curate-indexer 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: e1be92053b6ce30d9e75ac935c7000861725a4c5
+  data.tar.gz: babb5d4f0228d9210d096688d920d5c457f0f266
+SHA512:
+  metadata.gz: eb5f7aaecda93774887fe655bd9c9884901c65360f32575f74df1f1e15404ef5b0a3933e5992ef5a4a35b794364fddf5c0cbc63f5212214efe1d288a5f7099e3
+  data.tar.gz: 1aaf669fc93f8f435b6d116417da0433428cb72a0ff5871c362e8815d6348cbdb012dc2d8c7bee7b9a4ba9c17cdf315d435cc08c05a45d91223db0741aa66b7d

data/.gitignore

@@ -0,0 +1,9 @@
+/.bundle/
+/.yardoc
+/Gemfile.lock
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/

data/.rspec

@@ -0,0 +1,2 @@
+--format documentation
+--color

data/.rubocop.yml

@@ -0,0 +1,48 @@
+################################################################################
+## Releasing the hounds in your local environment.
+##
+## Setup:
+## $ gem install rubocop
+##
+## Run:
+## $ rubocop ./path/to/file ./or/path/to/directory -c ./.hound.yml
+##
+## Generation Notes:
+##   This file was generated via the commitment:install generator. You are free
+##   and expected to change this file.
+################################################################################
+AllCops:
+  Include:
+    - Rakefile
+  Exclude:
+    - 'vendor/**/*'
+    - 'tmp/**/*'
+    - 'bin/**/*'
+  TargetRubyVersion: 2.0
+LineLength:
+  Description: 'Limit lines to 140 characters.'
+  Max: 140
+  Enabled: true
+
+ModuleLength:
+  Exclude:
+    - 'spec/**/*'
+
+
+Style/StringLiterals:
+  Description: 'Checks if uses of quotes match the configured preference.'
+  Enabled: false
+
+PercentLiteralDelimiters:
+  Description: 'Use `%`-literal delimiters consistently'
+  Enabled: false
+
+Documentation:
+  Description: 'Document classes and non-namespace modules.'
+  Enabled: true
+  Exclude:
+  - spec/**/*
+  - test/**/*
+
+Style/WordArray:
+  Enabled: false

data/.ruby-version

@@ -0,0 +1 @@
+2.2.2

data/.travis.yml

@@ -0,0 +1,22 @@
+sudo: false
+cache: bundler
+
+language: ruby
+rvm:
+  - 2.3.1
+  - 2.2.5
+  - 2.2.2
+  - 2.1.10
+  - 2.0.0
+
+matrix:
+  allow_failures:
+    - rvm: "2.3.1"
+
+before_install: gem install bundler -v 1.12.5
+
+script: 'bundle exec rake'
+
+addons:
+    code_climate:
+        repo_token: 71b80cc45ed849e84e5943bb4874393b5ce26a2356381a839552395cd9b2f71a

data/Gemfile

@@ -0,0 +1,4 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in curate-indexer.gemspec
+gemspec

data/Guardfile

@@ -0,0 +1,49 @@
+# A sample Guardfile
+# More info at https://github.com/guard/guard#readme
+
+## Uncomment and set this to only include directories you want to watch
+# directories %w(app lib config test spec features) \
+#  .select{|d| Dir.exists?(d) ? d : UI.warning("Directory #{d} does not exist")}
+
+## Note: if you are using the `directories` clause above and you are not
+## watching the project directory ('.'), then you will want to move
+## the Guardfile to a watched dir and symlink it back, e.g.
+#
+#  $ mkdir config
+#  $ mv Guardfile config/
+#  $ ln -s config/Guardfile .
+#
+# and, you'll have to watch "config/Guardfile" instead of "Guardfile"
+
+# Note: The cmd option is now required due to the increasing number of ways
+#       rspec may be run, below are examples of the most common uses.
+#  * bundler: 'bundle exec rspec'
+#  * bundler binstubs: 'bin/rspec'
+#  * spring: 'bin/rspec' (This will use spring if running and you have
+#                          installed the spring binstubs per the docs)
+#  * zeus: 'zeus rspec' (requires the server to be started separately)
+#  * 'just' rspec: 'rspec'
+
+notification :terminal_notifier, subtitle: 'Curate::Indexer'
+
+guard :rspec, cmd: "bundle exec rspec" do
+  require "guard/rspec/dsl"
+  dsl = Guard::RSpec::Dsl.new(self)
+
+  # Feel free to open issues for suggestions and improvements
+
+  # RSpec files
+  rspec = dsl.rspec
+  watch(rspec.spec_helper) { rspec.spec_dir }
+  watch(rspec.spec_support) { rspec.spec_dir }
+  watch(rspec.spec_files)
+
+  # Ruby files
+  ruby = dsl.ruby
+  dsl.watch_spec_files_for(ruby.lib_files)
+end
+
+guard :rubocop do
+  watch(%r{.+\.rb$})
+  watch(%r{(?:.+/)?\.rubocop\.yml$}) { |m| File.dirname(m[0]) }
+end

data/LICENSE

@@ -0,0 +1,14 @@
+##########################################################################
+# Copyright 2014-2015 University of Notre Dame
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.

data/README.md

@@ -0,0 +1,9 @@
+# Curate::Indexer
+
+[![Build Status](https://travis-ci.org/ndlib/curate-indexer.png?branch=master)](https://travis-ci.org/ndlib/curate-indexer)
+[![Test Coverage](https://codeclimate.com/github/ndlib/curate-indexer/badges/coverage.svg)](https://codeclimate.com/github/ndlib/curate-indexer)
+[![Code Climate](https://codeclimate.com/github/ndlib/curate-indexer.png)](https://codeclimate.com/github/ndlib/curate-indexer)
+[![Documentation Status](http://inch-ci.org/github/ndlib/curate-indexer.svg?branch=master)](http://inch-ci.org/github/ndlib/curate-indexer)
+[![APACHE 2 License](http://img.shields.io/badge/APACHE2-license-blue.svg)](./LICENSE)
+
+This is a sandbox to work through the reindexing strategy as it relates to [CurateND Collections](https://github.com/ndlib/curate_nd/issues/420). At this point the code is separate to allow for rapid testing and prototyping (no sense spinning up SOLR and Fedora to walk an arbitrary graph).

data/Rakefile

@@ -0,0 +1,34 @@
+require "bundler/gem_tasks"
+require "rspec/core/rake_task"
+
+namespace :commitment do
+  require 'rubocop/rake_task'
+  # Why hound? Because hound-ci assumes this file, and perhaps you'll be using this
+  RuboCop::RakeTask.new
+
+  task :configure_test_for_code_coverage do
+    ENV['COVERAGE'] = 'true'
+  end
+  task :code_coverage do
+    require 'json'
+    $stdout.puts "Checking commitment:code_coverage"
+    coverage_percentage = JSON.parse(File.read('coverage/.last_run.json')).fetch('result').fetch('covered_percent').to_i
+    goal = 100
+    if goal > coverage_percentage
+      abort("Code Coverage Goal Not Met:\n\t#{coverage_percentage}%\tExpected\n\t#{goal}%\tActual")
+    end
+  end
+end
+
+task(
+  default: [
+    'commitment:rubocop',
+    'commitment:configure_test_for_code_coverage',
+    'spec',
+    'commitment:code_coverage'
+  ]
+)
+
+RSpec::Core::RakeTask.new(:spec)
+
+task default: :spec

data/bin/console

@@ -0,0 +1,14 @@
+#!/usr/bin/env ruby
+
+require "bundler/setup"
+require "curate/indexer"
+
+# You can add fixtures and/or initialization code here to make experimenting
+# with your gem easier. You can also use a different console, if you like.
+
+# (If you use this, don't forget to add pry to your Gemfile!)
+# require "pry"
+# Pry.start
+
+require "irb"
+IRB.start

data/bin/setup

@@ -0,0 +1,8 @@
+#!/usr/bin/env bash
+set -euo pipefail
+IFS=$'\n\t'
+set -vx
+
+bundle install
+
+# Do any other automated setup that you need to do here

data/curate-indexer.gemspec

@@ -0,0 +1,39 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'curate/indexer/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "curate-indexer"
+  spec.version       = Curate::Indexer::VERSION
+  spec.authors       = ["Jeremy Friesen"]
+  spec.email         = ["jeremy.n.friesen@gmail.com"]
+
+  spec.summary       = %q{A playground for CurateND collections indexing}
+  spec.description   = %q{A playground for CurateND collections indexing}
+  spec.homepage      = "https://github.com/ndlib/curate-indexer"
+
+  spec.files         = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
+  spec.bindir        = "bin"
+  spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
+  spec.require_paths = ["lib"]
+  spec.required_ruby_version = '~>2.0'
+
+  spec.add_development_dependency "bundler", "~> 1.12"
+  spec.add_development_dependency "rake", "~> 10.0"
+  spec.add_development_dependency "rspec", "~> 3.0"
+  spec.add_development_dependency "rspec-its"
+  spec.add_development_dependency "guard-rspec"
+  spec.add_development_dependency "guard-rubocop"
+  spec.add_development_dependency "terminal-notifier-guard"
+  spec.add_development_dependency "terminal-notifier"
+  spec.add_development_dependency "rubocop"
+  spec.add_development_dependency "simplecov"
+  spec.add_development_dependency "codeclimate-test-reporter"
+  spec.add_development_dependency "json"
+  spec.add_development_dependency "byebug"
+  spec.add_development_dependency "railties", '~> 4.0'
+  # As a secondary dependency, listen is preventing bundling
+  spec.add_development_dependency "listen", '~> 3.0.8'
+  spec.add_dependency "dry-equalizer"
+end

data/lib/curate/indexer/adapters.rb

@@ -0,0 +1,95 @@
+module Curate
+  module Indexer
+    module Adapters
+      # @api public
+      # A module that defines the interface of methods required to interact with Curate::Indexer operations
+      module AbstractAdapter
+        # @api public
+        # @param pid [String]
+        # @return Curate::Indexer::Document::PreservationDocument
+        def self.find_preservation_document_by(*)
+          raise NotImplementedError
+        end
+
+        # @api public
+        # @param pid [String]
+        # @return Curate::Indexer::Documents::IndexDocument
+        def self.find_index_document_by(*)
+          raise NotImplementedError
+        end
+
+        # @api public
+        # @yield Curate::Indexer::Document::PreservationDocument
+        def self.each_preservation_document
+          raise NotImplementedError
+        end
+
+        # @api public
+        # @param pid [String]
+        # @yield Curate::Indexer::Documents::IndexDocument
+        def self.each_child_document_of(*, &_block)
+          raise NotImplementedError
+        end
+
+        # @api public
+        # @return Curate::Indexer::Documents::IndexDocument
+        def self.write_document_attributes_to_index_layer(*)
+          raise NotImplementedError
+        end
+      end
+      # @api public
+      #
+      # Defines the interface for interacting with the InMemory layer. It is a reference
+      # implementation that is used throughout tests.
+      module InMemoryAdapter
+        extend AbstractAdapter
+        # @api public
+        # @param pid [String]
+        # @return Curate::Indexer::Document::PreservationDocument
+        def self.find_preservation_document_by(pid)
+          Preservation.find(pid)
+        end
+
+        # @api public
+        # @param pid [String]
+        # @return Curate::Indexer::Documents::IndexDocument
+        def self.find_index_document_by(pid)
+          Index.find(pid)
+        end
+
+        # @api public
+        # @yield Curate::Indexer::Document::PreservationDocument
+        def self.each_preservation_document
+          Preservation.find_each { |document| yield(document) }
+        end
+
+        # @api public
+        # @param pid [String]
+        # @yield Curate::Indexer::Documents::IndexDocument
+        def self.each_child_document_of(pid, &block)
+          Index.each_child_document_of(pid, &block)
+        end
+
+        # @api public
+        # This is not something that I envision using in the production environment;
+        # It is hear to keep the Preservation system isolated and accessible only through interfaces.
+        # @return Curate::Indexer::Documents::PreservationDocument
+        def self.write_document_attributes_to_preservation_layer(attributes = {})
+          Preservation.write_document(attributes)
+        end
+
+        # @api public
+        # @return Curate::Indexer::Documents::IndexDocument
+        def self.write_document_attributes_to_index_layer(attributes = {})
+          Index.write_document(attributes)
+        end
+
+        # @api private
+        def self.clear_cache!
+          Preservation.clear_cache!
+          Index.clear_cache!
+        end
+      end
+    end
+  end
+end

data/lib/curate/indexer/configuration.rb

@@ -0,0 +1,21 @@
+module Curate
+  # :nodoc:
+  module Indexer
+    # Responsible for the configuration of the Curate::Indexer
+    class Configuration
+      def adapter
+        @adapter || default_adapter
+      end
+      # TODO: Should we guard against a bad adapter?
+      attr_writer :adapter
+
+      private
+
+      def default_adapter
+        require 'curate/indexer/adapters'
+        Adapters::InMemoryAdapter
+      end
+    end
+    private_constant :Configuration
+  end
+end

data/lib/curate/indexer/documents.rb

@@ -0,0 +1,47 @@
+require 'dry-equalizer'
+
+module Curate
+  module Indexer
+    module Documents
+      # @api public
+      #
+      # A simplified document that reflects the necessary attributes for re-indexing
+      # the children of Fedora objects.
+      class PreservationDocument
+        def initialize(keywords = {})
+          @pid = keywords.fetch(:pid).to_s
+          @parent_pids = Array(keywords.fetch(:parent_pids))
+        end
+        attr_reader :pid, :parent_pids
+      end
+
+      # @api private
+      #
+      # A rudimentary representation of what is needed to reindex Solr documents
+      class IndexDocument
+        # A quick and dirty means of doing comparative logic
+        include Dry::Equalizer(:pid, :sorted_parent_pids, :sorted_pathnames, :sorted_ancestors)
+
+        def initialize(keywords = {})
+          @pid = keywords.fetch(:pid).to_s
+          @parent_pids = Array(keywords.fetch(:parent_pids))
+          @pathnames = Array(keywords.fetch(:pathnames))
+          @ancestors = Array(keywords.fetch(:ancestors))
+        end
+        attr_reader :pid, :parent_pids, :pathnames, :ancestors
+
+        def sorted_parent_pids
+          parent_pids.sort
+        end
+
+        def sorted_pathnames
+          pathnames.sort
+        end
+
+        def sorted_ancestors
+          ancestors.sort
+        end
+      end
+    end
+  end
+end

data/lib/curate/indexer/exceptions.rb

@@ -0,0 +1,16 @@
+module Curate
+  module Indexer
+    module Exceptions
+      class RuntimeError < ::RuntimeError
+      end
+      # Raised when we may have detected a cycle within the graph
+      class CycleDetectionError < RuntimeError
+        attr_reader :pid
+        def initialize(pid)
+          @pid = pid
+          super "Possible graph cycle discovered related to PID:#{pid}."
+        end
+      end
+    end
+  end
+end

data/lib/curate/indexer/index.rb

@@ -0,0 +1,39 @@
+require 'curate/indexer/storage_module'
+require 'curate/indexer/documents'
+
+module Curate
+  # :nodoc:
+  module Indexer
+    # @api private
+    #
+    # An abstract representation of the underlying index service. In the case of
+    # CurateND this is an abstraction of Solr.
+    module Index
+      def self.clear_cache!
+        Storage.clear_cache!
+      end
+
+      def self.find(pid)
+        Storage.find(pid)
+      end
+
+      def self.each_child_document_of(pid, &block)
+        Storage.find_children_of_pid(pid).each(&block)
+      end
+
+      def self.write_document(attributes = {})
+        Documents::IndexDocument.new(attributes).tap { |doc| Storage.write(doc) }
+      end
+
+      # :nodoc:
+      module Storage
+        extend StorageModule
+        def self.find_children_of_pid(pid)
+          cache.values.select { |document| document.parent_pids.include?(pid) }
+        end
+      end
+      private_constant :Storage
+    end
+    private_constant :Index
+  end
+end

data/lib/curate/indexer/preservation.rb

@@ -0,0 +1,39 @@
+require 'curate/indexer/storage_module'
+require 'curate/indexer/documents'
+
+module Curate
+  # :nodoc:
+  module Indexer
+    # @api private
+    #
+    # A module responsible for containing the "preservation interface" logic.
+    # In the case of CurateND, there will need to be an adapter to get a Fedora
+    # object coerced into a Curate::Indexer::Preservation::Document
+    module Preservation
+      def self.find(pid, *)
+        MemoryStorage.find(pid)
+      end
+
+      def self.find_each(*, &block)
+        MemoryStorage.find_each(&block)
+      end
+
+      def self.clear_cache!
+        MemoryStorage.clear_cache!
+      end
+
+      def self.write_document(attributes = {})
+        Documents::PreservationDocument.new(attributes).tap do |doc|
+          MemoryStorage.write(doc)
+        end
+      end
+
+      # :nodoc:
+      module MemoryStorage
+        extend StorageModule
+      end
+      private_constant :MemoryStorage
+    end
+    private_constant :Preservation
+  end
+end

data/lib/curate/indexer/railtie.rb

@@ -0,0 +1,13 @@
+require 'rails/railtie'
+
+module Curate
+  module Indexer
+    # Connect into the boot sequence of a Rails application
+    class Railtie < Rails::Railtie
+      config.eager_load_namespaces << Curate::Indexer
+      config.to_prepare do
+        Curate::Indexer.send(:configure!)
+      end
+    end
+  end
+end

data/lib/curate/indexer/relationship_reindexer.rb

@@ -0,0 +1,103 @@
+require 'curate/indexer/exceptions'
+require 'curate/indexer/index'
+require 'curate/indexer/preservation'
+require 'forwardable'
+require 'set'
+
+module Curate
+  # Establishing namespace
+  module Indexer
+    # Responsible for reindexing the PID and its descendants
+    # @note There is cycle detection via the TIME_TO_LIVE counter
+    # @api private
+    class RelationshipReindexer
+      def self.call(options = {})
+        new(options).call
+      end
+
+      def initialize(options = {})
+        @pid = options.fetch(:pid).to_s
+        @time_to_live = options.fetch(:time_to_live).to_i
+        @adapter = options.fetch(:adapter)
+        @queue = options.fetch(:queue, [])
+      end
+      attr_reader :pid, :time_to_live, :queue, :adapter
+
+      def call
+        enqueue(pid, time_to_live)
+        index_document = dequeue
+        while index_document
+          process_a_document(index_document)
+          adapter.each_child_document_of(index_document.pid) { |child| enqueue(child.pid, index_document.time_to_live - 1) }
+          index_document = dequeue
+        end
+        self
+      end
+
+      private
+
+      attr_writer :document
+
+      extend Forwardable
+      def_delegator :queue, :shift, :dequeue
+
+      ProcessingDocument = Struct.new(:pid, :time_to_live)
+      private_constant :ProcessingDocument
+      def enqueue(pid, time_to_live)
+        queue.push(ProcessingDocument.new(pid, time_to_live))
+      end
+
+      def process_a_document(index_document)
+        raise Exceptions::CycleDetectionError, pid if index_document.time_to_live <= 0
+        preservation_document = adapter.find_preservation_document_by(index_document.pid)
+        adapter.write_document_attributes_to_index_layer(parent_pids_and_path_and_ancestors_for(preservation_document))
+      end
+
+      def parent_pids_and_path_and_ancestors_for(preservation_document)
+        ParentAndPathAndAncestorsBuilder.new(preservation_document, adapter).to_hash
+      end
+
+      # A small object that helps encapsulate the logic of building the hash of information regarding
+      # the initialization of an Index::Document
+      class ParentAndPathAndAncestorsBuilder
+        def initialize(preservation_document, adapter)
+          @preservation_document = preservation_document
+          @parent_pids = Set.new
+          @pathnames = Set.new
+          @ancestors = Set.new
+          @adapter = adapter
+          compile!
+        end
+
+        def to_hash
+          { pid: @preservation_document.pid, parent_pids: @parent_pids.to_a, pathnames: @pathnames.to_a, ancestors: @ancestors.to_a }
+        end
+
+        private
+
+        attr_reader :adapter
+
+        def compile!
+          @preservation_document.parent_pids.each do |parent_pid|
+            parent_index_document = adapter.find_index_document_by(parent_pid)
+            compile_one!(parent_index_document)
+          end
+          # Ensuring that an "orphan" has a path to get to it
+          @pathnames << @preservation_document.pid if @parent_pids.empty?
+        end
+
+        def compile_one!(parent_index_document)
+          @parent_pids << parent_index_document.pid
+          parent_index_document.pathnames.each do |pathname|
+            @pathnames << File.join(pathname, @preservation_document.pid)
+            slugs = pathname.split("/")
+            slugs.each_index { |i| @ancestors << slugs[0..i].join('/') }
+          end
+          @ancestors += parent_index_document.ancestors
+        end
+      end
+      private_constant :ParentAndPathAndAncestorsBuilder
+    end
+    private_constant :RelationshipReindexer
+  end
+end

data/lib/curate/indexer/repository_reindexer.rb

@@ -0,0 +1,49 @@
+module Curate
+  # Establishing namespace
+  module Indexer
+    # Responsible for reindexing the entire repository
+    # @api private
+    # @note There is cycle detection logic for walking the graph prior to attempting relationship re-indexing
+    class RepositoryReindexer
+      def self.call(*args)
+        new(*args).call
+      end
+
+      def initialize(options = {})
+        @max_time_to_live = options.fetch(:time_to_live).to_i
+        @pid_reindexer = options.fetch(:pid_reindexer)
+        @adapter = options.fetch(:adapter)
+        @processed_pids = []
+      end
+
+      def call
+        @adapter.each_preservation_document { |document| recursive_reindex(document, max_time_to_live) }
+      end
+
+      private
+
+      attr_reader :max_time_to_live, :processed_pids, :pid_reindexer
+
+      # Given that we are attempting to reindex the parents before we reindex, we can't rely on
+      # the reindex time_to_live but instead must have a separate time to live.
+      #
+      # The reindexing process assumes that an object's parents have been indexed; Thus we need to
+      # walk up the parent graph to reindex the parents before we start on the child.
+      def recursive_reindex(document, time_to_live = max_time_to_live)
+        return true if processed_pids.include?(document.pid)
+        raise Exceptions::CycleDetectionError, document.pid if time_to_live <= 0
+        document.parent_pids.each do |parent_pid|
+          parent_document = @adapter.find_preservation_document_by(parent_pid)
+          recursive_reindex(parent_document, time_to_live - 1)
+        end
+        reindex_a_pid(document.pid)
+      end
+
+      def reindex_a_pid(pid)
+        pid_reindexer.call(pid)
+        processed_pids << pid
+      end
+    end
+    private_constant :RepositoryReindexer
+  end
+end

data/lib/curate/indexer/storage_module.rb

@@ -0,0 +1,34 @@
+module Curate
+  module Indexer
+    # @api private
+    #
+    # A module mixin to expose rudimentary read/write capabilities
+    #
+    # @example
+    #   module Foo
+    #     extend Curate::Indexer::StorageModule
+    #   end
+    module StorageModule
+      def write(doc)
+        cache[doc.pid] = doc
+      end
+
+      def find(pid)
+        cache.fetch(pid.to_s)
+      end
+
+      def find_each
+        cache.each { |_key, document| yield(document) }
+      end
+
+      def clear_cache!
+        @cache = {}
+      end
+
+      def cache
+        @cache ||= {}
+      end
+      private :cache
+    end
+  end
+end

data/lib/curate/indexer/version.rb

@@ -0,0 +1,5 @@
+module Curate
+  module Indexer
+    VERSION = "0.1.0".freeze
+  end
+end

data/lib/curate/indexer.rb

@@ -0,0 +1,71 @@
+require "curate/indexer/version"
+require 'curate/indexer/relationship_reindexer'
+require 'curate/indexer/repository_reindexer'
+require 'curate/indexer/configuration'
+require 'curate/indexer/railtie' if defined?(Rails)
+
+module Curate
+  # Responsible for performign the indexing of an object and its related child objects.
+  module Indexer
+    # This assumes a rather deep graph
+    DEFAULT_TIME_TO_LIVE = 15
+    # @api public
+    # Responsible for reindexing the associated document for the given :pid and the descendants of that :pid.
+    # In a perfect world we could reindex the pid as well; But that is for another test.
+    #
+    # @param pid [String] - The permanent identifier of the object that will be reindexed along with its children.
+    # @param time_to_live [Integer] - there to guard against cyclical graphs
+    # @return [Boolean] - It was successful
+    # @raise Curate::Exceptions::CycleDetectionError - A potential cycle was detected
+    def self.reindex_relationships(pid, time_to_live = DEFAULT_TIME_TO_LIVE)
+      RelationshipReindexer.call(pid: pid, time_to_live: time_to_live, adapter: configuration.adapter)
+      true
+    end
+
+    class << self
+      # Here because I made a previous declaration that .reindex was part of the
+      # public API. Then I decided I didn't want to use that method.
+      alias reindex reindex_relationships
+    end
+
+    # @api public
+    # Responsible for reindexing the entire preservation layer.
+    # @param time_to_live [Integer] - there to guard against cyclical graphs
+    # @return [Boolean] - It was successful
+    # @raise Curate::Exceptions::CycleDetectionError - A potential cycle was detected
+    def self.reindex_all!(time_to_live = DEFAULT_TIME_TO_LIVE)
+      RepositoryReindexer.call(time_to_live: time_to_live, pid_reindexer: method(:reindex_relationships), adapter: configuration.adapter)
+      true
+    end
+
+    # Contains the Curate::Indexer configuration information that is referenceable from wit
+    # @see Curate::Indexer::Configuration
+    def self.configuration
+      @configuration ||= Configuration.new
+    end
+
+    # @api public
+    def self.adapter
+      configuration.adapter
+    end
+
+    # @api public
+    # @see Curate::Indexer::Configuration
+    # @see .configuration
+    def self.configure(&block)
+      @configuration_block = block
+      configure!
+      # The Rails load sequence means that some of the configured Targets may
+      # not be loaded; As such I am not calling configure! instead relying on
+      # Curate::Indexer::Railtie to handle the configure! call
+      configure! unless defined?(Rails)
+    end
+
+    # @api public
+    def self.configure!
+      return false unless @configuration_block.respond_to?(:call)
+      @configuration_block.call(configuration)
+      @configuration_block = nil
+    end
+  end
+end

metadata

@@ -0,0 +1,293 @@
+--- !ruby/object:Gem::Specification
+name: curate-indexer
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Jeremy Friesen
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2016-06-16 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.12'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.12'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+- !ruby/object:Gem::Dependency
+  name: rspec-its
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: guard-rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: guard-rubocop
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: terminal-notifier-guard
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: terminal-notifier
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: rubocop
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: simplecov
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: codeclimate-test-reporter
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: json
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: byebug
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: railties
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '4.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '4.0'
+- !ruby/object:Gem::Dependency
+  name: listen
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 3.0.8
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 3.0.8
+- !ruby/object:Gem::Dependency
+  name: dry-equalizer
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+description: A playground for CurateND collections indexing
+email:
+- jeremy.n.friesen@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".rspec"
+- ".rubocop.yml"
+- ".ruby-version"
+- ".travis.yml"
+- Gemfile
+- Guardfile
+- LICENSE
+- README.md
+- Rakefile
+- bin/console
+- bin/setup
+- curate-indexer.gemspec
+- lib/curate/indexer.rb
+- lib/curate/indexer/adapters.rb
+- lib/curate/indexer/configuration.rb
+- lib/curate/indexer/documents.rb
+- lib/curate/indexer/exceptions.rb
+- lib/curate/indexer/index.rb
+- lib/curate/indexer/preservation.rb
+- lib/curate/indexer/railtie.rb
+- lib/curate/indexer/relationship_reindexer.rb
+- lib/curate/indexer/repository_reindexer.rb
+- lib/curate/indexer/storage_module.rb
+- lib/curate/indexer/version.rb
+homepage: https://github.com/ndlib/curate-indexer
+licenses: []
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - "~>"
+    - !ruby/object:Gem::Version
+      version: '2.0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.4.5
+signing_key: 
+specification_version: 4
+summary: A playground for CurateND collections indexing
+test_files: []
+has_rdoc: