hydra-works 0.1.0 → 0.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: b09c8a80126527ae1e46668a611225e85ed64b85
-  data.tar.gz: 863f6a4b6315edbc5825e65d560a24fcb8372910
+  metadata.gz: 28a2824769ab44dca4138961476455d25db0d016
+  data.tar.gz: 7e0c7dae7cc6873680eb07bf882a1cc1b008e13e
 SHA512:
-  metadata.gz: 79734196b519492daf40942ba488aedf9f303483dc3527b9f92ee400d04ef51467d69e65b4c0f4fb6ce23a74a836f3188177faeb5a073fc24ec3b6671de89905
-  data.tar.gz: 2266310f4f914ca326b95f8f57eb294ef2d75f7170c56620e00dbe5eacc3c629be077d785ef114e711e439221a57506a2105a3209dbc9d23e3dd7b1d2534772e
+  metadata.gz: 0ea7c389ceaeffe31367dffe19490162932afa1abeb5f5016ea2842003c7f36cc00bbe25a7b6160766f684fcb6009817074532d0bfc936928c6b0f570f9767be
+  data.tar.gz: cc6825f4d60eed260531714eb646d512debcdb004feba0c81f80b253c7ba935289a614202efa225966f178d677ea99898b135cd8619f911d7401aaf0f9b802e0

data/.gitignore

@@ -5,6 +5,7 @@
 /coverage/
 /doc/
 /pkg/
+/solr_conf/
 /spec/reports/
 spec/internal
 /tmp/

data/.rubocop.yml

@@ -0,0 +1,72 @@
+require: rubocop-rspec
+
+AllCops:
+  RunRailsCops: true
+  DisplayCopNames: true
+  Include:
+    - '**/Rakefile'
+  Exclude:
+    - 'vendor/**/*'
+    - 'spec/internal/bin/*'
+    - 'spec/internal/db/schema.rb'
+
+Metrics/LineLength:
+  Enabled: false
+
+Metrics/CyclomaticComplexity:
+  Exclude:
+    - lib/hydra/works/services/generic_file/add_file_to_generic_file.rb
+
+Metrics/PerceivedComplexity:
+  Exclude:
+    - lib/hydra/works/services/generic_file/add_file_to_generic_file.rb
+
+Metrics/MethodLength:
+  Exclude:
+    - lib/hydra/works/services/generic_file/add_file_to_generic_file.rb
+    - lib/hydra/works/models/concerns/generic_file/virus_check.rb
+
+Metrics/AbcSize:
+  Exclude:
+    - lib/hydra/works/services/generic_file/add_file_to_generic_file.rb
+    - lib/hydra/works/services/generic_file/full_text_extraction_service.rb	
+    - lib/hydra/works/models/concerns/generic_file/mime_types.rb
+    - lib/hydra/works/models/concerns/generic_file/virus_check.rb
+
+Style/CollectionMethods:
+  PreferredMethods:
+    collect: 'map'
+    collect!: 'map!'
+    inject: 'reduce'
+    detect: 'find'
+    find_all: 'select'
+
+Style/ClassAndModuleChildren:
+  Enabled: false
+
+Style/Documentation:
+  Enabled: false
+
+Style/StringLiterals:
+  Enabled: false
+
+Style/SignalException:
+  Enabled: false
+
+Style/IndentationConsistency:
+  EnforcedStyle: rails
+
+RSpec/ExampleWording:
+  CustomTransform:
+    be: is
+    have: has
+    not: does not
+    NOT: does NOT
+  IgnoredWords:
+    - only
+
+RSpec/FilePath:
+  Enabled: false
+
+RSpec/InstanceVariable:
+  Enabled: false

data/Gemfile

@@ -5,8 +5,9 @@ gemspec
 
 gem 'slop', '~> 3.6' # For byebug
 
-unless ENV['CI']
-  gem 'pry'
-  gem 'pry-byebug'
-  gem 'byebug'
+group :development, :test do
+  gem 'rubocop', require: false
+  gem 'rubocop-rspec', require: false
+  gem 'pry' unless ENV['CI']
+  gem 'pry-byebug' unless ENV['CI']
 end

data/README.md

@@ -1,23 +1,29 @@
 # Hydra::Works
+
+[![Version](https://badge.fury.io/rb/hydra-works.png)](http://badge.fury.io/rb/hydra-works)
 [![Build Status](https://travis-ci.org/projecthydra-labs/hydra-works.svg?branch=master)](https://travis-ci.org/projecthydra-labs/hydra-works)
 [![Coverage Status](https://coveralls.io/repos/projecthydra-labs/hydra-works/badge.svg?branch=master)](https://coveralls.io/r/projecthydra-labs/hydra-works?branch=master)
+[![Code Climate](https://codeclimate.com/github/projecthydra-labs/hydra-works/badges/gpa.svg)](https://codeclimate.com/github/projecthydra-labs/hydra-works)
+[![Apache 2.0 License](http://img.shields.io/badge/APACHE2-license-blue.svg)](./LICENSE)
+[![Contribution Guidelines](http://img.shields.io/badge/CONTRIBUTING-Guidelines-blue.svg)](./CONTRIBUTING.md)
+[![API Docs](http://img.shields.io/badge/API-docs-blue.svg)](http://rubydoc.info/gems/hydra-works)
+[![Stories in Ready](https://badge.waffle.io/projecthydra-labs/hydra-works.png?source=projecthydra-labs%2Fhydra-works&label=ready&title=Ready)](https://waffle.io/projecthydra-labs/hydra-works?source=projecthydra-labs%2Fhydra-works)
 
-The Hydra::Works gem provides a set of [Portland Common Data Model](https://wiki.duraspace.org/display/FF/Portland+Common+Data+Model)-compliant models and associated behaviors around the broad concept of multi-file "works", the need for which was expressed by a variety of [community use cases](https://github.com/projecthydra-labs/hydra-works/tree/master/use-cases). The Hydra::Works domain model includes:
+The Hydra::Works gem provides a set of [Portland Common Data Model](https://github.com/duraspace/pcdm/wiki)-compliant ActiveFedora models and associated behaviors around the broad concept of multi-file "works", the need for which was expressed by a variety of [community use cases](https://github.com/projecthydra-labs/hydra-works/tree/master/use-cases). The Hydra::Works domain model includes:
 
- * **GenericFile**: a *pcdm:Object* that encapsulates one or more directly related *pcdm:File*s, such as a PDF document, its derivatives, and extracted full-text
- * **GenericWork**: a *pcdm:Object* that holds zero or more **GenericFile**s and zero or more **GenericWork**s
- * **Collection**: a *pcdm:Collection* that indirectly contains zero or more **GenericWork**s and zero or more **Collection**s
+ * **GenericFile**: a *Hydra::PCDM::Object* that encapsulates one or more directly related *Hydra::PCDM::File*s, such as a PDF document, its derivatives, and extracted full-text
+ * **GenericWork**: a *Hydra::PCDM::Object* that holds zero or more **GenericFile**s and zero or more **GenericWork**s
+ * **Collection**: a *Hydra::PCDM::Collection* that indirectly contains zero or more **GenericWork**s and zero or more **Collection**s
 
 View [a diagram of the domain model](https://docs.google.com/drawings/d/1-NkkRPpGpZGoTimEpYTaGM1uUPRaT0SamuWDITvtG_8/edit).
 
+Checkout the readme for [hydra-derivatives](https://github.com/projecthydra/hydra-derivatives#dependencies) for additional dependencies.
+
 ## Installation
 
 Add these lines to your application's Gemfile:
 
-    # hydra-pcdm requires an unreleased version of ActiveFedora
-    gem 'active-fedora', github: 'projecthydra/active_fedora'
-    gem 'hydra-pcdm', github: 'projecthydra-labs/hydra-pcdm'
-    gem 'hydra-works', github: 'projecthydra-labs/hydra-works'
+    gem 'hydra-works', '~> 0.1'
 
 And then execute:
 
@@ -48,7 +54,7 @@ collection = Collection.create
 book = BookWork.create
 page = Page.create
 
-collection.child_generic_works << book
+collection.generic_works << book
 collection.save
 book.generic_files << page
 book.save
@@ -73,20 +79,20 @@ class BookFiles < ActiveFedora::Base
 end
 ```
 
-
 ## Access controls
 
 We are using [Web ACL](http://www.w3.org/wiki/WebAccessControl) as implemented by [hydra-access-controls](https://github.com/projecthydra/hydra-head/tree/master/hydra-access-controls).
 
 ## How to contribute
 
-If you'd like to contribute to this effort, please check out the [Contributing Guide](CONTRIBUTING.md)
+If you'd like to contribute to this effort, please check out the [contributing guidelines](CONTRIBUTING.md)
 
 ## Development
 
 To set up for running the test suite, you need a copy of jetty
 
     $ rake jetty:clean
+    $ rake jetty:config
 
 To run the test suite, generate the test app (which goes into spec/internal) and start jetty (if it's not already running)
 

data/Rakefile

@@ -1,23 +1,33 @@
-require "bundler/gem_tasks"
+require 'bundler/gem_tasks'
 require 'jettywrapper'
 require 'rspec/core'
 require 'rspec/core/rake_task'
 require 'engine_cart/rake_task'
+require 'rubocop/rake_task'
 
-RSpec::Core::RakeTask.new(:spec)
-Jettywrapper.hydra_jetty_version = "master"
+Dir.glob('lib/tasks/*.rake').each { |r| import r }
+
+desc 'Run style checker'
+RuboCop::RakeTask.new(:rubocop) do |task|
+  task.requires << 'rubocop-rspec'
+  task.fail_on_error = true
+end
+
+desc 'Run test suite and style checker'
+task :spec do
+  Rake::Task['rubocop'].invoke
+  RSpec::Core::RakeTask.new(:spec)
+end
 
 desc 'Spin up hydra-jetty and run specs'
-task ci: ['jetty:clean'] do
+task ci: ['jetty:clean', 'jetty:config'] do
   puts 'running continuous integration'
   jetty_params = Jettywrapper.load_config
-  jetty_params[:startup_wait]= 90
+  jetty_params[:startup_wait] = 90
   error = Jettywrapper.wrap(jetty_params) do
     Rake::Task['spec'].invoke
   end
-  raise "test failures: #{error}" if error
+  fail "test failures: #{error}" if error
 end
 
 task default: :ci
-
-

data/config/solrconfig.xml

@@ -0,0 +1,223 @@
+<?xml version="1.0" encoding="UTF-8" ?>
+<config>
+  <!-- NOTE: various comments and unused configuration possibilities have been purged
+     from this file.  Please refer to http://wiki.apache.org/solr/SolrConfigXml,
+     as well as the default solrconfig file included with Solr -->
+
+  <abortOnConfigurationError>${solr.abortOnConfigurationError:true}</abortOnConfigurationError>
+
+  <luceneMatchVersion>LUCENE_40</luceneMatchVersion>
+
+  <directoryFactory name="DirectoryFactory" class="${solr.directoryFactory:solr.StandardDirectoryFactory}"/>
+
+  <!-- solr lib dirs -->
+  <lib dir="../lib/contrib/analysis-extras/lib" />
+  <lib dir="../lib/contrib/analysis-extras/lucene-libs" />
+  <!-- for full-text indexing -->
+  <lib dir="../lib/contrib/extraction/lib" regex=".*\.jar" />
+
+  <dataDir>${solr.data.dir:}</dataDir>
+
+  <!-- The default high-performance update handler -->
+  <updateHandler class="solr.DirectUpdateHandler2">
+
+    <!-- Enables a transaction log, used for real-time get, durability, and
+         and solr cloud replica recovery.  The log can grow as big as
+         uncommitted changes to the index, so use of a hard autoCommit
+         is recommended (see below).
+         "dir" - the target directory for transaction logs, defaults to the
+                solr data directory.  -->
+    <updateLog>
+      <str name="dir">${solr.ulog.dir:}</str>
+    </updateLog>
+
+    <!-- AutoCommit
+         Perform a hard commit automatically under certain conditions.
+         Instead of enabling autoCommit, consider using "commitWithin"
+         when adding documents.
+         http://wiki.apache.org/solr/UpdateXmlMessages
+         maxDocs - Maximum number of documents to add since the last
+                   commit before automatically triggering a new commit.
+         maxTime - Maximum amount of time in ms that is allowed to pass
+                   since a document was added before automatically
+                   triggering a new commit.
+         openSearcher - if false, the commit causes recent index changes
+           to be flushed to stable storage, but does not cause a new
+           searcher to be opened to make those changes visible.
+         If the updateLog is enabled, then it's highly recommended to
+         have some sort of hard autoCommit to limit the log size.
+      -->
+     <autoCommit>
+       <maxTime>${solr.autoCommit.maxTime:15000}</maxTime>
+       <openSearcher>false</openSearcher>
+     </autoCommit>
+
+    <!-- softAutoCommit is like autoCommit except it causes a
+         'soft' commit which only ensures that changes are visible
+         but does not ensure that data is synced to disk.  This is
+         faster and more near-realtime friendly than a hard commit.
+      -->
+
+     <autoSoftCommit>
+       <maxTime>${solr.autoSoftCommit.maxTime:-1}</maxTime>
+     </autoSoftCommit>
+
+  </updateHandler>
+
+  <requestHandler name="search" class="solr.SearchHandler" default="true">
+    <!-- default values for query parameters can be specified, these
+         will be overridden by parameters in the request
+      -->
+     <lst name="defaults">
+       <str name="defType">edismax</str>
+       <str name="echoParams">explicit</str>
+       <str name="q.alt">*:*</str>
+       <str name="mm">2&lt;-1 5&lt;-2 6&lt;90%</str>
+       <int name="qs">1</int>
+       <int name="ps">2</int>
+       <float name="tie">0.01</float>
+       <!-- this qf and pf are used by default, if not otherwise specified by
+            client. The default blacklight_config will use these for the
+            "keywords" search. See the author_qf/author_pf, title_qf, etc
+            below, which the default blacklight_config will specify for
+            those searches. You may also be interested in:
+            http://wiki.apache.org/solr/LocalParams
+       -->
+        <str name="qf">
+          id
+          all_text_timv
+          active_fedora_model_ssi
+          object_type_si
+        </str>
+        <str name="pf">
+          all_text_timv^10
+        </str>
+
+       <str name="author_qf">
+       </str>
+       <str name="author_pf">
+       </str>
+       <str name="title_qf">
+       </str>
+       <str name="title_pf">
+       </str>
+       <str name="subject_qf">
+       </str>
+       <str name="subject_pf">
+       </str>
+
+       <str name="fl">
+         *,
+         score
+       </str>
+
+       <str name="facet">true</str>
+       <str name="facet.mincount">1</str>
+       <str name="facet.limit">10</str>
+       <str name="facet.field">active_fedora_model_ssi</str>
+       <str name="facet.field">object_type_si</str>
+
+       <str name="spellcheck">true</str>
+       <str name="spellcheck.dictionary">default</str>
+       <str name="spellcheck.onlyMorePopular">true</str>
+       <str name="spellcheck.extendedResults">true</str>
+       <str name="spellcheck.collate">false</str>
+       <str name="spellcheck.count">5</str>
+
+     </lst>
+    <arr name="last-components">
+      <str>spellcheck</str>
+    </arr>
+  </requestHandler>
+
+  <requestHandler name="permissions" class="solr.SearchHandler" >
+    <lst name="defaults">
+      <str name="facet">off</str>
+      <str name="echoParams">all</str>
+      <str name="rows">1</str>
+      <str name="q">{!raw f=id v=$id}</str> <!-- use id=666 instead of q=id:666 -->
+      <str name="fl">
+        id,
+        access_ssim,
+        discover_access_group_ssim,discover_access_person_ssim,
+        read_access_group_ssim,read_access_person_ssim,
+        edit_access_group_ssim,edit_access_person_ssim,
+        depositor_ti,
+        embargo_release_date_dtsi
+        inheritable_access_ssim,
+        inheritable_discover_access_group_ssim,inheritable_discover_access_person_ssim,
+        inheritable_read_access_group_ssim,inheritable_read_access_person_ssim,
+        inheritable_edit_access_group_ssim,inheritable_edit_access_person_ssim,
+        inheritable_embargo_release_date_dtsi
+      </str>
+    </lst>
+  </requestHandler>
+
+<requestHandler name="/update/extract" startup="lazy" class="org.apache.solr.handler.extraction.ExtractingRequestHandler" >
+    <lst name="defaults">
+      <!-- All the main content goes into "text"... if you need to return the extracted text or do highlighting, use a stored field. -->
+      <str name="fmap.content">text</str>
+      <str name="lowernames">true</str>
+      <str name="uprefix">ignored_</str>
+      <!-- capture link hrefs but ignore div attributes -->
+      <str name="captureAttr">true</str>
+      <str name="fmap.a">links</str>
+      <str name="fmap.div">ignored_</str>
+    </lst>
+ </requestHandler>
+
+  <requestHandler name="standard" class="solr.SearchHandler">
+     <lst name="defaults">
+       <str name="echoParams">explicit</str>
+       <str name="defType">lucene</str>
+     </lst>
+  </requestHandler>
+
+  <!-- for requests to get a single document; use id=666 instead of q=id:666 -->
+  <requestHandler name="document" class="solr.SearchHandler" >
+    <lst name="defaults">
+      <str name="echoParams">all</str>
+      <str name="fl">*</str>
+      <str name="rows">1</str>
+      <str name="q">{!raw f=id v=$id}</str> <!-- use id=666 instead of q=id:666 -->
+    </lst>
+  </requestHandler>
+
+  <searchComponent name="spellcheck" class="solr.SpellCheckComponent">
+    <str name="queryAnalyzerFieldType">textSpell</str>
+    <!-- Multiple "Spell Checkers" can be declared and used by this component
+      (e.g. for title_spell field)
+      -->
+    <lst name="spellchecker">
+      <str name="name">default</str>
+      <str name="field">spell</str>
+      <str name="spellcheckIndexDir">./spell</str>
+      <str name="buildOnOptimize">true</str>
+    </lst>
+  </searchComponent>
+
+  <requestHandler name="/replication" class="solr.ReplicationHandler" startup="lazy" />
+
+  <requestDispatcher handleSelect="true" >
+    <requestParsers enableRemoteStreaming="true" multipartUploadLimitInKB="2048" />
+  </requestDispatcher>
+
+  <requestHandler name="/analysis/field" startup="lazy" class="solr.FieldAnalysisRequestHandler" />
+  <requestHandler name="/update" class="solr.UpdateRequestHandler"  />
+  <requestHandler name="/admin/" class="org.apache.solr.handler.admin.AdminHandlers" />
+
+  <requestHandler name="/admin/ping" class="solr.PingRequestHandler">
+    <lst name="invariants">
+      <str name="q">solrpingquery</str>
+    </lst>
+    <lst name="defaults">
+      <str name="echoParams">all</str>
+    </lst>
+  </requestHandler>
+
+  <!-- config for the admin interface -->
+  <admin>
+    <defaultQuery>search</defaultQuery>
+  </admin>
+
+</config>

data/hydra-works.gemspec

@@ -4,30 +4,30 @@ $LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
 require 'hydra/works/version'
 
 Gem::Specification.new do |spec|
-  spec.name          = "hydra-works"
+  spec.name          = 'hydra-works'
   spec.version       = Hydra::Works::VERSION
-  spec.authors       = ["Justin Coyne"]
-  spec.email         = ["justin@curationexperts.com"]
+  spec.authors       = ['Justin Coyne']
+  spec.email         = ['justin@curationexperts.com']
   spec.summary       = %q{Fundamental repository data model for hydra}
   spec.description   = %q{Using this data model should enable easy collaboration amongst hydra projects.}
-  spec.homepage      = ""
-  spec.license       = "APACHE2"
+  spec.homepage      = ''
+  spec.license       = 'APACHE2'
 
   spec.files         = `git ls-files -z`.split("\x0")
   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.require_paths = ['lib']
 
-  spec.add_dependency "hydra-pcdm", "~> 0.1"
-  spec.add_dependency "hydra-derivatives", "~> 2.0"
-  spec.add_dependency "activefedora-aggregation", "~> 0.4"
-  spec.add_dependency "active-fedora", "~> 9.2"
+  spec.add_dependency 'hydra-pcdm', '~> 0.2'
+  spec.add_dependency 'hydra-derivatives', '~> 2.0'
+  spec.add_dependency 'active-fedora', '>= 9.4.1'
+  spec.add_dependency 'activefedora-aggregation', '~> 0.4'
 
-  spec.add_development_dependency "bundler", "~> 1.7"
-  spec.add_development_dependency "rake", "~> 10.0"
-  spec.add_development_dependency "rspec-rails", "~> 3.1"
-  spec.add_development_dependency "engine_cart", "~> 0"
-  spec.add_development_dependency "sqlite3"
+  spec.add_development_dependency 'bundler', '~> 1.7'
+  spec.add_development_dependency 'rake', '~> 10.0'
+  spec.add_development_dependency 'rspec-rails', '~> 3.1'
+  spec.add_development_dependency 'engine_cart', '~> 0'
+  spec.add_development_dependency 'sqlite3'
   spec.add_development_dependency 'jettywrapper', '>= 2.0.0'
   spec.add_development_dependency 'coveralls'
   spec.add_development_dependency 'rspec'