mobi 0.1.2 → 0.2.0

data/.rspec

@@ -0,0 +1,2 @@
+--color
+--format documentation

data/CHANGELOG.md

@@ -0,0 +1,5 @@
+= Changelog
+
+== 0.1.2
+
+* Trying to instantiate Mobi::Metadata with an invalid mobi file now raises an InvalidMobi exception 

data/Gemfile

@@ -6,8 +6,8 @@ source "http://rubygems.org"
 # Add dependencies to develop your gem here.
 # Include everything needed to run rake, tests, features, etc.
 group :development do
-  gem "shoulda", ">= 0"
-  gem "bundler", "~> 1.0.0"
-  gem "jeweler", "~> 1.5.1"
-  gem "rcov", ">= 0"
+  gem 'rspec', '~> 2.11.0'
+  gem 'rr', '~> 1.0.4'
+  gem 'bundler', '~> 1.1.0'
+  gem 'jeweler', '~> 1.8.0'
 end

data/Gemfile.lock

@@ -1,20 +1,32 @@
 GEM
   remote: http://rubygems.org/
   specs:
+    diff-lcs (1.1.3)
     git (1.2.5)
-    jeweler (1.5.1)
-      bundler (~> 1.0.0)
+    jeweler (1.8.3)
+      bundler (~> 1.0)
       git (>= 1.2.5)
       rake
-    rake (0.8.7)
-    rcov (0.9.9)
-    shoulda (2.11.3)
+      rdoc
+    json (1.6.6)
+    rake (0.9.2.2)
+    rdoc (3.12)
+      json (~> 1.4)
+    rr (1.0.4)
+    rspec (2.11.0)
+      rspec-core (~> 2.11.0)
+      rspec-expectations (~> 2.11.0)
+      rspec-mocks (~> 2.11.0)
+    rspec-core (2.11.1)
+    rspec-expectations (2.11.1)
+      diff-lcs (~> 1.1.3)
+    rspec-mocks (2.11.1)
 
 PLATFORMS
   ruby
 
 DEPENDENCIES
-  bundler (~> 1.0.0)
-  jeweler (~> 1.5.1)
-  rcov
-  shoulda
+  bundler (~> 1.1.0)
+  jeweler (~> 1.8.0)
+  rr (~> 1.0.4)
+  rspec (~> 2.11.0)

data/README.rdoc

@@ -10,6 +10,47 @@ The gem does NOT handle any errors in a mobi document, or some edge cases.
 
 Tests will be added soon.
 
+== Installation
+
+  gem install mobi
+
+== Usage
+
+Creating a Mobi::Metadata object
+
+  Mobi::Metadata.new(File.open('/path/to/file.mobi'))
+  
+A handy convenience method to do the exact same thing
+
+  Mobi.metadata File.open('/path/to/file.mobi')
+  
+Getting metadata information is as simple as:
+
+  metadata = Mobi.metadata File.open('/path/to/file.mobi')
+  author = metadata.author
+  
+Supported metadata options are:
+
+* author
+* publisher
+* imprint
+* description
+* isbn
+* subject
+* published_at
+* review
+* contributor
+* rights
+* subject_code
+* type
+* source
+* asin
+* version
+
+== Thanks
+
+* Calibre open source project. I ripped off the idea of a Stream Slicer and got a better understanding of mobi files from their code base. Check them out at http://calibre-ebook.com
+
 == Contributing to mobi
  
 * Check out the latest master to make sure the feature hasn't been implemented or the bug hasn't been fixed yet

data/Rakefile

@@ -15,8 +15,8 @@ Jeweler::Tasks.new do |gem|
   gem.name = "mobi"
   gem.homepage = "http://github.com/jkongie/mobi"
   gem.license = "MIT"
-  gem.summary = %Q{A Rubygem that inspects MOBI metadata}
-  gem.description = %Q{Mobi is a Rubygem that allows you to easily read MOBI e-book format metadata }
+  gem.summary = %Q{A Rubygem that inspects MOBI metadata.}
+  gem.description = %Q{Mobi is a Rubygem that allows you to easily read MOBI e-book format metadata.}
   gem.email = "jkongie@gmail.com"
   gem.authors = ["jkongie"]
   # Include your dependencies below. Runtime dependencies are required when using your gem,
@@ -26,23 +26,9 @@ Jeweler::Tasks.new do |gem|
 end
 Jeweler::RubygemsDotOrgTasks.new
 
-require 'rake/testtask'
-Rake::TestTask.new(:test) do |test|
-  test.libs << 'lib' << 'test'
-  test.pattern = 'test/**/test_*.rb'
-  test.verbose = true
-end
-
-require 'rcov/rcovtask'
-Rcov::RcovTask.new do |test|
-  test.libs << 'test'
-  test.pattern = 'test/**/test_*.rb'
-  test.verbose = true
-end
-
 task :default => :test
 
-require 'rake/rdoctask'
+require 'rdoc/task'
 Rake::RDocTask.new do |rdoc|
   version = File.exist?('VERSION') ? File.read('VERSION') : ""
 

data/VERSION

@@ -1 +1 @@
-0.1.2
+0.2.0

data/lib/mobi.rb

@@ -1,10 +1,14 @@
-require File.expand_path('../mobi/stream_slicer', __FILE__)
-require File.expand_path('../mobi/metadata', __FILE__)
+require 'mobi/stream_slicer'
+require 'mobi/metadata'
+require 'mobi/metadata_streams'
+require 'mobi/header/palm_doc_header'
+require 'mobi/header/mobi_header'
+require 'mobi/header/exth_header'
 
 module Mobi
 
   def self.metadata(file)
     Mobi::Metadata.new(file)
   end
-  
+
 end

data/lib/mobi/header/exth_header.rb

@@ -0,0 +1,46 @@
+module Mobi
+  module Header
+    class ExthHeader
+      RECORD_TYPES = { 100 => :author, 101 => :publisher, 102 => :imprint, 103 => :description, 104 => :isbn, 105 => :subject,
+                       106 => :published_at, 107 => :review, 108 => :contributor, 109 => :rights, 110 => :subject_code,
+                       111 => :type, 112 => :source, 113 => :asin, 114 => :version }
+
+      attr_reader *RECORD_TYPES.values
+
+      def initialize(data)
+        @data = data
+        @record_count, = @data[8, 4].unpack('N*')
+
+        define_data_methods
+      end
+
+      private
+
+      def define_data_methods
+        start = 12
+        @record_count.times do
+          record = ExthRecord.new(@data, start)
+
+          if RECORD_TYPES.key?(record.code)
+            instance_variable_set "@#{record.name}", record.value
+          end
+
+          start += record.length
+        end
+      end
+
+      class ExthRecord
+
+        attr_reader :code, :name, :length, :value
+
+        def initialize(data, start)
+          @code,   = data[start, 4].unpack('N*')[0].to_i
+          @name    = ExthHeader::RECORD_TYPES[@code]
+          @length, = data[start + 4, 4].unpack('N*')
+          @value   = data[start + 8, length - 8]
+        end
+      end
+
+    end
+  end
+end

data/lib/mobi/header/mobi_header.rb

@@ -0,0 +1,153 @@
+# Public: Parses the Mobi Header which follows the 16 bytes of the PalmDOC
+# header.
+module Mobi
+  module Header
+    class MobiHeader
+
+      # Initialize the MobiHeader.
+      #
+      # data - A StreamSlicer which starts at record 0 of the PalmDOC.
+      #
+      # Returns self.
+      def initialize(data)
+        @data = data
+      end
+
+      # A MOBI identifier.
+      #
+      # Returns a String.
+      def identifier
+        @identifier ||= @data[16, 4]
+      end
+
+      # The length of the MOBI header.
+      #
+      # Returns a Fixnum.
+      def header_length
+        @header_length ||= @data[20, 4].unpack('N*')[0]
+      end
+
+      # The kind of Mobipocket file as returned from byte code.
+      #
+      # Returns a Fixnum.
+      def raw_mobi_type
+        @raw_mobi_type ||= @data[24, 4].unpack('N*')[0]
+      end
+
+      # The kind of Mobipocket file.
+      #
+      # Returns a String.
+      def mobi_type
+        { 2 => 'MOBIpocket Book',
+          3 => 'PalmDoc Book',
+          4 => 'Audio',
+          232 => 'MOBIpocket',
+          248 => 'KF8',
+          257 => 'News',
+          258 => 'News Feed',
+          259 => 'News_Magazine',
+          513 => 'PICS',
+          514 => 'WORD',
+          515 => 'XLS',
+          516 => 'PPT',
+          517 => 'TEXT',
+          518 => 'HTML'
+        }.fetch(raw_mobi_type)
+      end
+
+      # The text encoding as return from byte code.
+      #
+      # Returns a Fixnum.
+      def raw_text_encoding
+        @text_encoding ||= @data[28, 4].unpack('N*')[0]
+      end
+
+      # The text encoding.
+      #
+      # Returns a String.
+      def text_encoding
+        { 1252 => 'CP1252 (WinLatin1)',
+          65001 => 'UTF-8'
+        }.fetch(raw_text_encoding)
+      end
+
+      # The unique ID.
+      #
+      # Returns an Integer.
+      def unique_id
+        @unique_id ||= @data[32, 4].unpack('N*')[0]
+      end
+
+      # The version of the MOBIpocket format used in this file.
+      #
+      # Returns a String
+      def file_version
+        @file_version ||= @data[36, 4].unpack('N*')[0]
+      end
+
+      # The first record number (starting with 0) that is not the book's text.
+      #
+      # Returns an Integer.
+      def first_non_book_index
+        @first_non_book_index ||= @data[80, 4].unpack('N*')[0]
+      end
+
+      # Offset in record 0 (not from start of file) of the full name of the book.
+      #
+      # Returns an Integer.
+      def full_name_offset
+        @full_name_offset ||= @data[84, 4].unpack('N*')[0]
+      end
+
+      # Length in bytes of the full name of the book.
+      #
+      # Returns an Integer.
+      def full_name_length
+        @full_name_length ||= @data[88, 4].unpack('N*')[0]
+      end
+
+      # The raw book locale code. I believe this refers to a LCID code.
+      #
+      # The low byte is the main language: 09 = English.
+      # The next byte is dialect: 08 = British, 04 = US.
+      # Thus US English is 1033, UK English is 2057.
+      #
+      # Returns an Integer.
+      def raw_locale_code
+        @raw_locale_code ||= @data[92, 4].unpack('N*')[0]
+      end
+
+      # The minimum MOBIpocket version support needed to read this file.
+      #
+      # Returns an Integer.
+      def minimum_supported_mobipocket_version
+        @minimum_supported_mobipocket_version ||= @data[104, 4].unpack('N*')[0]
+      end
+
+      # The first record number (starting with 0) that contains an image. Image
+      # records should be sequential.
+      #
+      # Returns an Integer.
+      def first_image_index_record_number
+        @first_image_index_record_number ||= @data[108, 4].unpack('N*')[0]
+      end
+
+      # The EXTH flag.
+      #
+      # If bit 6 is set, then there is an EXTH record.
+      #
+      # Returns a Fixnum, 1 or 0.
+      def exth_flag
+        @exth_flag ||= @data[128, 4].unpack('@3B8').first[1].to_i
+      end
+
+      # Does the book have an EXTH header?
+      #
+      # Returns true if the book has an EXTH header.
+      def exth_header?
+        exth_flag == 1
+      end
+
+    end
+  end
+end

data/lib/mobi/header/palm_doc_header.rb

@@ -0,0 +1,73 @@
+# Public:
+module Mobi
+  module Header
+    class PalmDocHeader
+
+      # Initializes the PalmDOC header.
+      #
+      # data - A StreamSlicer which starts at the PalmDOC header.
+      #
+      # Returns self.
+      def initialize(data)
+        @data = data
+      end
+
+      # The compression type as returned from byte code.
+      #
+      # Returns a Fixnum.
+      def raw_compression_type
+        @compression_type ||= @data[0, 2].unpack('n*')[0]
+      end
+
+      # The compression type.
+      #
+      # Returns a Fixnum.
+      def compression_type
+        { 1 => 'None',
+          2 => 'PalmDOC',
+          17480 => 'HUFF/CDIC'
+        }.fetch(raw_compression_type)
+      end
+
+      # The uncompressed length of the entire text of the book.
+      #
+      # Returns a Fixnum.
+      def text_length
+        @text_length ||= @data[4, 4].unpack('N*')[0]
+      end
+
+      # Number of PDB records used for the text of the book.
+      #
+      # Returns a Fixnum.
+      def record_count
+        @record_count ||= @data[8, 2].unpack('n*')[0]
+      end
+
+      # Maximum size of each record containing text. Note that this always
+      # returns 4096.
+      #
+      # Returns a Fixnum.
+      def record_size
+        @record_size ||= @data[10, 2].unpack('n*')[0]
+      end
+
+      # The encryption type as returned from byte code.
+      #
+      # Returns a Fixnum
+      def raw_encryption_type
+        @encryption_type ||= @data[12, 2].unpack('n*')[0]
+      end
+
+      # The encryption type.
+      #
+      # Returns a String.
+      def encryption_type
+        { 0 => 'None',
+          1 => 'Old MOBIpocket',
+          2 => 'MOBIpocket'
+        }.fetch(raw_encryption_type)
+      end
+
+    end
+  end
+end