assembly-objectfile 1.7.1 → 1.7.2

data/lib/assembly-objectfile/object_file.rb

@@ -1,8 +1,6 @@
 module Assembly
-  
   # This class contains generic methods to operate on any file.
   class ObjectFile
-
     include Assembly::ObjectFileable
 
     # Class level method that given an array of strings, return the longest common initial path.  Useful for removing a common path from a set of filenames when producing content metadata
@@ -13,18 +11,17 @@ module Assembly
     # Example:
     # puts Assembly::ObjectFile.common_prefix(['/Users/peter/00/test.tif','/Users/peter/05/test.jp2'])  # '/Users/peter/0'
     def self.common_path(strings)
-      return nil if strings.size == 0
+      return nil if strings.empty?
+
       n = 0
       x = strings.last
-      n += 1 while strings.all? { |s| s[n] and s[n] == x[n] }
-      common_prefix=x[0...n]
-      if common_prefix[-1,1] != '/' # check if last element of the common string is the end of a directory
-        return common_prefix.split('/')[0..-2].join('/') + "/"  # if not, split string along directories, and reject last one
+      n += 1 while strings.all? { |s| s[n] && (s[n] == x[n]) }
+      common_prefix = x[0...n]
+      if common_prefix[-1, 1] != '/' # check if last element of the common string is the end of a directory
+        return common_prefix.split('/')[0..-2].join('/') + '/' # if not, split string along directories, and reject last one
       else
         return common_prefix # if it was, then return the common prefix directly
       end
     end
-        
   end
-  
 end

data/lib/assembly-objectfile/object_fileable.rb

@@ -1,297 +1,230 @@
 require 'mini_exiftool'
 require 'mime/types'
-#require 'checksum-tools'
+# require 'checksum-tools'
 
 module Assembly
-
-  # Namespace to include common behaviors we need for other classes in the gem
+  # Common behaviors we need for other classes in the gem
   module ObjectFileable
-
-    # path is the full path to the user provided image
-    attr_accessor :path
-        
-    # an optional label that can be set for each file -- if provided, this will be used as a resource label when generating content metadata (files bundlded together will just get the first's files label attribute if set)
-    attr_accessor :label
-    
-    # an optional hash that is used to set the file attributes (publish,preserve,shelve) for the given file when generating content metadata (if not supplied, mimetype defaults are used)
-    # e.g. {:preserve=>'yes',:shelve=>'no',:publish=>'no'}
-    attr_accessor :file_attributes
-    
-    # relative path is useful when generating content metadata, if you want the file ids in the content metadata to be something other than the full path, it can be set
-    #  if not, content metadata will get the full path 
-    attr_accessor :relative_path
-    
-    # provider checksums are optional checksums given by the provider used in content metadata generation
-    attr_accessor :provider_md5, :provider_sha1
-    
-    # Initialize file from given path.
-    #
-    # @param [String] path full path to the file to be worked with 
-    #
-    # Example:
+    attr_accessor :file_attributes, :label, :path, :provider_md5, :provider_sha1, :relative_path
+
+    # @param [String] path full path to the file to be worked with
+    # @param [Hash<Symbol => Object>] params options used during content metadata generation
+    # @option params [Hash<Symbol => ['yes', 'no']>] :file_attributes e.g. {:preserve=>'yes',:shelve=>'no',:publish=>'no'}, defaults pulled from mimetype
+    # @option params [String] :label a resource label (files bundlded together will just get the first file's label attribute if set)
+    # @option params [String] :provider_md5 pre-computed MD5 checksum
+    # @option params [String] :provider_sha1 pre-computed SHA1 checksum
+    # @option params [String] :relative_path if you want the file ids in the content metadata it can be set, otherwise content metadata will get the full path
+    # @example
     #   Assembly::ObjectFile.new('/input/path_to_file.tif')
-    def initialize(path,params={})
+    def initialize(path, params = {})
       @path = path
       @label = params[:label]
       @file_attributes = params[:file_attributes]
       @relative_path = params[:relative_path]
-      @provider_md5 = params[:provide_md5]
+      @provider_md5 = params[:provider_md5]
       @provider_sha1 = params[:provider_sha1]
     end
-    
-    # Returns base DPG name for the current file.
-    #
+
     # @return [String] DPG base filename, removing the extension and the '00','05', etc. placeholders
-    #
-    # Example:
-    #   source_file=Assembly::ObjectFile.new('/input/cy565rm7188_00_001.tif')
+    # @example
+    #   source_file = Assembly::ObjectFile.new('/input/cy565rm7188_00_001.tif')
     #   puts source_file.dpg_basename # "cy565rm7188_001"
     def dpg_basename
-      file_parts=File.basename(path,ext).split('_')
+      file_parts = File.basename(path, ext).split('_')
       file_parts.size == 3 ? "#{file_parts[0]}_#{file_parts[2]}" : filename_without_ext
     end
 
-    # Returns DPG subfolder for the current file.
-    #
-    # @return [String] DPG subfolder for the given filename, i.e. '00','05', etc. 
-    #
-    # Example:
-    #   source_file=Assembly::ObjectFile.new('/input/cy565rm7188_00_001.tif')
+    # @return [String] DPG subfolder for the given filename, i.e. '00','05', etc.
+    # @example
+    #   source_file = Assembly::ObjectFile.new('/input/cy565rm7188_00_001.tif')
     #   puts source_file.dpg_folder # "00"
     def dpg_folder
-      file_parts=File.basename(path,ext).split('_')
+      file_parts = File.basename(path, ext).split('_')
       file_parts.size == 3 ? file_parts[1] : ''
     end
 
-    # Returns base filename for the current file.
-    #
     # @return [String] base filename
-    #
-    # Example:
-    #   source_file=Assembly::ObjectFile.new('/input/path_to_file.tif')
+    # @example
+    #   source_file = Assembly::ObjectFile.new('/input/path_to_file.tif')
     #   puts source_file.filename # "path_to_file.tif"
     def filename
       File.basename(path)
     end
 
-    # Returns base directory path for the current file.
-    #
     # @return [String] base directory
-    #
-    # Example:
-    #   source_file=Assembly::ObjectFile.new('/input/path_to_file.tif')
-    #   puts source_file.dirname # "/input"    
+    # @example
+    #   source_file = Assembly::ObjectFile.new('/input/path_to_file.tif')
+    #   puts source_file.dirname # "/input"
     def dirname
       File.dirname(path)
     end
 
-    # Returns filename extension
-    #
     # @return [String] filename extension
-    #
-    # Example:
-    #   source_file=Assembly::ObjectFile.new('/input/path_to_file.tif')
+    # @example
+    #   source_file = Assembly::ObjectFile.new('/input/path_to_file.tif')
     #   puts source_file.ext # ".tif"
     def ext
       File.extname(path)
     end
-    
-    # Returns base filename without extension for the current file.
-    #
+
     # @return [String] base filename without extension
-    #
-    # Example:
-    #   source_file=Assembly::ObjectFile.new('/input/path_to_file.tif')
+    # @example
+    #   source_file = Assembly::ObjectFile.new('/input/path_to_file.tif')
     #   puts source_file.filename # "path_to_file"
     def filename_without_ext
-      File.basename(path,ext)
+      File.basename(path, ext)
     end
-    
-    # Returns exif information for the current file.
-    #
+
     # @return [MiniExiftool] exif information stored as a hash and an object
-    #
-    # Example:
-    #   source_file=Assembly::ObjectFile.new('/input/path_to_file.tif')
-    #   puts source_file.exif # gives hash with exif information
+    # @example
+    #   source_file = Assembly::ObjectFile.new('/input/path_to_file.tif')
+    #   puts source_file.exif # hash with exif information
     def exif
-      check_for_file unless @exif
-      begin
-        @exif ||= MiniExiftool.new(@path,replace_invalid_chars: '?')
-      rescue
-        @exif = nil
-      end
-    end
-
-    # Compute md5 checksum or return value if already computed
-    #
-    # @return [string] md5 checksum for given file
-    #
-    # Example:
-    #   source_file=Assembly::ObjectFile.new('/input/path_to_file.tif')
-    #   puts source_file.md5 # gives XXX123XXX1243XX1243
+      @exif ||= begin
+                  check_for_file
+                  MiniExiftool.new(path, replace_invalid_chars: '?')
+                rescue StandardError
+                  nil
+                end
+    end
+
+    # Computes md5 checksum or returns cached value
+    # @return [String] md5 checksum
+    # @example
+    #   source_file = Assembly::ObjectFile.new('/input/path_to_file.tif')
+    #   puts source_file.md5 # 'XXX123XXX1243XX1243'
     def md5
       check_for_file unless @md5
       @md5 ||= Digest::MD5.file(path).hexdigest
     end
 
-    # Compute sha1 checksum or return value if already computed
-    #
-    # @return [string] sha1 checksum for given file
-    #
-    # Example:
-    #   source_file=Assembly::ObjectFile.new('/input/path_to_file.tif')
-    #   puts source_file.sha1 # gives XXX123XXX1243XX1243    
+    # Computes sha1 checksum or return cached value
+    # @return [String] sha1 checksum
+    # @example
+    #   source_file = Assembly::ObjectFile.new('/input/path_to_file.tif')
+    #   puts source_file.sha1 # 'XXX123XXX1243XX1243'
     def sha1
       check_for_file unless @sha1
       @sha1 ||= Digest::SHA1.file(path).hexdigest
     end
 
     # Returns mimetype information for the current file based on file extension or exif data (if available)
-    #
-    # @return [string] mime type for supplied file
-    #
-    # Example:
-    #   source_file=Assembly::ObjectFile.new('/input/path_to_file.txt')
-    #   puts source_file.mimetype # gives 'text/plain'
+    # @return [String] mime type
+    # @example
+    #   source_file = Assembly::ObjectFile.new('/input/path_to_file.txt')
+    #   puts source_file.mimetype # 'text/plain'
     def mimetype
-      if @mimetype.nil? # if we haven't computed it yet once for this object, try and get the mimetype
-        if (!exif.nil? && !exif.mimetype.nil?)  # try and get the mimetype from the exif data if it exists
-          @mimetype = exif.mimetype
-        else # otherwise get it from the mime-types gem (using the file extension) assuming we can find, if not, return blank     
-          mimetype = MIME::Types.type_for(@path).first
-          @mimetype= mimetype ? mimetype.content_type : ''
+      @mimetype ||= begin
+        if exif && exif.mimetype # try exif first
+          exif.mimetype
+        else # otherwise get it from the mime-types gem (using the file extension), else blank
+          mtype = MIME::Types.type_for(path).first
+          mtype ? mtype.content_type : ''
         end
       end
-      return @mimetype 
     end
 
-    
     # Returns mimetype information for the current file based on unix file system command or exif data (if available).
-    #
-    # @return [string] mime type for supplied file
-    #
-    # Example:
-    #   source_file=Assembly::ObjectFile.new('/input/path_to_file.txt')
-    #   puts source_file.file_mimetype # gives 'text/plain'
+    # @return [String] mime type for supplied file
+    # @example
+    #   source_file = Assembly::ObjectFile.new('/input/path_to_file.txt')
+    #   puts source_file.file_mimetype # 'text/plain'
     def file_mimetype
-      check_for_file unless @file_mimetype
-      if @file_mimetype.nil? # if we haven't computed it yet once for this object, try and get the mimetype
-        @file_mimetype = `file --mime-type "#{@path}"`.gsub(/\n/,"").split(':')[1].strip # first try and get the mimetype from the unix file command
-        @file_mimetype = exif.mimetype if (!Assembly::TRUSTED_MIMETYPES.include?(@file_mimetype) && !exif.nil? && !exif.mimetype.nil?)  # if it's not a "trusted" mimetype and there is exif data; get the mimetype from the exif
+      @file_mimetype ||= begin
+        check_for_file
+        mtype = `file --mime-type "#{path}"`.delete("\n").split(':')[1].strip # first try and get the mimetype from the unix file command
+        prefer_exif = !Assembly::TRUSTED_MIMETYPES.include?(mtype) && exif && exif.mimetype # if it's not a "trusted" mimetype and there is exif data; get the mimetype from the exif
+        prefer_exif ? exif.mimetype : mtype
       end
-      return @file_mimetype 
     end
 
-    # Returns encoding information for the current file (only on unix based systems).
-    #
-    # @return [string] encoding for supplied file
-    #
-    # Example:
-    #   source_file=Assembly::ObjectFile.new('/input/path_to_file.txt')
-    #   puts source_file.encoding # gives 'us-ascii'
+    # @note Uses shell call to "file", only expected to work on unix based systems
+    # @return [String] encoding for supplied file
+    # @example
+    #   source_file = Assembly::ObjectFile.new('/input/path_to_file.txt')
+    #   puts source_file.encoding # 'us-ascii'
     def encoding
-      check_for_file unless @encoding
-      @encoding ||= `file --mime-encoding "#{@path}"`.gsub(/\n/,"").split(':')[1].strip
+      @encoding ||= begin
+        check_for_file
+        `file --mime-encoding "#{path}"`.delete("\n").split(':')[1].strip
+      end
     end
 
-    # Returns a symbol with the objects type
-    #
-    # @return [symbol] the type of object, could be :application (for PDF or Word, etc), :audio, :image, :message, :model, :multipart, :text or :video
-    #
-    # Example:
-    #   source_file=Assembly::ObjectFile.new('/input/path_to_file.tif')
-    #   puts source_file.object_type # gives :image
+    # @return [Symbol] the type of object, could be :application (for PDF or Word, etc), :audio, :image, :message, :model, :multipart, :text or :video
+    # @example
+    #   source_file = Assembly::ObjectFile.new('/input/path_to_file.tif')
+    #   puts source_file.object_type # :image
     def object_type
-      lookup=MIME::Types[mimetype][0]
-      return (lookup.nil? ? "other".to_sym : lookup.media_type.to_sym)
+      lookup = MIME::Types[mimetype][0]
+      lookup.nil? ? :other : lookup.media_type.to_sym
     end
-        
-    # Returns if the object file is an image.
-    #
-    # @return [boolean] if object is an image
-    #
-    # Example:
-    #   source_file=Assembly::ObjectFile.new('/input/path_to_file.tif')
-    #   puts source_file.image? # gives TRUE
+
+    # @return [Boolean] if object is an image
+    # @example
+    #   source_file = Assembly::ObjectFile.new('/input/path_to_file.tif')
+    #   puts source_file.image? # true
     def image?
-      object_type == :image 
+      object_type == :image
     end
 
-    # Examines the input image for validity.  Used to determine if image is a valid and useful image.  If image is not a jp2, also checks if it is jp2able?
-    #
-    # @return [boolean] true if image is valid, false if not.
-    #
-    # Example:
-    #   source_img=Assembly::ObjectFile.new('/input/path_to_file.tif')
-    #   puts source_img.valid_image? # gives true
-    def valid_image?  
-      
-      result= image? ? true : false
-      result= jp2able? unless mimetype == 'image/jp2' # further checks if we are not already a jp2
+    # Examines the input image for validity.  Used to determine if image is a valid and useful image.
+    # If image is not a jp2, also checks if it is jp2able?
+    # @return [Boolean] true if image is valid, false if not.
+    # @example
+    #   source_img = Assembly::ObjectFile.new('/input/path_to_file.tif')
+    #   puts source_img.valid_image? # true
+    def valid_image?
+      return false unless image?
 
-      return result
-      
+      mimetype == 'image/jp2' || jp2able? ? true : false
     end
 
-    # Examines the input image for a color profile.
-    #
-    # @return [boolean] true if image has a color profile, false if not.
-    #
-    # Example:
-    #   source_img=Assembly::ObjectFile.new('/input/path_to_file.tif')
-    #   puts source_img.has_color_profile? # gives true
+    # @return [Boolean] true if image has a color profile, false if not.
+    # @example
+    #   source_img = Assembly::ObjectFile.new('/input/path_to_file.tif')
+    #   puts source_img.has_color_profile? # true
     def has_color_profile?
-      exif.nil? ? false : (!exif['profiledescription'].nil? || !exif['colorspace'].nil?) # check for existence of profile description  
+      return false unless exif
+
+      exif['profiledescription'] || exif['colorspace'] ? true : false
     end
 
     # Examines the input image for validity to create a jp2.  Same as valid_image? but also confirms the existence of a profile description and further restricts mimetypes.
     # It is used by the assembly robots to decide if a jp2 will be created and is also called before you create a jp2 using assembly-image.
-    # @return [boolean] true if image should have a jp2 created, false if not.
-    #
-    # Example:
-    #   source_img=Assembly::ObjectFile.new('/input/path_to_file.tif')
-    #   puts source_img.jp2able? # gives true    
+    # @return [Boolean] true if image should have a jp2 created, false if not.
+    # @example
+    #   source_img = Assembly::ObjectFile.new('/input/path_to_file.tif')
+    #   puts source_img.jp2able? # true
     def jp2able?
-      
-      result=false
-      unless exif.nil?
-        result=(Assembly::VALID_IMAGE_MIMETYPES.include?(mimetype)) # check for allowed image mimetypes that can be converted to jp2
-      end
-      return result
+      return false unless exif
 
+      Assembly::VALID_IMAGE_MIMETYPES.include?(mimetype)
     end
-      
+
     # Returns file size information for the current file in bytes.
-    #
-    # @return [integer] file size in bytes
-    #
-    # Example:
-    #   source_file=Assembly::ObjectFile.new('/input/path_to_file.tif')
-    #   puts source_file.filesize # gives 1345    
+    # @return [Integer] file size in bytes
+    # @example
+    #   source_file = Assembly::ObjectFile.new('/input/path_to_file.tif')
+    #   puts source_file.filesize # 1345
     def filesize
       check_for_file
-      @filesize ||= File.size @path
+      @filesize ||= File.size(path)
     end
 
-
     # Determines if the file exists (and is not a directory)
-    #
-    # @return [boolean] file exists
-    #
-    # Example:
-    #   source_file=Assembly::ObjectFile.new('/input/path_to_file.tif')
-    #   puts source_file.file_exists? # gives true
+    # @return [Boolean] file exists
+    # @example
+    #   source_file = Assembly::ObjectFile.new('/input/path_to_file.tif')
+    #   puts source_file.file_exists? # true
     def file_exists?
-      File.exists?(@path) && !File.directory?(@path) 
+      File.exist?(path) && !File.directory?(path)
     end
- 
+
     private
+
     # private method to check for file existence before operating on it
     def check_for_file
       raise "input file #{path} does not exist" unless file_exists?
     end
-    
   end
-
-end
+end