indirect/pdftoHTMLEBook.rb

## pdftoHTMLEBook.rb
#!/usr/bin/ruby -w

require 'fileutils'

$pageBreakTag = /<hr>\s<A name=[0-9]+><\/a>/i
$brTag = /<br>/i
$bodyTag = /<body[^>]*>/i

$fileHeaderTag = /file.*<br>/i

# Sadness, I know, but how else am I going to kill these?
$linesToKill = [ "Ursula K. LeGuin - The Ekumen 01 - ROCANNON'S WORLD<br>\n" ]

def cleanHTML( html )
  html = html.gsub $pageBreakTag, ''
  html = html.gsub $bodyTag, '<body>'

  final = ""

  sum = 0
  count = 0
  html.each_line do |line|
    sum += line_length(line) #.length()
    count += 1
  end

  avg_line_length = 0.8*sum/count

  html.each_line do |line| #for line in html.split( "\n" ) do
    if( $fileHeaderTag.match( line ) or $linesToKill.include?( line ) ) then
      next
    end

    @inBody ||= $bodyTag.match(line)

    if $brTag.match( line ) and line_length(line) > avg_line_length then
      line = line.gsub $brTag, ''
    else
      line << "<br>" if @inBody
    end

    final << line
  end

  return final
end

def line_length( html )
  return removeTags(html).length()
end

def removeTags( html )
  tag = /<[^>]*>/
  return html.gsub(tag, '')
end


if $0 == __FILE__ then

  pdf_files = ARGV.detect{|f| ".pdf" == File.extname(f).downcase }

  pdf_files.each do |pdf_file|
    directory = File.dirname(pdf_file)
    filename = File.basename(pdf_file, ".pdf") + ".html"
    html = `pdftohtml -stdout -q "#{ARGV[0]}"`
    File.open(filename, "w"){|f| f.write(cleanHTML(html))}

    puts filename
  end

end
	#!/usr/bin/ruby -w

	require 'fileutils'

	$pageBreakTag = /<hr>\s<A name=[0-9]+><\/a>/i
	$brTag = /<br>/i
	$bodyTag = /<body[^>]*>/i

	$fileHeaderTag = /file.*<br>/i

	# Sadness, I know, but how else am I going to kill these?
	$linesToKill = [ "Ursula K. LeGuin - The Ekumen 01 - ROCANNON'S WORLD<br>\n" ]

	def cleanHTML( html )
	html = html.gsub $pageBreakTag, ''
	html = html.gsub $bodyTag, '<body>'

	final = ""

	sum = 0
	count = 0
	html.each_line do \|line\|
	sum += line_length(line) #.length()
	count += 1
	end

	avg_line_length = 0.8*sum/count

	html.each_line do \|line\| #for line in html.split( "\n" ) do
	if( $fileHeaderTag.match( line ) or $linesToKill.include?( line ) ) then
	next
	end

	@inBody \|\|= $bodyTag.match(line)

	if $brTag.match( line ) and line_length(line) > avg_line_length then
	line = line.gsub $brTag, ''
	else
	line << "<br>" if @inBody
	end

	final << line
	end

	return final
	end

	def line_length( html )
	return removeTags(html).length()
	end

	def removeTags( html )
	tag = /<[^>]*>/
	return html.gsub(tag, '')
	end




	if $0 == __FILE__ then

	pdf_files = ARGV.detect{\|f\| ".pdf" == File.extname(f).downcase }

	pdf_files.each do \|pdf_file\|
	directory = File.dirname(pdf_file)
	filename = File.basename(pdf_file, ".pdf") + ".html"
	html = `pdftohtml -stdout -q "#{ARGV[0]}"`
	File.open(filename, "w"){\|f\| f.write(cleanHTML(html))}

	puts filename
	end

	end