mime-types 3.5.2 → 3.7.0

data/lib/mime/type.rb

@@ -4,20 +4,22 @@
 module MIME
 end
 
+require "mime/types/deprecations"
+
 # The definition of one MIME content-type.
 #
 # == Usage
-#  require 'mime/types'
+#  require "mime/types"
 #
-#  plaintext = MIME::Types['text/plain'] # => [ text/plain ]
+#  plaintext = MIME::Types["text/plain"] # => [ text/plain ]
 #  text = plaintext.first
-#  puts text.media_type            # => 'text'
-#  puts text.sub_type              # => 'plain'
+#  puts text.media_type            # => "text"
+#  puts text.sub_type              # => "plain"
 #
-#  puts text.extensions.join(' ')  # => 'txt asc c cc h hh cpp hpp dat hlp'
-#  puts text.preferred_extension   # => 'txt'
-#  puts text.friendly              # => 'Text Document'
-#  puts text.i18n_key              # => 'text.plain'
+#  puts text.extensions.join(" ")  # => "txt asc c cc h hh cpp hpp dat hlp"
+#  puts text.preferred_extension   # => "txt"
+#  puts text.friendly              # => "Text Document"
+#  puts text.i18n_key              # => "text.plain"
 #
 #  puts text.encoding              # => quoted-printable
 #  puts text.default_encoding      # => quoted-printable
@@ -28,45 +30,45 @@ end
 #  puts text.provisional?          # => false
 #  puts text.complete?             # => true
 #
-#  puts text                       # => 'text/plain'
+#  puts text                       # => "text/plain"
 #
-#  puts text == 'text/plain'       # => true
-#  puts 'text/plain' == text       # => true
-#  puts text == 'text/x-plain'     # => false
-#  puts 'text/x-plain' == text     # => false
+#  puts text == "text/plain"       # => true
+#  puts "text/plain" == text       # => true
+#  puts text == "text/x-plain"     # => false
+#  puts "text/x-plain" == text     # => false
 #
-#  puts MIME::Type.simplified('x-appl/x-zip') # => 'x-appl/x-zip'
-#  puts MIME::Type.i18n_key('x-appl/x-zip') # => 'x-appl.x-zip'
+#  puts MIME::Type.simplified("x-appl/x-zip") # => "x-appl/x-zip"
+#  puts MIME::Type.i18n_key("x-appl/x-zip") # => "x-appl.x-zip"
 #
-#  puts text.like?('text/x-plain') # => true
-#  puts text.like?(MIME::Type.new('x-text/x-plain')) # => true
+#  puts text.like?("text/x-plain") # => true
+#  puts text.like?(MIME::Type.new("content-type" => "x-text/x-plain")) # => true
 #
 #  puts text.xrefs.inspect # => { "rfc" => [ "rfc2046", "rfc3676", "rfc5147" ] }
 #  puts text.xref_urls # => [ "http://www.iana.org/go/rfc2046",
 #                      #      "http://www.iana.org/go/rfc3676",
 #                      #      "http://www.iana.org/go/rfc5147" ]
 #
-#  xtext = MIME::Type.new('x-text/x-plain')
-#  puts xtext.media_type # => 'text'
-#  puts xtext.raw_media_type # => 'x-text'
-#  puts xtext.sub_type # => 'plain'
-#  puts xtext.raw_sub_type # => 'x-plain'
+#  xtext = MIME::Type.new("x-text/x-plain")
+#  puts xtext.media_type # => "text"
+#  puts xtext.raw_media_type # => "x-text"
+#  puts xtext.sub_type # => "plain"
+#  puts xtext.raw_sub_type # => "x-plain"
 #  puts xtext.complete? # => false
 #
-#  puts MIME::Types.any? { |type| type.content_type == 'text/plain' } # => true
+#  puts MIME::Types.any? { |type| type.content_type == "text/plain" } # => true
 #  puts MIME::Types.all?(&:registered?) # => false
 #
 #  # Various string representations of MIME types
-#  qcelp = MIME::Types['audio/QCELP'].first # => audio/QCELP
-#  puts qcelp.content_type         # => 'audio/QCELP'
-#  puts qcelp.simplified           # => 'audio/qcelp'
+#  qcelp = MIME::Types["audio/QCELP"].first # => audio/QCELP
+#  puts qcelp.content_type         # => "audio/QCELP"
+#  puts qcelp.simplified           # => "audio/qcelp"
 #
-#  xwingz = MIME::Types['application/x-Wingz'].first # => application/x-Wingz
-#  puts xwingz.content_type        # => 'application/x-Wingz'
-#  puts xwingz.simplified          # => 'application/x-wingz'
+#  xwingz = MIME::Types["application/x-Wingz"].first # => application/x-Wingz
+#  puts xwingz.content_type        # => "application/x-Wingz"
+#  puts xwingz.simplified          # => "application/x-wingz"
 class MIME::Type
   # Reflects a MIME content-type specification that is not correctly
-  # formatted (it isn't +type+/+subtype+).
+  # formatted (it is not +type+/+subtype+).
   class InvalidContentType < ArgumentError
     # :stopdoc:
     def initialize(type_string)
@@ -92,15 +94,18 @@ class MIME::Type
     # :startdoc:
   end
 
-  # The released version of the mime-types library.
-  VERSION = "3.5.2"
-
   include Comparable
 
   # :stopdoc:
-  # TODO verify mime-type character restrictions; I am pretty sure that this is
-  # too wide open.
-  MEDIA_TYPE_RE = %r{([-\w.+]+)/([-\w.+]*)}.freeze
+  # Full conformance with RFC 6838 §4.2 (the recommendation for < 64 characters is not
+  # enforced or reported because MIME::Types mostly deals with registered data). RFC 4288
+  # §4.2 does not restrict the first character to alphanumeric, but the total length of
+  # each part is limited to 127 characters. RFCC 2045 §5.1 does not restrict the character
+  # composition except for whitespace, but MIME::Type was always more strict than this.
+  restricted_name_first = "[0-9a-zA-Z]"
+  restricted_name_chars = "[-!#{$&}^_.+0-9a-zA-Z]{0,126}"
+  restricted_name = "#{restricted_name_first}#{restricted_name_chars}"
+  MEDIA_TYPE_RE = %r{(#{restricted_name})/(#{restricted_name})}.freeze
   I18N_RE = /[^[:alnum:]]/.freeze
   BINARY_ENCODINGS = %w[base64 8bit].freeze
   ASCII_ENCODINGS = %w[7bit quoted-printable].freeze
@@ -110,12 +115,15 @@ class MIME::Type
     :ASCII_ENCODINGS
 
   # Builds a MIME::Type object from the +content_type+, a MIME Content Type
-  # value (e.g., 'text/plain' or 'application/x-eruby'). The constructed object
+  # value (e.g., "text/plain" or "application/x-eruby"). The constructed object
   # is yielded to an optional block for additional configuration, such as
   # associating extensions and encoding information.
   #
   # * When provided a Hash or a MIME::Type, the MIME::Type will be
   #   constructed with #init_with.
+  #
+  # There are two deprecated initialization forms:
+  #
   # * When provided an Array, the MIME::Type will be constructed using
   #   the first element as the content type and the remaining flattened
   #   elements as extensions.
@@ -125,18 +133,31 @@ class MIME::Type
   def initialize(content_type) # :yields: self
     @friendly = {}
     @obsolete = @registered = @provisional = false
-    @preferred_extension = @docs = @use_instead = nil
+    @preferred_extension = @docs = @use_instead = @__sort_priority = nil
+
     self.extensions = []
 
     case content_type
     when Hash
       init_with(content_type)
     when Array
+      MIME::Types.deprecated(
+        class: MIME::Type,
+        method: :new,
+        pre: "when called with an Array",
+        once: true
+      )
       self.content_type = content_type.shift
       self.extensions = content_type.flatten
     when MIME::Type
       init_with(content_type.to_h)
     else
+      MIME::Types.deprecated(
+        class: MIME::Type,
+        method: :new,
+        pre: "when called with a String",
+        once: true
+      )
       self.content_type = content_type
     end
 
@@ -144,6 +165,8 @@ class MIME::Type
     self.xrefs ||= {}
 
     yield self if block_given?
+
+    update_sort_priority
   end
 
   # Indicates that a MIME type is like another type. This differs from
@@ -162,60 +185,54 @@ class MIME::Type
   # simplified type (the simplified type will be used if comparing against
   # something that can be treated as a String with #to_s). In comparisons, this
   # is done against the lowercase version of the MIME::Type.
+  #
+  # Note that this implementation of #<=> is deprecated and will be changed
+  # in the next major version to be the same as #priority_compare.
+  #
+  # Note that MIME::Types no longer compare against nil.
   def <=>(other)
-    if other.nil?
-      -1
-    elsif other.respond_to?(:simplified)
+    return priority_compare(other) if other.is_a?(MIME::Type)
+    simplified <=> other
+  end
+
+  # Compares the +other+ MIME::Type using a pre-computed sort priority value,
+  # then the simplified representation for an alphabetical sort.
+  #
+  # For the next major version of MIME::Types, this method will become #<=> and
+  # #priority_compare will be removed.
+  def priority_compare(other)
+    if (cmp = __sort_priority <=> other.__sort_priority) == 0
       simplified <=> other.simplified
     else
-      filtered = "silent" if other == :silent
-      filtered ||= "true" if other == true
-      filtered ||= other.to_s
-
-      simplified <=> MIME::Type.simplified(filtered)
+      cmp
     end
   end
 
-  # Compares the +other+ MIME::Type based on how reliable it is before doing a
-  # normal <=> comparison. Used by MIME::Types#[] to sort types. The
-  # comparisons involved are:
-  #
-  # 1. self.simplified <=> other.simplified (ensures that we
-  #    don't try to compare different types)
-  # 2. IANA-registered definitions < other definitions.
-  # 3. Complete definitions < incomplete definitions.
-  # 4. Current definitions < obsolete definitions.
-  # 5. Obselete with use-instead names < obsolete without.
-  # 6. Obsolete use-instead definitions are compared.
+  # Uses a modified pre-computed sort priority value based on whether one of the provided
+  # extensions is the preferred extension for a type.
   #
-  # While this method is public, its use is strongly discouraged by consumers
-  # of mime-types. In mime-types 3, this method is likely to see substantial
-  # revision and simplification to ensure current registered content types sort
-  # before unregistered or obsolete content types.
-  def priority_compare(other)
-    pc = simplified <=> other.simplified
-    if pc.zero? || !(extensions & other.extensions).empty?
-      pc =
-        if (reg = registered?) != other.registered?
-          reg ? -1 : 1 # registered < unregistered
-        elsif (comp = complete?) != other.complete?
-          comp ? -1 : 1 # complete < incomplete
-        elsif (obs = obsolete?) != other.obsolete?
-          obs ? 1 : -1 # current < obsolete
-        elsif obs && ((ui = use_instead) != (oui = other.use_instead))
-          if ui.nil?
-            1
-          elsif oui.nil?
-            -1
-          else
-            ui <=> oui
-          end
-        else
-          0
-        end
+  # This is an internal function. If an extension provided is a preferred extension either
+  # for this instance or the compared instance, the corresponding extension has its top
+  # _extension_ bit cleared from its sort priority. That means that a type with between
+  # 0 and 8 extensions will be treated as if it had 9 extensions.
+  def __extension_priority_compare(other, exts) # :nodoc:
+    tsp = __sort_priority
+
+    if exts.include?(preferred_extension) && tsp & 0b1000 != 0
+      tsp = tsp & 0b11110111 | 0b0111
     end
 
-    pc
+    osp = other.__sort_priority
+
+    if exts.include?(other.preferred_extension) && osp & 0b1000 != 0
+      osp = osp & 0b11110111 | 0b0111
+    end
+
+    if (cmp = tsp <=> osp) == 0
+      simplified <=> other.simplified
+    else
+      cmp
+    end
   end
 
   # Returns +true+ if the +other+ object is a MIME::Type and the content types
@@ -243,13 +260,20 @@ class MIME::Type
   # +a.simplified+.
   #
   # Presumably, if <code>a.simplified <=> b.simplified</code> is +0+, then
-  # +a.simplified+ has the same hash as +b.simplified+. So we assume it's
+  # +a.simplified+ has the same hash as +b.simplified+. So we assume it is
   # suitable for #hash to delegate to #simplified in service of the #eql?
   # invariant.
   def hash
     simplified.hash
   end
 
+  # The computed sort priority value. This is _not_ intended to be used by most
+  # callers.
+  def __sort_priority # :nodoc:
+    update_sort_priority if !instance_variable_defined?(:@__sort_priority) || @__sort_priority.nil?
+    @__sort_priority
+  end
+
   # Returns the whole MIME content-type string.
   #
   # The content type is a presentation value from the MIME type registry and
@@ -304,6 +328,7 @@ class MIME::Type
 
   ##
   def extensions=(value) # :nodoc:
+    clear_sort_priority
     @extensions = Set[*Array(value).flatten.compact].freeze
     MIME::Types.send(:reindex_extensions, self)
   end
@@ -319,7 +344,7 @@ class MIME::Type
   # exceptions defined, the first extension will be used.
   #
   # When setting #preferred_extensions, if #extensions does not contain this
-  # extension, this will be added to #xtensions.
+  # extension, this will be added to #extensions.
   #
   # :attr_accessor: preferred_extension
 
@@ -343,7 +368,7 @@ class MIME::Type
   # provided is invalid.
   #
   # If the encoding is not provided on construction, this will be either
-  # 'quoted-printable' (for text/* media types) and 'base64' for eveything
+  # "quoted-printable" (for text/* media types) and "base64" for eveything
   # else.
   #
   # :attr_accessor: encoding
@@ -383,9 +408,17 @@ class MIME::Type
   attr_writer :use_instead
 
   # Returns +true+ if the media type is obsolete.
-  attr_accessor :obsolete
+  #
+  # :attr_accessor: obsolete
+  attr_reader :obsolete
   alias_method :obsolete?, :obsolete
 
+  ##
+  def obsolete=(value)
+    clear_sort_priority
+    @obsolete = !!value
+  end
+
   # The documentation for this MIME::Type.
   attr_accessor :docs
 
@@ -393,7 +426,7 @@ class MIME::Type
   #
   # call-seq:
   #   text_plain.friendly         # => "Text File"
-  #   text_plain.friendly('en')   # => "Text File"
+  #   text_plain.friendly("en")   # => "Text File"
   def friendly(lang = "en")
     @friendly ||= {}
 
@@ -443,11 +476,27 @@ class MIME::Type
   end
 
   # Indicates whether the MIME type has been registered with IANA.
-  attr_accessor :registered
+  #
+  # :attr_accessor: registered
+  attr_reader :registered
   alias_method :registered?, :registered
 
+  ##
+  def registered=(value)
+    clear_sort_priority
+    @registered = !!value
+  end
+
   # Indicates whether the MIME type's registration with IANA is provisional.
-  attr_accessor :provisional
+  #
+  # :attr_accessor: provisional
+  attr_reader :provisional
+
+  ##
+  def provisional=(value)
+    clear_sort_priority
+    @provisional = !!value
+  end
 
   # Indicates whether the MIME type's registration with IANA is provisional.
   def provisional?
@@ -486,7 +535,7 @@ class MIME::Type
   # Returns the MIME::Type as a string for implicit conversions. This allows
   # MIME::Type objects to appear on either side of a comparison.
   #
-  #   'text/plain' == MIME::Type.new('text/plain')
+  #   "text/plain" == MIME::Type.new("content-type" => "text/plain")
   def to_str
     content_type
   end
@@ -530,6 +579,7 @@ class MIME::Type
     coder["registered"] = registered?
     coder["provisional"] = provisional? if provisional?
     coder["signature"] = signature? if signature?
+    coder["sort-priority"] = __sort_priority || 0b11111111
     coder
   end
 
@@ -538,6 +588,7 @@ class MIME::Type
   #
   # This method should be considered a private implementation detail.
   def init_with(coder)
+    @__sort_priority = 0
     self.content_type = coder["content-type"]
     self.docs = coder["docs"] || ""
     self.encoding = coder["encoding"]
@@ -551,6 +602,8 @@ class MIME::Type
     self.use_instead = coder["use-instead"]
 
     friendly(coder["friendly"] || {})
+
+    update_sort_priority
   end
 
   def inspect # :nodoc:
@@ -606,6 +659,37 @@ class MIME::Type
 
   private
 
+  def clear_sort_priority
+    @__sort_priority = nil
+  end
+
+  # Update the __sort_priority value. Lower numbers sort better, so the
+  # bitmapping may seem a little odd. The _best_ sort priority is 0.
+  #
+  # | bit | meaning         | details   |
+  # | --- | --------------- | --------- |
+  # | 7   | obsolete        | 1 if true |
+  # | 6   | provisional     | 1 if true |
+  # | 5   | registered      | 0 if true |
+  # | 4   | complete        | 0 if true |
+  # | 3   | # of extensions | see below |
+  # | 2   | # of extensions | see below |
+  # | 1   | # of extensions | see below |
+  # | 0   | # of extensions | see below |
+  #
+  # The # of extensions is marked as the number of extensions subtracted from
+  # 16, to a minimum of 0.
+  def update_sort_priority
+    extension_count = @extensions.length
+    obsolete = (instance_variable_defined?(:@obsolete) && @obsolete) ? 1 << 7 : 0
+    provisional = (instance_variable_defined?(:@provisional) && @provisional) ? 1 << 6 : 0
+    registered = (instance_variable_defined?(:@registered) && @registered) ? 0 : 1 << 5
+    complete = extension_count.nonzero? ? 0 : 1 << 4
+    extension_count = [0, 16 - extension_count].max
+
+    @__sort_priority = obsolete | registered | provisional | complete | extension_count
+  end
+
   def content_type=(type_string)
     match = MEDIA_TYPE_RE.match(type_string)
     fail InvalidContentType, type_string if match.nil?
@@ -627,7 +711,7 @@ class MIME::Type
       -string
     end
   else
-    # MRI 2.2 and older don't have a method for string interning,
+    # MRI 2.2 and older do not have a method for string interning,
     # so we simply freeze them for keeping a similar interface
     def intern_string(string)
       string.freeze
@@ -658,3 +742,5 @@ class MIME::Type
     "http://www.iana.org/assignments/media-types/%s" % value
   end
 end
+
+require "mime/types/version"

data/lib/mime/types/_columnar.rb

@@ -18,6 +18,10 @@ module MIME::Types::Columnar
     obj.instance_variable_set(:@__files__, Set.new)
   end
 
+  def __fully_loaded? # :nodoc:
+    @__files__.size == 10
+  end
+
   # Load the first column data file (type and extensions).
   def load_base_data(path) # :nodoc:
     @__root__ = path
@@ -26,13 +30,16 @@ module MIME::Types::Columnar
       line = line.split
       content_type = line.shift
       extensions = line
-      # content_type, *extensions = line.split
 
       type = MIME::Type::Columnar.new(self, content_type, extensions)
       @__mime_data__ << type
       add(type)
     end
 
+    each_file_byte("spri") do |type, byte|
+      type.instance_variable_set(:@__sort_priority, byte)
+    end
+
     self
   end
 
@@ -60,10 +67,29 @@ module MIME::Types::Columnar
     end
   end
 
+  def each_file_byte(name)
+    LOAD_MUTEX.synchronize do
+      next if @__files__.include?(name)
+
+      i = -1
+
+      filename = File.join(@__root__, "mime.#{name}.column")
+
+      next unless File.exist?(filename)
+
+      IO.binread(filename).unpack("C*").each do |byte|
+        (type = @__mime_data__[i += 1]) || next
+        yield type, byte
+      end
+
+      @__files__ << name
+    end
+  end
+
   def load_encoding
     each_file_line("encoding") do |type, line|
       pool ||= {}
-      type.instance_variable_set(:@encoding, (pool[line] ||= line))
+      type.instance_variable_set(:@encoding, pool[line] ||= line)
     end
   end
 
@@ -91,7 +117,7 @@ module MIME::Types::Columnar
 
   def load_xrefs
     each_file_line("xrefs") { |type, line|
-      type.instance_variable_set(:@xrefs, dict(line, array: true))
+      type.instance_variable_set(:@xrefs, dict(line, transform: :array))
     }
   end
 
@@ -107,18 +133,39 @@ module MIME::Types::Columnar
     end
   end
 
-  def dict(line, array: false)
+  def dict(line, transform: nil)
     if line == "-"
       {}
     else
       line.split("|").each_with_object({}) { |l, h|
         k, v = l.split("^")
         v = nil if v.empty?
-        h[k] = array ? Array(v) : v
+
+        if transform
+          send(:"dict_#{transform}", h, k, v)
+        else
+          h[k] = v
+        end
       }
     end
   end
 
+  def dict_extension_priority(h, k, v)
+    return if v.nil?
+
+    v = v.to_i if v.is_a?(String)
+    v = v.trunc if v.is_a?(Float)
+    v = [[-20, v].max, 20].min
+
+    return if v.zero?
+
+    h[k] = v
+  end
+
+  def dict_array(h, k, v)
+    h[k] = Array(v)
+  end
+
   def arr(line)
     if line == "-"
       []

data/lib/mime/types/container.rb

@@ -1,17 +1,14 @@
 # frozen_string_literal: true
 
 require "set"
-require "forwardable"
 
 # MIME::Types requires a serializable keyed container that returns an empty Set
 # on a key miss. Hash#default_value cannot be used because, while it traverses
-# the Marshal format correctly, it won't survive any other serialization
+# the Marshal format correctly, it will not survive any other serialization
 # format (plus, a default of a mutable object resuls in a shared mess).
 # Hash#default_proc cannot be used without a wrapper because it prevents
-# Marshal serialization (and doesn't survive the round-trip).
+# Marshal serialization (and does not survive the round-trip).
 class MIME::Types::Container # :nodoc:
-  extend Forwardable
-
   def initialize(hash = {})
     @container = {}
     merge!(hash)
@@ -47,16 +44,49 @@ class MIME::Types::Container # :nodoc:
     container
   end
 
-  def_delegators :@container,
-    :==,
-    :count,
-    :each,
-    :each_value,
-    :empty?,
-    :flat_map,
-    :keys,
-    :select,
-    :values
+  def ==(other)
+    container == other
+  end
+
+  def count(*args, &block)
+    if args.size == 0
+      container.count
+    elsif block
+      container.count(&block)
+    else
+      container.count(args.first)
+    end
+  end
+
+  def each_pair(&block)
+    container.each_pair(&block)
+  end
+
+  alias_method :each, :each_pair
+
+  def each_value(&block)
+    container.each_value(&block)
+  end
+
+  def empty?
+    container.empty?
+  end
+
+  def flat_map(&block)
+    container.flat_map(&block)
+  end
+
+  def keys
+    container.keys
+  end
+
+  def values
+    container.values
+  end
+
+  def select(&block)
+    container.select(&block)
+  end
 
   def add(key, value)
     (container[key] ||= Set.new).add(value)