zip2mobi

zip2mobi.rb

#!/usr/bin/env ruby
# -*- coding: utf-8 -*-
require 'cgi'
require 'open-uri'
require 'rubygems'
require 'zipruby'
require 'RMagick'
require 'kconv'
require 'logger'
require 'amazon/aws'
require 'amazon/aws/search'

ENV['AMAZONRCDIR'] = './'
# settings to get author of the book
ASSOCIATES_ID = "YOUR_ID"
AWS_SECRET = 'YOUR_SECRET'
AWS_KEY_ID = "YOUR_AWS_KEY_ID"
# includes zip2mobi.rb, log/*, kindlegen
SCRIPTS_DIR = "/path/to/scripts/dir/"
# mobi and epub files are saved
MOBI_DIR = "/path/to/mobidir/"
# image file format to convert
SUPPORT_FORMAT = /\.(png|jpg|gif)$/
# image size
ROW = 1024
COL = 768
# log setting
$log = Logger.new("#{SCRIPTS_DIR}log/zip2mobi.log", 'daily')
$log.level = Logger::DEBUG

class Zip2mobi
include Amazon::AWS
include Amazon::AWS::Search

def convertZip(path, epubname)
  Zip::Archive.open(epubname, Zip::CREATE, Zip::NO_COMPRESSION) do |epub|
    epub.add_or_replace_buffer "mimetype", "application/epub+zip"
  end
  Zip::Archive.open(epubname) do |epub|
    epub.add_or_replace_buffer "META-INF/container.xml", container_xml
    xhtmls = []
    open(path) do | zipFile |
      Zip::Archive.open_buffer(zipFile.read) do |zip|
        images = zip.map do |f|
          if f.name.match(SUPPORT_FORMAT)
            [f.name] + f.name.scan(/(\d+)(\w?)/).map do |num, letter|
              "0000000000000000#{num}"[-16,16]+(letter.empty? ? " " : letter)
            end
          else
            nil
          end
        end
        sorted_images = images.compact.sort do |a, b|
          flg = nil
          [a.length, b.length].min.times do |i|
            flg = a[i+1]<=>b[i+1] if flg.nil? && a[i+1]!=b[i+1]
          end
          flg = 0 if flg.nil?
          flg
        end # sorted_images
        images = []
        sorted_images.each_with_index do |name, i|
          nname = name.first.gsub(/[^\w\/\.\-]/, '_')
          $log.debug name.first
          image = Magick::Image.from_blob(zip.fopen(name.first).read)[0]
          if image.rows > image.columns
              # comment out if like to change contrast
              # image.contrast#.contrast.contrast
              image.fuzz = '60%'
              im = image.trim()
              # trimed
              image = im unless (im.rows == 1)
              image.resize_to_fit!(COL, ROW)
              epub.add_or_replace_buffer "OEBPS/#{nname}", image.to_blob
              epub.add_or_replace_buffer "OEBPS/#{i}.xhtml", page_xhtml(nname, nname, image.columns, image.rows)
              $log.debug "added #{nname}"
              xhtmls << ["#{i}.xhtml", nname]
          else
              # split if landscape image
              image.resize_to_fit!(COL*2, ROW)
              [0, 1].each{|a|
                  d = image.crop((a>0)?0:(image.columns/2).floor, 0, image.columns/2, image.rows, true)
                  d.fuzz = '60%'
                  im = d.trim()
                  d = im unless (im.rows == 1)
                  d.resize_to_fit!(COL, ROW)
                  dname = nname.sub(/(\.[^\.]+)$/){"_#{a+1}#$1"}
                  epub.add_or_replace_buffer "OEBPS/#{dname}", d.to_blob
                  epub.add_or_replace_buffer "OEBPS/#{i}_#{a}.xhtml", page_xhtml(dname, dname, d.columns, d.rows)
                  $log.debug dname
                  xhtmls << ["#{i}_#{a}.xhtml", dname]
                  d.destroy!
                  i+=1
                  break if i == 2
              }
          end
          image.destroy!
          run_gc
        end
      end # open zipFile
    end # open path
    epub.add_or_replace_buffer "OEBPS/content.opf", content_opf(xhtmls)
    epub.add_or_replace_buffer "OEBPS/toc.ncx", toc_ncx(xhtmls)
  end # open epub
end

def run_gc
    fDisabled = GC.enable
    GC.start
    GC.disable if fDisabled
end

def container_xml
  <<__XML__
<?xml version="1.0"?>
<container version="1.0" xmlns="urn:oasis:names:tc:opendocument:xmlns:container">
  <rootfiles>
    <rootfile full-path="OEBPS/content.opf" media-type="application/oebps-package+xml" />
  </rootfiles>
</container>
__XML__
end

def content_opf(files)

  <<__XML__
<?xml version="1.0"?>
<package xmlns="http://www.idpf.org/2007/opf" unique-identifier="BookID" version="2.0">
    <metadata xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:opf="http://www.idpf.org/2007/opf">
        <dc:title>#{@title.toutf8}</dc:title>
        <dc:creator opf:role="aut">#{@author.toutf8}</dc:creator>
        <dc:language>ja</dc:language>
        <dc:identifier id="BookID" opf:scheme="URL">http://example.com/epub/sample/sample1.epub</dc:identifier>
    </metadata>
    <manifest>
        <item id="ncx" href="toc.ncx" media-type="application/x-dtbncx+xml"/>
#{files.map{|f| '        <item id="%s" href="%s" media-type="application/xhtml+xml"/>' % [CGI.escapeHTML(f[0]), CGI.escapeHTML(f[0])]}.join("\n")}
    </manifest>
    <spine toc="ncx">
#{files.map{|f| '        <itemref idref="%s"/>' % CGI.escapeHTML(f[0])}.join("\n")}
    </spine>
</package>
__XML__
end

def toc_ncx(files)
  xml = <<__XML__
<!DOCTYPE ncx PUBLIC "-//NISO//DTD ncx 2005-1//EN"
   "http://www.daisy.org/z3986/2005/ncx-2005-1.dtd">
<ncx xmlns="http://www.daisy.org/z3986/2005/ncx/" version="2005-1" dir="rtl">
    <head>
        <meta name="dtb:uid"
              content="http://example.com/epub/sample/sample1.epub"/>
        <meta name="dtb:depth" content="1"/>
        <meta name="dtb:totalPageCount" content="0"/>
        <meta name="dtb:maxPageNumber" content="0"/>
    </head>
    <docTitle>
        <text>sample</text>
    </docTitle>
    <navMap>
__XML__
  files.each_with_index do |f, i|
    xml += <<__XML__
        <navPoint id="navPoint-#{i+1}" playOrder="#{i+1}">
            <navLabel>
                <text>#{CGI.escapeHTML(f[1].to_s)}</text>
            </navLabel>
            <content src="#{CGI.escapeHTML(f[0])}"/>
        </navPoint>
__XML__
  end
  xml += <<__XML__
    </navMap>
</ncx>
__XML__
end

def page_xhtml(title, img, w, h)

  <<__XML__
<?xml version="1.0"?>
<html xmlns="http://www.w3.org/1999/xhtml" lang="en" xml:lang="en">
<head>
<title>#{CGI.escapeHTML title}</title>
<style>
img { vertical-align: middle; }
</style>
</head>
<body><img src="#{CGI.escapeHTML img}" width="#{CGI.escapeHTML w.to_s}" height="#{CGI.escapeHTML h.to_s}"/></body>
</html>
__XML__
end

def makemobi(zip_path)
    @title = File.basename(zip_path, ".zip")
    epub_path = "#{MOBI_DIR}#{@title}.epub"
    mobi_path = "#{MOBI_DIR}#{@title}.mobi"
    $log.debug "title: #{@title}"
    @author = get_author(@title)
    $log.debug "convert to #{epub_path}"
    $log.debug "convert to #{mobi_path}"
    convertZip(zip_path, epub_path) unless File.exist?(epub_path)
    command = "#{SCRIPTS_DIR}kindlegen \"#{epub_path}\" -unicode"
    $log.debug command
    $log.debug `#{command}` unless File.exist?(mobi_path)
end

def get_author(title)
    $log.debug "get author: #{title}"
    title = title.sub(/\s*(第\d+(巻|部)|(part\s*)?\d+)$/i, '')
    $log.debug "search: #{title}"
    request = Request.new(AWS_KEY_ID, ASSOCIATES_ID, 'jp', false)
    request.config['secret_key_id'] = AWS_SECRET
    il = ItemSearch.new('Books', {'Title' => title})
    response = request.search(il)
    response.item_search_response[0].items.item.each do |i|
        author = i.item_attributes.author if i.item_attributes.author
        $log.debug author.to_s
        return author if author
    end
    return "noname"
end
end

if ARGV.length>0
    start = Time.now
    zip = ARGV[0]
    $log.debug zip
    begin
        z2m = Zip2mobi.new()
        z2m.makemobi(zip)
        # settings to get author of the book
    rescue => error
        $log.error $!
        epub_path = "#{MOBI_DIR}#{File.basename(zip, ".zip")}.epub"
        mobi_path = "#{MOBI_DIR}#{File.basename(zip, ".zip")}.mobi"
        File.delete(epub_path) if File.exists?(epub_path)
        File.delete(mobi_path) if File.exists?(mobi_path)
    end
    cost = Time.now - start
    min = cost.divmod(60)[0].to_i
    sec = cost.divmod(60)[1].to_i
    $log.debug "zip2mobi cost: #{min}min #{sec}sec"
end