wahwah 0.1.0 → 1.2.0

data/lib/wahwah/id3/frame.rb

@@ -0,0 +1,176 @@
+# frozen_string_literal: true
+
+module WahWah
+  module ID3
+    class Frame
+      prepend LazyRead
+
+      ID_MAPPING = {
+        # ID3v2.2 frame id
+        COM: :comment,
+        TRK: :track,
+        TYE: :year,
+        TAL: :album,
+        TP1: :artist,
+        TT2: :title,
+        TCO: :genre,
+        TPA: :disc,
+        TP2: :albumartist,
+        TCM: :composer,
+        PIC: :image,
+
+        # ID3v2.3 and ID3v2.4 frame id
+        COMM: :comment,
+        TRCK: :track,
+        TYER: :year,
+        TALB: :album,
+        TPE1: :artist,
+        TIT2: :title,
+        TCON: :genre,
+        TPOS: :disc,
+        TPE2: :albumartist,
+        TCOM: :composer,
+        APIC: :image,
+
+        # ID3v2.4 use TDRC replace TYER
+        TDRC: :year
+      }
+
+      # ID3v2.3 frame flags field is defined as follows.
+      #
+      # %abc00000 %ijk00000
+      #
+      # a - Tag alter preservation
+      # b - File alter preservation
+      # c - Read only
+      # i - Compression
+      # j - Encryption
+      # k - Grouping identity
+      V3_HEADER_FLAGS_INDICATIONS = Array.new(16).tap do |array|
+        array[0] = :tag_alter_preservation
+        array[1] = :file_alter_preservation
+        array[2] = :read_only
+        array[8] = :compression
+        array[9] = :encryption
+        array[10] = :grouping_identity
+      end
+
+      # ID3v2.4 frame flags field is defined as follows.
+      #
+      # %0abc0000 %0h00kmnp
+      #
+      # a - Tag alter preservation
+      # b - File alter preservation
+      # c - Read only
+      # h - Grouping identity
+      # k - Compression
+      # m - Encryption
+      # n - Unsynchronisation
+      # p - Data length indicator
+      V4_HEADER_FLAGS_INDICATIONS = Array.new(16).tap do |array|
+        array[1] = :tag_alter_preservation
+        array[2] = :file_alter_preservation
+        array[3] = :read_only
+        array[9] = :grouping_identity
+        array[12] = :compression
+        array[13] = :encryption
+        array[14] = :unsynchronisation
+        array[15] = :data_length_indicator
+      end
+
+      attr_reader :name
+
+      def initialize(version)
+        @version = version
+
+        parse_frame_header
+
+        # In ID3v2.3 when frame is compressed using zlib
+        # with 4 bytes for 'decompressed size' appended to the frame header.
+        #
+        # In ID3v2.4 A 'Data Length Indicator' byte MUST be included in the frame
+        # when frame is compressed, and 'Data Length Indicator'represented as a 32 bit
+        # synchsafe integer
+        #
+        # So skip those 4 byte.
+        if compressed? || data_length_indicator?
+          @file_io.seek(4, IO::SEEK_CUR)
+          @size -= 4
+        end
+      end
+
+      def valid?
+        @size > 0 && !@name.nil?
+      end
+
+      def compressed?
+        @flags.include? :compression
+      end
+
+      def data_length_indicator?
+        @flags.include? :data_length_indicator
+      end
+
+      def value
+        return unless @size > 0
+
+        content = compressed? ? Zlib.inflate(data) : data
+        frame_body = frame_body_class.new(content, @version)
+        frame_body.value
+      end
+
+      private
+
+      # ID3v2.2 frame header structure:
+      #
+      # Frame ID      $xx xx xx(tree characters)
+      # Size          3 * %xxxxxxxx
+      #
+      # ID3v2.3 frame header structure:
+      #
+      # Frame ID      $xx xx xx xx (four characters)
+      # Size          4 * %xxxxxxxx
+      # Flags         $xx xx
+      #
+      # ID3v2.4 frame header structure:
+      #
+      # Frame ID      $xx xx xx xx (four characters)
+      # Size          4 * %0xxxxxxx
+      # Flags         $xx xx
+      def parse_frame_header
+        header_size = @version == 2 ? 6 : 10
+        header_formate = @version == 2 ? "A3B24" : "A4B32B16"
+        id, size_bits, flags_bits = @file_io.read(header_size).unpack(header_formate)
+
+        @name = ID_MAPPING[id.to_sym]
+        @size = Helper.id3_size_caculate(size_bits, has_zero_bit: @version == 4)
+        @flags = parse_flags(flags_bits)
+      end
+
+      def parse_flags(flags_bits)
+        return [] if flags_bits.nil?
+
+        frame_flags_indications = @version == 4 ?
+          V4_HEADER_FLAGS_INDICATIONS :
+          V3_HEADER_FLAGS_INDICATIONS
+
+        flags_bits.chars.map.with_index do |flag_bit, index|
+          frame_flags_indications[index] if flag_bit == "1"
+        end.compact
+      end
+
+      def frame_body_class
+        case @name
+        when :comment
+          CommentFrameBody
+        when :genre
+          GenreFrameBody
+        when :image
+          ImageFrameBody
+        else
+          TextFrameBody
+        end
+      end
+    end
+  end
+end

data/lib/wahwah/id3/frame_body.rb

@@ -0,0 +1,35 @@
+# frozen_string_literal: true
+
+module WahWah
+  module ID3
+    class FrameBody
+      # Textual frames are marked with an encoding byte.
+      #
+      # $00   ISO-8859-1 [ISO-8859-1]. Terminated with $00.
+      # $01   UTF-16 [UTF-16] encoded Unicode [UNICODE] with BOM.
+      # $02   UTF-16BE [UTF-16] encoded Unicode [UNICODE] without BOM.
+      # $03   UTF-8 [UTF-8] encoded Unicode [UNICODE].
+      ENCODING_MAPPING = %w[ISO-8859-1 UTF-16 UTF-16BE UTF-8]
+
+      ENCODING_TERMINATOR_SIZE = {
+        "ISO-8859-1" => 1,
+        "UTF-16" => 2,
+        "UTF-16BE" => 2,
+        "UTF-8" => 1
+      }
+
+      attr_reader :value
+
+      def initialize(content, version)
+        @content = content
+        @version = version
+
+        parse
+      end
+
+      def parse
+        raise WahWahNotImplementedError, "The parse method is not implemented"
+      end
+    end
+  end
+end

data/lib/wahwah/id3/genre_frame_body.rb

@@ -0,0 +1,15 @@
+# frozen_string_literal: true
+
+module WahWah
+  module ID3
+    class GenreFrameBody < TextFrameBody
+      def parse
+        super
+
+        # If value is numeric value, or contain numeric value in parens
+        # can use as index for ID3v1 genre list
+        @value = ID3::V1::GENRES[$1.to_i] if @value =~ /^\((\d+)\)$/ || @value =~ /^(\d+)$/
+      end
+    end
+  end
+end

data/lib/wahwah/id3/image_frame_body.rb

@@ -0,0 +1,60 @@
+# frozen_string_literal: true
+
+module WahWah
+  module ID3
+    class ImageFrameBody < FrameBody
+      TYPES = %i[
+        other
+        file_icon
+        other_file_icon
+        cover_front
+        cover_back
+        leaflet
+        media
+        lead_artist
+        artist
+        conductor
+        band
+        composer
+        lyricist
+        recording_location
+        during_recording
+        during_performance
+        movie_screen_capture
+        bright_coloured_fish
+        illustration
+        band_logotype
+        publisher_logotype
+      ]
+
+      def mime_type
+        mime_type = @mime_type.downcase.yield_self { |type| type == "jpg" ? "jpeg" : type }
+        @version > 2 ? mime_type : "image/#{mime_type}"
+      end
+
+      # ID3v2.2 image frame structure:
+      #
+      # Text encoding  $xx
+      # Image format   $xx xx xx
+      # Picture type   $xx
+      # Description    <text string according to encoding> $00 (00)
+      # Picture data   <binary data>
+      #
+      # ID3v2.3 and ID3v2.4 image frame structure:
+      #
+      # Text encoding $xx
+      # MIME type     <text string> $00
+      # Picture type  $xx
+      # Description   <text string according to encoding> $00 (00)
+      # Picture data  <binary data>
+      def parse
+        frame_format = @version > 2 ? "CZ*Ca*" : "Ca3Ca*"
+        encoding_id, @mime_type, type_index, reset_content = @content.unpack(frame_format)
+        encoding = ENCODING_MAPPING[encoding_id]
+        _description, data = Helper.split_with_terminator(reset_content, ENCODING_TERMINATOR_SIZE[encoding])
+
+        @value = {data: data, mime_type: mime_type, type: TYPES[type_index]}
+      end
+    end
+  end
+end

data/lib/wahwah/id3/text_frame_body.rb

@@ -0,0 +1,16 @@
+# frozen_string_literal: true
+
+module WahWah
+  module ID3
+    class TextFrameBody < FrameBody
+      # Text frame boby structure:
+      #
+      # Text encoding  $xx
+      # Information    <text string according to encoding>
+      def parse
+        encoding_id, text = @content.unpack("Ca*")
+        @value = Helper.encode_to_utf8(text, source_encoding: ENCODING_MAPPING[encoding_id])
+      end
+    end
+  end
+end

data/lib/wahwah/id3/v1.rb

@@ -0,0 +1,97 @@
+# frozen_string_literal: true
+
+module WahWah
+  module ID3
+    class V1 < Tag
+      TAG_SIZE = 128
+      TAG_ID = "TAG"
+      DEFAULT_ENCODING = "iso-8859-1"
+      GENRES = [
+        # Standard Genres
+        "Blues", "Classic Rock", "Country", "Dance", "Disco", "Funk", "Grunge",
+        "Hip-Hop", "Jazz", "Metal", "New Age", "Oldies", "Other", "Pop",
+        "R&B", "Rap", "Reggae", "Rock", "Techno", "Industrial", "Alternative",
+        "Ska", "Death Metal", "Pranks", "Soundtrack", "Euro-Techno", "Ambient", "Trip-Hop",
+        "Vocal", "Jazz+Funk", "Fusion", "Trance", "Classical", "Instrumental", "Acid",
+        "House", "Game", "Sound Clip", "Gospel", "Noise", "AlternRock", "Bass",
+        "Soul", "Punk", "Space", "Meditative", "Instrumental Pop", "Instrumental Rock", "Ethnic",
+        "Gothic", "Darkwave", "Techno-Industrial", "Electronic", "Pop-Folk", "Eurodance", "Dream",
+        "Southern Rock", "Comedy", "Cult", "Gangsta", "Top 40", "Christian Rap", "Pop/Funk",
+        "Jungle", "Native American", "Cabaret", "New Wave", "Psychadelic", "Rave", "Showtunes",
+        "Trailer", "Lo-Fi", "Tribal", "Acid Punk", "Acid Jazz", "Polka", "Retro",
+        "Musical", "Rock & Roll", "Hard Rock",
+
+        # Winamp Extended Genres
+        "Folk", "Folk-Rock", "National Folk", "Swing", "Fast Fusion", "Bebob", "Latin",
+        "Revival", "Celtic", "Bluegrass", "Avantgarde", "Gothic Rock", "Progressive Rock", "Psychedelic Rock",
+        "Symphonic Rock", "Slow Rock", "Big Band", "Chorus", "Easy Listening", "Acoustic", "Humour",
+        "Speech", "Chanson", "Opera", "Chamber Music", "Sonata", "Symphony", "Booty Bass",
+        "Primus", "Porn Groove", "Satire", "Slow Jam", "Club", "Tango", "Samba",
+        "Folklore", "Ballad", "Power Ballad", "Rhythmic Soul", "Freestyle", "Duet", "Punk Rock",
+        "Drum Solo", "A capella", "Euro-House", "Dance Hall", "Goa", "Drum & Bass", "Club-House",
+        "Hardcore Techno", "Terror", "Indie", "BritPop", "Negerpunk", "Polsk Punk", "Beat",
+        "Christian Gangsta Rap", "Heavy Metal", "Black Metal", "Contemporary Christian", "Christian Rock",
+
+        # Added on WinAmp 1.91
+        "Merengue", "Salsa", "Thrash Metal", "Anime", "Jpop", "Synthpop",
+
+        # Added on WinAmp 5.6
+        "Abstract", "Art Rock", "Baroque", "Bhangra", "Big Beat", "Breakbeat", "Chillout",
+        "Downtempo", "Dub", "EBM", "Eclectic", "Electro", "Electroclash", "Emo",
+        "Experimental", "Garage", "Illbient", "Industro-Goth", "Jam Band", "Krautrock", "Leftfield",
+        "Lounge", "Math Rock", "New Romantic", "Nu-Breakz", "Post-Punk", "Post-Rock", "Psytrance",
+        "Shoegaze", "Space Rock", "Trop Rock", "World Music", "Neoclassical", "Audiobook", "Audio Theatre",
+        "Neue Deutsche Welle", "Podcast", "Indie Rock", "G-Funk", "Dubstep", "Garage Rock", "Psybient"
+      ]
+
+      def size
+        TAG_SIZE
+      end
+
+      def version
+        "v1"
+      end
+
+      def valid?
+        @id == TAG_ID
+      end
+
+      private
+
+      # For ID3v1 info, see here https://en.wikipedia.org/wiki/ID3#ID3v1
+      #
+      # header    3         "TAG"
+      # title     30        30 characters of the title
+      # artist    30        30 characters of the artist name
+      # album     30        30 characters of the album name
+      # year      4         A four-digit year
+      # comment   28 or 30  The comment.
+      # zero-byte 1         If a track number is stored, this byte contains a binary 0.
+      # track     1         The number of the track on the album, or 0. Invalid, if previous byte is not a binary 0.
+      # genre     1         Index in a list of genres, or 255
+      def parse
+        return unless @file_io.size >= TAG_SIZE
+
+        @file_io.seek(-TAG_SIZE, IO::SEEK_END)
+        @id = Helper.encode_to_utf8(@file_io.read(3), source_encoding: DEFAULT_ENCODING)
+
+        return unless valid?
+
+        @title = Helper.encode_to_utf8(@file_io.read(30), source_encoding: DEFAULT_ENCODING)
+        @artist = Helper.encode_to_utf8(@file_io.read(30), source_encoding: DEFAULT_ENCODING)
+        @album = Helper.encode_to_utf8(@file_io.read(30), source_encoding: DEFAULT_ENCODING)
+        @year = Helper.encode_to_utf8(@file_io.read(4), source_encoding: DEFAULT_ENCODING)
+
+        comment = @file_io.read(30)
+
+        if comment.getbyte(-2) == 0
+          @track = comment.getbyte(-1)
+          comment = comment.byteslice(0..-3)
+        end
+
+        @comments.push(Helper.encode_to_utf8(comment, source_encoding: DEFAULT_ENCODING))
+        @genre = GENRES[@file_io.getbyte] || ""
+      end
+    end
+  end
+end

data/lib/wahwah/id3/v2.rb

@@ -0,0 +1,67 @@
+# frozen_string_literal: true
+
+module WahWah
+  module ID3
+    class V2 < Tag
+      extend Forwardable
+
+      def_delegators :@header, :major_version, :size, :has_extended_header?, :valid?
+
+      def version
+        "v2.#{major_version}"
+      end
+
+      private
+
+      def parse
+        @file_io.rewind
+        @header = V2Header.new(@file_io)
+
+        return unless valid?
+
+        until end_of_tag?
+          frame = ID3::Frame.new(@file_io, major_version)
+
+          unless frame.valid?
+            frame.skip
+            next
+          end
+
+          update_attribute(frame)
+        end
+      end
+
+      def update_attribute(frame)
+        name = frame.name
+
+        case name
+        when :comment
+          # Because there may be more than one comment frame in each tag,
+          # so push it into a array.
+          @comments.push(frame.value)
+        when :image
+          # Because there may be more than one image frame in each tag,
+          # so push it into a array.
+          @images_data.push(frame)
+          frame.skip
+        when :track, :disc
+          # Track and disc value may be extended with a "/" character
+          # and a numeric string containing the total numer.
+          count, total_count = frame.value.split("/", 2)
+          instance_variable_set("@#{name}", count)
+          instance_variable_set("@#{name}_total", total_count) unless total_count.nil?
+        else
+          instance_variable_set("@#{name}", frame.value)
+        end
+      end
+
+      def end_of_tag?
+        size <= @file_io.pos || file_size <= @file_io.pos
+      end
+
+      def parse_image_data(image_frame)
+        image_frame.value
+      end
+    end
+  end
+end

data/lib/wahwah/id3/v2_header.rb

@@ -0,0 +1,53 @@
+# frozen_string_literal: true
+
+module WahWah
+  module ID3
+    # The ID3v2 tag header, which should be the first information in the file,
+    # is 10 bytes as follows:
+
+    # ID3v2/file identifier   "ID3"
+    # ID3v2 version           $03 00
+    # ID3v2 flags             %abc00000
+    # ID3v2 size              4 * %0xxxxxxx
+    class V2Header
+      TAG_ID = "ID3"
+      HEADER_SIZE = 10
+      HEADER_FORMAT = "A3CxB8B*"
+
+      attr_reader :major_version, :size
+
+      def initialize(file_io)
+        header_content = file_io.read(HEADER_SIZE)
+        @id, @major_version, @flags, size_bits = header_content.unpack(HEADER_FORMAT) if header_content.size >= HEADER_SIZE
+
+        return unless valid?
+
+        # Tag size is the size excluding the header size,
+        # so add header size back to get total size.
+        @size = Helper.id3_size_caculate(size_bits) + HEADER_SIZE
+
+        if has_extended_header?
+          # Extended header structure:
+          #
+          # Extended header size   $xx xx xx xx
+          # Extended Flags         $xx xx
+          # Size of padding        $xx xx xx xx
+
+          # Skip extended_header
+          extended_header_size = Helper.id3_size_caculate(file_io.read(4).unpack1("B32"))
+          file_io.seek(extended_header_size - 4, IO::SEEK_CUR)
+        end
+      end
+
+      def valid?
+        @id == TAG_ID
+      end
+
+      # The second bit in flags byte indicates whether or not the header
+      # is followed by an extended header.
+      def has_extended_header?
+        @flags[1] == "1"
+      end
+    end
+  end
+end

data/lib/wahwah/lazy_read.rb

@@ -0,0 +1,40 @@
+# frozen_string_literal: true
+
+module WahWah
+  module LazyRead
+    def self.prepended(base)
+      base.class_eval do
+        attr_reader :size
+      end
+    end
+
+    def initialize(file_io, *arg)
+      @file_io = file_io
+      super(*arg)
+      @position = @file_io.pos
+      @data = get_data if @file_io.is_a?(StringIO)
+    end
+
+    def data
+      if @file_io.closed? && @file_io.is_a?(File)
+        @file_io = File.open(@file_io.path)
+        @data = get_data
+        @file_io.close
+      end
+
+      @data ||= get_data
+    end
+
+    def skip
+      @file_io.seek(@position)
+      @file_io.seek(size, IO::SEEK_CUR)
+    end
+
+    private
+
+    def get_data
+      @file_io.seek(@position)
+      @file_io.read(size)
+    end
+  end
+end