EPUBChop 0.0.7 → 0.0.10

checksums.yaml

@@ -1,15 +1,7 @@
 ---
-!binary "U0hBMQ==":
-  metadata.gz: !binary |-
-    ZDdjMWZlMTIyOTJmMjJiN2I0OGQxYTUzMjA5MTlkNzZhZjcwMDQ3MQ==
-  data.tar.gz: !binary |-
-    ZjdjY2JiNzkwY2RiZTIxMDMyM2M4YTU1MjY0OGMwOTZiYjI4NmY4Mw==
+SHA1:
+  metadata.gz: 2ff6270a266184b41507e29e43994de705c56357
+  data.tar.gz: a257fd9d69ba6eb453c936626b509cc40596adf5
 SHA512:
-  metadata.gz: !binary |-
-    ZjJkYTdmNDI4OGFkNWUxZDRlZjlkZWQ1NDZkYTA3MWE2MmQ3YWMwYmZjZjkz
-    NDZiZGVjMGEwNWY5ZjgwZjA2ZjQ4OTM4MDBhMGRlNWQ3ODk5Njc1ODhlY2U2
-    ZmVjNmEwNGYwYTQ1ZGZiNDc0Nzc4ODliZWI0N2Y1MjcxNDQzMGY=
-  data.tar.gz: !binary |-
-    ZTNlY2E2OTA4NTNkM2I0YWRjMDc1YTkxMWU5YjgyMDY4YWM0ODE2MGVjZjQ5
-    OGI2YmNjNWFmZjA1ZTI1OGViZjI0N2UyNjJiOTQ3MmRhOTUyOTYwZDIwNDc2
-    NGQ0ZWU1N2RhZDBmNGMyOGZlZWM1NzIwMDgzMGM3Y2FkZjdhYWI=
+  metadata.gz: 5b8d5d76d9aabb81e9f0afe92d2c0b3aa058b6be46ce9eb3dc6c61f15eceaaaa49a27a696a2063b6bc9158ddb4992be0020ba1f7072ff9b90c2cbdf73b286527
+  data.tar.gz: 47742a21f5173c931b35f82df4c4fa5ea2f23e2b040073a9f575f38cab819c34a100b3bf3f1dcdd6e05d88ebe3c44445c2dfadb5e378d6f509332371caa00577

data/bin/epubchop

@@ -19,6 +19,7 @@ BANNER
   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, "Follow the SPINE or the NCX of the ePub", :type => :string, :default => 'spine'
+  opt :verbose, "more loging true/false", :type => :boolean, :default => false
 end
 
 Trollop::die "need an EPUB file name" if ARGV.empty?
@@ -32,9 +33,10 @@ begin
     text << options[:line1] if options.has_key?(:line1)
     text << options[:line2] if options.has_key?(:line2)
     chop_by = options[:chop]
+    verbose = options[:verbose]
 
-    puts 'loading EPUB'
-    b=EPUBChop.get(filename, :chop_by => chop_by.to_sym)
+    puts "loading EPUB #{filename}"
+    b=EPUBChop.get(filename, :chop_by => chop_by.to_sym, :verbose => verbose)
     puts 'chopping EPUB'
     c=b.chop({:base => base.to_s, :words => words, :text => text})
     puts 'rebuilding EPUB'

data/lib/EPUBChop/chop.rb

@@ -1,3 +1,4 @@
+#encoding: UTF-8
 require 'nokogiri'
 require 'epubinfo'
 require 'tempfile'
@@ -38,12 +39,10 @@ module EPUBChop
 
       return rebuild_epub_from_tmp_dir(extract_dir)
     rescue Zip::ZipError => e
-      raise RuntimeError, "Error processing EPUB. #{e.message}"
+      raise RuntimeError, "Error processing EPUB #{@book.table_of_contents.parser.path}.\n #{e.message}", e.backtrace
     rescue Exception => e
-      puts "Chopping went wrong. #{e.message}"
-      puts e.backtrace
-
-      return nil
+      puts e.backtrace.join("\n")
+      raise RuntimeError, "Chopping went wrong for #{@book.table_of_contents.parser.path}.\n #{e.message}", e.backtrace
     ensure
       FileUtils.remove_entry_secure(extract_dir)
     end
@@ -80,50 +79,18 @@ module EPUBChop
 
           else
             #noinspection RubyResolve
-            resource = Nokogiri::XML(@book.table_of_contents.resources[filename]) do |config|
+            resource = Nokogiri::HTML(@book.table_of_contents.resources[filename]) do |config|
+            #resource = Nokogiri::HTML.parse(@book.table_of_contents.resources[filename], 'UTF-8') 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
-
-            # get a string that can be found
-            data = nil
-            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)]
-
-              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
+            resource.encoding = 'UTF-8'
 
-            #limit on found string
-            if data
-              next_data = data.next_element
-              while next_data
-                in_resource = resource.css(next_data.css_path)
-                in_resource.remove
-
-                next_data = data.nil? || data.next_element.to_s.length == 1 ? nil : data.next_element
-              end
-            end
+            resource = chop_file(resource, processed_file_size)
 
             #persist page
-            File.open("#{extract_dir}/#{filename}", 'w') do |f|
-              f.puts resource.to_xml(:save_with => Nokogiri::XML::Node::SaveOptions::NO_DECLARATION)
+            File.open("#{extract_dir}/#{filename}", 'w:UTF-8') do |f|
+              #  f.puts resource.to_xml(:save_with => Nokogiri::XML::Node::SaveOptions::NO_DECLARATION)
+              f.puts resource.serialize(:encoding => 'UTF-8', :save_with => Nokogiri::XML::Node::SaveOptions::NO_DECLARATION)
             end
 
           end
@@ -131,6 +98,61 @@ module EPUBChop
       end
     end
 
+    def chop_file(resource, processed_file_size)
+      #TODO: get a better algorithm to determine where to chop
+      return resource if resource.nil?
+
+      resource.css('script').remove
+      resource.css('style').remove
+      resource_text = resource.at_css('body').text.split[0..processed_file_size]
+
+      # get a string that can be found
+      data = nil
+      window_begin = default_window_begin = 5
+      window_end = 0
+      while data.nil?
+        puts "data window:#{(processed_file_size - window_begin)}..#{(processed_file_size - window_end)}" if @verbose
+        processed_window_begin = processed_file_size - window_begin
+        processed_window_end   = processed_file_size - window_end
+
+        processed_window_begin = 0 if processed_window_begin < 0
+        processed_window_end   = processed_file_size
+
+        look_for = resource_text[processed_window_begin..processed_window_end]
+
+        if look_for.nil?
+          window_begin = default_window_begin += 5
+          window_end = 0
+        else
+          look_for.map! {|m| m.gsub("'", "\'")}
+          data = resource.at_css("p:contains(\"#{look_for.join(' ')}\")")
+          data = resource.at_css("body:contains(\"#{look_for.join(' ')}\")") if data.nil?
+
+          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
+      if data
+        next_data = data.next_element
+        while next_data
+          in_resource = resource.css(next_data.css_path)
+          in_resource.remove
+
+          next_data = data.nil? || data.next_element.to_s.length == 1 ? nil : data.next_element
+        end
+      end
+
+      resource
+    end
+
+
     def rebuild_epub_from_tmp_dir(extract_dir)
       #zip new ebook
       new_ebook_name = Tempfile.new(['epub', '.epub'], Dir.tmpdir)
@@ -143,7 +165,7 @@ module EPUBChop
 
       #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)
+      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
@@ -164,13 +186,14 @@ module EPUBChop
 
     #noinspection RubyInstanceMethodNamingConvention
     def remove_unused_images_from_tmp_dir(extract_dir)
-      puts 'removing unused media'
+      puts 'removing unused media' if @verbose
       not_to_be_deleted_images = []
-      all_images = @book.table_of_contents.resources.images.map {|i| i[:uri]}
+      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|
+          next if image.nil?
           i = image.split('/').last
           data = file.at_css("img[src$='#{i}']")
 
@@ -182,7 +205,8 @@ module EPUBChop
 
       to_be_deleted_images = (all_images - not_to_be_deleted_images)
       to_be_deleted_images.each do |image|
-        puts "\t\tremoving #{image}"
+        next if image.nil?
+        puts "\t\tremoving #{image}" if @verbose
         File.delete("#{extract_dir}/#{image}") if File.exists?("#{extract_dir}/#{image}")
       end
 
@@ -202,13 +226,14 @@ module EPUBChop
       end
 
       @chop_by = options[:chop_by] || :spine
+      @verbose = options[:verbose] || false
     end
 
     def empty_file_with_cover(filename)
       number_of_subdirectories = filename.split('/').size - 1
 
       cover_path = ''
-      number_of_subdirectories.times{ cover_path += '../'}
+      number_of_subdirectories.times { cover_path += '../' }
 
       cover_path += @book.cover && @book.cover.exists? ? @book.cover.exists?.to_s : ''
 
@@ -233,7 +258,7 @@ module EPUBChop
       </div>
 
       <div style='padding-top:10px;'>
-        <h3>#{CGI.escape_html(@book.titles.first ? @book.titles.first : '' )}</h3>
+        <h3>#{CGI.escape_html(@book.titles.first ? @book.titles.first : '')}</h3>
       </div>
 
       <div>
@@ -259,7 +284,7 @@ DATA
       resource_word_count = {}
       if @book
         resources = @book.table_of_contents.resources.to_a
-        chop_by = @chop_by.eql?(:ncx)  ? @book.table_of_contents.resources.ncx : @book.table_of_contents.resources.spine
+        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|

data/lib/EPUBChop/version.rb

@@ -1,3 +1,3 @@
 module EPUBChop
-  VERSION = "0.0.7"
+  VERSION = "0.0.10"
 end

metadata

@@ -1,99 +1,99 @@
 --- !ruby/object:Gem::Specification
 name: EPUBChop
 version: !ruby/object:Gem::Version
-  version: 0.0.7
+  version: 0.0.10
 platform: ruby
 authors:
 - Mehmet Celik
-autorequire: 
+autorequire:
 bindir: bin
 cert_chain: []
-date: 2014-02-19 00:00:00.000000000 Z
+date: 2014-02-20 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
-  requirement: !ruby/object:Gem::Requirement
+  version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
         version: '1.3'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
+  requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
         version: '1.3'
+  prerelease: false
+  type: :development
 - !ruby/object:Gem::Dependency
   name: rake
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
-  type: :development
   prerelease: false
+  type: :development
+- !ruby/object:Gem::Dependency
+  name: rspec
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
-- !ruby/object:Gem::Dependency
-  name: rspec
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
-  type: :development
   prerelease: false
+  type: :development
+- !ruby/object:Gem::Dependency
+  name: epubinfo_with_toc
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
-- !ruby/object:Gem::Dependency
-  name: epubinfo_with_toc
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
-  type: :runtime
   prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ! '>='
-      - !ruby/object:Gem::Version
-        version: '0'
+  type: :runtime
 - !ruby/object:Gem::Dependency
   name: rubyzip
-  requirement: !ruby/object:Gem::Requirement
+  version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
         version: '1.0'
-  type: :runtime
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
+  requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
         version: '1.0'
+  prerelease: false
+  type: :runtime
 - !ruby/object:Gem::Dependency
   name: nokogiri
-  requirement: !ruby/object:Gem::Requirement
+  version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
-  type: :runtime
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
+  requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
+  prerelease: false
+  type: :runtime
 description: Create EPUB previews
 email:
 - mehmet@celik.be
@@ -122,24 +122,24 @@ homepage: https://github.com/mehmetc/EPUBChop
 licenses:
 - MIT
 metadata: {}
-post_install_message: 
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
-  - - ! '>='
+  - - '>='
     - !ruby/object:Gem::Version
       version: '0'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
-  - - ! '>='
+  - - '>='
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.1.10
-signing_key: 
+rubyforge_project:
+rubygems_version: 2.2.2
+signing_key:
 specification_version: 4
 summary: Removes unwanted content from an EPUB
 test_files: