ebook_tools 0.1.4 → 0.1.5

data/ebook_tools.gemspec

@@ -2,13 +2,13 @@
 
 Gem::Specification.new do |s|
   s.name = %q{ebook_tools}
-  s.version = '0.1.4'
+  s.version = '0.1.5'
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["Aaron"]
-  s.date = %q{2013-04-05}
+  s.date = %q{2013-06-04}
   s.description = %q{电子书工具集.}
-  s.email = %q{aaron@nonobo.com}
+  s.email = %q{yalong1976@gmail.com}
   s.require_paths = ["lib"]
   s.requirements = ["none"]
   s.summary = %q{电子书工具集.}
@@ -25,15 +25,16 @@ Gem::Specification.new do |s|
     "bin/doc_book_import_mongo",
     "bin/para_import_scheduling",
     "bin/xml2json",
+    "lib/doc_book_in_mongo.rb",    
     "lib/ebook_tools.rb",
-    "lib/txt_book.rb",
-    "lib/header_detect.rb",
-    "lib/pdf.rb",
-    "lib/txt.rb",
     "lib/epub.rb",
+    "lib/epub_book.rb",
+    "lib/header_detect.rb",    
+    "lib/paras_in_mongo.rb",    
+    "lib/pdf.rb",    
+    "lib/txt.rb",    
+    "lib/txt_book.rb",
     "lib/utils.rb",
-    "lib/paras_in_mongo.rb",
-    "lib/doc_book_in_mongo.rb",
     "workers/para_import_worker.rb",
     "ebook_tools.gemspec"
   ]

data/lib/ebook_tools.rb

@@ -1,6 +1,6 @@
 #!/usr/bin/env ruby
 # encoding: UTF-8
-['utils','epub','txt','pdf','header_detect','txt_book'].each do |file|
+['utils','epub','txt','pdf','header_detect','txt_book','epub_book'].each do |file|
   require File.join(File.dirname(__FILE__),file)
 end
 
@@ -202,27 +202,34 @@ module EbookTools
 
   def extract_book_struct_to_file(source,destination,options={})
     options[:title] ||= File.basename(source,File.extname(source))
-    content = case File.extname(source)
-      when '.html'
-        extract_text_from_file(source,'.html')
-      when '.epub'
-        text = extract_text_from_file(source,'.epub')
-        sanitize_for_epub_text(text)
-      when '.txt'
-        File.open(source).read
-    end
-    txt_book = TxtBook.new(content,options)
-    docbook_xml = txt_book.to_doc_book
-    if docbook_xml
-      FileUtils.mkdir_p(File.dirname(destination)) unless Dir.exists?(File.dirname(destination))
-      File.open(destination,'wb'){|file|file.write docbook_xml}
-      puts "目录结构:"
-      puts txt_book.toc_to_text
-      puts "共修复#{txt_book.breaklines_count}个断点."
-      return true
+    if File.extname(source) == '.epub'
+      epub_book = EpubBook.new(source,options)
+      docbook_xml = epub_book.to_doc_book
+      if docbook_xml
+        write_doc_book(destination,docbook_xml)
+        puts "目录结构:"
+        puts epub_book.toc_to_text
+        return true
+      end
     else
-      return nil
+      content = case File.extname(source)
+        when '.html'
+          Utils.extract_text_from_file(source,'.html')
+        when '.txt'
+          File.open(source).read
+      end
+      txt_book = TxtBook.new(content,options)
+      docbook_xml = txt_book.to_doc_book
+      if docbook_xml
+        write_doc_book(destination,docbook_xml)
+        puts "目录结构:"
+        puts txt_book.toc_to_text
+        puts "共修复#{txt_book.breaklines_count}个断点."
+        return true
+      end
     end
+
+    return nil
   end
 
   # batch_extract_from_dir
@@ -262,6 +269,11 @@ module EbookTools
     end
   end 
 
+  def write_doc_book(destination, docbook_xml)
+    FileUtils.mkdir_p(File.dirname(destination)) unless Dir.exists?(File.dirname(destination))
+    File.open(destination,'wb'){|file|file.write docbook_xml}    
+  end
+
   # text_paras_repair
   # 对文本文件格式中的中断段落进行修复
   def text_paras_repair(source_file,target_file,options={})
@@ -271,21 +283,6 @@ module EbookTools
     File.open(target_file,'w'){|file| file.write content}
   end
 
-  def extract_text_from_file(filename,format)
-    txt_file = File.basename(filename,format)
-    if !filename.include?("'")
-      cmd = %Q(ebook-convert '#{filename}' '#{txt_file}.txt')
-    elsif !filename.include?('"')
-      cmd = %Q(ebook-convert "#{filename}" "#{txt_file}.txt")
-    else
-      cmd = %Q(ebook-convert #{filename} #{txt_file}.txt)
-    end
-    output = `#{cmd}`
-    content = File.open("#{txt_file}.txt").read
-    FileUtils.remove_file("#{txt_file}.txt",true)
-    return content
-  end
-
   # sanitize_for_epub_text
   def sanitize_for_epub_text(content)
     return content if content.blank?

data/lib/epub_book.rb

@@ -0,0 +1,164 @@
+# encoding: utf-8
+require 'uuid'
+require 'cgi'
+
+# epub_book
+#  处理EPUB书的类。
+class EpubBook
+  attr_reader :title,:author,:publisher,:pubdate,:isbn,:content,:outline
+
+  def initialize(filename,options={})
+    raise '无效的文件' unless File.exists?(filename)
+    @title = options[:title]
+    @author = options[:author]
+    @publisher = options[:publisher]
+    @pubdate= options[:pubdate]
+    @isbn = options[:isbn]
+
+    text = Utils.extract_text_from_file(filename,'.epub')
+    unless  Utils.detect_utf8(text)
+      text = Utils.to_utf8(text)
+    end
+    text = preprocess_content(text)
+    @outline, @content = extract_for_epub_text(text)
+  end
+
+  def toc_to_text
+    outline
+  end
+
+  def to_doc_book
+    build_doc_book(@outline,@content,{:title=>title,:publisher=>publisher,:pubdate=>pubdate,:author=>author,:isbn=>isbn})
+  end
+
+
+  private
+    def preprocess_content(content)
+      paras = extract_paras(content)
+      paras.join("\n")
+    end
+
+    def extract_paras(content)
+      paras = []
+      return paras if content.blank?
+      content.each_line do |line|
+        text = Utils.clean_text(line)
+        paras << text if text.length > 0
+      end
+      paras
+    end
+
+    def build_doc_book(outline,content,options={})
+      doc_toc = gen_docbook_toc(outline.split("\n"))
+
+      doc_content = gen_docbook_content(content)
+
+<<-EOS
+<?xml version="1.0" encoding="utf-8"?>
+      <book xmlns="http://docbook.org/ns/docbook" version="5.0" id="#{UUID.generate}">
+      <info>
+      <title>#{options[:title]}</title>
+      <authorgroup>
+      <author><personname>#{options[:author]}</personname></author>
+      </authorgroup>
+      <pubdate>#{options[:pubdate]}</pubdate>
+      <publisher><publishername>#{options[:publisher]}</publishername></publisher>
+      </info>
+      #{doc_toc}
+      #{doc_content}
+      </book>
+EOS
+    end
+
+    def gen_docbook_toc(toc)
+      "<toc><title>Table of contents</title>#{gen_docbook_tocdiv(toc)}</toc>"
+    end
+
+    def gen_docbook_tocdiv(toc)
+      toc.map do |item|
+        text = Utils.escape_html(Utils.clean_text(item))
+        "<tocdiv><title>#{item}</title></tocdiv>"
+      end.join("")
+    end
+
+    def gen_docbook_content(content)
+      paras = extract_paras(content)
+      paras_content = paras.map do |para|
+        text = Utils.escape_html(Utils.clean_text(para))
+        "<para id='#{UUID.generate}'>#{text}</para>"
+      end.join("\n")
+      "<sect1>#{paras_content}</sect1>"
+    end
+
+    # extract_for_epub_text
+    def extract_for_epub_text(content)
+      return content if content.blank?
+      if outline_type?(content)
+        extract_outline_with_content(content)
+      elsif toc_type?(content)
+        extract_toc_with_content(content)
+      else
+        ['',content]
+      end
+    end
+
+    def extract_outline_with_content(content)
+      outline_flag = false
+      lines = []
+      outline = []
+      content.each_line do |line|
+        if line.strip.downcase == 'document outline'
+          outline_flag = true
+          next
+        end
+        unless outline_flag
+          lines << line
+        else
+          outline << line;
+        end
+      end
+      [outline.join("") , lines.join("")]
+    end
+
+    def extract_toc_with_content(content)
+      toc = []
+      lines = []
+
+      paras = extract_paras(content)
+      index = paras.index('Content')
+      paras = paras[(index+1)..-1]
+
+      point = nil
+
+      paras.each_with_index do |para, index|
+        if toc.include?(para)
+          point = index
+          break
+        else
+          toc << para
+        end
+      end
+
+      lines = paras[(point+1)..-1]
+      [toc.join("\n") , lines.join("\n")]
+    rescue
+      ['', content]
+    end
+
+    def outline_type?(content)
+      content.each_line do |line|
+          return true if line.strip.downcase  == 'document outline'
+      end
+      false
+    end
+
+    def toc_type?(content)
+      toc_flag = false
+      toc_flag1 = false
+      content.each_line do |line|
+          toc_flag = true if line.strip.downcase == '目录'
+          toc_flag1 = true if line.strip.downcase == 'content'
+      end
+      toc_flag && toc_flag1
+    end
+end

data/lib/paras_in_mongo.rb

@@ -2,6 +2,7 @@
 require 'moped'
 require 'nokogiri'
 require 'active_support'
+require 'active_support/core_ext/hash'
 
 module ParasInMongo
   extend self

data/lib/txt_book.rb

@@ -87,18 +87,22 @@ class TxtBook
   end
 
   def toc
-    @toc ||= extract_toc_from_struct(struct_content)
+    @toc ||= extract_toc_from_struct(struct_content) if struct_content
   end
 
   def toc_to_text
-    gen_toc(toc) do |item,children|
-      "#{item[:title]}\n#{children}"
+    if toc
+      gen_toc(toc) do |item,children|
+        "#{item[:title]}\n#{children}"
+      end
     end
   end
 
   def to_doc_book
     if struct_content
       build_doc_book(struct_content,{:title=>title,:publisher=>publisher,:pubdate=>pubdate,:author=>author,:isbn=>isbn})    
+    else
+      build_doc_book(content,{:title=>title,:publisher=>publisher,:pubdate=>pubdate,:author=>author,:isbn=>isbn})
     end
   end
 
@@ -184,12 +188,15 @@ class TxtBook
     marked_content
   end
 
-  def build_doc_book(struct,options={})
-    doc_toc = gen_docbook_toc(toc)
+  def build_doc_book(content,options={})
+    doc_toc = gen_docbook_toc(toc) if toc
 
-    struct = struct.map{|item| item if item.is_a?(Hash)}.compact
-
-    doc_content = gen_docbook_content(struct)
+    doc_content =  if content.is_a?(Array)
+      struct = content.map{|item| item if item.is_a?(Hash)}.compact
+      gen_docbook_content_with_struct(struct)
+    else
+      gen_docbook_content(content)
+    end
 
 <<-EOS
 <?xml version="1.0" encoding="utf-8"?>
@@ -208,6 +215,8 @@ class TxtBook
 EOS
   end
 
+
+
   def build_struct(content)
     stack = Array.new(8)
     struct = []
@@ -314,18 +323,20 @@ EOS
   end
 
   def extract_toc_from_struct(struct)
-    toc = []
-    struct.each do |item|
-      if item.is_a?(Hash)
-        children = []
-        if item[:children].any?
-          children = extract_toc_from_struct(item[:children])
+    if struct
+      toc = []
+      struct.each do |item|
+        if item.is_a?(Hash)
+          children = []
+          if item[:children].any?
+            children = extract_toc_from_struct(item[:children])
+          end
+          item_hash = {:title=>item[:title], :type=> item[:type],:children=>children}
+          toc << item_hash
         end
-        item_hash = {:title=>item[:title], :type=> item[:type],:children=>children}
-        toc << item_hash
       end
+      toc
     end
-    toc
   end
 
   def gen_docbook_toc(toc)
@@ -350,7 +361,16 @@ EOS
     end
   end
 
-  def gen_docbook_content(struct)
+  def gen_docbook_content(content)
+    paras = extract_paras(content)
+    paras_content = paras.map do |para|
+      text = Utils.escape_html(Utils.clean_text(para))
+      "<para id='#{UUID.generate}'>#{text}</para>"
+    end.join("\n")
+    "<sect1>#{paras_content}</sect1>"
+  end
+
+  def gen_docbook_content_with_struct(struct)
     content = []
     struct.each do |item|
       if item.is_a?(Hash)

data/lib/utils.rb

@@ -256,4 +256,19 @@ module Utils
     sections
   end
 
+  def extract_text_from_file(filename,format)
+    txt_file = File.basename(filename,format)
+    if !filename.include?("'")
+      cmd = %Q(ebook-convert '#{filename}' '#{txt_file}.txt')
+    elsif !filename.include?('"')
+      cmd = %Q(ebook-convert "#{filename}" "#{txt_file}.txt")
+    else
+      cmd = %Q(ebook-convert #{filename} #{txt_file}.txt)
+    end
+    output = `#{cmd}`
+    content = File.open("#{txt_file}.txt").read
+    FileUtils.remove_file("#{txt_file}.txt",true)
+    return content
+  end  
+
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: ebook_tools
 version: !ruby/object:Gem::Version
-  version: 0.1.4
+  version: 0.1.5
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-04-05 00:00:00.000000000 Z
+date: 2013-06-04 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: uuid
@@ -156,7 +156,7 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '0'
 description: 电子书工具集.
-email: aaron@nonobo.com
+email: yalong1976@gmail.com
 executables:
 - ebook_tools
 - para_import_mongo
@@ -171,15 +171,16 @@ files:
 - bin/doc_book_import_mongo
 - bin/para_import_scheduling
 - bin/xml2json
+- lib/doc_book_in_mongo.rb
 - lib/ebook_tools.rb
-- lib/txt_book.rb
+- lib/epub.rb
+- lib/epub_book.rb
 - lib/header_detect.rb
+- lib/paras_in_mongo.rb
 - lib/pdf.rb
 - lib/txt.rb
-- lib/epub.rb
+- lib/txt_book.rb
 - lib/utils.rb
-- lib/paras_in_mongo.rb
-- lib/doc_book_in_mongo.rb
 - workers/para_import_worker.rb
 - ebook_tools.gemspec
 homepage: