Merge pull request #122 from collectionspace/cache-stuff

Use cache provided by collectionspace-csv-importer

.rubocop.yml

@@ -0,0 +1,11 @@
+AllCops:
+  NewCops: enable
+  SuggestExtensions:
+    rubocop-rake: false
+Layout/SpaceBeforeBlockBraces:
+  EnforcedStyle: no_space
+  EnforcedStyleForEmptyBraces: no_space
+Layout/SpaceInsideHashLiteralBraces:
+  EnforcedStyle: no_space
+Lint/RedundantCopDisableDirective:
+  Enabled: false

CHANGELOG.md

@@ -11,6 +11,12 @@ This project bumps the version number for any changes (including documentation u
 ## [Unreleased] - i.e. pushed to main branch but not yet tagged as a release
 - nothing
 
+## [2.5.1] - 2021-10-13
+### Changed
+- accept and handle collectionspace-refcache passed in from collectionspace-csv-importer
+- bug fixes for dealing with cached data
+- refactoring 
+
 ## [2.5.0] - 2021-09-23
 ### Added
 - `multiple_recs_found` batch configuration option added to allow batch deletion of duplicate records. This defaults to `fail`, which means if there are two or more existing records sharing the same ID, the batch importer will not transfer anything for that ID. In rare cases, however, you may really need to delete duplicates, and now you can. The batch importer will transfer your update or delete to the first result found via a search for the record ID. See [the batch configuration options documentation](https://github.com/collectionspace/collectionspace-mapper/blob/main/doc/batch_configuration.adoc) for more information.

Gemfile

@@ -1,5 +1,7 @@
-source "https://rubygems.org"
-git_source(:github) {|repo_name| "https://github.com/#{repo_name}" }
+# frozen_string_literal: true
+
+source 'https://rubygems.org'
+git_source(:github){|repo_name| "https://github.com/#{repo_name}" }
 
 ruby '2.7.4'
 

Rakefile

@@ -1,6 +1,8 @@
-require "bundler/gem_tasks"
-require "rspec/core/rake_task"
+# frozen_string_literal: true
+
+require 'bundler/gem_tasks'
+require 'rspec/core/rake_task'
 
 RSpec::Core::RakeTask.new(:spec)
 
-task :default => :spec
+task default: :spec

bin/console

@@ -1,4 +1,5 @@
 #!/usr/bin/env ruby
+# frozen_string_literal: true
 
 require 'bundler/setup'
 require 'collectionspace/mapper'

collectionspace-mapper.gemspec

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 lib = File.expand_path('../lib', __FILE__)
 $LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
 require 'collectionspace/mapper/version'
@@ -29,20 +31,26 @@ Gem::Specification.new do |spec|
 
   # Specify which files should be added to the gem when it is released.
   # The `git ls-files -z` loads the files in the RubyGem that have been added into git.
-  spec.files         = Dir.chdir(File.expand_path('..', __FILE__)) do
-    `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
+  spec.files = Dir.chdir(File.expand_path('..', __FILE__)) do
+    `git ls-files -z`.split("\x0").reject{ |f| f.match(%r{^(test|spec|features)/}) }
   end
   spec.bindir        = 'exe'
-  spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
+  spec.executables   = spec.files.grep(%r{^exe/}){ |f| File.basename(f) }
   spec.require_paths = ['lib']
 
   spec.add_dependency 'chronic'
   spec.add_dependency 'facets'
+  spec.add_dependency 'memo_wise', '~> 1.1.0'
   spec.add_dependency 'nokogiri', '>= 1.10.9'
   spec.add_dependency 'xxhash', '>= 0.4.0'
 
   spec.add_development_dependency 'bundler', '>= 2.1.2'
   spec.add_development_dependency 'pry-byebug'
   spec.add_development_dependency 'rake', '>= 13.0.1'
   spec.add_development_dependency 'rspec', '~> 3.0'
+  spec.add_development_dependency 'rubocop', '~> 1.18.3'
+
+  # Uncomment these if you need to use the scripts in utils/benchmarking
+  #spec.add_development_dependency 'ruby-prof', '~> 1.4.3'
+  #spec.add_development_dependency 'time_up', '~> 0.0.7'
 end

lib/collectionspace/mapper.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require 'collectionspace/mapper/version'
 require 'collectionspace/client'
 require 'collectionspace/refcache'
@@ -19,7 +21,7 @@ module Mapper
     LOGGER = Logger.new(STDERR)
 
     THE_BOMB = "\u{1F4A3}"
-    
+
     Dir[File.dirname(__FILE__) + 'mapper/tools/*.rb'].sort.each do |file|
       require "collectionspace/mapper/tools/#{File.basename(file, File.extname(file))}"
     end
@@ -31,8 +33,8 @@ module Mapper
     end
 
     module Errors
-        class UnprocessableDataError < StandardError
-          UnprocessableDataError = CollectionSpace::Mapper::Errors::UnprocessableDataError
+      class UnprocessableDataError < StandardError
+        UnprocessableDataError = CollectionSpace::Mapper::Errors::UnprocessableDataError
         attr_reader :input
         def initialize(message, input)
           super(message)
@@ -47,7 +49,8 @@ def setup_data(data, config = Mapper::Config.new)
       elsif data.is_a?(CollectionSpace::Mapper::Response)
         response = data
       else
-        raise Errors::UnprocessableDataError.new("Cannot process a #{data.class}. Need a Hash or Mapper::Response", data)
+        raise Errors::UnprocessableDataError.new("Cannot process a #{data.class}. Need a Hash or Mapper::Response",
+                                                 data)
       end
 
       response.merged_data.empty? ? merge_default_values(response, config) : response
@@ -56,7 +59,7 @@ def setup_data(data, config = Mapper::Config.new)
     def merge_default_values(data, batchconfig)
       defaults = batchconfig.default_values
       return data unless defaults
-      
+
       mdata = data.orig_data.clone
       defaults.each do |f, val|
         if batchconfig.force_defaults
@@ -69,10 +72,10 @@ def merge_default_values(data, batchconfig)
       data.merged_data = mdata.compact.transform_keys(&:downcase)
       data
     end
-    
+
     def term_key(term)
       "#{term[:refname].type}-#{term[:refname].subtype}-#{term[:refname].display_name}"
     end
 
-  end    
+  end
 end

lib/collectionspace/mapper/authority_hierarchy_prepper.rb

@@ -8,16 +8,16 @@ module Mapper
     class AuthorityHierarchyPrepper < CollectionSpace::Mapper::DataPrepper
       include CollectionSpace::Mapper::TermSearchable
       attr_reader :errors, :warnings, :type, :subtype
-      
+
       def initialize(data, handler)
         super
-        @cache = @handler.mapper.csidcache
+        @cache = @handler.mapper.termcache
         @type = @response.merged_data['term_type']
         @subtype = @response.merged_data['term_subtype']
         @errors = []
         @warnings = []
       end
-      
+
       def prep
         set_id
         split_data
@@ -34,13 +34,12 @@ def set_id
         nt = @response.merged_data['narrower_term']
         @response.identifier = "#{bt} > #{nt}"
       end
-      
+
       def process_xpaths
         clear_unmapped_mappings
         @handler.mapper.xpath = @handler.xpath_hash
         super
       end
-
 
       # these mappings were needed to get data in via template for processing, but
       #  do not actually get used to produce XML

lib/collectionspace/mapper/authority_transformer.rb

@@ -7,7 +7,7 @@ module Mapper
 
     # transforms authority display name into RefName
     class AuthorityTransformer < Transformer
-      
+
       def initialize(opts)
         super
         @type = opts[:transform][0]

lib/collectionspace/mapper/column_mapping.rb

@@ -6,10 +6,10 @@ module Mapper
     # :reek:InstanceVariableAssumption is spurious; we are setting the instance variables here
     #  by iterating through the mapper hash. Given that the mapper data is created by the
     #  Untangler, I am trusting it will be consistent and I'm not validating that expected
-    #  keys are present for now. This also makes writing tests onthe methods here a bit easier. 
+    #  keys are present for now. This also makes writing tests onthe methods here a bit easier.
     class ColumnMapping
       attr_reader :recmapper, :data_type, :fieldname, :in_repeating_group, :is_group, :namespace, :opt_list_values,
-        :repeats, :source_type, :transforms, :xpath
+                  :repeats, :source_type, :transforms, :xpath
       def initialize(mapping_hash, recmapper)
         @recmapper = recmapper
         mapping_hash.each do |key, value|
@@ -26,20 +26,20 @@ def fullpath
         @fullpath ||= [@namespace, @xpath].flatten.join('/')
       end
 
-      # includes both truly required and "required in template" 
+      # includes both truly required and "required in template"
       def required?
         @required.start_with?('y')
       end
 
       def update_transforms(new_transforms)
         @transforms = @transforms.merge(new_transforms)
       end
-      
+
       private
 
       def symbolize_transforms
         return if @transforms.blank?
-        
+
         @transforms.transform_keys!(&:to_sym)
       end
     end

lib/collectionspace/mapper/column_mappings.rb

@@ -11,7 +11,7 @@ class ColumnMappings
 
       attr_reader :config
       def_delegators :@all, :each, :length, :map, :reject!, :select
-      
+
       def initialize(opts = {})
         @mapper = opts[:mapper]
         @config = @mapper.config
@@ -45,6 +45,7 @@ def required_columns
 
       def service_type=(mawdule)
         return unless mawdule
+
         extend(mawdule)
       end
 

lib/collectionspace/mapper/column_value.rb

@@ -20,7 +20,7 @@ def self.create(column:, value:, recmapper:, mapping:)
           MultivalColumnValue.new(column: column, value: value, recmapper: recmapper, mapping: mapping)
         when 2
           GroupColumnValue.new(column: column, value: value, recmapper: recmapper, mapping: mapping)
-        when 3 #bonsai conservation fertilizerToBeUsed is the only field like this
+        when 3 # bonsai conservation fertilizerToBeUsed is the only field like this
           GroupMultivalColumnValue.new(column: column, value: value, recmapper: recmapper, mapping: mapping)
         when 4
           SubgroupColumnValue.new(column: column, value: value, recmapper: recmapper, mapping: mapping)

lib/collectionspace/mapper/config.rb

@@ -9,13 +9,13 @@ module Mapper
     #   or non-hierarchichal relationships via module extension
     # :reek:InstanceVariableAssumption - instance variables are set during initialization
     class Config
-      attr_reader :delimiter, :subgroup_delimiter, :response_mode, :multiple_recs_found, :force_defaults, :check_record_status,
-        :check_terms, :date_format, :two_digit_year_handling, :transforms, :default_values,
+      attr_reader :delimiter, :subgroup_delimiter, :response_mode, :multiple_recs_found, :force_defaults,
+        :check_record_status, :check_terms, :date_format, :two_digit_year_handling, :transforms, :default_values,
         :record_type
       # todo: move default config in here
       include Tools::Symbolizable
 
-      DEFAULT_CONFIG = { delimiter: '|',
+      DEFAULT_CONFIG = {delimiter: '|',
                         subgroup_delimiter: '^^',
                         response_mode: 'normal',
                         multiple_recs_found: 'fail',
@@ -41,7 +41,7 @@ def initialize(opts = {})
         self.record_type = opts[:record_type]
 
         @default_values = {}
-        
+
         if config.is_a?(String)
           set_instance_variables(JSON.parse(config))
         elsif config.is_a?(Hash)
@@ -60,7 +60,7 @@ def hash
         config = symbolize(config)
         transforms = config[:transforms]
         return config unless transforms
-        
+
         config[:transforms] = symbolize_transforms(transforms)
         config
       end
@@ -74,13 +74,15 @@ def add_default_value(column, value)
 
       def record_type=(mawdule)
         return unless mawdule
+
         extend(mawdule)
       end
 
       def to_h
         hash = {}
         instance_variables.each do |var|
           next if var == :@record_type
+
           key = var.to_s.delete('@').to_sym
           hash[key] = instance_variable_get(var)
         end
@@ -90,7 +92,7 @@ def to_h
       def set_instance_variables(hash)
         hash.each{ |key, value| instance_variable_set("@#{key}", value) }
       end
-      
+
       def validate
         begin
           has_required_attributes
@@ -112,7 +114,7 @@ def valid_response_mode
           raise ConfigResponseModeError.new("Invalid response_mode value in config: #{@response_mode}")
         end
       end
-      
+
       def has_required_attributes
         required_keys = DEFAULT_CONFIG.keys
         remaining_keys = required_keys - hash.keys