From: William James <w_a_x_man@...>
Date: 2005-10-14T07:46:55+09:00
Subject: Re: A (minor) coding challenge


rubyhacker@gmail.com wrote:
> I knew somebody would bring that up. :)
>
> My gut feeling is that a page break can take the place
> of an arbitrary number of newlines. So I guess that means
> they are "consumed" in the page break. Additionally it
> seems "wrong" to start a page with blank lines.
>
> The only reason for preserving the extra blank lines is
> in case the text happened to use them significantly, e.g.,
> to separate sections or before/after an inset quotation.
>


Lines_per_page = 60

# Read and parse a file.
def grab( i )
  IO.read( ARGV[i] ).split( /^((?:[ \t]*\n)*[ \t]*\n)/ ).map{ |s|
    s.scan( /.*?\n|.+$/ ) }
end

texts = grab(0).zip(grab(1)).inject([]){ |arr,pair|
  m = [ pair.first.size, pair.last.size ].max
  if pair.first.first =~ /\S/
    # Equalize lengths of parallel paragraphs.
    2.times { |i| pair[i] += Array.new( m - pair[i].size ) { "" } }
    arr << pair
  else
    # Equalize runs of blank lines and make them breakable.
    m.times { arr << [ [""], [""] ] }
  end
  arr
}

class Array
  def page_break
    each { |handle|  handle.puts "----" }
  end
end

handles = []
2.times {|i| handles << File.open( "out-junk#{ i }", "w" ) }
count = 0

texts.each { |x|
  psize = x.first.size
  # Print paragraph or blank line.
  if psize > Lines_per_page - count
    handles.page_break
    count = 0
  end
  # Don't print blank lines at top of page.
  if count > 0  or  x.first.first =~ /\S/
    2.times { |i|  handles[i].puts x[i] }
    count += psize
  end
}

handles.each { |h| h.close }