waveform.rb

require 'rubygems'
require 'RMagick'
require 'narray'

class WaveformRenderer
  # image size in pixel
  DEFAULT_WIDTH  = 1024
  DEFAULT_HEIGHT = 512
  # default graph color
  DEFAULT_COLOR = "#666"
  # default graph background color
  DEFAULT_BACKGROUND_COLOR = "none"
  
  def initialize(input, output)
    @input = input
    @output = output
  end
  
  def render_waveform(width = DEFAULT_WIDTH, height = DEFAULT_HEIGHT, color = DEFAULT_COLOR, background_color = 
DEFAULT_BACKGROUND_COLOR)

    buckets = fill_buckets(width, @input)
    
    o = [('a'..'f'),('0'..'9')].map{ |i| i.to_a }.flatten
    color = "#" + (0..5).map{ o[rand(o.length)] }.join
    RAILS_DEFAULT_LOGGER.info "color: #{color}"

    gc = build_graph(buckets, width, height, color)

    canvas = Magick::Image.new(width, height) { self.background_color = background_color }
    gc.draw(canvas)
    canvas.write(@output)
  end
  
protected
  
  # fill the buckets
  def fill_buckets(width, file)
    buckets = NArray.int(width,2)
    # let sox fetch the byte array
    bytes = sox_get_bytes(file)
    bucket_size = (((bytes.size-1).to_f / width)+0.5).to_i + 1
    @max = 0
    @min = 0
    (0..bytes.total-1).each do |i|
        value = bytes[i]
        index = i/bucket_size

        # minimum
        buckets[index,0] = value if value < buckets[index,0]
        @min = value if value < @min

        # maximum
        buckets[index,1] = value if value > buckets[index,1]
        @max = value if value > @max
    end
    return buckets
  end
 
  # open file with sox and return a byte array with sweet waveform information in it
  def sox_get_bytes(file)
    #
    # Sox command help
    #
    # -t, --type file-type
    #   Gives  the type of the audio file.  This is useful when the file
    #   extension is non-standard or when the type can not be determined
    #   by looking at the header of the file.
    #
    #   The  -t  option can also be used to override the type implied by
    #   an input filename extension, but if overriding with a type  that
    #   has a header, SoX will exit with an appropriate error message if
    #   such a header is not actually present.
    #
    # -r (rate): output sample rate (4kHz)
    #
    # -c CHANNELS, --channels CHANNELS
    #   The number of audio channels in the audio file; this can be  any
    #   number  greater  than  zero.  To cause the output file to have a
    #   different number of channels than the input file,  include  this
    #   option  with  the  output file options.  If the input and output
    #   file have a different number of channels then the  mixer  effect
    #   must  be used.  If the mixer effect is not specified on the com-
    #   mand line it will be invoked internally with default parameters.
    #
    #   Alternatively,  some effects (e.g.  synth, remix) determine what
    #   will be the number of output channels;  in  this  case,  neither
    #   this option nor the mixer effect is necessary.
    #
    # -s (signed-integer)
    #   The audio encoding type.
    #    
    #   PCM data stored as signed (`two's complement') integers.
    #   Commonly used with a 16 or 24-bit encoding size.
    #   A value of 0 represents minimum signal power.
    #
    # -L, --endian little
    # -B, --endian big
    # -x, --endian swap
    #   These options specify whether the byte-order of the  audio  data
    #   is, respectively, `little endian', `big endian', or the opposite
    #   to that of the system on which SoX is  being  used.   Endianness
    #   applies  only  to data encoded as signed or unsigned integers of
    #   16 or more bits.  It is often necessary to specify one of  these
    #   options  for headerless files, and sometimes necessary for (oth-
    #   erwise) self-describing files.  A  given  endian-setting  option
    #   may  be  ignored  for an input file whose header contains a spe-
    #   cific endianness identifier, or for an output file that is actu-
    #   ally an audio device.
    #
    #   N.B.   Unlike  normal  format  characteristics,  the  endianness
    #   (byte, nibble, & bit ordering) of the input file is not automat-
    #   ically  used for the output file; so, for example, when the fol-
    #   lowing is run on a little-endian system:
    #
    #     sox -B audio.s2 trimmed.s2 trim 2
    #
    #   trimmed.s2 will be created as little-endian;
    #
    #     sox -B audio.s2 -B trimmed.s2 trim 2
    #
    #   must be used to preserve big-endianness in the output file.
    #
    sox_command = [ 'sox', file, '-t', 'raw', '-r', '22050', '-c', '1', '-s', '-L', '-' ]
    
    x = nil
    # we have to fork/exec to get a clean commandline
    IO.popen('-') do |p|
      if p.nil? then
        $stderr.close
        # raw 16 bit linear PCM one channel
        exec *sox_command
      end
      x = p.read
    end
    if x.size == 0 then
      raise "sox returned no data, command was\n> #{sox_command.join(' ')}"
    end
    
    NArray.to_na(x.unpack("s*"))
  end
 
  # build the waveform graph
  def build_graph(buckets, width, height, color)
    gc = Magick::Draw.new
    offset = 0
    scale = ([@max, (0-1)*@min].max/height + 1)*2
    midpoint = height/2
 
    (0..(buckets.size/2)-1).each do |i|
      low  = buckets[i,0]
      high = buckets[i,1]
      
      gc.stroke(color)
      gc.stroke_width(1)
      gc.line(i+offset, midpoint+low/scale, i+offset, midpoint+high/scale)
    end
    return gc
  end
end