: 'foo'})
+    .filter({numeric_range: {rating: {gte: 100}}})
+    .order(created_at: :desc)
+    .limit(20).offset(100)
+
+  scope.to_a # => will produce array of UserIndex::User or other types instances
+  scope.map { |user| user.email }
+  scope.total_count # => will return total objects count
+
+  scope.per(10).page(3) # supports kaminari pagination
+  scope.explain.map { |user| user._explanation }
+  scope.only(:id, :email) # returns ids and emails only
+```
+
+Also, queries can be performed on a type individually
+
+```ruby
+  UsersIndex.search.query(term: {name: 'foo'}).count # will return UserIndex::User array only
+```
+
+### Objects loading
+
+It is possible to load source objects from database for every search result:
+
+```ruby
+  scope = UsersIndex.search.filter({numeric_range: {rating: {gte: 100}}})
+
+  scope.load # => will return User instances array (not a scope because )
+  scope.load(scopes: { user: ->(_) { includes(:country) }}) # => you can also pass loading scopes for each
+                                                            # possibly returned type
+  scope.only(:id).load # it is optimal to request ids only if you are not planning to use type objects
+```
+
+## TODO a.k.a coming soon:
+
+* Dynamic templates additional DSL
+* Typecasting support
+* Advanced (simplyfied) query DSL: `UsersIndex.query { email == 'my@gmail.com' }` will produce term query
+* Remove Index.search method, all the query DSL methods should be delegated to the Index
+* Observing strategies reworking
+* update_all support
+* Other than ActiveRecord ORMs support (Mongoid)
+* Maybe, closer ORM/ODM integration, creating index classes implicitly
+* Better facets support
+
+## Contributing
+
+1. Fork it ( http://github.com/<my-github-username>/chewy/fork )
+2. Create your feature branch (`git checkout -b my-new-feature`)
+3. Commit your changes (`git commit -am 'Add some feature'`)
+4. Push to the branch (`git push origin my-new-feature`)
+5. Create new Pull Request

data/Rakefile

@@ -0,0 +1,6 @@
+require "bundler/gem_tasks"
+require "rspec/core/rake_task"
+
+RSpec::Core::RakeTask.new(:spec)
+
+task :default => :spec

data/chewy.gemspec

@@ -0,0 +1,32 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'chewy/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = 'chewy'
+  spec.version       = Chewy::VERSION
+  spec.authors       = ['pyromaniac']
+  spec.email         = ['kinwizard@gmail.com']
+  spec.summary       = %q{Elasticsearch ODM client wrapper}
+  spec.description   = %q{Chewy provides functionality for Elasticsearch index handling, documents import mappings and chainable query DSL}
+  spec.homepage      = ''
+  spec.license       = 'MIT'
+
+  spec.files         = `git ls-files`.split($/)
+  spec.executables   = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
+  spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
+  spec.require_paths = ['lib']
+
+  spec.add_development_dependency 'bundler'
+  spec.add_development_dependency 'rake'
+  spec.add_development_dependency 'rspec'
+  spec.add_development_dependency 'sqlite3'
+  spec.add_development_dependency 'kaminari'
+  spec.add_development_dependency 'activerecord', '>= 3.2'
+  spec.add_development_dependency 'database_cleaner'
+  spec.add_development_dependency 'rubysl', '~> 2.0' if RUBY_ENGINE == 'rbx'
+
+  spec.add_dependency 'activesupport', '>= 3.2'
+  spec.add_dependency 'elasticsearch'
+end

data/lib/chewy.rb

@@ -0,0 +1,55 @@
+require 'active_support/concern'
+require 'active_support/core_ext'
+require 'active_support/json'
+require 'singleton'
+
+require 'elasticsearch'
+
+require 'chewy/version'
+require 'chewy/config'
+require 'chewy/index'
+require 'chewy/type'
+require 'chewy/query'
+require 'chewy/fields/base'
+require 'chewy/fields/default'
+require 'chewy/fields/root'
+
+ActiveSupport.on_load(:active_record) do
+  extend Chewy::Type::Observe::ActiveRecordMethods
+end
+
+module Chewy
+  class Error < StandardError
+  end
+
+  class UndefinedIndex < Error
+  end
+
+  class UndefinedType < Error
+  end
+
+  class UnderivableType < Error
+  end
+
+  def self.derive_type name
+    return name if name.is_a?(Class) && name < Chewy::Type::Base
+
+    index_name, type_name = name.split('#', 2)
+    class_name = "#{index_name.camelize}Index"
+    index = class_name.safe_constantize
+    raise Chewy::UnderivableType.new("Can not find index named `#{class_name}`") unless index && index < Chewy::Index
+    type = if type_name.present?
+      index.types[type_name] or raise Chewy::UnderivableType.new("Index `#{class_name}` doesn`t have type named `#{type_name}`")
+    elsif index.types.values.one?
+      index.types.values.first
+    else
+      raise Chewy::UnderivableType.new("Index `#{class_name}` has more than one type, please specify type via `#{index_name}#type_name`")
+    end
+  end
+
+  def self.config
+    Chewy::Config.instance
+  end
+
+  singleton_class.delegate *Chewy::Config.delegated, to: :config
+end

data/lib/chewy/config.rb

@@ -0,0 +1,48 @@
+module Chewy
+  class Config
+    include Singleton
+
+    attr_accessor :observing_enabled, :client_options
+
+    def self.delegated
+      public_instance_methods - self.superclass.public_instance_methods - Singleton.public_instance_methods
+    end
+
+    def initialize
+      @observing_enabled = true
+      @client_options = {}
+    end
+
+    def client_options
+      yaml_options = if defined? Rails
+        file = Rails.root.join(*%w(config chewy.yml))
+        YAML.load_file(file)[Rails.env].try(:deep_symbolize_keys) if File.exists?(file)
+      end
+      @client_options.merge(yaml_options || {})
+    end
+
+    def atomic?
+      atomic_stash.any?
+    end
+
+    def atomic
+      atomic_stash.push({})
+      result = yield
+      atomic_stash.last.each { |type, ids| type.import(ids) }
+      result
+    ensure
+      atomic_stash.pop
+    end
+
+    def atomic_stash(type = nil, *ids)
+      if type
+        raise ArgumentError.new('Only Chewy::Type::Base accepted as the first argument') unless type < Chewy::Type::Base
+        atomic_stash.push({}) unless atomic_stash.last
+        atomic_stash.last[type] ||= []
+        atomic_stash.last[type] |= ids.flatten
+      else
+        Thread.current[:chewy_atomic] ||= []
+      end
+    end
+  end
+end