ro-crate 0.5.2 → 0.6.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: f2462dcf00e2593cf8ea7108af9f9b6ef54ef773aea01be125f7c79ce67c2850
-  data.tar.gz: 40955bc76cd0344b80b727a79f5888ddc99d3874ecf3f8ce4db64ac2a722d713
+  metadata.gz: 2c4aabc50994541bbcbb2071b805f457e47c9e30176299fdde40741aa5ff1094
+  data.tar.gz: 0f4d7df6b4eb21961446ce2e3c05fe337fa7ed9e161eb21a7651b8ea6292f988
 SHA512:
-  metadata.gz: 7bd16f57d802a39d378cbcfa663ecc55acfbc77256013a50d7490a652cf383186c99dbbd0c28d5747751c33aa79fe06033e1a90a15cb6f2052139045992afc76
-  data.tar.gz: 8a6f755b6fa96e511ca1ff4c034f049c6148acd2fe4f1aa8e7a71ab231217dd2dfc4fdde7cc92cae0d6ab1d077aa36f2d13afe98ee7fbecfe0ccd532a0580325
+  metadata.gz: f590b0e08e5f813474e4c46e3230b01999d17cf349645b8c86285c8dbe3cd371563405e1e1143a7b68d115764373847ace352029beed404a5cc069e64ef40dab
+  data.tar.gz: 972a1e14b6faa4986bad9138fdd39861bf54af81dd5678354f84cc0f4bbc3b50252e38cf948d013bb6a979365dedc74e81c48661115f0cd3f408fcdd0744f777

data/.github/workflows/docs.yml

@@ -7,7 +7,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@v2.3.1 # If you're using actions/checkout@v2 you must set persist-credentials to false in most cases for the deployment to work correctly.
+        uses: actions/checkout@v6
         with:
           persist-credentials: false
       - name: Setup Ruby

data/.github/workflows/tests.yml

@@ -5,11 +5,11 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        ruby: ['2.6', '2.7', '3.0', '3.1']
+        ruby: ['2.7', '3.0', '3.1', '3.2', '3.3', '3.4', '4.0']
       fail-fast: false
     steps:
       - name: Checkout
-        uses: actions/checkout@v2.3.1 # If you're using actions/checkout@v2 you must set persist-credentials to false in most cases for the deployment to work correctly.
+        uses: actions/checkout@v6
         with:
           persist-credentials: false
       - name: Setup Ruby

data/.ruby-version

@@ -1 +1 @@
-ruby-3.0.4
+ruby-3.4.9

data/README.md

@@ -2,10 +2,10 @@
 
 ![Tests](https://github.com/ResearchObject/ro-crate-ruby/actions/workflows/tests.yml/badge.svg)
 
-This is a WIP gem for creating, manipulating and reading RO-Crates (conforming to version 1.1 of the specification).
+This is a WIP gem for creating, manipulating and reading RO-Crates (conforming to version 1.2 of the specification). RO-Crates produced by older versions (1.0, 1.1) of the spec can still be read.
 
-* RO-Crate - https://researchobject.github.io/ro-crate/
-* RO-Crate spec (1.1) - https://researchobject.github.io/ro-crate/1.1/
+* RO-Crate - https://www.researchobject.org/ro-crate/
+* RO-Crate spec (1.2) - https://www.researchobject.org/ro-crate/specification/1.2/
 
 ## Installation
 

data/Rakefile

@@ -1,6 +1,5 @@
 require 'bundler/gem_tasks'
 require 'rake/testtask'
-require 'rdoc/task'
 
 desc 'Default: run unit tests.'
 task default: :test
@@ -13,14 +12,6 @@ Rake::TestTask.new(:test) do |t|
   t.warning = false
 end
 
-Rake::RDocTask.new(:rdoc) do |rdoc|
-  rdoc.rdoc_dir = 'rdoc'
-  rdoc.title    = 'Devise'
-  rdoc.options << '--line-numbers' << '--inline-source'
-  rdoc.rdoc_files.include('README.md')
-  rdoc.rdoc_files.include('lib/**/*.rb')
-end
-
 task :console do
   require 'irb'
   require 'irb/completion'

data/lib/ro_crate/model/crate.rb

@@ -21,9 +21,16 @@ module ROCrate
 
     ##
     # Initialize an empty RO-Crate.
-    def initialize(id = IDENTIFIER, properties = {})
+    #
+    # @param id [String] The crate's identifier.
+    # @param properties [Hash] Initial properties for the root data entity.
+    # @param version [String] RO-Crate spec version to declare (default: ROCrate::Metadata::DEFAULT_VERSION).
+    #   Must be one of ROCrate::Metadata::SUPPORTED_VERSIONS.
+    def initialize(id = IDENTIFIER, properties = {}, version: ROCrate::Metadata::DEFAULT_VERSION)
+      ROCrate::Metadata.warn_unrecognized_version(version)
       @data_entities = Set.new
       @contextual_entities = Set.new
+      @metadata_version = version
       super(self, nil, id, properties)
     end
 
@@ -168,7 +175,7 @@ module ROCrate
     #
     # @return [Metadata]
     def metadata
-      @metadata ||= ROCrate::Metadata.new(self)
+      @metadata ||= ROCrate::Metadata.new(self, {}, version: @metadata_version || ROCrate::Metadata::DEFAULT_VERSION)
     end
 
     ##

data/lib/ro_crate/model/directory.rb

@@ -74,9 +74,8 @@ module ROCrate
     end
 
     def list_all_files(source_directory, include_hidden: false)
-      args = ['**/*']
-      args << ::File::FNM_DOTMATCH if include_hidden
-      Dir.chdir(source_directory) { Dir.glob(*args) }.reject do |path|
+      flags = include_hidden ? ::File::FNM_DOTMATCH : 0
+      Dir.glob('**/*', flags, base: source_directory).reject do |path|
         path == '.' || path == '..' || path.end_with?('/.')
       end
     end

data/lib/ro_crate/model/metadata.rb

@@ -5,13 +5,46 @@ module ROCrate
     IDENTIFIER = 'ro-crate-metadata.json'.freeze
     IDENTIFIER_1_0 = 'ro-crate-metadata.jsonld'.freeze # 1.0 spec identifier
     RO_CRATE_BASE = 'https://w3id.org/ro/crate/'
-    CONTEXT = "#{RO_CRATE_BASE}1.1/context".freeze
-    SPEC = "#{RO_CRATE_BASE}1.1".freeze
 
-    def initialize(crate, properties = {})
+    SUPPORTED_VERSIONS = %w[1.0 1.0-DRAFT 1.1 1.1-DRAFT 1.2 1.2-DRAFT].freeze
+    DEFAULT_VERSION = '1.2'.freeze
+
+    CONTEXT = "#{RO_CRATE_BASE}#{DEFAULT_VERSION}/context".freeze
+    SPEC = "#{RO_CRATE_BASE}#{DEFAULT_VERSION}".freeze
+
+    attr_reader :version
+
+    ##
+    # Emit a warning if the given version is not in SUPPORTED_VERSIONS.
+    # Does not raise — unrecognized versions are still accepted so the library
+    # stays forward-compatible with future spec versions that need no changes.
+    def self.warn_unrecognized_version(v)
+      return if SUPPORTED_VERSIONS.include?(v)
+      warn "Unrecognized RO-Crate version: #{v.inspect}. Known versions: #{SUPPORTED_VERSIONS.join(', ')}"
+    end
+
+    def initialize(crate, properties = {}, version: DEFAULT_VERSION)
+      self.class.warn_unrecognized_version(version)
+      @version = version
       super(crate, nil, IDENTIFIER, properties)
     end
 
+    ##
+    # Update the spec version this metadata declares.
+    # Used by the Reader to preserve the version of a parsed crate.
+    def version=(v)
+      self.class.warn_unrecognized_version(v)
+      @version = v
+    end
+
+    def context_url
+      "#{RO_CRATE_BASE}#{@version}/context"
+    end
+
+    def spec_url
+      "#{RO_CRATE_BASE}#{@version}"
+    end
+
     ##
     # Generate the crate's `ro-crate-metadata.jsonld`.
     # @return [String] The rendered JSON-LD as a "prettified" string.
@@ -21,7 +54,7 @@ module ROCrate
     end
 
     def context
-      @context || CONTEXT
+      @context || context_url
     end
 
     def context= c
@@ -39,7 +72,7 @@ module ROCrate
         '@id' => IDENTIFIER,
         '@type' => 'CreativeWork',
         'about' => { '@id' => crate.id },
-        'conformsTo' => { '@id' => SPEC }
+        'conformsTo' => { '@id' => spec_url }
       }
     end
   end

data/lib/ro_crate/reader.rb

@@ -1,7 +1,11 @@
+require 'zip/version'
+
 module ROCrate
   ##
   # A class to handle reading of RO-Crates from Zip files or directories.
   class Reader
+    LEGACY_EXTRACT = Zip::VERSION.start_with?('2.').freeze
+
     ##
     # Reads an RO-Crate from a directory or zip file.
     #
@@ -42,15 +46,15 @@ module ROCrate
     #
     # @param source [#read] An IO-like object containing a Zip file.
     # @param target [String, ::File, Pathname] The target directory where the file should be unzipped.
-    def self.unzip_io_to(io, target)
-      Dir.chdir(target) do
-        Zip::InputStream.open(io) do |input|
-          while (entry = input.get_next_entry)
-            unless ::File.exist?(entry.name) || entry.name_is_directory?
-              FileUtils::mkdir_p(::File.dirname(entry.name))
-              ::File.binwrite(entry.name, input.read)
-            end
-          end
+    def self.unzip_io_to(source, target)
+      target_path = Pathname(target)
+      Zip::InputStream.open(source) do |input|
+        while (entry = input.get_next_entry)
+          next if entry.name_is_directory?
+          dest = safe_join(target_path, entry.name)
+          next if dest.exist?
+          FileUtils.mkdir_p(dest.dirname)
+          ::File.binwrite(dest, input.read)
         end
       end
     end
@@ -60,15 +64,14 @@ module ROCrate
     #
     # @param source [String, ::File, Pathname] The location of the zip file.
     # @param target [String, ::File, Pathname] The target directory where the file should be unzipped.
-    def self.unzip_file_to(file_or_path, target)
-      Dir.chdir(target) do
-        Zip::File.open(file_or_path) do |zipfile|
-          zipfile.each do |entry|
-            unless ::File.exist?(entry.name)
-              FileUtils::mkdir_p(::File.dirname(entry.name))
-              zipfile.extract(entry, entry.name)
-            end
-          end
+    def self.unzip_file_to(source, target)
+      target_path = Pathname(target)
+      Zip::File.open(source) do |zipfile|
+        zipfile.each do |entry|
+          dest = safe_join(target_path, entry.name)
+          next if dest.exist?
+          FileUtils.mkdir_p(dest.dirname)
+          LEGACY_EXTRACT ? entry.extract(dest) : entry.extract(entry.name, destination_directory: target_path)
         end
       end
     end
@@ -87,6 +90,7 @@ module ROCrate
 
       # Traverse the unzipped directory to try and find the crate's root
       root_dir = detect_root_directory(target_dir)
+      raise ROCrate::ReadException, "No metadata found!" unless root_dir
 
       read_directory(root_dir)
     end
@@ -184,7 +188,10 @@ module ROCrate
     def self.initialize_crate(entity_hash, source, crate_class: ROCrate::Crate, context:)
       crate_class.new.tap do |crate|
         crate.properties = entity_hash.delete(ROCrate::Crate::IDENTIFIER)
-        crate.metadata.properties = entity_hash.delete(ROCrate::Metadata::IDENTIFIER)
+        metadata_props = entity_hash.delete(ROCrate::Metadata::IDENTIFIER)
+        crate.metadata.properties = metadata_props
+        parsed_version = extract_version(metadata_props)
+        crate.metadata.version = parsed_version if parsed_version
         crate.metadata.context = context
         preview_properties = entity_hash.delete(ROCrate::Preview::IDENTIFIER)
         preview_path = ::File.join(source, ROCrate::Preview::IDENTIFIER)
@@ -204,7 +211,9 @@ 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)
@@ -263,7 +272,7 @@ module ROCrate
 
     ##
     # Extract the metadata entity from the entity hash, according to the rules defined here:
-    # https://www.researchobject.org/ro-crate/1.1/root-data-entity.html#finding-the-root-data-entity
+    # https://www.researchobject.org/ro-crate/specification/1.2/root-data-entity.html#finding-the-root-data-entity
     # @return [nil, Hash{String => Hash}] A Hash containing (hopefully) one value, the metadata entity's properties
     # mapped by its @id, or nil if nothing is found.
     def self.extract_metadata_entity(entities)
@@ -282,6 +291,24 @@ module ROCrate
           entities.delete(ROCrate::Metadata::IDENTIFIER_1_0))
     end
 
+    ##
+    # Extract the spec version from the metadata entity's `conformsTo`.
+    # Looks for an `@id` matching `https://w3id.org/ro/crate/<version>` and returns `<version>`.
+    # @param metadata_props [Hash, nil] The metadata entity's properties.
+    # @return [String, nil] The parsed version string, or nil if not found.
+    def self.extract_version(metadata_props)
+      return nil unless metadata_props
+      conforms = metadata_props['conformsTo']
+      conforms = [conforms] unless conforms.is_a?(Array)
+      conforms.compact.each do |c|
+        id = c.is_a?(Hash) ? c['@id'] : c
+        next unless id&.start_with?(ROCrate::Metadata::RO_CRATE_BASE)
+        version = id.sub(ROCrate::Metadata::RO_CRATE_BASE, '').split('/').first
+        return version if version && !version.empty?
+      end
+      nil
+    end
+
     ##
     # Extract the ro-crate-preview entity from the entity hash.
     # @return [Hash{String => Hash}] A Hash containing the preview entity's properties mapped by its @id, or nil if nothing is found.
@@ -291,7 +318,7 @@ module ROCrate
 
     ##
     # Extract the root entity from the entity hash, according to the rules defined here:
-    # https://www.researchobject.org/ro-crate/1.1/root-data-entity.html#finding-the-root-data-entity
+    # https://www.researchobject.org/ro-crate/specification/1.2/root-data-entity.html#finding-the-root-data-entity
     # @return [Hash{String => Hash}] A Hash containing (hopefully) one value, the root entity's properties,
     # mapped by its @id.
     def self.extract_root_entity(entities)
@@ -301,21 +328,48 @@ module ROCrate
     end
 
     ##
-    # Finds an RO-Crate's root directory (where `ro-crate-metdata.json` is located) within a given directory.
+    # Finds an RO-Crate's root directory (where `ro-crate-metadata.json` is located) within a given directory.
     #
     # @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
 
       nil
     end
+
+    ##
+    # Safely joins a desired file path onto a base directory, raising an exception if the path attempts to traverse
+    # outside it.
+    #
+    # @param base [Pathname] The base directory where the file will go.
+    # @param path [String] The desired file path.
+    #
+    # @raise [ROCrate::ReadException] Raised if an unsafe path is given.
+    #
+    # @return [Pathname] The safely joined base + path.
+    def self.safe_join(base, path)
+      dest = base.join(path)
+      # Guard against zip-slip attacks.
+      begin
+        unsafe = dest.expand_path.relative_path_from(base.expand_path).each_filename.first == '..'
+      rescue ArgumentError # Handle unjoinable paths, e.g. on different drives.
+        unsafe = true
+      end
+      raise ROCrate::ReadException, "Unsafe path in zip entry: #{path}" if unsafe
+
+      dest
+    end
   end
 end

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

@@ -1,3 +1,23 @@
+<%
+  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 lang="en">
 <head>
@@ -18,36 +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)
-      Zip::File.open(destination, Zip::File::CREATE) do |zip|
+    # @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, create: true) 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/ro_crate.gemspec

@@ -1,6 +1,6 @@
 Gem::Specification.new do |s|
   s.name        = 'ro-crate'
-  s.version     = '0.5.2'
+  s.version     = '0.6.0'
   s.summary     = 'Create, manipulate, read RO-Crates.'
   s.authors     = ['Finn Bacall']
   s.email       = 'finn.bacall@manchester.ac.uk'
@@ -8,12 +8,13 @@ Gem::Specification.new do |s|
   s.homepage    = 'https://github.com/ResearchObject/ro-crate-ruby'
   s.require_paths = ['lib']
   s.licenses    = ['MIT']
-  s.add_runtime_dependency 'addressable', '>= 2.7', '< 2.9'
-  s.add_runtime_dependency 'rubyzip', '~> 2.0.0'
-  s.add_development_dependency 'rake', '~> 13.0.0'
+  s.required_ruby_version = '>= 2.7.0'
+  s.add_runtime_dependency 'addressable', '>= 2.7', '< 3'
+  s.add_runtime_dependency 'rubyzip', '>= 2.3', '< 4'
+  s.add_development_dependency 'rake', '~> 13.4.2'
   s.add_development_dependency 'test-unit', '~> 3.5.3'
   s.add_development_dependency 'simplecov', '~> 0.21.2'
   s.add_development_dependency 'yard', '~> 0.9.25'
-  s.add_development_dependency 'webmock', '~> 3.8.3'
-  s.add_development_dependency 'rexml', '~> 3.2.5'
+  s.add_development_dependency 'webmock', '~> 3.26.2'
+  s.add_development_dependency 'rexml', '~> 3.4.4'
 end

data/test/crate_test.rb

@@ -377,4 +377,33 @@ class CrateTest < Test::Unit::TestCase
     assert_nil crate.get('#joe')
     assert crate.get('#joehouse')
   end
+
+  test 'defaults to RO-Crate spec 1.2' do
+    crate = ROCrate::Crate.new
+    assert_equal '1.2', crate.metadata.version
+    assert_equal 'https://w3id.org/ro/crate/1.2/context', crate.metadata.context
+    assert_equal 'https://w3id.org/ro/crate/1.2', crate.metadata.spec_url
+    assert_equal({ '@id' => 'https://w3id.org/ro/crate/1.2' }, crate.metadata.properties['conformsTo'])
+  end
+
+  test 'can write older spec version' do
+    crate = ROCrate::Crate.new(ROCrate::Crate::IDENTIFIER, {}, version: '1.1')
+    assert_equal '1.1', crate.metadata.version
+    assert_equal 'https://w3id.org/ro/crate/1.1/context', crate.metadata.context
+    assert_equal({ '@id' => 'https://w3id.org/ro/crate/1.1' }, crate.metadata.properties['conformsTo'])
+  end
+
+  test 'warns but accepts unrecognized spec version' do
+    original_stderr = $stderr
+    begin
+      $stderr = StringIO.new
+      crate = ROCrate::Crate.new(ROCrate::Crate::IDENTIFIER, {}, version: '1.5')
+      err = $stderr.string
+      assert_match(/Unrecognized RO-Crate version/, err)
+      assert_equal '1.5', crate.metadata.version
+      assert_equal 'https://w3id.org/ro/crate/1.5', crate.metadata.spec_url
+    ensure
+      $stderr = original_stderr
+    end
+  end
 end

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/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

@@ -358,6 +358,11 @@ class ReaderTest < Test::Unit::TestCase
       ROCrate::Reader.read(fixture_file('broken/missing_file'))
     end
     assert_include e.message, 'not found in crate: file1.txt'
+
+    e = check_exception(ROCrate::ReadException) do
+      ROCrate::Reader.read(fixture_file('just_a_zip.zip').path)
+    end
+    assert_include e.message, 'No metadata found'
   end
 
   test 'tolerates arcp identifier on root data entity (and missing hasPart)' do
@@ -367,18 +372,70 @@ class ReaderTest < Test::Unit::TestCase
     assert_empty crate.data_entities
   end
 
-  private
+  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
+
+  test 'protect against zip-slip' do
+    Dir.mktmpdir do |dir|
+      subdir = ::File.join(dir, 'subdir')
+      ::Dir.mkdir(subdir)
+
+      # Relative
+      e = check_exception(ROCrate::ReadException) do
+        ROCrate::Reader.unzip_file_to(fixture_file('unsafe/relative0.zip').path, subdir)
+      end
+      assert_include e.message, 'Unsafe path in zip entry: ../moo'
+      refute ::File.exist?(::File.join(dir, 'moo'))
+
+      e = check_exception(ROCrate::ReadException) do
+        ROCrate::Reader.unzip_io_to(fixture_file('unsafe/relative0.zip'), subdir)
+      end
+      assert_include e.message, 'Unsafe path in zip entry: ../moo'
+      refute ::File.exist?(::File.join(dir, 'moo'))
 
-  def check_exception(exception_class)
-    e = nil
-    assert_raise(exception_class) do
+      # Absolute
+      e = check_exception(ROCrate::ReadException) do
+        ROCrate::Reader.unzip_file_to(fixture_file('unsafe/absolute1.zip').path, subdir)
+      end
+      assert_include e.message, 'Unsafe path in zip entry: /tmp/moo'
+
+      e = check_exception(ROCrate::ReadException) do
+        ROCrate::Reader.unzip_io_to(fixture_file('unsafe/absolute1.zip'), subdir)
+      end
+      assert_include e.message, 'Unsafe path in zip entry: /tmp/moo'
+
+      # Simulate ArgumentError in safe_join
       begin
-        yield
-      rescue exception_class => e
-        raise e
+        original_expand_path = Pathname.instance_method(:expand_path)
+        Pathname.define_method(:expand_path) do |*args|
+          raise ArgumentError, 'Oh no'
+        end
+        e = check_exception(ROCrate::ReadException) do
+          ROCrate::Reader.unzip_file_to(fixture_file('unsafe/absolute1.zip').path, subdir)
+        end
+        assert_include e.message, 'Unsafe path in zip entry: /tmp/moo'
+      ensure
+        Pathname.define_method(:expand_path, original_expand_path)
       end
     end
+  end
+
+  test 'reads spec 1.1 RO-Crate and preserves version' do
+    crate = ROCrate::Reader.read(fixture_file('crate-spec1.1').path)
 
-    e
+    assert_equal '1.1', crate.metadata.version
+    assert_equal 'https://w3id.org/ro/crate/1.1', crate.metadata.spec_url
+    assert_equal 'https://w3id.org/ro/crate/1.1/context', crate.metadata.context_url
   end
 end

data/test/test_helper.rb

@@ -5,10 +5,37 @@ require 'test/unit'
 require 'ro_crate'
 require 'webmock/test_unit'
 
+class Test::Unit::TestCase
+  def teardown
+    self._opened_files.each do |f|
+      f.close unless f.closed?
+    end
+  end
+
+  def _opened_files
+    @opened_files ||= []
+  end
+end
+
 def fixture_file(name, *args)
-  ::File.open(::File.join(fixture_dir, name), *args)
+  f = ::File.open(::File.join(fixture_dir, name), *args)
+  self._opened_files << f
+  f
 end
 
 def fixture_dir
   ::File.join(::File.dirname(__FILE__), 'fixtures')
 end
+
+def check_exception(exception_class)
+  e = nil
+  assert_raise(exception_class) do
+    begin
+      yield
+    rescue exception_class => e
+      raise e
+    end
+  end
+
+  e
+end

data/test/writer_test.rb

@@ -274,4 +274,39 @@ class WriterTest < Test::Unit::TestCase
       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 +1,13 @@
 --- !ruby/object:Gem::Specification
 name: ro-crate
 version: !ruby/object:Gem::Version
-  version: 0.5.2
+  version: 0.6.0
 platform: ruby
 authors:
 - Finn Bacall
-autorequire: 
 bindir: bin
 cert_chain: []
-date: 2024-04-16 00:00:00.000000000 Z
+date: 1980-01-02 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: addressable
@@ -19,7 +18,7 @@ dependencies:
         version: '2.7'
     - - "<"
       - !ruby/object:Gem::Version
-        version: '2.9'
+        version: '3'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
@@ -29,35 +28,41 @@ dependencies:
         version: '2.7'
     - - "<"
       - !ruby/object:Gem::Version
-        version: '2.9'
+        version: '3'
 - !ruby/object:Gem::Dependency
   name: rubyzip
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: 2.0.0
+        version: '2.3'
+    - - "<"
+      - !ruby/object:Gem::Version
+        version: '4'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '2.3'
+    - - "<"
       - !ruby/object:Gem::Version
-        version: 2.0.0
+        version: '4'
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 13.0.0
+        version: 13.4.2
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 13.0.0
+        version: 13.4.2
 - !ruby/object:Gem::Dependency
   name: test-unit
   requirement: !ruby/object:Gem::Requirement
@@ -106,29 +111,28 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 3.8.3
+        version: 3.26.2
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 3.8.3
+        version: 3.26.2
 - !ruby/object:Gem::Dependency
   name: rexml
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 3.2.5
+        version: 3.4.4
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 3.2.5
-description: 
+        version: 3.4.4
 email: finn.bacall@manchester.ac.uk
 executables: []
 extensions: []
@@ -200,7 +204,9 @@ files:
 - test/fixtures/directory_crate/ro-crate-preview.html
 - test/fixtures/file with spaces.txt
 - test/fixtures/info.txt
+- test/fixtures/just_a_zip.zip
 - 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
@@ -209,6 +215,8 @@ 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
@@ -229,6 +237,8 @@ files:
 - test/fixtures/unlinked_entity_crate/test/test1/input.bed
 - test/fixtures/unlinked_entity_crate/test/test1/output_exp.bed
 - test/fixtures/unlinked_entity_crate/test/test1/sort-and-change-case-test.yml
+- test/fixtures/unsafe/absolute1.zip
+- test/fixtures/unsafe/relative0.zip
 - test/fixtures/uri_heavy_crate/main.nf
 - test/fixtures/uri_heavy_crate/ro-crate-metadata.json
 - test/fixtures/uri_heavy_crate/ro-crate-preview.html
@@ -2462,6 +2472,7 @@ 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
@@ -2469,7 +2480,6 @@ homepage: https://github.com/ResearchObject/ro-crate-ruby
 licenses:
 - MIT
 metadata: {}
-post_install_message: 
 rdoc_options: []
 require_paths:
 - lib
@@ -2477,15 +2487,14 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: '0'
+      version: 2.7.0
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.2.33
-signing_key: 
+rubygems_version: 3.6.9
 specification_version: 4
 summary: Create, manipulate, read RO-Crates.
 test_files: []