epub_tools 0.4.0 → 0.5.0

data/lib/epub_tools/style_finder.rb

@@ -1,4 +1,6 @@
 #!/usr/bin/env ruby
+# frozen_string_literal: true
+
 require 'nokogiri'
 require 'yaml'
 require_relative 'loggable'
@@ -9,6 +11,7 @@ module EpubTools
   # {SplitChapters}[rdoc-ref:EpubTools::SplitChapters].
   class StyleFinder
     include Loggable
+
     # Initializes the class
     # @param options [Hash] Configuration options
     # @option options [String] :file_path XHTML file to be analyzed (required)
@@ -24,18 +27,26 @@ module EpubTools
     # Runs the finder
     # @return [Hash] Data containing the extracted style classes (italics and bolds)
     def run
+      style_blocks = extract_style_blocks
+      italics, bolds = extract_style_classes(style_blocks)
+      generate_output(italics, bolds)
+    end
+
+    def extract_style_blocks
       doc = Nokogiri::HTML(File.read(@file_path))
-      style_blocks = doc.xpath('//style').map(&:text).join("\n")
+      doc.xpath('//style').map(&:text).join("\n")
+    end
 
+    def extract_style_classes(style_blocks)
       italics = extract_classes(style_blocks, /font-style\s*:\s*italic/)
-      bolds   = extract_classes(style_blocks, /font-weight\s*:\s*700/)
+      bolds = extract_classes(style_blocks, /font-weight\s*:\s*700/)
+      [italics, bolds]
+    end
 
+    def generate_output(italics, bolds)
       print_summary(italics, bolds) if @verbose
 
-      data = {
-        'italics' => italics,
-        'bolds' => bolds
-      }
+      data = { 'italics' => italics, 'bolds' => bolds }
       File.write(@output_path, data.to_yaml)
       data
     end

data/lib/epub_tools/unpack_ebook.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require 'zip'
 require 'fileutils'
 require_relative 'loggable'
@@ -6,6 +8,7 @@ module EpubTools
   # Unpacks an EPUB (.epub file) into a directory
   class UnpackEbook
     include Loggable
+
     # Initializes the class
     # @param options [Hash] Configuration options
     # @option options [String] :epub_file Path to the .epub file to unpack (required)
@@ -23,22 +26,29 @@ module EpubTools
     def run
       validate!
       FileUtils.mkdir_p(@output_dir)
+      extract_entries
+      log "Unpacked #{File.basename(@epub_file)} to #{@output_dir}"
+      @output_dir
+    end
+
+    private
+
+    def extract_entries
       Zip::File.open(@epub_file) do |zip|
         zip.each do |entry|
-          dest_path = File.join(@output_dir, entry.name)
-          if entry.directory?
-            FileUtils.mkdir_p(dest_path)
-          else
-            FileUtils.mkdir_p(File.dirname(dest_path))
-            entry.extract(dest_path) { true }
-          end
+          extract_entry(entry)
         end
       end
-      log "Unpacked #{File.basename(@epub_file)} to #{@output_dir}"
-      @output_dir
     end
 
-    private
+    def extract_entry(entry)
+      if entry.directory?
+        FileUtils.mkdir_p(File.join(@output_dir, entry.name))
+      else
+        FileUtils.mkdir_p(File.join(@output_dir, File.dirname(entry.name)))
+        entry.extract(destination_directory: @output_dir) { true }
+      end
+    end
 
     def default_dir
       [File.dirname(@epub_file), File.basename(@epub_file, '.epub')].join('/')

data/lib/epub_tools/version.rb

@@ -1,4 +1,6 @@
+# frozen_string_literal: true
+
 module EpubTools
   # Ruby Gem version number
-  VERSION = '0.4.0'.freeze
+  VERSION = '0.5.0'
 end

data/lib/epub_tools/xhtml_cleaner.rb

@@ -1,4 +1,5 @@
 #!/usr/bin/env ruby
+# frozen_string_literal: true
 
 require 'nokogiri'
 require 'yaml'

data/lib/epub_tools/xhtml_extractor.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require 'zip'
 require 'fileutils'
 require_relative 'loggable'
@@ -6,6 +8,7 @@ module EpubTools
   # Extracts text .xhtml files from EPUB archives, excluding nav.xhtml
   class XHTMLExtractor
     include Loggable
+
     # Initializes the class
     # @param options [Hash] Configuration options
     # @option options [String] :source_dir Directory containing source .epub files (required)
@@ -39,21 +42,28 @@ module EpubTools
       epub_name = File.basename(epub_path, '.epub')
       log "Extracting from #{epub_name}.epub"
       extracted_files = []
+
       Zip::File.open(epub_path) do |zip_file|
-        zip_file.each do |entry|
-          next unless entry.name.downcase.end_with?('.xhtml')
-          next if File.basename(entry.name).downcase == 'nav.xhtml'
-
-          output_path = File.join(@target_dir, "#{epub_name}_#{File.basename(entry.name)}")
-          FileUtils.mkdir_p(File.dirname(output_path))
-          entry.extract(output_path) { true }
-          log output_path
-          extracted_files << output_path
-        end
+        zip_file.each { |entry| extract_entry_if_xhtml(entry, epub_name, extracted_files) }
       end
       extracted_files
     rescue Zip::Error => e
       warn "⚠️ Failed to process #{epub_path}: #{e.message}"
     end
+
+    def extract_entry_if_xhtml(entry, epub_name, extracted_files)
+      return unless xhtml_entry?(entry)
+
+      renamed = "#{epub_name}_#{File.basename(entry.name)}"
+      output_path = File.join(@target_dir, renamed)
+      FileUtils.mkdir_p(File.dirname(output_path))
+      entry.extract(renamed, destination_directory: @target_dir) { true }
+      log output_path
+      extracted_files << output_path
+    end
+
+    def xhtml_entry?(entry)
+      entry.name.downcase.end_with?('.xhtml') && File.basename(entry.name).downcase != 'nav.xhtml'
+    end
   end
 end

data/lib/epub_tools/xhtml_generator.rb

@@ -0,0 +1,71 @@
+# frozen_string_literal: true
+
+module EpubTools
+  # Generates XHTML content for EPUB files
+  class XhtmlGenerator
+    attr_accessor :cover_image_fname
+
+    def initialize(title:, author:)
+      @title = title
+      @author = author
+      @cover_image_fname = nil
+    end
+
+    # Generates title page XHTML content
+    def build_title_page
+      <<~XHTML
+        <?xml version="1.0" encoding="UTF-8"?>
+        <html xmlns="http://www.w3.org/1999/xhtml" lang="en">
+          <head>
+            <meta charset="UTF-8" />
+            <title>#{@title}</title>
+            <link rel="stylesheet" type="text/css" href="style.css"/>
+          </head>
+          <body>
+            <h1 class="title">#{@title}</h1>
+            <p class="author">by #{@author}</p>
+          </body>
+        </html>
+      XHTML
+    end
+
+    # Generates cover page XHTML content
+    def build_cover_page
+      <<~XHTML
+        <?xml version="1.0" encoding="UTF-8"?>
+        <html xmlns="http://www.w3.org/1999/xhtml" lang="en">
+          <head>
+            <meta charset="UTF-8" />
+            <title>Cover</title>
+            <link rel="stylesheet" type="text/css" href="style.css"/>
+          </head>
+          <body>
+            <div class="cover-image">
+              <img src="#{@cover_image_fname}" alt="Cover"/>
+            </div>
+          </body>
+        </html>
+      XHTML
+    end
+
+    # Generates navigation XHTML content
+    def build_nav_page
+      <<~XHTML
+        <?xml version="1.0" encoding="utf-8"?>
+        <html xmlns="http://www.w3.org/1999/xhtml" xmlns:epub="http://www.idpf.org/2007/ops" lang="en">
+          <head>
+            <title>Table of Contents</title>
+          </head>
+          <body>
+            <nav epub:type="toc" id="toc">
+              <h1>Table of Contents</h1>
+              <ol>
+                <li><a href="title.xhtml">Title Page</a></li>
+              </ol>
+            </nav>
+          </body>
+        </html>
+      XHTML
+    end
+  end
+end

data/lib/epub_tools.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require_relative 'epub_tools/version'
 require_relative 'epub_tools/loggable'
 require_relative 'epub_tools/add_chapters'

data/test/add_chapters_test.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require_relative 'test_helper'
 require_relative '../lib/epub_tools/add_chapters'
 require 'nokogiri'
@@ -53,47 +55,69 @@ class AddChaptersTest < Minitest::Test
   end
 
   def test_run_moves_files_and_updates_opf_and_nav
-    # Run the add chapters task
-    result = EpubTools::AddChapters.new(chapters_dir: @chapters_dir, epub_dir: @epub_dir).run
+    result = EpubTools::AddChapters.new(chapters_dir: @chapters_dir, oebps_dir: @epub_dir).run
+
+    verify_return_value(result)
+    verify_files_moved
+    verify_opf_structure
+    verify_nav_structure
+  end
 
-    # Check return value is an array of moved file basenames
+  private
+
+  def verify_return_value(result)
     assert_instance_of Array, result
     assert_equal 2, result.size
     assert_includes result, 'chapter_0.xhtml'
     assert_includes result, 'chapter_1.xhtml'
+  end
 
-    # Original chapter files should be moved
+  def verify_files_moved
     assert_empty Dir.glob(File.join(@chapters_dir, '*.xhtml'))
     assert_path_exists File.join(@epub_dir, 'chapter_0.xhtml')
     assert_path_exists File.join(@epub_dir, 'chapter_1.xhtml')
+  end
 
-    # package.opf should include manifest items and spine refs
-    doc = Nokogiri::XML(File.read(@opf_file)) { |cfg| cfg.default_xml.noblanks }
-    items   = doc.xpath('//xmlns:manifest/xmlns:item')
-    idrefs  = doc.xpath('//xmlns:spine/xmlns:itemref')
-    hrefs   = items.map { |i| i['href'] }
-    ids     = items.map { |i| i['id'] }
-    refs    = idrefs.map { |ir| ir['idref'] }
-
-    assert_includes hrefs, 'chapter_0.xhtml'
-    assert_includes hrefs, 'chapter_1.xhtml'
-    assert_includes ids,   'chap0'
-    assert_includes ids,   'chap1'
-    assert_includes refs,  'chap0'
-    assert_includes refs,  'chap1'
-
-    # nav.xhtml should have list entries for each chapter
-    nav_doc = Nokogiri::XML(File.read(@nav_file))
-    # strip namespaces for easy querying
-    nav_doc.remove_namespaces!
-    links = nav_doc.xpath('//nav/ol/li/a')
+  def verify_opf_structure
+    doc = parse_opf_document
+    opf_data = extract_opf_data(doc)
+
+    assert_includes opf_data[:hrefs], 'chapter_0.xhtml'
+    assert_includes opf_data[:hrefs], 'chapter_1.xhtml'
+    assert_includes opf_data[:ids], 'chap0'
+    assert_includes opf_data[:ids], 'chap1'
+    assert_includes opf_data[:refs], 'chap0'
+    assert_includes opf_data[:refs], 'chap1'
+  end
+
+  def verify_nav_structure
+    links = extract_nav_links
 
     assert_equal 2, links.size
-    # First is Prologue (chapter_0)
     assert_equal 'chapter_0.xhtml', links[0]['href']
     assert_equal 'Prologue', links[0].text
-    # Second is Chapter 1
     assert_equal 'chapter_1.xhtml', links[1]['href']
     assert_equal 'Chapter 1', links[1].text
   end
+
+  def parse_opf_document
+    Nokogiri::XML(File.read(@opf_file)) { |cfg| cfg.default_xml.noblanks }
+  end
+
+  def extract_opf_data(doc)
+    items = doc.xpath('//xmlns:manifest/xmlns:item')
+    idrefs = doc.xpath('//xmlns:spine/xmlns:itemref')
+
+    {
+      hrefs: items.map { |i| i['href'] },
+      ids: items.map { |i| i['id'] },
+      refs: idrefs.map { |ir| ir['idref'] }
+    }
+  end
+
+  def extract_nav_links
+    nav_doc = Nokogiri::XML(File.read(@nav_file))
+    nav_doc.remove_namespaces!
+    nav_doc.xpath('//nav/ol/li/a')
+  end
 end

data/test/chapter_validator_test.rb

@@ -0,0 +1,47 @@
+# frozen_string_literal: true
+
+require_relative 'test_helper'
+require_relative '../lib/epub_tools/chapter_validator'
+
+class ChapterValidatorTest < Minitest::Test
+  def setup
+    @tmp = Dir.mktmpdir
+    @validator = EpubTools::ChapterValidator.new(chapters_dir: @tmp)
+  end
+
+  def teardown
+    FileUtils.rm_rf(@tmp)
+  end
+
+  def test_validates_complete_sequence
+    create_chapter_files([1, 2, 3, 4, 5])
+
+    assert_silent { @validator.validate }
+  end
+
+  def test_raises_on_missing_chapters
+    create_chapter_files([1, 2, 4, 5]) # Missing 3
+
+    error = assert_raises(RuntimeError) { @validator.validate }
+    assert_match(/Missing chapter numbers: 3/, error.message)
+  end
+
+  def test_raises_on_no_chapters
+    error = assert_raises(RuntimeError) { @validator.validate }
+    assert_match(/No chapter files found/, error.message)
+  end
+
+  def test_handles_non_sequential_start
+    create_chapter_files([5, 6, 7, 8])
+
+    assert_silent { @validator.validate }
+  end
+
+  private
+
+  def create_chapter_files(numbers)
+    numbers.each do |num|
+      File.write(File.join(@tmp, "chapter_#{num}.xhtml"), '<html></html>')
+    end
+  end
+end

data/test/cli/command_registry_test.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require_relative '../test_helper'
 require_relative '../../lib/epub_tools'
 

data/test/cli/option_builder_test.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require_relative '../test_helper'
 require_relative '../../lib/epub_tools'
 require 'stringio'
@@ -41,17 +43,13 @@ class OptionBuilderTest < Minitest::Test
   def test_with_input_file
     @builder.with_input_file('Test input')
 
-    assert_includes @builder.parser.to_s, '-i, --input-file FILE'
-    assert_includes @builder.parser.to_s, 'Test input (required)'
+    verify_parser_option_format('-i, --input-file FILE', 'Test input (required)')
 
-    # Test with required=false
     builder2 = EpubTools::CLI::OptionBuilder.new
-    builder2.with_input_file('Test input', false)
+    builder2.with_input_file('Test input', required: false)
 
-    assert_includes builder2.parser.to_s, 'Test input'
-    refute_includes builder2.parser.to_s, 'Test input (required)'
+    verify_optional_parser_format(builder2, 'Test input')
 
-    # Test with actual parsing
     @builder.parse(['-i', 'file.txt'])
 
     assert_equal 'file.txt', @builder.options[:input_file]
@@ -69,20 +67,16 @@ class OptionBuilderTest < Minitest::Test
   end
 
   def test_with_output_dir
-    # Test with default value
     @builder.with_output_dir('Test output dir', 'default/path')
 
-    assert_includes @builder.parser.to_s, '-o, --output-dir DIR'
-    assert_includes @builder.parser.to_s, 'Test output dir (default: default/path)'
+    verify_parser_option_format('-o, --output-dir DIR', 'Test output dir (default: default/path)')
+
     assert_equal 'default/path', @builder.options[:output_dir]
 
-    # Test without default
     builder2 = EpubTools::CLI::OptionBuilder.new
     builder2.with_output_dir('Test output dir')
+    verify_required_parser_format(builder2, 'Test output dir (required)')
 
-    assert_includes builder2.parser.to_s, 'Test output dir (required)'
-
-    # Test actual parsing
     @builder.parse(['-o', 'new/path'])
 
     assert_equal 'new/path', @builder.options[:output_dir]
@@ -170,4 +164,20 @@ class OptionBuilderTest < Minitest::Test
 
     assert_equal @builder, result
   end
+
+  private
+
+  def verify_parser_option_format(option_format, description)
+    assert_includes @builder.parser.to_s, option_format
+    assert_includes @builder.parser.to_s, description
+  end
+
+  def verify_optional_parser_format(builder, description)
+    assert_includes builder.parser.to_s, description
+    refute_includes builder.parser.to_s, "#{description} (required)"
+  end
+
+  def verify_required_parser_format(builder, description)
+    assert_includes builder.parser.to_s, description
+  end
 end

data/test/cli/runner_test.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require_relative '../test_helper'
 require_relative '../../lib/epub_tools'
 require 'stringio'
@@ -33,15 +35,18 @@ class RunnerTest < Minitest::Test
   end
 
   def test_handle_command
-    assert_output(/Usage: test-program test-cmd/) do
-      assert_raises(SystemExit) { @runner.handle_command('test-cmd', ['-h']) }
+    @runner.registry.register('add', TestCommand)
+
+    assert_output(/Usage: test-program add/) do
+      assert_raises(SystemExit) { @runner.handle_command('add', ['-h']) }
     end
   end
 
   def test_handle_command_with_required_args
     runner = EpubTools::CLI::Runner.new('test-program')
-    runner.registry.register('test-cmd', TestCommand)
-    assert_output("Called!\n") { assert runner.handle_command('test-cmd') }
+    runner.registry.register('add', TestCommand)
+
+    assert_output("Called!\n") { assert runner.handle_command('add') }
   end
 
   def test_handle_nonexistent_command
@@ -69,18 +74,13 @@ class RunnerTest < Minitest::Test
   end
 
   def test_configure_command_options
-    # This is testing a private method, which is generally not recommended,
-    # but it's useful to ensure all command configurations work
+    # Test command configuration through public interface
+    @runner.registry.register('add', TestCommand)
 
-    # Use send to access private method
-    builder = EpubTools::CLI::OptionBuilder.new
-
-    # Test each command configuration - we'll just check one example
-    @runner.send(:configure_command_options, 'add', builder)
-
-    # Check add command options were added
-    assert_includes builder.parser.to_s, '--chapters-dir DIR'
-    assert_includes builder.parser.to_s, '--epub-oebps-dir DIR'
+    # Should show help without errors
+    assert_output(/Usage: test-program add/) do
+      assert_raises(SystemExit) { @runner.handle_command('add', ['-h']) }
+    end
   end
 
   def test_run_with_unknown_command

data/test/cli_commands_test.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require_relative 'test_helper'
 require 'fileutils'
 require 'tempfile'
@@ -79,7 +81,7 @@ class CLICommandsTest < Minitest::Test
 
     assert_match(/Usage: epub-tools add \[options\]/, output)
     assert_includes output, '--chapters-dir DIR'
-    assert_includes output, '--epub-oebps-dir DIR'
+    assert_includes output, '--oebps-dir DIR'
   end
 
   def test_pack_command

data/test/cli_test.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require_relative 'test_helper'
 require_relative 'cli/command_registry_test'
 require_relative 'cli/option_builder_test'

data/test/cli_version_test.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require_relative 'test_helper'
 require_relative '../lib/epub_tools/version'
 require 'open3'