EPUBChop 0.0.1 → 0.0.6

checksums.yaml

@@ -1,15 +1,15 @@
 ---
 !binary "U0hBMQ==":
   metadata.gz: !binary |-
-    NTk5MTRjMjQ1ZDk2YTEzM2E3MWNkN2ViODEzYzdlYWQ4ODE0YWE4NA==
+    MmM1ZTY5M2E0NjMwN2ViZDFkYzUzODAyZmZhN2VmOGVkZTkwNTNkYQ==
   data.tar.gz: !binary |-
-    YzYyMTA1YmYzOWY1N2UwNWRlM2ZiOTIwMmU0NTRhNGQ2YjE3YTc3Nw==
+    N2IwZThjYjA2Yjg3YjRhZDBiOTliMDY5Y2FmMzJmMjc4YTI3NGI3MA==
 SHA512:
   metadata.gz: !binary |-
-    MjI4ZDgzNWY0NzI3NmQ4YzAzNzNlNTZkMGMzZDA4MjIwMmVhOTQ4Y2EwODI5
-    ZWZjNDNkNDRhOWI4N2YxYWMxZjc5MDU2MjFkMTIzYWQ2MTk5YmI2YTczZjEx
-    ZWFjMWY4YTgwN2FkYjJiOGNlYTJhNTk5ZGY3N2VlZDE5MGU0NWM=
+    MTg1YWMwYmU5NzI1ZTEwZTQxNzJlM2M0YzU3MGY2ZGZjZTE4NDk1ZmJmMDkw
+    OTRkN2M0OTQ3ZDQxYThhMjRlN2ZhZjA5ZGExODIyNTg1NDczNTQ4MWM0MjU4
+    MzdmNDMyMWNiMDNhNzQ4ZmQ3NDY3ODgxNzQ2MjQ2ZDI5MmI1MGY=
   data.tar.gz: !binary |-
-    YWYyZDNiMDFkOGExMWY5MGFiM2Y4MDdkYWQ3MWNlMDkxMTQ2MDkzNzIxOWE1
-    Mzg3ZDBhNGVmMGJiZmQ0ODgzMmQzYmFkZWU2ZmNhYmZkMjUxMzc0NDQzNzE1
-    YWNhOGZhMTVmMzhiODFhMTY1ODAzNGE2MDI5YmE5MzI4MGI3ZmI=
+    NTM0NzdkZDNmY2E3MzkwOGU0ODQxZjA5YmQ4ZWRjNDM1N2JlYzhkY2Q5YTcy
+    MDZiMjUyZDZmNzY4NDE1YzJhZTA1NzY0MjUzOWQ1ZDc3ZmQ3N2FkMzBjYjZm
+    NzQ3NGM2ZDUyODU0ZmEwNTA4OTQ4NGUwYTJlNDgzNmJlNDUzYjg=

data/EPUBChop.gemspec

@@ -10,7 +10,7 @@ Gem::Specification.new do |spec|
   spec.email         = ["mehmet@celik.be"]
   spec.description   = %q{Create EPUB previews}
   spec.summary       = %q{Removes unwanted content from an EPUB}
-  spec.homepage      = ""
+  spec.homepage      = "https://github.com/mehmetc/EPUBChop"
   spec.license       = "MIT"
 
   spec.files         = `git ls-files`.split($/)

data/README.md

@@ -19,10 +19,14 @@ where [options] are:
 ```
 
 ### Example:
+Create a new EPUB with 10% of the content all other pages should contain the lines "Want to read more? Buy the book!"
 ```ruby
 epubchop --words 10 --base percentage -line1 "Want to read more?" -line2 "Buy the book!" my.epub
 ```
 
+This gem depends on [![epubinfo](http://github.com/chdorner/epubinfo)] I made some additions to the gem but they are still in a branch. Until they get accepted I'll be using the [![epubinfo_with_toc](https://github.com/mehmetc/epubinfo/tree/table_of_contents)]
+gem.
+
 ## Contributing to EPUBChop
 * Fork the project.
 * Create a new branch to implement your bugfixes or features

data/bin/epubchop

@@ -18,6 +18,7 @@ BANNER
   opt :base,  "How to interprete the --words options... Possible value: percentage", :type => :string, :default => 'percentage'
   opt :line1, "Text that is shown on line 1 of the chopped pages", :type => :string, :default => 'Continue reading?'
   opt :line2, "Text that is shown on line 2 of the chopped pages", :type => :string, :default => 'Go to your local library or buy the book.'
+  opt :chop_by, "Follow the SPINE or the NCX of the ePub", :type => :string, :default => :spine
 end
 
 Trollop::die "need an EPUB file name" if ARGV.empty?
@@ -30,11 +31,12 @@ begin
     text  = []
     text << options[:line1] if options.has_key?(:line1)
     text << options[:line2] if options.has_key?(:line2)
+    chop_by << options[:chop_by]
 
     puts 'loading EPUB'
     b=EPUBChop.get(filename)
     puts 'chopping EPUB'
-    c=b.chop({:base => base.to_s, :words => words, :text => text})
+    c=b.chop({:base => base.to_s, :words => words, :text => text, :chop_by => chop_by})
     puts 'rebuilding EPUB'
     FileUtils.move(c, "chopped_#{File.basename(filename)}")
 

data/lib/EPUBChop/chop.rb

@@ -10,7 +10,6 @@ module EPUBChop
     def initialize(input, options ={})
       set_defaults(options)
 
-
       raise 'Please supply an input file name' if input.nil?
 
       #count the number of words in a file
@@ -31,14 +30,40 @@ module EPUBChop
       set_defaults(options)
 
       original_zip_file = @book.table_of_contents.parser.zip_file
+      extract_dir = extract_epub_to_tmp_dir(original_zip_file)
+
+      chop_files_in_tmp_dir(extract_dir)
+      remove_unused_media_from_tmp_dir(extract_dir)
+
+
+      return rebuild_epub_from_tmp_dir(extract_dir)
+    rescue Zip::ZipError => e
+      raise RuntimeError, "Error processing EPUB. #{e.message}"
+    rescue Exception => e
+      puts "Chopping went wrong. #{e.message}"
+      puts e.backtrace
+
+      return nil
+    ensure
+      FileUtils.remove_entry_secure(extract_dir)
+    end
+
+    private
+
+    def extract_epub_to_tmp_dir(original_zip_file)
       #unzip in temp dir
       extract_dir = Dir.mktmpdir('epub_extract')
       original_zip_file.entries.each do |e|
         file_dir = File.split(e.name)[0]
-        Dir.mkdir(File.join(extract_dir, file_dir)) unless Dir.exists?(File.join(extract_dir, file_dir)) || file_dir.eql?(".")
+        FileUtils.mkdir_p(File.join(extract_dir, file_dir)) unless Dir.exists?(File.join(extract_dir, file_dir)) || file_dir.eql?('.')
         original_zip_file.extract(e, File.join(extract_dir, e.name))
       end
 
+      extract_dir
+    end
+
+
+    def chop_files_in_tmp_dir(extract_dir)
       #fix spine files
       filename_list = @resource_word_count.keys
       filename_list.each do |filename|
@@ -50,27 +75,39 @@ module EPUBChop
             FileUtils.rm("#{extract_dir}/#{filename}", :force => true)
             FileUtils.touch "#{extract_dir}/#{filename}"
             File.open("#{extract_dir}/#{filename}", 'w') do |f|
-              f.puts empty_file
+              f.puts empty_file_with_cover(filename)
             end
 
           else
+            #noinspection RubyResolve
             resource = Nokogiri::XML(@book.table_of_contents.resources[filename]) do |config|
               config.noblanks.nonet
             end
             resource.css('script').remove
             resource.css('style').remove
             resource_text = resource.at_css('body').text.split[0..processed_file_size]
-            resource_text_length = resource_text.length
+            #resource_text_length = resource_text.length
 
             # get a string that can be found
             data = nil
-            window_begin = 5
+            window_begin = default_window_begin = 5
             window_end = 0
             while data.nil?
-              look_for = resource_text[(processed_file_size - window_begin)..(processed_file_size - window_end)].join(' ')
-              data = resource.at_css("p:contains('#{look_for}')")
-              window_begin += 1
-              window_end += 1
+              look_for = resource_text[(processed_file_size - window_begin)..(processed_file_size - window_end)]
+
+              if look_for.nil?
+                window_begin = default_window_begin += 5
+                window_end = 0
+              else
+                data = resource.at_css("*:contains('#{look_for.join(' ')}')")
+                window_begin -= 1
+                window_end += 1
+
+                if window_begin == window_end
+                  window_begin = default_window_begin += 5
+                  window_end = 0
+                end
+              end
             end
 
             #limit on found string
@@ -92,8 +129,9 @@ module EPUBChop
           end
         end
       end
-      #TODO:remove unwanted media
+    end
 
+    def rebuild_epub_from_tmp_dir(extract_dir)
       #zip new ebook
       new_ebook_name = Tempfile.new(['epub', '.epub'], Dir.tmpdir)
       new_ebook_name_path = new_ebook_name.path
@@ -101,24 +139,56 @@ module EPUBChop
 
       zipfile = Zip::File.open(new_ebook_name_path, Zip::File::CREATE)
 
-      Dir[File.join(extract_dir, '**', '**')].each do |file|
+      epub_files = Dir[File.join(extract_dir, '**', '**')]
+
+      #minetype should be the first entry and should not be zipped. Else FIDO will not know that this is an EPUB
+      mimetype = epub_files.delete("#{extract_dir}/mimetype")
+      mimetype_entry = Zip::Entry.new(zipfile, mimetype.sub("#{extract_dir}/", ''), '', '', 0,0, Zip::Entry::STORED)
+      zipfile.add(mimetype_entry, mimetype) unless mimetype.nil?
+
+      #all the other files
+      epub_files.each do |file|
         zipfile.add(file.sub("#{extract_dir}/", ''), file)
       end
       zipfile.close
 
-      return new_ebook_name_path
-    rescue Zip::ZipError => e
-      raise RuntimeError, ''
-    rescue Exception => e
-      puts "Chopping went wrong. #{e.message}"
-      puts e.backtrace
+      new_ebook_name_path
+    end
 
-      return nil
-    ensure
-      FileUtils.remove_entry_secure(extract_dir)
+    #noinspection RubyInstanceMethodNamingConvention
+    def remove_unused_media_from_tmp_dir(extract_dir)
+      #TODO: remove other media
+      #TODO: rebuild toc.ncx and content.opf
+      remove_unused_images_from_tmp_dir(extract_dir)
+    end
+
+    #noinspection RubyInstanceMethodNamingConvention
+    def remove_unused_images_from_tmp_dir(extract_dir)
+      puts 'removing unused media'
+      not_to_be_deleted_images = []
+      all_images = @book.table_of_contents.resources.images.map {|i| i[:uri]}
+      @book.table_of_contents.resources.html.each do |resource|
+        file = Nokogiri::HTML(File.read("#{extract_dir}/#{resource[:uri]}"))
+
+        all_images.each do |image|
+          i = image.split('/').last
+          data = file.at_css("img[src$='#{i}']")
+
+          if data
+            not_to_be_deleted_images << image
+          end
+        end
+      end
+
+      to_be_deleted_images = (all_images - not_to_be_deleted_images)
+      to_be_deleted_images.each do |image|
+        puts "\t\tremoving #{image}"
+        File.delete("#{extract_dir}/#{image}") if File.exists?("#{extract_dir}/#{image}")
+      end
+
+      to_be_deleted_images
     end
 
-    private
 
     def set_defaults(options)
       @words = options[:words] || 10
@@ -130,34 +200,69 @@ module EPUBChop
         @text1 = options[:text] || 'Continue reading? Go to your local library or buy the book.'
         @text2 = ''
       end
+
+      @chop_by = options[:chop_by] || :spine
     end
 
-    def empty_file
+    def empty_file_with_cover(filename)
+      number_of_subdirectories = filename.split('/').size - 1
+
+      cover_path = ''
+      number_of_subdirectories.times{ cover_path += '../'}
+
+      cover_path += @book.cover && @book.cover.exists? ? @book.cover.exists?.to_s : ''
+
       data = <<DATA
 <?xml version="1.0" encoding="utf-8" standalone="no"?>
-<!DOCTYPE html>
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">
 <html xmlns="http://www.w3.org/1999/xhtml">
-<head>
-<title>Read more</title>
-</head>
-<body>
-<center>
-<div style='width:100%;border:1px solid black;margin-top:20px;padding:5px'>
-<div><h2>#{@text1}</h2></div>
-<div><h2>#{@text2}</h2></div>
-</div>
-</center>
+  <head>
+      <title>Read more</title>
+  </head>
+
+  <body>
+  <div style="margin-top:100px;width:500px;margin-left:auto;margin-right:auto;">
+    <div style='text-align:center;'>
+      <h2>#{CGI.escape_html(@text1 ? @text1 : '')}</h2>
+      <span>#{CGI.escape_html(@text2 ? @text2 : '')}</span>
+    </div>
+
+    <div style="margin-top:20px;">
+      <div style="float:left;margin-right:30px;max-height: 190px; min-height: 120px; width: 125px;">
+        <img src="#{cover_path}" alt="" style="width:100%" />
+      </div>
+
+      <div style='padding-top:10px;'>
+        <h3>#{CGI.escape_html(@book.titles.first ? @book.titles.first : '' )}</h3>
+      </div>
+
+      <div>
+        <h4>#{CGI.escape_html(@book.creators.first ? @book.creators.first.name : '')}</h4>
+      </div>
+
+    </div>
+
+    <br />
+
+    <div style="clear:both;text-align:center;font-size:0.5em;"> #{CGI.escape_html(@book.rights ? @book.rights : '')} </div>
+  </div>
 </body>
 </html>
+
 DATA
+
+      data
     end
 
     def count_words(input)
       @book = EPUBInfo.get(input)
       resource_word_count = {}
       if @book
-        @book.table_of_contents.resources.spine.each do |resource|
+        chop_by = @chop_by.eql?(:ncx)  ? @book.table_of_contents.resources.ncx : @book.table_of_contents.resources.spine
+
+        chop_by.each do |resource|
           raw = Nokogiri::HTML(@book.table_of_contents.resources[resource[:uri]]) do |config|
+            #noinspection RubyResolve
             config.noblanks.nonet
           end
           raw.css('script').remove
@@ -187,11 +292,14 @@ DATA
       resource_allowed_word_count = @resource_word_count.select do |r|
         (word_counter += @resource_word_count[r]) < allowed_words
       end
+
       word_counter = resource_allowed_word_count.values.inject(0) { |sum, i| sum + i }
 
       how_many_words_left = allowed_words - word_counter
       if how_many_words_left > 0
         resource_to_split_name = @resource_word_count.keys[resource_allowed_word_count.length]
+
+        #noinspection RubyLocalVariableNamingConvention
         word_count_of_resource_to_split = @resource_word_count[resource_to_split_name]
         if  how_many_words_left < word_count_of_resource_to_split
           resource_allowed_word_count.store(resource_to_split_name, how_many_words_left)

data/lib/EPUBChop/version.rb

@@ -1,3 +1,3 @@
 module EPUBChop
-  VERSION = "0.0.1"
+  VERSION = "0.0.6"
 end

data/spec/epubchop_spec.rb

@@ -4,7 +4,7 @@ require 'spec_helper'
 describe 'EPUBChop' do
     before(:all) do
       #chop EPUB at 10% of total words
-      @chop = EPUBChop.get('./spec/Verne_20000_West_pg11393.epub', {:base => :percentage, :words => 10})
+      @chop = EPUBChop.get('./spec/epub/Verne_20000_West_pg11393.epub', {:base => :percentage, :words => 10})
     end
 
     it 'load an epub' do

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: EPUBChop
 version: !ruby/object:Gem::Version
-  version: 0.0.1
+  version: 0.0.6
 platform: ruby
 authors:
 - Mehmet Celik
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-10-28 00:00:00.000000000 Z
+date: 2014-01-20 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -114,10 +114,11 @@ files:
 - lib/EPUBChop/chop.rb
 - lib/EPUBChop/version.rb
 - lib/trollop.rb
-- spec/Verne_20000_West_pg11393.epub
+- spec/epub/Verne_20000_West_pg11393.epub
+- spec/epub/default.epub
 - spec/epubchop_spec.rb
 - spec/spec_helper.rb
-homepage: ''
+homepage: https://github.com/mehmetc/EPUBChop
 licenses:
 - MIT
 metadata: {}
@@ -142,7 +143,7 @@ signing_key:
 specification_version: 4
 summary: Removes unwanted content from an EPUB
 test_files:
-- spec/Verne_20000_West_pg11393.epub
+- spec/epub/Verne_20000_West_pg11393.epub
+- spec/epub/default.epub
 - spec/epubchop_spec.rb
 - spec/spec_helper.rb
-has_rdoc: