hydra-works 0.8.1 → 0.9.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 07b6006359065b77e76cc0b9d5542c9da189a2fb
-  data.tar.gz: 7d37f4d93a294ec62adf36a63362663ca8dea153
+  metadata.gz: 8e1d3bbe7957645b6170f8bc00a7084fa94e670b
+  data.tar.gz: 901fcd09d4e40f5a97114e2f070ee36dffd231d6
 SHA512:
-  metadata.gz: 5cf2ff2d43e8fec1805c228e2d46793b178993e49ce6837c68e064ec9b68573cfc9f7a51011185cfbbd146d4da55208d6643383adb037e6d4f5772f6d776c57e
-  data.tar.gz: 71eadabf972b27c11dcfdcedb8fba6c078fb78ae7929cbae0678c4450713361980c3e5bf765a8547c362caf8243dd9c3f92ddbf1db672467fe191508b699adb8
+  metadata.gz: d9b4ff1445474ab473dd55a97fa0de5d3e29a5879614ec0fea840929f959c9b8a8e6d424c1d7224b925863b8f157d20d8cebcce4bdf1abc1f3bb38b8f91752f2
+  data.tar.gz: b2cbefad14f81c691c5129fe0c6e7895a6f1a6b3392bd6a129490e2556b42ff4e796836de751752068d4c5c984b675dfdee7b832c2e272649cf62d5ac7d3c01f

data/README.md

@@ -15,6 +15,8 @@ The Hydra::Works gem implements the [PCDM](https://github.com/duraspace/pcdm/wik
  * **Work**: a *pcdm:Object* that holds zero or more **FileSets** and zero or more **Works**
  * **FileSet**: a *pcdm:Object* that groups one or more related *pcdm:Files*, such as an original file (e.g., PDF document), its derivatives (e.g., a thumbnail), and extracted full-text
 
+View [a diagram of the Hydra::Works domain model](https://docs.google.com/drawings/d/1if47TYgEhqDLPh3D0026B_cBLa0BEAOpWPs8AqoQMZE/edit).
+
 Behaviors included in the model include:
 
  * Characterization of original files within FileSets

data/hydra-works.gemspec

@@ -18,7 +18,7 @@ Gem::Specification.new do |spec|
   spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
   spec.require_paths = ['lib']
 
-  spec.add_dependency 'hydra-pcdm', '~> 0.5'
+  spec.add_dependency 'hydra-pcdm', '>= 0.6'
   spec.add_dependency 'hydra-derivatives', '~> 3.0'
   spec.add_dependency 'hydra-file_characterization', '~> 0.3', '>= 0.3.3'
 

data/lib/hydra/works.rb

@@ -1,5 +1,4 @@
 require 'hydra/works/version'
-require 'active_fedora/aggregation'
 require 'hydra/pcdm'
 require 'hydra/derivatives'
 

data/lib/hydra/works/characterization/schema/document_schema.rb

@@ -1,9 +1,9 @@
 module Hydra::Works::Characterization
   class DocumentSchema < ActiveTriples::Schema
     property :file_title, predicate: RDF::Vocab::DC11.title
-    property :file_author, predicate: RDF::Vocab::DC11.creator
+    property :creator, predicate: RDF::Vocab::DC11.creator
     property :page_count, predicate: RDF::Vocab::NFO.pageCount
-    property :file_language, predicate: RDF::Vocab::DC11.language
+    property :language, predicate: RDF::Vocab::DC11.language
     property :word_count, predicate: RDF::Vocab::NFO.wordCount
     property :character_count, predicate: RDF::Vocab::NFO.characterCount
     property :line_count, predicate: RDF::Vocab::NFO.lineCount

data/lib/hydra/works/models/concerns/file_set/characterization/document.rb

@@ -5,6 +5,7 @@ module Hydra::Works::Characterization
     included do
       # Apply the document schema. This will add properties defined in the schema.
       apply_schema DocumentSchema, AlreadyThereStrategy
+      parser_mapping.merge!(file_author: :creator, file_language: :language)
     end
   end
 end

data/lib/hydra/works/models/concerns/file_set/virus_check.rb

@@ -41,7 +41,8 @@ module Hydra::Works
         else
           Tempfile.open('') do |t|
             t.binmode
-            t.write(file)
+            t.write(file.content.read)
+            file.content.rewind
             t.close
             t.path
           end

data/lib/hydra/works/version.rb

@@ -1,5 +1,5 @@
 module Hydra
   module Works
-    VERSION = '0.8.1'.freeze
+    VERSION = '0.9.0'.freeze
   end
 end

data/solr/config/schema.xml

@@ -59,32 +59,32 @@
 
   <types>
     <fieldType name="string" class="solr.StrField" sortMissingLast="true" />
-    <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>    
+    <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
     <fieldType name="rand" class="solr.RandomSortField" omitNorms="true"/>
-    
+
     <!-- Default numeric field types.  -->
     <fieldType name="int" class="solr.TrieIntField" precisionStep="0" positionIncrementGap="0"/>
     <fieldType name="float" class="solr.TrieFloatField" precisionStep="0" positionIncrementGap="0"/>
     <fieldType name="long" class="solr.TrieLongField" precisionStep="0" positionIncrementGap="0"/>
     <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" positionIncrementGap="0"/>
-    
+
     <!-- trie numeric field types for faster range queries -->
     <fieldType name="tint" class="solr.TrieIntField" precisionStep="8" positionIncrementGap="0"/>
     <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" positionIncrementGap="0"/>
     <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" positionIncrementGap="0"/>
     <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" positionIncrementGap="0"/>
-    
+
     <!-- The format for this date field is of the form 1995-12-31T23:59:59Z
          Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
       -->
     <fieldType name="date" class="solr.TrieDateField" precisionStep="0" positionIncrementGap="0"/>
     <!-- A Trie based date field for faster date range queries and date faceting. -->
     <fieldType name="tdate" class="solr.TrieDateField" precisionStep="6" positionIncrementGap="0"/>
-    
-    
+
+
     <!-- This point type indexes the coordinates as separate fields (subFields)
       If subFieldType is defined, it references a type, and a dynamic field
-      definition is created matching *___<typename>.  Alternately, if 
+      definition is created matching *___<typename>.  Alternately, if
       subFieldSuffix is defined, that is used to create the subFields.
       Example: if subFieldType="double", then the coordinates would be
         indexed in fields myloc_0___double,myloc_1___double.
@@ -94,17 +94,17 @@
       users normally should not need to know about them.
      -->
     <fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>
-    
+
     <!-- A specialized field for geospatial search. If indexed, this fieldType must not be multivalued. -->
     <fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/>
-    
+
     <!-- An alternative geospatial field type new to Solr 4.  It supports multiValued and polygon shapes.
       For more information about this and other Spatial fields new to Solr 4, see:
       http://wiki.apache.org/solr/SolrAdaptersForLuceneSpatial4
     -->
     <fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType"
-      geo="true" distErrPct="0.025" maxDistErr="0.000009" units="degrees" />
-    
+      geo="true" distErrPct="0.025" maxDistErr="0.000009" distanceUnits="degrees" />
+
     <fieldType name="text" class="solr.TextField" omitNorms="false">
       <analyzer>
         <tokenizer class="solr.ICUTokenizerFactory"/>
@@ -112,7 +112,7 @@
         <filter class="solr.TrimFilterFactory"/>
       </analyzer>
     </fieldType>
-    
+
     <!-- A text field that only splits on whitespace for exact matching of words -->
     <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
       <analyzer>
@@ -120,7 +120,7 @@
         <filter class="solr.TrimFilterFactory"/>
       </analyzer>
     </fieldType>
-        
+
     <!-- single token analyzed text, for sorting.  Punctuation is significant. -->
     <fieldtype name="alphaSort" class="solr.TextField" sortMissingLast="true" omitNorms="true">
       <analyzer>
@@ -129,7 +129,7 @@
         <filter class="solr.TrimFilterFactory" />
       </analyzer>
     </fieldtype>
-    
+
     <!-- A text field with defaults appropriate for English -->
     <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
       <analyzer>
@@ -144,7 +144,7 @@
         <filter class="solr.TrimFilterFactory"/>
       </analyzer>
     </fieldType>
-        
+
     <!-- queries for paths match documents at that path, or in descendent paths -->
     <fieldType name="descendent_path" class="solr.TextField">
       <analyzer type="index">
@@ -154,7 +154,7 @@
         <tokenizer class="solr.KeywordTokenizerFactory" />
       </analyzer>
     </fieldType>
-    
+
     <!-- queries for paths match documents at that path, or in ancestor paths -->
     <fieldType name="ancestor_path" class="solr.TextField">
       <analyzer type="index">
@@ -179,12 +179,12 @@
   <fields>
     <!-- If you remove this field, you must _also_ disable the update log in solrconfig.xml
     or Solr won't start. _version_ and update log are required for SolrCloud
-    --> 
+    -->
     <field name="_version_" type="long" indexed="true" stored="true"/>
-   
+
     <field name="id" type="string" stored="true" indexed="true" multiValued="false" required="true"/>
     <field name="timestamp" type="date" indexed="true" stored="true" default="NOW" multiValued="false"/>
-    
+
     <field name="lat" type="tdouble" stored="true" indexed="true" multiValued="false"/>
     <field name="lng" type="tdouble" stored="true" indexed="true" multiValued="false"/>
 
@@ -201,7 +201,7 @@
     <dynamicField name="*_timv" type="text" stored="false" indexed="true" multiValued="true" termVectors="true" termPositions="true" termOffsets="true"/>
     <dynamicField name="*_tsiv" type="text" stored="true" indexed="true" multiValued="false" termVectors="true" termPositions="true" termOffsets="true"/>
     <dynamicField name="*_tsimv" type="text" stored="true" indexed="true" multiValued="true" termVectors="true" termPositions="true" termOffsets="true"/>
-    
+
     <!-- English text (_te...) -->
     <dynamicField name="*_tei" type="text_en" stored="false" indexed="true" multiValued="false"/>
     <dynamicField name="*_teim" type="text_en" stored="false" indexed="true" multiValued="true"/>
@@ -213,7 +213,7 @@
     <dynamicField name="*_teimv" type="text_en" stored="false" indexed="true" multiValued="true" termVectors="true" termPositions="true" termOffsets="true"/>
     <dynamicField name="*_tesiv" type="text_en" stored="true" indexed="true" multiValued="false" termVectors="true" termPositions="true" termOffsets="true"/>
     <dynamicField name="*_tesimv" type="text_en" stored="true" indexed="true" multiValued="true" termVectors="true" termPositions="true" termOffsets="true"/>
-    
+
     <!-- string (_s...) -->
     <dynamicField name="*_si" type="string" stored="false" indexed="true" multiValued="false"/>
     <dynamicField name="*_sim" type="string" stored="false" indexed="true" multiValued="true"/>
@@ -222,7 +222,7 @@
     <dynamicField name="*_ssi" type="string" stored="true" indexed="true" multiValued="false"/>
     <dynamicField name="*_ssim" type="string" stored="true" indexed="true" multiValued="true"/>
     <dynamicField name="*_ssort" type="alphaSort" stored="false" indexed="true" multiValued="false"/>
-    
+
     <!-- integer (_i...) -->
     <dynamicField name="*_ii" type="int" stored="false" indexed="true" multiValued="false"/>
     <dynamicField name="*_iim" type="int" stored="false" indexed="true" multiValued="true"/>
@@ -230,7 +230,7 @@
     <dynamicField name="*_ism" type="int" stored="true" indexed="false" multiValued="true"/>
     <dynamicField name="*_isi" type="int" stored="true" indexed="true" multiValued="false"/>
     <dynamicField name="*_isim" type="int" stored="true" indexed="true" multiValued="true"/>
-    
+
     <!-- trie integer (_it...) (for faster range queries) -->
     <dynamicField name="*_iti" type="tint" stored="false" indexed="true" multiValued="false"/>
     <dynamicField name="*_itim" type="tint" stored="false" indexed="true" multiValued="true"/>
@@ -238,7 +238,7 @@
     <dynamicField name="*_itsm" type="tint" stored="true" indexed="false" multiValued="true"/>
     <dynamicField name="*_itsi" type="tint" stored="true" indexed="true" multiValued="false"/>
     <dynamicField name="*_itsim" type="tint" stored="true" indexed="true" multiValued="true"/>
-    
+
     <!-- date (_dt...) -->
     <!-- The format for this date field is of the form 1995-12-31T23:59:59Z
          Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z -->
@@ -248,7 +248,7 @@
     <dynamicField name="*_dtsm" type="date" stored="true" indexed="false" multiValued="true"/>
     <dynamicField name="*_dtsi" type="date" stored="true" indexed="true" multiValued="false"/>
     <dynamicField name="*_dtsim" type="date" stored="true" indexed="true" multiValued="true"/>
-    
+
     <!-- trie date (_dtt...) (for faster range queries) -->
     <dynamicField name="*_dtti" type="tdate" stored="false" indexed="true" multiValued="false"/>
     <dynamicField name="*_dttim" type="tdate" stored="false" indexed="true" multiValued="true"/>
@@ -256,7 +256,7 @@
     <dynamicField name="*_dttsm" type="tdate" stored="true" indexed="false" multiValued="true"/>
     <dynamicField name="*_dttsi" type="tdate" stored="true" indexed="true" multiValued="false"/>
     <dynamicField name="*_dttsim" type="tdate" stored="true" indexed="true" multiValued="true"/>
-    
+
     <!-- long (_l...) -->
     <dynamicField name="*_li" type="long" stored="false" indexed="true" multiValued="false"/>
     <dynamicField name="*_lim" type="long" stored="false" indexed="true" multiValued="true"/>
@@ -264,7 +264,7 @@
     <dynamicField name="*_lsm" type="long" stored="true" indexed="false" multiValued="true"/>
     <dynamicField name="*_lsi" type="long" stored="true" indexed="true" multiValued="false"/>
     <dynamicField name="*_lsim" type="long" stored="true" indexed="true" multiValued="true"/>
-    
+
     <!-- trie long (_lt...) (for faster range queries) -->
     <dynamicField name="*_lti" type="tlong" stored="false" indexed="true" multiValued="false"/>
     <dynamicField name="*_ltim" type="tlong" stored="false" indexed="true" multiValued="true"/>
@@ -272,7 +272,7 @@
     <dynamicField name="*_ltsm" type="tlong" stored="true" indexed="false" multiValued="true"/>
     <dynamicField name="*_ltsi" type="tlong" stored="true" indexed="true" multiValued="false"/>
     <dynamicField name="*_ltsim" type="tlong" stored="true" indexed="true" multiValued="true"/>
-    
+
     <!-- double (_db...) -->
     <dynamicField name="*_dbi" type="double" stored="false" indexed="true" multiValued="false"/>
     <dynamicField name="*_dbim" type="double" stored="false" indexed="true" multiValued="true"/>
@@ -280,7 +280,7 @@
     <dynamicField name="*_dbsm" type="double" stored="true" indexed="false" multiValued="true"/>
     <dynamicField name="*_dbsi" type="double" stored="true" indexed="true" multiValued="false"/>
     <dynamicField name="*_dbsim" type="double" stored="true" indexed="true" multiValued="true"/>
-    
+
     <!-- trie double (_dbt...) (for faster range queries) -->
     <dynamicField name="*_dbti" type="tdouble" stored="false" indexed="true" multiValued="false"/>
     <dynamicField name="*_dbtim" type="tdouble" stored="false" indexed="true" multiValued="true"/>
@@ -288,7 +288,7 @@
     <dynamicField name="*_dbtsm" type="tdouble" stored="true" indexed="false" multiValued="true"/>
     <dynamicField name="*_dbtsi" type="tdouble" stored="true" indexed="true" multiValued="false"/>
     <dynamicField name="*_dbtsim" type="tdouble" stored="true" indexed="true" multiValued="true"/>
-    
+
     <!-- float (_f...) -->
     <dynamicField name="*_fi" type="float" stored="false" indexed="true" multiValued="false"/>
     <dynamicField name="*_fim" type="float" stored="false" indexed="true" multiValued="true"/>
@@ -296,7 +296,7 @@
     <dynamicField name="*_fsm" type="float" stored="true" indexed="false" multiValued="true"/>
     <dynamicField name="*_fsi" type="float" stored="true" indexed="true" multiValued="false"/>
     <dynamicField name="*_fsim" type="float" stored="true" indexed="true" multiValued="true"/>
-    
+
     <!-- trie float (_ft...) (for faster range queries) -->
     <dynamicField name="*_fti" type="tfloat" stored="false" indexed="true" multiValued="false"/>
     <dynamicField name="*_ftim" type="tfloat" stored="false" indexed="true" multiValued="true"/>
@@ -304,12 +304,12 @@
     <dynamicField name="*_ftsm" type="tfloat" stored="true" indexed="false" multiValued="true"/>
     <dynamicField name="*_ftsi" type="tfloat" stored="true" indexed="true" multiValued="false"/>
     <dynamicField name="*_ftsim" type="tfloat" stored="true" indexed="true" multiValued="true"/>
-    
+
     <!-- boolean (_b...) -->
     <dynamicField name="*_bi" type="boolean" stored="false" indexed="true" multiValued="false"/>
     <dynamicField name="*_bs" type="boolean" stored="true" indexed="false" multiValued="false"/>
     <dynamicField name="*_bsi" type="boolean" stored="true" indexed="true" multiValued="false"/>
-    
+
     <!-- Type used to index the lat and lon components for the "location" FieldType -->
     <dynamicField name="*_coordinate" type="tdouble" indexed="true"  stored="false" />
 
@@ -329,7 +329,7 @@
 
   </fields>
 
- <!-- Field to use to determine and enforce document uniqueness. 
+ <!-- Field to use to determine and enforce document uniqueness.
       Unless this field is marked with required="false", it will be a required field
    -->
  <uniqueKey>id</uniqueKey>

data/spec/fixtures/eicar.txt

@@ -0,0 +1 @@
+X5O!P%@AP[4\PZX54(P^)7CC)7}$EICAR-STANDARD-ANTIVIRUS-TEST-FILE!$H+H*

data/spec/hydra/works/models/concerns/file_set/virus_check_spec.rb

@@ -23,7 +23,7 @@ describe Hydra::Works::VirusCheck do
     end
 
     subject { FileWithVirusCheck.new }
-    let(:file) { Hydra::PCDM::File.new File.join(fixture_path, 'sample-file.pdf') }
+    let(:file) { Hydra::PCDM::File.new { |f| f.content = File.new(File.join(fixture_path, 'sample-file.pdf')) } }
 
     before do
       allow(subject).to receive(:original_file) { file }
@@ -61,6 +61,18 @@ describe Hydra::Works::VirusCheck do
         expect(subject.send(:local_path_for_file, file)).to eq('/tmp/file.pdf')
       end
     end
+
+    context 'original file does not respond to path' do
+      before do
+        allow(file).to receive(:respond_to?).and_call_original
+        allow(file).to receive(:respond_to?).with(:path).and_return(false)
+      end
+
+      it 'reads the content of the original_file' do
+        expect(file.content).to receive(:read)
+        subject.detect_viruses
+      end
+    end
   end
 
   context "Without ClamAV" do
@@ -73,7 +85,7 @@ describe Hydra::Works::VirusCheck do
     end
 
     subject { FileWithVirusCheck.new }
-    let(:file) { Hydra::PCDM::File.new File.join(fixture_path, 'sample-file.pdf') }
+    let(:file) { Hydra::PCDM::File.new { |f| f.content = File.new(File.join(fixture_path, 'sample-file.pdf')) } }
 
     before do
       allow(subject).to receive(:original_file) { file }

metadata

@@ -1,29 +1,29 @@
 --- !ruby/object:Gem::Specification
 name: hydra-works
 version: !ruby/object:Gem::Version
-  version: 0.8.1
+  version: 0.9.0
 platform: ruby
 authors:
 - Justin Coyne
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2016-03-25 00:00:00.000000000 Z
+date: 2016-05-04 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: hydra-pcdm
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '0.5'
+        version: '0.6'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '0.5'
+        version: '0.6'
 - !ruby/object:Gem::Dependency
   name: hydra-derivatives
   requirement: !ruby/object:Gem::Requirement
@@ -241,6 +241,7 @@ files:
 - spec/fixtures/Example.ogg
 - spec/fixtures/charter.docx
 - spec/fixtures/countdown.avi
+- spec/fixtures/eicar.txt
 - spec/fixtures/fits_0.6.2_avi.xml
 - spec/fixtures/fits_0.6.2_jp2.xml
 - spec/fixtures/fits_0.6.2_jpg.xml
@@ -303,7 +304,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.4.5.1
+rubygems_version: 2.4.8
 signing_key: 
 specification_version: 4
 summary: Fundamental repository data model for hydra
@@ -311,6 +312,7 @@ test_files:
 - spec/fixtures/Example.ogg
 - spec/fixtures/charter.docx
 - spec/fixtures/countdown.avi
+- spec/fixtures/eicar.txt
 - spec/fixtures/fits_0.6.2_avi.xml
 - spec/fixtures/fits_0.6.2_jp2.xml
 - spec/fixtures/fits_0.6.2_jpg.xml