ro-crate 0.4.1 → 0.4.6

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 9b5b7dfe4513a995ac2d5040a0fb94380d0a4da0a2181d2b0978a0dfd667715c
-  data.tar.gz: c5f6a40b5d3eac383ddecfa79088ecf102cf54413000944c619b4936fd775247
+  metadata.gz: 4880110308b68d8bc35333b1fc8a8396ea30e36069f92e059b8c57ec3567d33e
+  data.tar.gz: 77a17a0436f2dea14254a3501f9db349eed5460851d94ab4e87adb7be83e1b38
 SHA512:
-  metadata.gz: bf966c315804ae8855683eceac6ba725ad607682a630873f2d84ceee8471fe23c22b00127e9391d7b1737aa0e1c8c65e54be085e2a7c47a4436aece62fa56d0f
-  data.tar.gz: 2464ebbbb77c3d71c9a47da2908c61f8d90cd76f043f00f748d1ccab41270b2d0ff9255ba06632dbdddf7d1d295e1204a314fc4f0cef69eb9419d213fc0a0232
+  metadata.gz: 711a45d7aaa63f8a5a7bba78e433d82875311472d6f4abfd6d388dd8565a7707036152c81de4059fd92da5b7851925caf9d808f39d115752e68eaddbdc85bac1
+  data.tar.gz: ce14efaf63e7224adc79cdb11d27bdec933be290ccf60196014cb7ce9380136451265a8f814e1ca7b70286fc32852024d429334bbaab18208d31095cd619dc9e

data/.ruby-version

@@ -1 +1 @@
-ruby-2.4.9
+ruby-2.6.6

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    ro-crate (0.4.1)
+    ro-crate (0.4.6)
       addressable (~> 2.7.0)
       rubyzip (~> 2.0.0)
 

data/README.md

@@ -1,9 +1,9 @@
 # ro-crate-ruby
 
-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 1.1 of the specification).
 
-* RO Crate - https://researchobject.github.io/ro-crate/
-* RO Crate spec (1.1) - https://researchobject.github.io/ro-crate/1.1/
+* RO-Crate - https://researchobject.github.io/ro-crate/
+* RO-Crate spec (1.1) - https://researchobject.github.io/ro-crate/1.1/
 
 ## Installation
 
@@ -31,13 +31,17 @@ crate = ROCrate::Crate.new
 crate.add_file(File.open('Gemfile')) # Using IO-like objects
 crate.add_file('README.md') # or paths
 
+# Quickly add everything from a directory into the crate
+crate = ROCrate::Crate.new
+crate.add_all('workspace/secret_project/dataset123')
+
 # Write to a zip file
 ROCrate::Writer.new(crate).write_zip(File.new('ro_crate.zip', 'w'))
 
 # Write to a directory
 ROCrate::Writer.new(crate).write('./ro_crate_stuff')
 
-# Read an RO crate
+# Read an RO-Crate
 crate = ROCrate::Reader.read('./an_ro_crate_directory')
 
 # Make some changes
@@ -55,9 +59,9 @@ ext_file = crate.add_external_file('https://example.com/my_file.txt')
 ROCrate::Writer.new(crate).write('./an_ro_crate_directory')
 ```
 
-### RO Crate Preview
-A simple HTML preview page is generated when an RO Crate is written, containing a list of the crate's contents and some
-metadata. This preview is written to `ro-crate-preview.html` at the root of the RO Crate.
+### RO-Crate Preview
+A simple HTML preview page is generated when an RO-Crate is written, containing a list of the crate's contents and some
+metadata. This preview is written to `ro-crate-preview.html` at the root of the RO-Crate.
 
 The default template can be seen here [here](lib/ro_crate/ro-crate-preview.html.erb).
 

data/lib/ro_crate/json_ld_hash.rb

@@ -1,6 +1,6 @@
 module ROCrate
   ##
-  # A wrapper class for Hash that adds methods to dereference Entities within an RO Crate.
+  # A wrapper class for Hash that adds methods to dereference Entities within an RO-Crate.
   class JSONLDHash < ::Hash
     def initialize(graph, content = {})
       @graph = graph

data/lib/ro_crate/model/contextual_entity.rb

@@ -1,6 +1,6 @@
 module ROCrate
   ##
-  # A class to represent a "Contextual Entity" within an RO Crate.
+  # A class to represent a "Contextual Entity" within an RO-Crate.
   # Contextual Entities are used to describe and provide context to the Data Entities within the crate.
   class ContextualEntity < Entity
     def self.format_id(id)

data/lib/ro_crate/model/crate.rb

@@ -1,6 +1,6 @@
 module ROCrate
   ##
-  # A Ruby abstraction of an RO Crate.
+  # A Ruby abstraction of an RO-Crate.
   class Crate < Directory
     IDENTIFIER = './'.freeze
     attr_reader :data_entities
@@ -13,7 +13,7 @@ module ROCrate
     end
 
     ##
-    # Initialize an empty RO Crate.
+    # Initialize an empty RO-Crate.
     def initialize(id = IDENTIFIER, properties = {})
       @data_entities = []
       @contextual_entities = []
@@ -24,7 +24,7 @@ module ROCrate
     # Create a new file and add it to the crate.
     #
     # @param source [String, Pathname, ::File, #read, nil] The source on the disk where this file will be read.
-    # @param crate_path [String] The relative path within the RO crate where this file will be written.
+    # @param crate_path [String] The relative path within the RO-Crate where this file will be written.
     # @param entity_class [Class] The class to use to instantiate the Entity,
     #   useful if you have created a subclass of ROCrate::File that you want to use. (defaults to ROCrate::File).
     # @param properties [Hash{String => Object}] A hash of JSON-LD properties to associate with this file.
@@ -51,7 +51,7 @@ module ROCrate
     # Create a new directory and add it to the crate.
     #
     # @param source_directory [String, Pathname, ::File, #read, nil] The source directory that will be included in the crate.
-    # @param crate_path [String] The relative path within the RO crate where this directory will be written.
+    # @param crate_path [String] The relative path within the RO-Crate where this directory will be written.
     # @param entity_class [Class] The class to use to instantiate the Entity,
     #   useful if you have created a subclass of ROCrate::Directory that you want to use. (defaults to ROCrate::Directory).
     # @param properties [Hash{String => Object}] A hash of JSON-LD properties to associate with this directory.
@@ -61,6 +61,35 @@ module ROCrate
       entity_class.new(self, source_directory, crate_path, properties).tap { |e| add_data_entity(e) }
     end
 
+    ##
+    # Recursively add the contents of the given source directory at the root of the crate.
+    # Useful for quickly RO-Crate-ifying a directory.
+    # Creates data entities for each file/directory discovered (excluding the top level directory itself) if `create_entities` is true.
+    #
+    # @param source_directory [String, Pathname, ::File,] The source directory that will be included in the crate.
+    # @param create_entities [Boolean] Whether to create data entities for the added content, or just include them anonymously.
+    # @param include_hidden [Boolean] Whether to include hidden files, i.e. those prefixed by a `.` (period).
+    #
+    # @return [Array<DataEntity>] Any entities that were created from the directory contents. Will be empty if `create_entities` was false.
+    def add_all(source_directory, create_entities = true, include_hidden: false)
+      added = []
+
+      if create_entities
+        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
+          if source_path.directory?
+            added << add_directory(source_path, rel_path)
+          else
+            added << add_file(source_path, rel_path)
+          end
+        end
+      else
+        populate_entries(Pathname.new(::File.expand_path(source_directory)), include_hidden: include_hidden)
+      end
+
+      added
+    end
+
     ##
     # Create a new ROCrate::Person and add it to the crate
     #
@@ -119,7 +148,7 @@ module ROCrate
     end
 
     ##
-    # The RO crate metadata file
+    # The RO-Crate metadata file
     #
     # @return [Metadata]
     def metadata
@@ -127,7 +156,7 @@ module ROCrate
     end
 
     ##
-    # The RO crate preview file
+    # The RO-Crate preview file
     #
     # @return [Preview]
     def preview
@@ -143,7 +172,7 @@ module ROCrate
     end
 
     ##
-    # Entities for the metadata file and crate itself, which should be present in all RO crates.
+    # Entities for the metadata file and crate itself, which should be present in all RO-Crates.
     #
     # @return [Array<Entity>]
     def default_entities
@@ -186,18 +215,22 @@ module ROCrate
       entity.class.new(crate, entity.id, entity.raw_properties)
     end
 
+    alias_method :own_entries, :entries
     ##
-    # A map of all the files/directories contained in the RO crate, where the key is the destination path within the crate
-    # and the value is an Entry where the source data can be read.
+    # # The RO-Crate's "payload" of the crate - a map of all the files/directories contained in the RO-Crate, where the
+    # key is the destination path within the crate and the value is an Entry where the source data can be read.
     #
     # @return [Hash{String => Entry}>]
     def entries
-      entries = {}
-
-      (default_entities | data_entities).each do |entity|
-        next if entity == self
-        entity.entries.each do |path, io|
-          entries[path] = io
+      # Gather a map of entries, starting from the crate itself, then any directory data entities, then finally any
+      # file data entities. This ensures in the case of a conflict, the more "specific" data entities take priority.
+      entries = own_entries
+      non_self_entities = default_entities.reject { |e| e == self }
+      sorted_entities = (non_self_entities | data_entities).sort_by { |e| e.is_a?(ROCrate::Directory) ? 0 : 1 }
+
+      sorted_entities.each do |entity|
+        entity.entries.each do |path, entry|
+          entries[path] = entry
         end
       end
 
@@ -207,5 +240,11 @@ module ROCrate
     def get_binding
       binding
     end
+
+    private
+
+    def full_entry_path(relative_path)
+      relative_path
+    end
   end
 end

data/lib/ro_crate/model/data_entity.rb

@@ -1,6 +1,6 @@
 module ROCrate
   ##
-  # A class to represent a "Data Entity" within an RO Crate.
+  # A class to represent a "Data Entity" within an RO-Crate.
   # Data Entities are the actual physical files and directories within the Crate.
   class DataEntity < Entity
     def self.format_id(id)

data/lib/ro_crate/model/directory.rb

@@ -12,37 +12,34 @@ module ROCrate
     # Create a new Directory. PLEASE NOTE, the new directory will not be added to the crate. To do this, call
     # Crate#add_data_entity, or just use Crate#add_directory.
     #
-    # @param crate [Crate] The RO crate that owns this directory.
+    # @param crate [Crate] The RO-Crate that owns this directory.
     # @param source_directory [String, Pathname, ::File, nil] The source directory that will be included in the crate.
-    # @param crate_path [String] The relative path within the RO crate where this directory will be written.
+    # @param crate_path [String] The relative path within the RO-Crate where this directory will be written.
     # @param properties [Hash{String => Object}] A hash of JSON-LD properties to associate with this directory.
     def initialize(crate, source_directory = nil, crate_path = nil, properties = {})
       @directory_entries = {}
 
       if source_directory
-        raise 'Not a directory' unless ::File.directory?(source_directory)
         source_directory = Pathname.new(::File.expand_path(source_directory))
+        @entry = Entry.new(source_directory)
+        populate_entries(source_directory)
         crate_path = source_directory.basename.to_s if crate_path.nil?
-
-        Dir.chdir(source_directory) { Dir.glob('**/*') }.each do |rel_path|
-          source_path = Pathname.new(::File.join(source_directory, rel_path)).expand_path
-          @directory_entries[rel_path] = Entry.new(source_path)
-        end
       end
 
       super(crate, crate_path, properties)
     end
 
     ##
-    # A map of all the files/directories under this directory, where the key is the destination path within the crate
-    # and the value is an Entry where the source data can be read.
+    # The "payload" of this directory - a map of all the files/directories, where the key is the destination path
+    # within the crate and the value is an Entry where the source data can be read.
     #
     # @return [Hash{String => Entry}>]
     def entries
       entries = {}
+      entries[filepath.chomp('/')] = @entry if @entry
 
       @directory_entries.each do |rel_path, entry|
-        entries[::File.join(filepath, rel_path)] = entry
+        entries[full_entry_path(rel_path)] = entry
       end
 
       entries
@@ -50,6 +47,37 @@ module ROCrate
 
     private
 
+    ##
+    # Populate this directory with files/directories from a given source directory on disk.
+    #
+    # @param source_directory [Pathname] The source directory to populate from.
+    # @param include_hidden [Boolean] Whether to include hidden files, i.e. those prefixed by a `.` (period).
+    #
+    # @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)
+      @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
+        @directory_entries[rel_path] = Entry.new(source_path)
+      end
+
+      @directory_entries
+    end
+
+    def full_entry_path(relative_path)
+      ::File.join(filepath, relative_path)
+    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|
+        path == '.' || path == '..' || path.end_with?('/.')
+      end
+    end
+
     def default_properties
       super.merge(
         '@id' => "#{SecureRandom.uuid}/",

data/lib/ro_crate/model/entity.rb

@@ -1,7 +1,7 @@
 module ROCrate
   ##
-  # A generic "Entity" within an RO Crate. It has an identifier and a set of properties, and will be referenced in the
-  # RO Crate Metadata's @graph.
+  # A generic "Entity" within an RO-Crate. It has an identifier and a set of properties, and will be referenced in the
+  # RO-Crate Metadata's @graph.
   class Entity
     attr_reader :crate
     attr_reader :properties
@@ -60,7 +60,7 @@ module ROCrate
     ##
     # Automatically replace an Entity or Array of Entities with a reference or Array of references. Also associates
     # the Entity/Entities with the current crate. This is useful for maintaining the flat @graph of entities that the
-    # RO crate metadata file requires.
+    # RO-Crate metadata file requires.
     #
     # @param value [Entity, Array<Entity>, Object] A value that may be reference or array of references.
     # @return [Hash, Array<Hash>, Object] Return a reference, Array of references, or just the object itself if

data/lib/ro_crate/model/entry.rb

@@ -1,6 +1,6 @@
 module ROCrate
   ##
-  # A class to represent a "physical" file or directory within an RO crate.
+  # A class to represent a "physical" file or directory within an RO-Crate.
   # It handles the actual reading/writing of bytes.
   class Entry
     attr_reader :source

data/lib/ro_crate/model/file.rb

@@ -8,9 +8,9 @@ module ROCrate
     # Create a new ROCrate::File. PLEASE NOTE, the new file will not be added to the crate. To do this, call
     # Crate#add_data_entity, or just use Crate#add_file.
     #
-    # @param crate [Crate] The RO crate that owns this file.
+    # @param crate [Crate] The RO-Crate that owns this file.
     # @param source [String, Pathname, ::File, #read, URI, nil] The source on the disk (or on the internet if a URI) where this file will be read.
-    # @param crate_path [String] The relative path within the RO crate where this file will be written.
+    # @param crate_path [String] The relative path within the RO-Crate where this file will be written.
     # @param properties [Hash{String => Object}] A hash of JSON-LD properties to associate with this file.
     def initialize(crate, source, crate_path = nil, properties = {})
       if crate_path.is_a?(Hash) && properties.empty?
@@ -52,7 +52,9 @@ module ROCrate
     end
 
     ##
-    # A map of all the files/directories associated with this File. Should only be a single key and value.
+    # The "payload". A map with a single key and value, of the relative filepath within the crate, to the source on disk
+    # where the actual bytes of the file can be read. Blank if remote.
+    #
     # (for compatibility with Directory#entries)
     #
     # @return [Hash{String => Entry}>] The key is the location within the crate, and the value is an Entry.

data/lib/ro_crate/model/remote_entry.rb

@@ -1,6 +1,6 @@
 module ROCrate
   ##
-  # A class to represent a reference within an RO crate, to a remote file held on the internet somewhere.
+  # A class to represent a reference within an RO-Crate, to a remote file held on the internet somewhere.
   # It handles the actual reading/writing of bytes.
   class RemoteEntry
     attr_reader :uri

data/lib/ro_crate/reader.rb

@@ -1,13 +1,13 @@
 module ROCrate
   ##
-  # A class to handle reading of RO Crates from Zip files or directories.
+  # A class to handle reading of RO-Crates from Zip files or directories.
   class Reader
     ##
-    # Reads an RO Crate from a directory of zip file.
+    # Reads an RO-Crate from a directory of zip file.
     #
     # @param source [String, ::File, Pathname] The source location for the crate.
     # @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.
+    # @return [Crate] The RO-Crate.
     def self.read(source, target_dir: Dir.mktmpdir)
       raise "Not a directory!" unless ::File.directory?(target_dir)
       if ::File.directory?(source)
@@ -37,12 +37,12 @@ module ROCrate
     end
 
     ##
-    # Reads an RO Crate from a zip file. It first extracts the Zip file to a temporary directory, and then calls
+    # Reads an RO-Crate from a zip file. It first extracts the Zip file to a temporary directory, and then calls
     # #read_directory.
     #
     # @param source [String, ::File, Pathname] The location of the zip file.
     # @param target_dir [String, ::File, Pathname] The target directory where the crate should be unzipped.
-    # @return [Crate] The RO Crate.
+    # @return [Crate] The RO-Crate.
     def self.read_zip(source, target_dir: Dir.mktmpdir)
       unzip_to(source, target_dir)
 
@@ -50,10 +50,10 @@ module ROCrate
     end
 
     ##
-    # Reads an RO Crate from a directory.
+    # Reads an RO-Crate from a directory.
     #
     # @param source [String, ::File, Pathname] The location of the directory.
-    # @return [Crate] The RO Crate.
+    # @return [Crate] The RO-Crate.
     def self.read_directory(source)
       source = ::File.expand_path(source)
       metadata_file = Dir.entries(source).detect { |entry| entry == ROCrate::Metadata::IDENTIFIER ||
@@ -68,7 +68,7 @@ module ROCrate
     end
 
     ##
-    # Extracts all the entities from the @graph of the RO Crate Metadata.
+    # Extracts all the entities from the @graph of the RO-Crate Metadata.
     #
     # @param metadata_json [String] A string containing the metadata JSON.
     # @return [Hash{String => Hash}] A Hash of all the entities, mapped by their @id.
@@ -99,12 +99,15 @@ module ROCrate
     # Create a crate from the given set of entities.
     #
     # @param entity_hash [Hash{String => Hash}] A Hash containing all the entities in the @graph, mapped by their @id.
-    # @param source [String, ::File, Pathname] The location of the RO Crate being read.
-    # @return [Crate] The RO Crate.
+    # @param source [String, ::File, Pathname] The location of the RO-Crate being read.
+    # @return [Crate] The RO-Crate.
     def self.build_crate(entity_hash, source)
       ROCrate::Crate.new.tap do |crate|
         crate.properties = entity_hash.delete(ROCrate::Crate::IDENTIFIER)
         crate.metadata.properties = entity_hash.delete(ROCrate::Metadata::IDENTIFIER)
+        preview_properties = entity_hash.delete(ROCrate::Preview::IDENTIFIER)
+        crate.preview.properties = preview_properties if preview_properties
+        crate.add_all(source, false)
         extract_data_entities(crate, source, entity_hash).each do |entity|
           crate.add_data_entity(entity)
         end
@@ -118,8 +121,8 @@ module ROCrate
     ##
     # Discover data entities from the `hasPart` property of a crate, and create DataEntity objects for them.
     # Entities are looked up in the given `entity_hash` (and then removed from it).
-    # @param crate [Crate] The RO Crate being read.
-    # @param source [String, ::File, Pathname] The location of the RO Crate being read.
+    # @param crate [Crate] The RO-Crate being read.
+    # @param source [String, ::File, Pathname] The location of the RO-Crate being read.
     # @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)
@@ -135,7 +138,7 @@ module ROCrate
 
     ##
     # Create appropriately specialized ContextualEntity objects from the given hash of entities and their properties.
-    # @param crate [Crate] The RO Crate being read.
+    # @param crate [Crate] The RO-Crate being read.
     # @param entity_hash [Hash] A Hash containing all the entities in the @graph, mapped by their @id.
     # @return [Array<ContextualEntity>] The extracted ContextualEntity objects.
     def self.extract_contextual_entities(crate, entity_hash)
@@ -152,8 +155,8 @@ module ROCrate
 
     ##
     # Create a DataEntity of the given class.
-    # @param crate [Crate] The RO Crate being read.
-    # @param source [String, ::File, Pathname] The location of the RO Crate being read.
+    # @param crate [Crate] The RO-Crate being read.
+    # @param source [String, ::File, Pathname] The location of the RO-Crate being read.
     # @param entity_props [Hash] A Hash containing the entity's properties, including its @id.
     # @return [ROCrate::File, ROCrate::Directory, nil] The DataEntity object,
     #          or nil if it referenced a local file that wasn't found.

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

@@ -1,13 +1,13 @@
 <!DOCTYPE html>
 <html>
 <head>
-  <title><%= name || "New RO Crate" %></title>
+  <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="keywords" content="RO Crate">
+  <meta name="keywords" content="RO-Crate">
 </head>
 <body>
-  <h1><%= name || "New RO Crate" %></h1>
+  <h1><%= name || "New RO-Crate" %></h1>
   <% if url %>
     <a href="<%= url %>" target="_blank"><%= url %></a>
   <% end %>

data/lib/ro_crate/writer.rb

@@ -1,10 +1,10 @@
 module ROCrate
   ##
-  # A class to handle writing of RO Crates to Zip files or directories.
+  # A class to handle writing of RO-Crates to Zip files or directories.
   class Writer
     ##
     # Initialize a new Writer for the given Crate.
-    # @param crate [Crate] The RO Crate to be written.
+    # @param crate [Crate] The RO-Crate to be written.
     def initialize(crate)
       @crate = crate
     end
@@ -35,7 +35,7 @@ module ROCrate
     ##
     # Write the crate to a zip file.
     #
-    # @param destination [String, ::File] The destination where to write the RO Crate zip.
+    # @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|
         @crate.entries.each do |path, entry|

data/ro_crate.gemspec

@@ -1,7 +1,7 @@
 Gem::Specification.new do |s|
   s.name        = 'ro-crate'
-  s.version     = '0.4.1'
-  s.summary     = 'Create, manipulate, read RO crates.'
+  s.version     = '0.4.6'
+  s.summary     = 'Create, manipulate, read RO-Crates.'
   s.authors     = ['Finn Bacall']
   s.email       = 'finn.bacall@manchester.ac.uk'
   s.files       = `git ls-files`.split("\n")

data/test/crate_test.rb

@@ -198,4 +198,99 @@ class CrateTest < Test::Unit::TestCase
     assert_equal file, new_crate.get('some/file.txt')
     assert_equal file, new_crate.get('http://mycoolwebsite.golf/ro_crate/some/file.txt')
   end
+
+  test 'can add an entire directory tree as data entities' do
+    crate = ROCrate::Crate.new
+    entities = crate.add_all(fixture_file('directory').path, include_hidden: true)
+
+    paths = crate.entries.keys
+    assert_equal 11, paths.length
+    assert_includes paths, 'data'
+    assert_includes paths, 'root.txt'
+    assert_includes paths, 'info.txt'
+    assert_includes paths, 'data/binary.jpg'
+    assert_includes paths, 'data/info.txt'
+    assert_includes paths, 'data/nested.txt'
+    assert_includes paths, '.dotfile'
+    assert_includes paths, '.dir'
+    assert_includes paths, '.dir/test.txt'
+    assert_includes paths, 'ro-crate-metadata.json'
+    assert_includes paths, 'ro-crate-preview.html'
+
+    assert_equal 9, entities.length
+    assert_equal 'ROCrate::Directory', crate.dereference('data/').class.name
+    assert_equal 'ROCrate::File', crate.dereference('root.txt').class.name
+    assert_equal 'ROCrate::File', crate.dereference('info.txt').class.name
+    assert_equal 'ROCrate::File', crate.dereference('data/binary.jpg').class.name
+    assert_equal 'ROCrate::File', crate.dereference('data/info.txt').class.name
+    assert_equal 'ROCrate::File', crate.dereference('data/nested.txt').class.name
+    assert_equal 'ROCrate::File', crate.dereference('.dotfile').class.name
+    assert_equal 'ROCrate::Directory', crate.dereference('.dir/').class.name
+    assert_equal 'ROCrate::File', crate.dereference('.dir/test.txt').class.name
+
+    assert_equal "5678\n", crate.dereference('data/info.txt').source.read
+    assert_equal "Am I included?\n", crate.dereference('.dotfile').source.read
+  end
+
+  test 'can create an RO-Crate using content from a given directory' do
+    crate = ROCrate::Crate.new
+    entities = crate.add_all(fixture_file('directory').path, false, include_hidden: true)
+
+    assert_empty entities
+
+    paths = crate.entries.keys
+    assert_equal 11, paths.length
+    assert_includes paths, 'data'
+    assert_includes paths, 'root.txt'
+    assert_includes paths, 'info.txt'
+    assert_includes paths, 'data/binary.jpg'
+    assert_includes paths, 'data/info.txt'
+    assert_includes paths, 'data/nested.txt'
+    assert_includes paths, '.dotfile'
+    assert_includes paths, '.dir'
+    assert_includes paths, '.dir/test.txt'
+    assert_includes paths, 'ro-crate-metadata.json'
+    assert_includes paths, 'ro-crate-preview.html'
+
+    # Should not create any data entities
+    assert_nil crate.dereference('data/')
+    assert_nil crate.dereference('root.txt')
+    assert_nil crate.dereference('info.txt')
+    assert_nil crate.dereference('data/binary.jpg')
+    assert_nil crate.dereference('data/info.txt')
+    assert_nil crate.dereference('data/nested.txt')
+    assert_nil crate.dereference('.dotfile')
+  end
+
+  test 'can create an RO-Crate using content from a given directory, excluding hidden files' do
+    crate = ROCrate::Crate.new
+    entities = crate.add_all(fixture_file('directory').path)
+
+    paths = crate.entries.keys
+    assert_equal 8, paths.length
+    assert_includes paths, 'data'
+    assert_includes paths, 'root.txt'
+    assert_includes paths, 'info.txt'
+    assert_includes paths, 'data/binary.jpg'
+    assert_includes paths, 'data/info.txt'
+    assert_includes paths, 'data/nested.txt'
+    assert_not_includes paths, '.dotfile'
+    assert_not_includes paths, '.dir'
+    assert_not_includes paths, '.dir/test.txt'
+    assert_includes paths, 'ro-crate-metadata.json'
+    assert_includes paths, 'ro-crate-preview.html'
+
+    assert_equal 6, entities.length
+    assert_equal 'ROCrate::Directory', crate.dereference('data/').class.name
+    assert_equal 'ROCrate::File', crate.dereference('root.txt').class.name
+    assert_equal 'ROCrate::File', crate.dereference('info.txt').class.name
+    assert_equal 'ROCrate::File', crate.dereference('data/binary.jpg').class.name
+    assert_equal 'ROCrate::File', crate.dereference('data/info.txt').class.name
+    assert_equal 'ROCrate::File', crate.dereference('data/nested.txt').class.name
+    assert_nil crate.dereference('.dotfile')
+    assert_nil crate.dereference('.dir/')
+    assert_nil crate.dereference('.dir/test.txt')
+
+    assert_equal "5678\n", crate.dereference('data/info.txt').source.read
+  end
 end

data/test/fixtures/directory/.dir/test.txt

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

data/test/fixtures/directory/.dotfile

@@ -0,0 +1 @@
+Am I included?

data/test/fixtures/directory_crate/ro-crate-metadata.jsonld

@@ -8,6 +8,13 @@
         "@id": "./"
       }
     },
+    {
+      "@id": "ro-crate-preview.html",
+      "@type": "CreativeWork",
+      "about": {
+        "@id": "./"
+      }
+    },
     {
       "@id": "./",
       "@type": "Dataset",

data/test/fixtures/directory_crate/ro-crate-preview.html

@@ -0,0 +1,66 @@
+<!DOCTYPE html>
+<html>
+<head>
+  <title>New RO-Crate</title>
+  <script type="application/ld+json">{
+  "@context": "https://w3id.org/ro/crate/1.1/context",
+  "@graph": [
+    {
+      "@id": "ro-crate-metadata.jsonld",
+      "@type": "CreativeWork",
+      "about": {
+        "@id": "./"
+      }
+    },
+    {
+      "@id": "ro-crate-preview.html",
+      "@type": "CreativeWork",
+      "about": {
+        "@id": "./"
+      }
+    },
+    {
+      "@id": "./",
+      "@type": "Dataset",
+      "hasPart": [
+        {
+          "@id": "fish/"
+        }
+      ]
+    },
+    {
+      "@id": "fish/",
+      "@type": "Dataset"
+    }
+  ]
+}</script>
+  <meta name="generator" content="https://github.com/fbacall/ro-crate-ruby">
+  <meta name="keywords" content="RO-Crate">
+</head>
+<body>
+  <h1>New RO-Crate</h1>
+  
+  <p>
+    
+  </p>
+  <dl>
+    
+    
+    
+    
+  </dl>
+
+  <h2>Contents</h2>
+  <ul>
+    
+      <li id="__data_entity_fish/">
+        
+          <strong>fish/</strong>
+        
+        
+        
+      </li>
+    
+  </ul>
+</body>
+</html>

data/test/fixtures/sparse_directory_crate/fish/data/info.txt

@@ -0,0 +1 @@
+5678

data/test/fixtures/sparse_directory_crate/fish/data/nested.txt

@@ -0,0 +1 @@
+I'm nested

data/test/fixtures/sparse_directory_crate/fish/info.txt

@@ -0,0 +1 @@
+1234

data/test/fixtures/sparse_directory_crate/fish/root.txt

@@ -0,0 +1 @@
+I'm at the root

data/test/fixtures/sparse_directory_crate/listed_file.txt

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

data/test/fixtures/sparse_directory_crate/ro-crate-metadata.jsonld

@@ -0,0 +1,32 @@
+{
+  "@context": "https://w3id.org/ro/crate/1.0/context",
+  "@graph": [
+    {
+      "@id": "ro-crate-metadata.jsonld",
+      "@type": "CreativeWork",
+      "about": {
+        "@id": "./"
+      }
+    },
+    {
+      "@id": "ro-crate-preview.html",
+      "@type": "CreativeWork",
+      "about": {
+        "@id": "./"
+      }
+    },
+    {
+      "@id": "./",
+      "@type": "Dataset",
+      "hasPart": [
+        {
+          "@id": "listed_file.txt"
+        }
+      ]
+    },
+    {
+      "@id": "listed_file.txt",
+      "@type": "File"
+    }
+  ]
+}

data/test/fixtures/sparse_directory_crate/ro-crate-preview.html

@@ -0,0 +1,66 @@
+<!DOCTYPE html>
+<html>
+<head>
+  <title>New RO-Crate</title>
+  <script type="application/ld+json">{
+  "@context": "https://w3id.org/ro/crate/1.1/context",
+  "@graph": [
+    {
+      "@id": "ro-crate-metadata.jsonld",
+      "@type": "CreativeWork",
+      "about": {
+        "@id": "./"
+      }
+    },
+    {
+      "@id": "ro-crate-preview.html",
+      "@type": "CreativeWork",
+      "about": {
+        "@id": "./"
+      }
+    },
+    {
+      "@id": "./",
+      "@type": "Dataset",
+      "hasPart": [
+        {
+          "@id": "fish/"
+        }
+      ]
+    },
+    {
+      "@id": "fish/",
+      "@type": "Dataset"
+    }
+  ]
+}</script>
+  <meta name="generator" content="https://github.com/fbacall/ro-crate-ruby">
+  <meta name="keywords" content="RO-Crate">
+</head>
+<body>
+  <h1>New RO-Crate</h1>
+  
+  <p>
+    
+  </p>
+  <dl>
+    
+    
+    
+    
+  </dl>
+
+  <h2>Contents</h2>
+  <ul>
+    
+      <li id="__data_entity_fish/">
+        
+          <strong>fish/</strong>
+        
+        
+        
+      </li>
+    
+  </ul>
+</body>
+</html>

data/test/fixtures/sparse_directory_crate/unlisted_file.txt

@@ -0,0 +1 @@
+456

data/test/reader_test.rb

@@ -109,11 +109,13 @@ class ReaderTest < Test::Unit::TestCase
   test 'reading from directory with directories' do
     crate = ROCrate::Reader.read_directory(fixture_file('directory_crate').path)
 
+    assert crate.entries.values.all? { |e| e.is_a?(ROCrate::Entry) }
     assert crate.entries['fish/info.txt']
     assert_equal '1234', crate.entries['fish/info.txt'].source.read.chomp
-    assert crate.entries['fish/root.txt']
+    refute crate.entries['fish/root.txt'].directory?
+    assert crate.entries['fish/data'].directory?
     assert crate.entries['fish/data/info.txt']
-    assert crate.entries['fish/data/nested.txt']
+    refute crate.entries['fish/data/nested.txt'].remote?
     assert crate.entries['fish/data/binary.jpg']
     assert_equal ['./', 'fish/', 'ro-crate-metadata.jsonld', 'ro-crate-preview.html'], crate.entities.map(&:id).sort
   end
@@ -161,4 +163,36 @@ class ReaderTest < Test::Unit::TestCase
     assert_equal 'http://example.com/external_ref.txt', ext_file.id
     assert_equal 'file contents', ext_file.source.read
   end
+
+  test 'reading from directory with unlisted files' do
+    crate = ROCrate::Reader.read_directory(fixture_file('sparse_directory_crate').path)
+
+    assert_equal 11, crate.entries.count
+    assert crate.entries['listed_file.txt']
+    assert crate.entries['unlisted_file.txt']
+    assert crate.entries['fish']
+    assert_equal '1234', crate.entries['fish/info.txt'].source.read.chomp
+    refute crate.entries['fish/root.txt'].directory?
+    assert crate.entries['fish/data'].directory?
+    assert crate.entries['fish/data/info.txt']
+    refute crate.entries['fish/data/nested.txt'].remote?
+    assert crate.entries['fish/data/binary.jpg']
+    assert_equal ['./', 'listed_file.txt', 'ro-crate-metadata.jsonld', 'ro-crate-preview.html'], crate.entities.map(&:id).sort
+  end
+
+  test 'reading from a zip with unlisted files' do
+    crate = ROCrate::Reader.read_zip(fixture_file('sparse_directory_crate.zip').path)
+
+    assert_equal 11, crate.entries.count
+    assert crate.entries['listed_file.txt']
+    assert crate.entries['unlisted_file.txt']
+    assert crate.entries['fish']
+    assert_equal '1234', crate.entries['fish/info.txt'].source.read.chomp
+    refute crate.entries['fish/root.txt'].directory?
+    assert crate.entries['fish/data'].directory?
+    assert crate.entries['fish/data/info.txt']
+    refute crate.entries['fish/data/nested.txt'].remote?
+    assert crate.entries['fish/data/binary.jpg']
+    assert_equal ['./', 'listed_file.txt', 'ro-crate-metadata.jsonld', 'ro-crate-preview.html'], crate.entities.map(&:id).sort
+  end
 end

data/test/writer_test.rb

@@ -99,4 +99,37 @@ class WriterTest < Test::Unit::TestCase
       end
     end
   end
+
+  test 'should write out same contents that it was created with' do
+    crate = ROCrate::Crate.new
+    crate.add_all(fixture_file('directory').path, false)
+
+    Dir.mktmpdir do |dir|
+      ROCrate::Writer.new(crate).write(dir)
+      assert ::File.exist?(::File.join(dir, ROCrate::Metadata::IDENTIFIER))
+      assert ::File.exist?(::File.join(dir, ROCrate::Preview::IDENTIFIER))
+      assert_equal 5, ::File.size(::File.join(dir, 'info.txt'))
+      assert_equal 2529, ::File.size(::File.join(dir, 'data', 'binary.jpg'))
+    end
+  end
+
+  test 'reading and writing out a directory crate produces an identical crate' do
+    fixture = fixture_file('sparse_directory_crate').path
+    Dir.mktmpdir do |dir|
+      dir = ::File.join(dir, 'new_directory')
+      crate = ROCrate::Reader.read(fixture)
+
+      ROCrate::Writer.new(crate).write(dir)
+      expected_files = Dir.chdir(fixture) { Dir.glob('**/*') }
+      actual_files =  Dir.chdir(dir) { Dir.glob('**/*') }
+      assert_equal expected_files, actual_files
+      expected_files.each do |file|
+        next if file == 'ro-crate-metadata.jsonld' # Expected context gets updated.
+        next if file == 'ro-crate-preview.html' # RO-Crate preview format changed
+        abs_file_path = ::File.join(fixture, file)
+        next if ::File.directory?(abs_file_path)
+        assert_equal ::File.read(abs_file_path), ::File.read(::File.join(dir, file)), "#{file} didn't match"
+      end
+    end
+  end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: ro-crate
 version: !ruby/object:Gem::Version
-  version: 0.4.1
+  version: 0.4.6
 platform: ruby
 authors:
 - Finn Bacall
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2021-01-18 00:00:00.000000000 Z
+date: 2021-02-25 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: addressable
@@ -149,6 +149,8 @@ files:
 - test/fixtures/crate-spec1.1/ro-crate-metadata.json
 - test/fixtures/data.csv
 - test/fixtures/directory.zip
+- test/fixtures/directory/.dir/test.txt
+- test/fixtures/directory/.dotfile
 - test/fixtures/directory/data/binary.jpg
 - test/fixtures/directory/data/info.txt
 - test/fixtures/directory/data/nested.txt
@@ -160,10 +162,21 @@ files:
 - test/fixtures/directory_crate/fish/info.txt
 - test/fixtures/directory_crate/fish/root.txt
 - test/fixtures/directory_crate/ro-crate-metadata.jsonld
+- test/fixtures/directory_crate/ro-crate-preview.html
 - test/fixtures/file with spaces.txt
 - test/fixtures/info.txt
 - test/fixtures/spaces/file with spaces.txt
 - test/fixtures/spaces/ro-crate-metadata.jsonld
+- test/fixtures/sparse_directory_crate.zip
+- test/fixtures/sparse_directory_crate/fish/data/binary.jpg
+- test/fixtures/sparse_directory_crate/fish/data/info.txt
+- test/fixtures/sparse_directory_crate/fish/data/nested.txt
+- test/fixtures/sparse_directory_crate/fish/info.txt
+- test/fixtures/sparse_directory_crate/fish/root.txt
+- test/fixtures/sparse_directory_crate/listed_file.txt
+- 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/workflow-0.2.0.zip
 - test/fixtures/workflow-0.2.0/Dockerfile
 - test/fixtures/workflow-0.2.0/README.md
@@ -2414,5 +2427,5 @@ requirements: []
 rubygems_version: 3.0.8
 signing_key: 
 specification_version: 4
-summary: Create, manipulate, read RO crates.
+summary: Create, manipulate, read RO-Crates.
 test_files: []