ro-crate 0.5.1 → 0.5.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 28049e56f761e9b8684970817cc4eace0a60c78aee05b6a16688e589a2088357
-  data.tar.gz: 3e731b4c6039aa74ea34ab7d672fa665b99d4d030598a16ac593877cb0bf306f
+  metadata.gz: 987f4bf5543890ca23264eaa771134f6ec2ba848a84ea32424cf951429141523
+  data.tar.gz: f05c5166d95be3cec706fbb5d550c5af916f5f4c444112575ec49d5fe961e12a
 SHA512:
-  metadata.gz: ac8be2df8a04041f7cafc51e04c2ee67d0e25599b1c7a16716aa0b61a4db132b5fb1e55a1bef48b7c6c83aea6bfaba1826a1ac294f58e3092a35438e1938433c
-  data.tar.gz: 13a3780ee9ff9c85ac6829b0f93e393df3917e9286468c54cd127d1fdba704d14ced069fafb7bcb76378c6b120c6598e431e905059983f1dcec704efefc038cf
+  metadata.gz: '0848a81d03d8cdf7b4809de8613d90b67950f4339ae20ab5ce4ba6fa8d9e9559033c4a53ca47391b99ed5287ba7a2f2be7976b87c7ea8479051b8e7dfc9da6e8'
+  data.tar.gz: c1fc1ffdadafd04c19d81c37befec9eed9bcf9e40db9c39158b20a2a8ec8b8368841c65211d31439ba585f637de9541e2b7d58673da4964c7b8afccbfb9bf6ff

data/.github/workflows/tests.yml

@@ -5,7 +5,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        ruby: ['2.6', '2.7', '3.0', '3.1']
+        ruby: ['2.6', '2.7', '3.0', '3.1', '3.2', '3.3']
       fail-fast: false
     steps:
       - name: Checkout

data/.gitignore

@@ -48,3 +48,5 @@ build-iPhoneSimulator/
 
 # unless supporting rvm < 1.11.0 or doing something fancy, ignore this:
 .rvmrc
+
+Gemfile.lock

data/.ruby-version

@@ -1 +1 @@
-ruby-3.0.4
+ruby-3.2.5

data/lib/ro_crate/json_ld_hash.rb

@@ -2,11 +2,6 @@ module ROCrate
   ##
   # A wrapper class for Hash that adds methods to dereference Entities within an RO-Crate.
   class JSONLDHash < ::Hash
-    def self.[](graph, content = {})
-      @graph = graph
-      super(stringified(content))
-    end
-
     def initialize(graph, content = {})
       @graph = graph
       super()

data/lib/ro_crate/model/directory.rb

@@ -59,7 +59,7 @@ module ROCrate
     # @return [Hash{String => Entry}>] The files/directories that were populated.
     #   The key is the relative path of the file/directory, and the value is an Entry object where data can be read etc.
     def populate_entries(source_directory, include_hidden: false)
-      raise 'Not a directory' unless ::File.directory?(source_directory)
+      raise TypeError, 'Not a directory' unless ::File.directory?(source_directory)
       @directory_entries = {}
       list_all_files(source_directory, include_hidden: include_hidden).each do |rel_path|
         source_path = Pathname.new(::File.join(source_directory, rel_path)).expand_path

data/lib/ro_crate/model/exceptions/exception.rb

@@ -0,0 +1,15 @@
+module ROCrate
+  class Exception < StandardError
+    attr_reader :inner_exception
+
+    def initialize(message, _inner_exception = nil)
+      if _inner_exception
+        @inner_exception = _inner_exception
+        super("#{message}: #{@inner_exception.class.name} - #{@inner_exception.message}")
+        set_backtrace(@inner_exception.backtrace)
+      else
+        super(message)
+      end
+    end
+  end
+end

data/lib/ro_crate/model/exceptions/read_exception.rb

@@ -0,0 +1,4 @@
+module ROCrate
+  class ReadException < ROCrate::Exception
+  end
+end

data/lib/ro_crate/reader.rb

@@ -9,7 +9,6 @@ module ROCrate
     # @param target_dir [String, ::File, Pathname] The target directory where the crate should be unzipped (if its a Zip file).
     # @return [Crate] The RO-Crate.
     def self.read(source, target_dir: Dir.mktmpdir)
-      raise "Not a directory!" unless ::File.directory?(target_dir)
       begin
         is_dir = ::File.directory?(source)
       rescue TypeError
@@ -82,6 +81,8 @@ module ROCrate
     # @param target_dir [String, ::File, Pathname] The target directory where the crate should be unzipped.
     # @return [Crate] The RO-Crate.
     def self.read_zip(source, target_dir: Dir.mktmpdir)
+      raise ROCrate::ReadException, "Target is not a directory!" unless ::File.directory?(target_dir)
+
       unzip_to(source, target_dir)
 
       # Traverse the unzipped directory to try and find the crate's root
@@ -96,7 +97,7 @@ module ROCrate
     # @param source [String, ::File, Pathname] The location of the directory.
     # @return [Crate] The RO-Crate.
     def self.read_directory(source)
-      raise "Not a directory!" unless ::File.directory?(source)
+      raise ROCrate::ReadException, "Source is not a directory!" unless ::File.directory?(source)
 
       source = ::File.expand_path(source)
       metadata_file = Dir.entries(source).detect { |entry| entry == ROCrate::Metadata::IDENTIFIER ||
@@ -104,13 +105,18 @@ module ROCrate
 
       if metadata_file
         metadata_json = ::File.read(::File.join(source, metadata_file))
-        metadata = JSON.parse(metadata_json)
+        begin
+          metadata = JSON.parse(metadata_json)
+        rescue JSON::ParserError => e
+          raise ROCrate::ReadException.new("Error parsing metadata", e)
+        end
+
         entities = entities_from_metadata(metadata)
         context = metadata['@context']
 
         build_crate(entities, source, context: context)
       else
-        raise 'No metadata found!'
+        raise ROCrate::ReadException, "No metadata found!"
       end
     end
 
@@ -131,14 +137,14 @@ module ROCrate
 
         # Do some normalization...
         entities[ROCrate::Metadata::IDENTIFIER] = extract_metadata_entity(entities)
-        raise "No metadata entity found in @graph!" unless entities[ROCrate::Metadata::IDENTIFIER]
+        raise ROCrate::ReadException, "No metadata entity found in @graph!" unless entities[ROCrate::Metadata::IDENTIFIER]
         entities[ROCrate::Preview::IDENTIFIER] = extract_preview_entity(entities)
         entities[ROCrate::Crate::IDENTIFIER] = extract_root_entity(entities)
-        raise "No root entity (with @id: #{entities[ROCrate::Metadata::IDENTIFIER].dig('about', '@id')}) found in @graph!" unless entities[ROCrate::Crate::IDENTIFIER]
+        raise ROCrate::ReadException, "No root entity (with @id: #{entities[ROCrate::Metadata::IDENTIFIER].dig('about', '@id')}) found in @graph!" unless entities[ROCrate::Crate::IDENTIFIER]
 
         entities
       else
-        raise "No @graph found in metadata!"
+        raise ROCrate::ReadException, "No @graph found in metadata!"
       end
     end
 
@@ -198,7 +204,9 @@ module ROCrate
     # @param entity_hash [Hash] A Hash containing all the entities in the @graph, mapped by their @id.
     # @return [Array<ROCrate::File, ROCrate::Directory>] The extracted DataEntity objects.
     def self.extract_data_entities(crate, source, entity_hash)
-      crate.raw_properties['hasPart'].map do |ref|
+      parts = crate.raw_properties['hasPart'] || []
+      parts = [parts] unless parts.is_a?(Array)
+      parts.map do |ref|
         entity_props = entity_hash.delete(ref['@id'])
         next unless entity_props
         entity_class = ROCrate::DataEntity.specialize(entity_props)
@@ -234,21 +242,21 @@ module ROCrate
     #          or nil if it referenced a local file that wasn't found.
     def self.create_data_entity(crate, entity_class, source, entity_props)
       id = entity_props.delete('@id')
+      raise ROCrate::ReadException, "Data Entity missing '@id': #{entity_props.inspect}" unless id
       decoded_id = URI.decode_www_form_component(id)
       path = nil
       uri = URI(id) rescue nil
       if uri&.absolute?
         path = uri
         decoded_id = nil
-      else
+      elsif !id.start_with?('#')
         [id, decoded_id].each do |i|
           fullpath = ::File.join(source, i)
           path = Pathname.new(fullpath) if ::File.exist?(fullpath)
         end
-        # unless path
-        #   warn "Missing file/directory: #{id}, skipping..."
-        #   return nil
-        # end
+        if path.nil?
+          raise ROCrate::ReadException, "Local Data Entity not found in crate: #{id}"
+        end
       end
 
       entity_class.new(crate, path, decoded_id, entity_props)
@@ -290,7 +298,7 @@ module ROCrate
     # mapped by its @id.
     def self.extract_root_entity(entities)
       root_id = entities[ROCrate::Metadata::IDENTIFIER].dig('about', '@id')
-      raise "Metadata entity does not reference any root entity" unless root_id
+      raise ROCrate::ReadException, "Metadata entity does not reference any root entity" unless root_id
       entities.delete(root_id)
     end
 
@@ -300,12 +308,16 @@ module ROCrate
     # @param source [String, ::File, Pathname] The location of the directory.
     # @return [Pathname, nil] The path to the root, or nil if not found.
     def self.detect_root_directory(source)
-      Pathname(source).find do |entry|
+      queue = [source]
+      until queue.empty?
+        entry = Pathname(queue.shift)
         if entry.file?
           name = entry.basename.to_s
           if name == ROCrate::Metadata::IDENTIFIER || name == ROCrate::Metadata::IDENTIFIER_1_0
             return entry.parent
           end
+        elsif entry.directory?
+          queue += entry.children
         end
       end
 

data/lib/ro_crate/ro-crate-preview.html.erb

@@ -1,10 +1,31 @@
+<%
+  def entity_to_html(entity)
+    if entity.is_a?(Array)
+      if entity.length == 1
+        entity_to_html(entity.first)
+      else
+        "<ul><li>#{entity.map { |e| entity_to_html(e) }.join('</li><li>')}</li></ul>"
+      end
+    elsif entity.is_a?(ROCrate::Entity)
+      label = entity['name'] || entity.id
+      if entity.external?
+        "<a href=\"#{entity.id}\" target=\"_blank\">#{label}</a>"
+      else
+        label
+      end
+    else
+      entity
+    end
+  end
+%>
 <!DOCTYPE html>
-<html>
+<html lang="en">
 <head>
   <title><%= name || "New RO-Crate" %></title>
   <script type="application/ld+json"><%= metadata.generate %></script>
-  <meta name="generator" content="https://github.com/fbacall/ro-crate-ruby">
+  <meta name="generator" content="https://github.com/ResearchObject/ro-crate-ruby">
   <meta name="keywords" content="RO-Crate">
+  <meta charset="utf-8">
 </head>
 <body>
   <h1><%= name || "New RO-Crate" %></h1>
@@ -17,36 +38,32 @@
   <dl>
     <% if author %>
       <dt>Author</dt>
-      <dd><%= author %></dd>
+      <dd><%= entity_to_html author %></dd>
     <% end %>
     <% if contact_point %>
       <dt>Contact</dt>
-      <dd><%= contact_point %></dd>
+      <dd><%= entity_to_html contact_point %></dd>
     <% end %>
     <% if publisher %>
       <dt>Publisher</dt>
-      <dd><%= publisher %></dd>
+      <dd><%= entity_to_html publisher %></dd>
     <% end %>
     <% if license %>
       <dt>License</dt>
-      <dd><%= license %></dd>
+      <dd><%= entity_to_html license %></dd>
     <% end %>
   </dl>
 
   <h2>Contents</h2>
   <ul>
     <% data_entities.each do |data_entity| %>
-      <li id="__data_entity_<%= data_entity.id.gsub(/\s/, '-') %>">
-        <% if data_entity.external? %>
-          <strong><a href="<%= data_entity.id %>" target="_blank"><%= data_entity.name || data_entity.id %></a></strong>
-        <% else %>
-          <strong><%= data_entity.name || data_entity.id %></strong>
-        <% end %>
+      <li>
+        <strong><%= entity_to_html data_entity %></strong>
         <% if data_entity.content_size %>
-          <br/>Size: <%= data_entity.content_size %>
+          <br/>Size: <%= entity_to_html data_entity.content_size %>
         <% end %>
         <% if data_entity.encoding_format %>
-          <br/>Format: <%= data_entity.encoding_format %>
+          <br/>Format: <%= entity_to_html data_entity.encoding_format %>
         <% end %>
       </li>
     <% end %>

data/lib/ro_crate/writer.rb

@@ -14,9 +14,11 @@ module ROCrate
     #
     # @param dir [String] A path for the directory for the crate to be written to. All parent directories will be created.
     # @param overwrite [Boolean] Whether or not to overwrite existing files.
-    def write(dir, overwrite: true)
+    # @param skip_preview [Boolean] Whether or not to skip generation of the RO-Crate preview HTML file.
+    def write(dir, overwrite: true, skip_preview: false)
       FileUtils.mkdir_p(dir) # Make any parent directories
       @crate.payload.each do |path, entry|
+        next if skip_preview && entry&.source.is_a?(ROCrate::PreviewGenerator)
         fullpath = ::File.join(dir, path)
         next if !overwrite && ::File.exist?(fullpath)
         next if entry.directory?
@@ -40,10 +42,12 @@ module ROCrate
     # Write the crate to a zip file.
     #
     # @param destination [String, ::File] The destination where to write the RO-Crate zip.
-    def write_zip(destination)
+    # @param skip_preview [Boolean] Whether or not to skip generation of the RO-Crate preview HTML file.
+    def write_zip(destination, skip_preview: false)
       Zip::File.open(destination, Zip::File::CREATE) do |zip|
         @crate.payload.each do |path, entry|
           next if entry.directory?
+          next if skip_preview && entry&.source.is_a?(ROCrate::PreviewGenerator)
           if entry.symlink?
             zip.add(path, entry.path) if entry.path
           else

data/lib/ro_crate.rb

@@ -6,6 +6,8 @@ require 'zip/filesystem'
 require 'addressable'
 require 'open-uri'
 
+require 'ro_crate/model/exceptions/exception'
+require 'ro_crate/model/exceptions/read_exception'
 require 'ro_crate/json_ld_hash'
 require 'ro_crate/model/entity'
 require 'ro_crate/model/data_entity'

data/ro_crate.gemspec

@@ -1,6 +1,6 @@
 Gem::Specification.new do |s|
   s.name        = 'ro-crate'
-  s.version     = '0.5.1'
+  s.version     = '0.5.3'
   s.summary     = 'Create, manipulate, read RO-Crates.'
   s.authors     = ['Finn Bacall']
   s.email       = 'finn.bacall@manchester.ac.uk'

data/test/entity_test.rb

@@ -72,6 +72,23 @@ class EntityTest < Test::Unit::TestCase
     assert_equal(person.canonical_id, crate.author.canonical_id)
   end
 
+  test 'to_json' do
+    crate = ROCrate::Crate.new
+
+    crate['test'] = 'hello'
+    crate['test2'] = ['hello']
+    crate['test3'] = 123
+    crate['test4'] = { a: 'bc' }
+
+    json = crate.to_json
+    parsed = JSON.parse(json)
+
+    assert_equal 'hello', parsed['test']
+    assert_equal ['hello'], parsed['test2']
+    assert_equal 123, parsed['test3']
+    assert_equal({ 'a' => 'bc' }, parsed['test4'])
+  end
+
   test 'format various IDs' do
     assert_equal "#Hello%20World/Goodbye%20World", ROCrate::ContextualEntity.format_id('#Hello World/Goodbye World')
     assert_equal "#Hello%20World/Goodbye%20World", ROCrate::ContextualEntity.format_id('Hello World/Goodbye World')

data/test/entry_test.rb

@@ -0,0 +1,110 @@
+# encoding: utf-8
+require 'test_helper'
+
+class EntryTest < Test::Unit::TestCase
+  setup do
+    stub_request(:get, 'http://example.com/dir/file.txt').to_return(status: 200, body: 'file contents')
+    stub_request(:get, 'http://example.com/dir/').to_return(status: 200, body: '<html>...')
+
+    @local_file = ROCrate::Entry.new(fixture_file('info.txt'))
+    @local_path = ROCrate::Entry.new(Pathname.new(fixture_dir).join('directory', 'info.txt'))
+    @local_io = ROCrate::Entry.new(StringIO.new('stringio'))
+    @local_dir = ROCrate::Entry.new(Pathname.new(fixture_dir).join('directory'))
+    @local_symlink = ROCrate::Entry.new(Pathname.new(fixture_dir).join('symlink'))
+    @local_dir_symlink = ROCrate::Entry.new(Pathname.new(fixture_dir).join('dir_symlink'))
+    @remote_file = ROCrate::RemoteEntry.new(URI('http://example.com/dir/file.txt'))
+    @remote_dir = ROCrate::RemoteEntry.new(URI('http://example.com/dir/'), directory: true)
+  end
+
+  test 'read' do
+    assert_equal "Hello\n", @local_file.read
+    assert_equal "1234\n", @local_path.read
+    assert_equal "stringio", @local_io.read
+    assert_raises(Errno::EISDIR) { @local_dir.read }
+    assert_raises(Errno::EISDIR) { @local_dir_symlink.read }
+    assert_equal "I have spaces in my name\n", @local_symlink.read
+    assert_equal "file contents", @remote_file.read
+    assert_equal "<html>...", @remote_dir.read
+  end
+
+  test 'write_to' do
+    dest = StringIO.new
+    @local_file.write_to(dest)
+    dest.rewind
+    assert_equal "Hello\n", dest.read
+
+    dest = StringIO.new
+    @local_path.write_to(dest)
+    dest.rewind
+    assert_equal "1234\n", dest.read
+
+    dest = StringIO.new
+    @local_io.write_to(dest)
+    dest.rewind
+    assert_equal "stringio", dest.read
+
+    assert_raises(Errno::EISDIR) { @local_dir.write_to(dest) }
+
+    assert_raises(Errno::EISDIR) { @local_dir_symlink.write_to(dest) }
+
+    dest = StringIO.new
+    @local_symlink.write_to(dest)
+    dest.rewind
+    assert_equal "I have spaces in my name\n", dest.read
+
+    dest = StringIO.new
+    @remote_file.write_to(dest)
+    dest.rewind
+    assert_equal "file contents", dest.read
+
+    dest = StringIO.new
+    @remote_dir.write_to(dest)
+    dest.rewind
+    assert_equal "<html>...", dest.read
+  end
+
+  test 'directory?' do
+    refute @local_file.directory?
+    refute @local_path.directory?
+    refute @local_io.directory?
+    assert @local_dir.directory?
+    refute @local_symlink.directory?
+    assert @local_dir_symlink.directory?
+    refute @remote_file.directory?
+    assert @remote_dir.directory?
+  end
+
+  test 'symlink?' do
+    refute @local_file.symlink?
+    refute @local_path.symlink?
+    refute @local_io.symlink?
+    refute @local_dir.symlink?
+    assert @local_symlink.symlink?
+    assert @local_dir_symlink.symlink?
+    refute @remote_file.symlink?
+    refute @remote_dir.symlink?
+  end
+
+  test 'remote?' do
+    refute @local_file.remote?
+    refute @local_path.remote?
+    refute @local_io.remote?
+    refute @local_dir.remote?
+    refute @local_symlink.remote?
+    refute @local_dir_symlink.remote?
+    assert @remote_file.remote?
+    assert @remote_dir.remote?
+  end
+
+  test 'path' do
+    base = Pathname.new(fixture_dir).expand_path.to_s
+    assert_equal "#{base}/info.txt", @local_file.path
+    assert_equal "#{base}/directory/info.txt", @local_path.path
+    assert_nil @local_io.path
+    assert_equal "#{base}/directory", @local_dir.path
+    assert_equal "#{base}/symlink", @local_symlink.path
+    assert_equal "#{base}/dir_symlink", @local_dir_symlink.path
+    assert_nil @remote_file.path
+    assert_nil @remote_dir.path
+  end
+end

data/test/fixtures/arcp/ro-crate-metadata.json

@@ -0,0 +1,21 @@
+{
+    "@context": "https://w3id.org/ro/crate/1.1/context",
+    "@graph": [
+        {
+            "@id": "arcp://name,somethingsomething",
+            "@type": "Dataset",
+            "datePublished": "2024-01-31T10:47:17+00:00"
+            
+        },
+        {
+            "@id": "ro-crate-metadata.json",
+            "@type": "CreativeWork",
+            "about": {
+                "@id": "arcp://name,somethingsomething"
+            },
+            "conformsTo": {
+                "@id": "https://w3id.org/ro/crate/1.1"
+            }
+        }
+    ]
+}

data/test/fixtures/broken/missing_file/file2.txt

@@ -0,0 +1 @@
+2

data/test/fixtures/broken/missing_file/ro-crate-metadata.json

@@ -0,0 +1,32 @@
+{
+  "@context": "https://w3id.org/ro/crate/1.1/context",
+  "@graph": [
+    {
+      "@id": "ro-crate-metadata.json",
+      "@type": "CreativeWork",
+      "about": {
+        "@id": "./"
+      }
+    },
+    {
+      "@id": "./",
+      "@type": "Dataset",
+      "hasPart": [
+        {
+          "@id": "file1.txt"
+        },
+        {
+          "@id": "file2.txt"
+        }
+      ]
+    },
+    {
+      "@id": "file1.txt",
+      "@type": "File"
+    },
+    {
+      "@id": "file2.txt",
+      "@type": "File"
+    }
+  ]
+}

data/test/fixtures/broken/no_graph/ro-crate-metadata.json

@@ -0,0 +1,3 @@
+{
+  "@context": "https://w3id.org/ro/crate/1.1/context"
+}

data/test/fixtures/broken/no_metadata_entity/ro-crate-metadata.json

@@ -0,0 +1,6 @@
+{
+  "@context": "https://w3id.org/ro/crate/1.1/context",
+  "@graph": [
+
+  ]
+}

data/test/fixtures/broken/no_metadata_file/test.txt

@@ -0,0 +1 @@
+123

data/test/fixtures/broken/no_root_entity/ro-crate-metadata.json

@@ -0,0 +1,12 @@
+{
+  "@context": "https://w3id.org/ro/crate/1.1/context",
+  "@graph": [
+    {
+      "@id": "ro-crate-metadata.json",
+      "@type": "CreativeWork",
+      "about": {
+        "@id": "./"
+      }
+    }
+  ]
+}

data/test/fixtures/broken/not_json/ro-crate-metadata.json

@@ -0,0 +1,9 @@
+<!DOCTYPE html>
+<html>
+<head>
+<title>Error</title>
+</head>
+<body>
+Were you expecting JSON?
+</body>
+</html>

data/test/fixtures/dir_symlink

@@ -0,0 +1 @@
+directory

data/test/fixtures/singleton-haspart/a_file

@@ -0,0 +1 @@
+123

data/test/fixtures/singleton-haspart/ro-crate-metadata.json

@@ -0,0 +1,57 @@
+{
+  "@context": [
+    "https://w3id.org/ro/crate/1.1/context",
+    "https://w3id.org/ro/terms/workflow-run/context"
+  ],
+  "@graph": [
+    {
+      "@id": "./",
+      "@type": "Dataset",
+      "datePublished": "2025-01-28T02:44:51.523Z",
+      "hasPart": {
+        "@id": "a_file"
+      },
+      "dateCreated": "2025-01-28T02:45:05.906Z",
+      "dateModified": "2025-01-28T02:44:51.523Z",
+      "description": "Something",
+      "license": {
+        "@id": "https://spdx.org/licenses/MIT"
+      },
+      "mainEntity": {
+        "@id": "a_file"
+      },
+      "name": "An RO-Crate containing just a single item"
+    },
+    {
+      "@id": "ro-crate-metadata.json",
+      "@type": "CreativeWork",
+      "conformsTo": [
+        {
+          "@id": "https://w3id.org/ro/crate/1.1"
+        },
+        {
+          "@id": "https://w3id.org/workflowhub/workflow-ro-crate/1.0"
+        }
+      ],
+      "about": {
+        "@id": "./"
+      }
+    },
+    {
+      "@id": "a_file",
+      "@type": [
+        "File",
+        "ComputationalWorkflow",
+        "SoftwareSourceCode"
+      ],
+      "contentSize": 4,
+      "description": "A workflow",
+      "encodingFormat": "text/plain",
+      "name": "a_file",
+      "programmingLanguage": {
+        "@id": "https://example.com/workflow_format"
+      }
+    }
+  ]
+}
+

data/test/fixtures/symlink

@@ -0,0 +1 @@
+file with spaces.txt

data/test/preview_test.rb

@@ -0,0 +1,48 @@
+# encoding: utf-8
+require 'test_helper'
+
+class PreviewTest < Test::Unit::TestCase
+  test 'simple attributes' do
+    crate = ROCrate::Crate.new
+    crate.author = 'Finn'
+
+    html = crate.preview.source.read
+    assert_includes html, '<dd>Finn</dd>'
+  end
+
+  test 'list attributes' do
+    crate = ROCrate::Crate.new
+    crate.author = ['Finn', 'Josiah']
+
+    html = crate.preview.source.read
+    assert_includes html, '<dd><ul><li>Finn</li><li>Josiah</li></ul></dd>'
+  end
+
+  test 'entity attributes' do
+    crate = ROCrate::Crate.new
+    crate.author = crate.add_person('https://orcid.org/0000-0002-0048-3300', name: 'Finn')
+
+    html = crate.preview.source.read
+    assert_includes html, '<dd><a href="https://orcid.org/0000-0002-0048-3300" target="_blank">Finn</a></dd>'
+  end
+
+  test 'complex attributes' do
+    crate = ROCrate::Crate.new
+    crate.author = [crate.add_person('https://orcid.org/0000-0002-0048-3300', name: 'Finn'), 'Josiah']
+
+    html = crate.preview.source.read
+
+    assert_includes html, '<dd><ul><li><a href="https://orcid.org/0000-0002-0048-3300" target="_blank">Finn</a></li><li>Josiah</li></ul></dd>'
+  end
+
+  test 'files' do
+    crate = ROCrate::Crate.new
+    crate.add_file(fixture_file('info.txt'))
+    crate.add_external_file('https://raw.githubusercontent.com/ResearchObject/ro-crate-ruby/master/README.md')
+
+    html = crate.preview.source.read
+
+    assert_includes html, '<strong>info.txt</strong>'
+    assert_includes html, '<strong><a href="https://raw.githubusercontent.com/ResearchObject/ro-crate-ruby/master/README.md" target="_blank">https://raw.githubusercontent.com/ResearchObject/ro-crate-ruby/master/README.md</a></strong>'
+  end
+end

data/test/reader_test.rb

@@ -116,6 +116,19 @@ class ReaderTest < Test::Unit::TestCase
     end
   end
 
+  test 'reading from zip IO' do
+    io = StringIO.new(fixture_file('directory.zip').read)
+    crate = ROCrate::Reader.read(io)
+
+    assert crate.payload['fish/info.txt']
+    assert_equal '1234', crate.payload['fish/info.txt'].source.read.chomp
+    assert crate.payload['fish/root.txt']
+    assert crate.payload['fish/data/info.txt']
+    assert crate.payload['fish/data/nested.txt']
+    assert crate.payload['fish/data/binary.jpg']
+    assert_equal ['./', 'fish/', 'ro-crate-metadata.jsonld', 'ro-crate-preview.html'], crate.entities.map(&:id).sort
+  end
+
   test 'reading from directory with directories' do
     crate = ROCrate::Reader.read_directory(fixture_file('directory_crate').path)
 
@@ -303,4 +316,83 @@ class ReaderTest < Test::Unit::TestCase
     refute real_file.payload.values.first.remote?
     refute real_file.payload.values.first.directory?
   end
+
+  test 'handles exceptions' do
+    e = check_exception(ROCrate::ReadException) do
+      ROCrate::Reader.read(fixture_file('broken/no_graph'))
+    end
+    assert_include e.message, 'No @graph'
+
+    e = check_exception(ROCrate::ReadException) do
+      ROCrate::Reader.read(fixture_file('broken/no_metadata_entity'))
+    end
+    assert_include e.message, 'No metadata entity'
+
+    e = check_exception(ROCrate::ReadException) do
+      ROCrate::Reader.read(fixture_file('broken/no_metadata_file'))
+    end
+    assert_include e.message, 'No metadata found'
+
+    e = check_exception(ROCrate::ReadException) do
+      ROCrate::Reader.read(fixture_file('broken/no_root_entity'))
+    end
+    assert_include e.message, 'No root'
+
+    e = check_exception(ROCrate::ReadException) do
+      ROCrate::Reader.read(fixture_file('broken/not_json'))
+    end
+    assert_include e.message, 'Error parsing metadata: JSON::ParserError'
+    assert_equal JSON::ParserError, e.inner_exception.class
+
+    e = check_exception(ROCrate::ReadException) do
+      ROCrate::Reader.read(fixture_file('workflow-0.2.0.zip'), target_dir: fixture_file('workflow-0.2.0.zip'))
+    end
+    assert_include e.message, 'Target is not a directory!'
+
+    e = check_exception(ROCrate::ReadException) do
+      ROCrate::Reader.read_directory(fixture_file('workflow-0.2.0.zip'))
+    end
+    assert_include e.message, 'Source is not a directory!'
+
+    e = check_exception(ROCrate::ReadException) do
+      ROCrate::Reader.read(fixture_file('broken/missing_file'))
+    end
+    assert_include e.message, 'not found in crate: file1.txt'
+  end
+
+  test 'tolerates arcp identifier on root data entity (and missing hasPart)' do
+    crate = ROCrate::Reader.read(fixture_file('arcp').path)
+
+    assert_equal 'arcp://name,somethingsomething', crate.id
+    assert_empty crate.data_entities
+  end
+
+  test 'reads first metadata file it encounters' do
+    crate = ROCrate::Reader.read(fixture_file('multi_metadata_crate.crate.zip').path)
+
+    assert_equal 'At the root', crate.name
+  end
+
+  test 'reads crate with singleton hasPart' do
+    crate = ROCrate::Reader.read(fixture_file('singleton-haspart').path)
+
+    data = crate.data_entities
+    assert_equal 1, data.length
+    assert_equal 'a_file', data.first.name
+  end
+
+  private
+
+  def check_exception(exception_class)
+    e = nil
+    assert_raise(exception_class) do
+      begin
+        yield
+      rescue exception_class => e
+        raise e
+      end
+    end
+
+    e
+  end
 end

data/test/writer_test.rb

@@ -230,36 +230,83 @@ class WriterTest < Test::Unit::TestCase
 
   test 'write crate with remote files and directories' do
     orig = ROCrate::Reader.read(fixture_file('uri_heavy_crate').path)
-      Tempfile.create do |file|
-        ROCrate::Writer.new(orig).write_zip(file)
+    Tempfile.create do |file|
+      ROCrate::Writer.new(orig).write_zip(file)
 
-        Zip::File.open(file) do |zipfile|
-          refute zipfile.find_entry('nih:sha-256;3a2c-8d14-a40b-3755-4abc-5af8-a56d-ba3a-e159-d688-c9b3-f169-6751-4b88-fbd2-6a9f;7')
-        end
+      Zip::File.open(file) do |zipfile|
+        refute zipfile.find_entry('nih:sha-256;3a2c-8d14-a40b-3755-4abc-5af8-a56d-ba3a-e159-d688-c9b3-f169-6751-4b88-fbd2-6a9f;7')
+      end
 
-        file.rewind
-
-        crate = ROCrate::Reader.read(file)
-
-        dir = crate.get('nih:sha-256;f70e-eb2e-89d0-b3dc-5c99-8541-fa4b-6e64-a194-cf9d-ebd8-ca58-24e7-c47a-553f-86fa;c/')
-        assert dir
-        assert dir.is_a?(ROCrate::Directory)
-        assert dir.remote?
-        assert_empty dir.payload
-
-        file = crate.get('nih:sha-256;3a2c-8d14-a40b-3755-4abc-5af8-a56d-ba3a-e159-d688-c9b3-f169-6751-4b88-fbd2-6a9f;7')
-        assert file
-        assert file.is_a?(ROCrate::File)
-        assert file.remote?
-        assert_empty file.payload
-
-        real_file = crate.get('main.nf')
-        assert real_file
-        assert real_file.is_a?(ROCrate::File)
-        refute real_file.remote?
-        assert_not_empty real_file.payload
-        refute real_file.payload.values.first.remote?
-        refute real_file.payload.values.first.directory?
+      file.rewind
+
+      crate = ROCrate::Reader.read(file)
+
+      dir = crate.get('nih:sha-256;f70e-eb2e-89d0-b3dc-5c99-8541-fa4b-6e64-a194-cf9d-ebd8-ca58-24e7-c47a-553f-86fa;c/')
+      assert dir
+      assert dir.is_a?(ROCrate::Directory)
+      assert dir.remote?
+      assert_empty dir.payload
+
+      file = crate.get('nih:sha-256;3a2c-8d14-a40b-3755-4abc-5af8-a56d-ba3a-e159-d688-c9b3-f169-6751-4b88-fbd2-6a9f;7')
+      assert file
+      assert file.is_a?(ROCrate::File)
+      assert file.remote?
+      assert_empty file.payload
+
+      real_file = crate.get('main.nf')
+      assert real_file
+      assert real_file.is_a?(ROCrate::File)
+      refute real_file.remote?
+      assert_not_empty real_file.payload
+      refute real_file.payload.values.first.remote?
+      refute real_file.payload.values.first.directory?
+    end
+  end
+
+  test 'write crate with arcp root identifier' do
+    crate = ROCrate::Reader.read(fixture_file('arcp').path)
+
+    assert_equal 'arcp://name,somethingsomething', crate.id
+    Dir.mktmpdir do |dir|
+      ROCrate::Writer.new(crate).write(dir)
+      Dir.chdir(dir) do
+        assert File.exist?('ro-crate-metadata.json')
       end
+    end
+  end
+
+  test 'skip generating the preview in a directory' do
+    crate = ROCrate::Crate.new
+    crate.add_file(fixture_file('info.txt'))
+    crate.add_file(StringIO.new('just a string!'), 'notice.txt')
+    crate.add_file(fixture_file('data.csv'), 'directory/data.csv')
+
+    Dir.mktmpdir do |dir|
+      ROCrate::Writer.new(crate).write(dir, skip_preview: true)
+      assert ::File.exist?(::File.join(dir, ROCrate::Metadata::IDENTIFIER))
+      refute ::File.exist?(::File.join(dir, ROCrate::Preview::IDENTIFIER))
+      assert_equal 6, ::File.size(::File.join(dir, 'info.txt'))
+      assert_equal 14, ::File.size(::File.join(dir, 'notice.txt'))
+      assert_equal 20, ::File.size(::File.join(dir, 'directory', 'data.csv'))
+    end
+  end
+
+  test 'skip generating the preview in a zip file' do
+    crate = ROCrate::Crate.new
+    crate.add_directory(fixture_file('directory').path.to_s, 'fish')
+
+    Tempfile.create do |file|
+      ROCrate::Writer.new(crate).write_zip(file, skip_preview: true)
+
+      Zip::File.open(file) do |zipfile|
+        assert zipfile.file.exist?(ROCrate::Metadata::IDENTIFIER)
+        refute zipfile.file.exist?(ROCrate::Preview::IDENTIFIER)
+        assert zipfile.file.exist? 'fish/info.txt'
+        assert zipfile.file.exist? 'fish/root.txt'
+        assert zipfile.file.exist? 'fish/data/info.txt'
+        assert zipfile.file.exist? 'fish/data/nested.txt'
+        assert zipfile.file.exist? 'fish/data/binary.jpg'
+      end
+    end
   end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: ro-crate
 version: !ruby/object:Gem::Version
-  version: 0.5.1
+  version: 0.5.3
 platform: ruby
 authors:
 - Finn Bacall
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2022-12-12 00:00:00.000000000 Z
+date: 2025-01-30 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: addressable
@@ -139,7 +139,6 @@ files:
 - ".gitignore"
 - ".ruby-version"
 - Gemfile
-- Gemfile.lock
 - LICENSE
 - README.md
 - Rakefile
@@ -152,6 +151,8 @@ files:
 - lib/ro_crate/model/directory.rb
 - lib/ro_crate/model/entity.rb
 - lib/ro_crate/model/entry.rb
+- lib/ro_crate/model/exceptions/exception.rb
+- lib/ro_crate/model/exceptions/read_exception.rb
 - lib/ro_crate/model/file.rb
 - lib/ro_crate/model/metadata.rb
 - lib/ro_crate/model/organization.rb
@@ -166,12 +167,22 @@ files:
 - test/crate_test.rb
 - test/directory_test.rb
 - test/entity_test.rb
+- test/entry_test.rb
+- test/fixtures/arcp/ro-crate-metadata.json
 - test/fixtures/biobb_hpc_workflows-condapack.zip
+- test/fixtures/broken/missing_file/file2.txt
+- test/fixtures/broken/missing_file/ro-crate-metadata.json
+- test/fixtures/broken/no_graph/ro-crate-metadata.json
+- test/fixtures/broken/no_metadata_entity/ro-crate-metadata.json
+- test/fixtures/broken/no_metadata_file/test.txt
+- test/fixtures/broken/no_root_entity/ro-crate-metadata.json
+- test/fixtures/broken/not_json/ro-crate-metadata.json
 - test/fixtures/conflicting_data_directory/info.txt
 - test/fixtures/conflicting_data_directory/nested.txt
 - test/fixtures/crate-spec1.1/file with spaces.txt
 - test/fixtures/crate-spec1.1/ro-crate-metadata.json
 - test/fixtures/data.csv
+- test/fixtures/dir_symlink
 - test/fixtures/directory.zip
 - test/fixtures/directory/.dir/test.txt
 - test/fixtures/directory/.dotfile
@@ -190,6 +201,7 @@ files:
 - test/fixtures/file with spaces.txt
 - test/fixtures/info.txt
 - test/fixtures/misc_data_entity_crate/ro-crate-metadata.json
+- test/fixtures/multi_metadata_crate.crate.zip
 - test/fixtures/nested_directory.zip
 - test/fixtures/ro-crate-galaxy-sortchangecase/LICENSE
 - test/fixtures/ro-crate-galaxy-sortchangecase/README.md
@@ -198,6 +210,8 @@ files:
 - test/fixtures/ro-crate-galaxy-sortchangecase/test/test1/input.bed
 - test/fixtures/ro-crate-galaxy-sortchangecase/test/test1/output_exp.bed
 - test/fixtures/ro-crate-galaxy-sortchangecase/test/test1/sort-and-change-case-test.yml
+- test/fixtures/singleton-haspart/a_file
+- test/fixtures/singleton-haspart/ro-crate-metadata.json
 - test/fixtures/spaces/file with spaces.txt
 - test/fixtures/spaces/ro-crate-metadata.jsonld
 - test/fixtures/sparse_directory_crate.zip
@@ -210,6 +224,7 @@ files:
 - test/fixtures/sparse_directory_crate/ro-crate-metadata.jsonld
 - test/fixtures/sparse_directory_crate/ro-crate-preview.html
 - test/fixtures/sparse_directory_crate/unlisted_file.txt
+- test/fixtures/symlink
 - test/fixtures/unlinked_entity_crate/LICENSE
 - test/fixtures/unlinked_entity_crate/README.md
 - test/fixtures/unlinked_entity_crate/ro-crate-metadata.json
@@ -2450,6 +2465,7 @@ files:
 - test/fixtures/workflow-test-fixture-symlink/concat_two_files.ga
 - test/fixtures/workflow-test-fixture-symlink/diagram.png
 - test/fixtures/workflow-test-fixture-symlink/images/workflow-diagram.png
+- test/preview_test.rb
 - test/reader_test.rb
 - test/test_helper.rb
 - test/writer_test.rb
@@ -2472,7 +2488,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.2.33
+rubygems_version: 3.4.19
 signing_key: 
 specification_version: 4
 summary: Create, manipulate, read RO-Crates.

data/Gemfile.lock

@@ -1,50 +0,0 @@
-PATH
-  remote: .
-  specs:
-    ro-crate (0.5.1)
-      addressable (>= 2.7, < 2.9)
-      rubyzip (~> 2.0.0)
-
-GEM
-  remote: https://rubygems.org/
-  specs:
-    addressable (2.8.0)
-      public_suffix (>= 2.0.2, < 5.0)
-    crack (0.4.3)
-      safe_yaml (~> 1.0.0)
-    docile (1.3.5)
-    hashdiff (1.0.1)
-    power_assert (2.0.1)
-    public_suffix (4.0.6)
-    rake (13.0.0)
-    rexml (3.2.5)
-    rubyzip (2.0.0)
-    safe_yaml (1.0.5)
-    simplecov (0.21.2)
-      docile (~> 1.1)
-      simplecov-html (~> 0.11)
-      simplecov_json_formatter (~> 0.1)
-    simplecov-html (0.12.3)
-    simplecov_json_formatter (0.1.2)
-    test-unit (3.5.3)
-      power_assert
-    webmock (3.8.3)
-      addressable (>= 2.3.6)
-      crack (>= 0.3.2)
-      hashdiff (>= 0.4.0, < 2.0.0)
-    yard (0.9.25)
-
-PLATFORMS
-  ruby
-
-DEPENDENCIES
-  rake (~> 13.0.0)
-  rexml (~> 3.2.5)
-  ro-crate!
-  simplecov (~> 0.21.2)
-  test-unit (~> 3.5.3)
-  webmock (~> 3.8.3)
-  yard (~> 0.9.25)
-
-BUNDLED WITH
-   2.3.6