epub_worm 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 9409a4447bad81747a2f2362f77a24e6b5f18e9a2fc0ca75cf81392ee51641ed
+  data.tar.gz: d6fbdef6cc37926a95f78cf39ef9a53affc49da417a5d3c8ce884135dbe31993
+SHA512:
+  metadata.gz: 0fd94060f4ccc097483f2e13f364791764d1838017c67e031218f87d7b9a8d7795ff1c8b4468ca15ac01cc58314e75bd573f8509bf951a46d3a3f591bdf41850
+  data.tar.gz: 26d80e19011fb2c2af13727f8126a7373f5f044b40e2a0db4cf2abe9b788bb3fb623e6194c98a20811b340012896cead43a390c718f021789479c456c0e21c6a

data/.standard.yml

@@ -0,0 +1,3 @@
+# For available configuration options, see:
+#   https://github.com/standardrb/standard
+ruby_version: 3.0

data/CHANGELOG.md

@@ -0,0 +1,13 @@
+## [Unreleased]
+
+## [0.1.0] - 2025-07-11
+
+### Added
+- Initial release
+- Reads Metadata from epub files.
+- Reads Cover from epub files.
+- Reads Version from epub files.
+- Reads Navigation from epub files.
+- Reads Spine from epub files.
+- Reads Manifest from epub files.
+- Reads Content from epub files.

data/CODE_OF_CONDUCT.md

@@ -0,0 +1,132 @@
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+We as members, contributors, and leaders pledge to make participation in our
+community a harassment-free experience for everyone, regardless of age, body
+size, visible or invisible disability, ethnicity, sex characteristics, gender
+identity and expression, level of experience, education, socio-economic status,
+nationality, personal appearance, race, caste, color, religion, or sexual
+identity and orientation.
+
+We pledge to act and interact in ways that contribute to an open, welcoming,
+diverse, inclusive, and healthy community.
+
+## Our Standards
+
+Examples of behavior that contributes to a positive environment for our
+community include:
+
+* Demonstrating empathy and kindness toward other people
+* Being respectful of differing opinions, viewpoints, and experiences
+* Giving and gracefully accepting constructive feedback
+* Accepting responsibility and apologizing to those affected by our mistakes,
+  and learning from the experience
+* Focusing on what is best not just for us as individuals, but for the overall
+  community
+
+Examples of unacceptable behavior include:
+
+* The use of sexualized language or imagery, and sexual attention or advances of
+  any kind
+* Trolling, insulting or derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or email address,
+  without their explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Enforcement Responsibilities
+
+Community leaders are responsible for clarifying and enforcing our standards of
+acceptable behavior and will take appropriate and fair corrective action in
+response to any behavior that they deem inappropriate, threatening, offensive,
+or harmful.
+
+Community leaders have the right and responsibility to remove, edit, or reject
+comments, commits, code, wiki edits, issues, and other contributions that are
+not aligned to this Code of Conduct, and will communicate reasons for moderation
+decisions when appropriate.
+
+## Scope
+
+This Code of Conduct applies within all community spaces, and also applies when
+an individual is officially representing the community in public spaces.
+Examples of representing our community include using an official email address,
+posting via an official social media account, or acting as an appointed
+representative at an online or offline event.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported to the community leaders responsible for enforcement at
+[INSERT CONTACT METHOD].
+All complaints will be reviewed and investigated promptly and fairly.
+
+All community leaders are obligated to respect the privacy and security of the
+reporter of any incident.
+
+## Enforcement Guidelines
+
+Community leaders will follow these Community Impact Guidelines in determining
+the consequences for any action they deem in violation of this Code of Conduct:
+
+### 1. Correction
+
+**Community Impact**: Use of inappropriate language or other behavior deemed
+unprofessional or unwelcome in the community.
+
+**Consequence**: A private, written warning from community leaders, providing
+clarity around the nature of the violation and an explanation of why the
+behavior was inappropriate. A public apology may be requested.
+
+### 2. Warning
+
+**Community Impact**: A violation through a single incident or series of
+actions.
+
+**Consequence**: A warning with consequences for continued behavior. No
+interaction with the people involved, including unsolicited interaction with
+those enforcing the Code of Conduct, for a specified period of time. This
+includes avoiding interactions in community spaces as well as external channels
+like social media. Violating these terms may lead to a temporary or permanent
+ban.
+
+### 3. Temporary Ban
+
+**Community Impact**: A serious violation of community standards, including
+sustained inappropriate behavior.
+
+**Consequence**: A temporary ban from any sort of interaction or public
+communication with the community for a specified period of time. No public or
+private interaction with the people involved, including unsolicited interaction
+with those enforcing the Code of Conduct, is allowed during this period.
+Violating these terms may lead to a permanent ban.
+
+### 4. Permanent Ban
+
+**Community Impact**: Demonstrating a pattern of violation of community
+standards, including sustained inappropriate behavior, harassment of an
+individual, or aggression toward or disparagement of classes of individuals.
+
+**Consequence**: A permanent ban from any sort of public interaction within the
+community.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage],
+version 2.1, available at
+[https://www.contributor-covenant.org/version/2/1/code_of_conduct.html][v2.1].
+
+Community Impact Guidelines were inspired by
+[Mozilla's code of conduct enforcement ladder][Mozilla CoC].
+
+For answers to common questions about this code of conduct, see the FAQ at
+[https://www.contributor-covenant.org/faq][FAQ]. Translations are available at
+[https://www.contributor-covenant.org/translations][translations].
+
+[homepage]: https://www.contributor-covenant.org
+[v2.1]: https://www.contributor-covenant.org/version/2/1/code_of_conduct.html
+[Mozilla CoC]: https://github.com/mozilla/diversity
+[FAQ]: https://www.contributor-covenant.org/faq
+[translations]: https://www.contributor-covenant.org/translations

data/LICENSE.txt

@@ -0,0 +1,21 @@
+The MIT License (MIT)
+
+Copyright (c) 2025 Luis Adrián Chávez Fregoso
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.

data/README.md

@@ -0,0 +1,129 @@
+# EpubWorm
+
+EpubWorm is just another EPUB parser gem, with only two dependencies: "rubyzip" and "nokogiri".
+
+## Installation
+
+Install the gem and add to the application's Gemfile by executing:
+
+    $ bundle add epub_worm
+
+Or add this line to your Gemfile:
+
+```ruby
+gem "epub_worm"
+```
+
+And run
+
+    $ bundle install
+
+If bundler is not being used to manage dependencies, install the gem by executing:
+
+    $ gem install epub_worm
+
+## Usage
+
+To read EPUB files:
+
+```ruby
+require "epub_worm"
+
+epub = EpubWorm::Reader.new(path: "your_file.epub")
+```
+
+### Metadata
+
+```ruby
+epub.metadata.title        # => "Alice's Adventures in Wonderland"
+epub.metadata.authors      # => ["Lewis Carroll"]
+epub.metadata.language     # => "en"
+epub.metadata.publisher    # => "Project Gutenberg"
+epub.metadata.published_at # => Date or nil
+epub.metadata.subjects     # => ["Fantasy", "Children’s literature"]
+```
+
+### EPUB version
+
+```ruby
+epub.version # => 2.0 or 3.0
+```
+
+### Cover image
+
+Returns a ManifestItem that includes .file to access the image as a tempfile.
+
+```ruby
+cover_item = epub.cover
+cover_item.media_type # => "image/jpeg"
+File.open("cover.jpg", "wb") { |f| f.write(cover_item.file.read) }
+```
+
+### Manifest
+
+The manifest lists all items in the EPUB: XHTML pages, CSS files, images, fonts, etc.
+
+```ruby
+epub.manifest.each do |manifest_item|
+  puts "#{manifest_item.id}: #{manifest_item.reference} (#{manifest_item.media_type})"
+end
+```
+
+### Spine (Reading Order)
+
+The spine lists the linear reading order of content documents.
+
+```ruby
+epub.spine.each do |manifest_item|
+  puts item.reference # => e.g., "chapter1.xhtml"
+end
+```
+
+### Navigation (Table of Contents)
+
+The navigation object provides a tree structure of headings.
+
+```ruby
+epub.navigation.each do |entry|
+  puts entry.title
+  puts entry.reference
+end
+```
+
+You can also recursively access nested entries:
+
+```ruby
+epub.navigation.each do |top|
+  puts top.title
+  top.children.each do |child|
+    puts "  - #{child.title}"
+  end
+end
+```
+
+### Extract Content
+
+You can fetch a specific file by its navigation or spine reference:
+
+```ruby
+doc = epub.content("chapter1.xhtml")
+doc.at_css("h1").text # => "Chapter 1"
+```
+
+## Development
+
+After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake test` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
+
+To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and the created tag, and push the `.gem` file to [rubygems.org](https://rubygems.org).
+
+## Contributing
+
+Bug reports and pull requests are welcome on GitHub at https://github.com/lacf95/epub_worm. This project is intended to be a safe, welcoming space for collaboration, and contributors are expected to adhere to the [code of conduct](https://github.com/lacf95/epub_worm/blob/master/CODE_OF_CONDUCT.md).
+
+## License
+
+The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).
+
+## Code of Conduct
+
+Everyone interacting in the EpubWorm project's codebases, issue trackers, chat rooms and mailing lists is expected to follow the [code of conduct](https://github.com/lacf95/epub_worm/blob/master/CODE_OF_CONDUCT.md).

data/Rakefile

@@ -0,0 +1,10 @@
+# frozen_string_literal: true
+
+require "bundler/gem_tasks"
+require "minitest/test_task"
+
+Minitest::TestTask.create
+
+require "standard/rake"
+
+task default: %i[test standard]

data/lib/epub_worm/extractors/base.rb

@@ -0,0 +1,62 @@
+# frozen_string_literal: true
+
+require "nokogiri"
+require "zip"
+
+module EpubWorm
+  module Extractors
+    module Base
+      DEFAULT_NS = {
+        "container" => "urn:oasis:names:tc:opendocument:xmlns:container"
+      }.freeze
+
+      def self.extended(base)
+        base.instance_variable_set(:@ns, DEFAULT_NS.dup)
+      end
+
+      def ns_entry(prefix, uri)
+        @ns ||= {}
+        @ns[prefix.to_s] = uri
+      end
+
+      def ns
+        @ns || {}
+      end
+
+      def open_opf(path)
+        Zip::File.open(path) do |zip_file|
+          # Get the container.xml file to get the opf file path.
+          container_file = zip_file.find_entry "META-INF/container.xml"
+          raise ::EpubWorm::Error, "container.xml not found" unless container_file
+
+          # Read the container file to get opf file path.
+          container_doc = Nokogiri::XML(container_file.get_input_stream.read)
+          opf_file_path = element_at(container_doc, "//container:rootfile")["full-path"]
+
+          # Read the opf file to get metadata.
+          opf_file = zip_file.find_entry opf_file_path
+          raise ::EpubWorm::Error, "opf file not found" unless opf_file
+
+          opf_doc = Nokogiri::XML(opf_file.get_input_stream.read)
+          yield(opf_doc, opf_file_path, zip_file) if block_given?
+        end
+      end
+
+      def as_xml(file)
+        Nokogiri::XML(file.get_input_stream.read)
+      end
+
+      def element_at(doc, path)
+        doc.at_xpath(path, ns)
+      end
+
+      def elements_at(doc, path)
+        doc.xpath(path, ns)
+      end
+
+      def text_at(doc, path)
+        element_at(doc, path)&.text&.strip
+      end
+    end
+  end
+end

data/lib/epub_worm/extractors/content.rb

@@ -0,0 +1,26 @@
+# frozen_string_literal: true
+
+module EpubWorm
+  module Extractors
+    class Content
+      extend ::EpubWorm::Extractors::Base
+
+      def self.extract(path, reference)
+        open_opf(path) do |_opf_doc, opf_file_path, zip_file|
+          content_file_name, content_fragment = reference.split("#", 2)
+          content_file_path = ::File.join(::File.dirname(opf_file_path), content_file_name)
+          content_file = zip_file.find_entry(content_file_path)
+          raise ::EpubWorm::Error, "#{content_file_name} not found" unless content_file
+
+          content_doc = as_xml(content_file)
+          return content_doc unless content_fragment
+
+          fragment_content_doc = element_at(content_doc, "//*[@id='#{content_fragment}']")
+          raise ::EpubWorm::Error, "#{content_file_name}#{content_fragment} not found" unless fragment_content_doc
+
+          fragment_content_doc
+        end
+      end
+    end
+  end
+end

data/lib/epub_worm/extractors/cover_reference.rb

@@ -0,0 +1,24 @@
+# frozen_string_literal: true
+
+module EpubWorm
+  module Extractors
+    class CoverReference
+      extend ::EpubWorm::Extractors::Base
+
+      ns_entry :opf, "http://www.idpf.org/2007/opf"
+
+      def self.extract(path)
+        open_opf(path) do |opf_doc, opf_file_path, zip_file|
+          cover_id = element_at(opf_doc, "//opf:metadata/opf:meta[@name='cover']")&.[]("content")
+          item_xpath = if cover_id
+            "//opf:manifest/opf:item[@id='#{cover_id}']"
+          else
+            "//opf:manifest/opf:item[contains(@href, 'cover') and contains(@media-type, 'image')]"
+          end
+
+          element_at(opf_doc, item_xpath)&.[]("href")
+        end
+      end
+    end
+  end
+end

data/lib/epub_worm/extractors/file.rb

@@ -0,0 +1,32 @@
+# frozen_string_literal: true
+
+module EpubWorm
+  module Extractors
+    class File
+      extend ::EpubWorm::Extractors::Base
+
+      ns_entry :opf, "http://www.idpf.org/2007/opf"
+
+      def self.extract(path, reference)
+        open_opf(path) do |_opf_doc, opf_file_path, zip_file|
+          file_path = ::File.join(::File.dirname(opf_file_path), reference)
+          file = zip_file.find_entry file_path
+          raise ::EpubWorm::Error, "#{reference} file not found" unless file
+
+          file_basename = ::File.basename file_path
+          copy_to_temp_file(file, file_basename)
+        end
+      end
+
+      def self.copy_to_temp_file(file, file_name)
+        tempfile = Tempfile.new [file_name]
+        tempfile.binmode
+        tempfile.write file.get_input_stream.read
+        tempfile.rewind
+        tempfile
+      end
+
+      private_class_method :copy_to_temp_file
+    end
+  end
+end

data/lib/epub_worm/extractors/manifest.rb

@@ -0,0 +1,36 @@
+# frozen_string_literal: true
+
+module EpubWorm
+  module Extractors
+    class Manifest
+      extend ::EpubWorm::Extractors::Base
+
+      ns_entry :opf, "http://www.idpf.org/2007/opf"
+
+      def self.extract(path)
+        open_opf(path) do |opf_doc|
+          manifest_items = elements_at(opf_doc, "//opf:manifest/opf:item")
+          build_manifest(manifest_items, path)
+        end
+      end
+
+      def self.build_manifest(manifest_items, path)
+        ::EpubWorm::Manifest.new(
+          manifest_items: manifest_items.map { |e| as_manifest_item(e, path) }
+        )
+      end
+
+      def self.as_manifest_item(manifest_entry, path)
+        ::EpubWorm::ManifestItem.new(
+          id: manifest_entry["id"],
+          reference: manifest_entry["href"],
+          media_type: manifest_entry["media-type"],
+          path: path
+        )
+      end
+
+      private_class_method :build_manifest
+      private_class_method :as_manifest_item
+    end
+  end
+end

data/lib/epub_worm/extractors/metadata.rb

@@ -0,0 +1,32 @@
+# frozen_string_literal: true
+
+require "date"
+
+module EpubWorm
+  module Extractors
+    class Metadata
+      SUBJECT_SEPARATOR = " -- "
+
+      extend ::EpubWorm::Extractors::Base
+
+      ns_entry :dc, "http://purl.org/dc/elements/1.1/"
+
+      def self.extract(path)
+        open_opf(path) do |opf_doc|
+          ::EpubWorm::Metadata.new(
+            title: text_at(opf_doc, "//dc:title"),
+            authors: elements_at(opf_doc, "//dc:creator").map(&:text).map(&:strip).reject(&:empty?),
+            language: text_at(opf_doc, "//dc:language"),
+            publisher: text_at(opf_doc, "//dc:publisher"),
+            description: text_at(opf_doc, "//dc:description"),
+            published_at: text_at(opf_doc, "//dc:date") && Date.parse(text_at(opf_doc, "//dc:date")),
+            subjects: elements_at(opf_doc, "//dc:subject").reduce([]) do |subjects, subject|
+              subjects += subject.text.split(SUBJECT_SEPARATOR).map(&:strip).reject(&:empty?)
+              subjects.uniq
+            end
+          )
+        end
+      end
+    end
+  end
+end

data/lib/epub_worm/extractors/navigation.rb

@@ -0,0 +1,22 @@
+# frozen_string_literal: true
+
+module EpubWorm
+  module Extractors
+    class Navigation
+      def self.extract(path, version:)
+        extractor_for(version).extract(path)
+      end
+
+      def self.extractor_for(version)
+        case version
+        when 3
+          ::EpubWorm::Extractors::XhtmlNavigation
+        when 2
+          ::EpubWorm::Extractors::NcxNavigation
+        else
+          raise ::EpubWorm::Error, "unsupported epub version: #{version.inspect}"
+        end
+      end
+    end
+  end
+end

data/lib/epub_worm/extractors/ncx_navigation.rb

@@ -0,0 +1,53 @@
+# frozen_string_literal: true
+
+module EpubWorm
+  module Extractors
+    class NcxNavigation
+      extend ::EpubWorm::Extractors::Base
+
+      ns_entry :opf, "http://www.idpf.org/2007/opf"
+      ns_entry :ncx, "http://www.daisy.org/z3986/2005/ncx/"
+
+      def self.extract(path)
+        open_opf(path) do |opf_doc, opf_file_path, zip_file|
+          toc_file_path = ::File.join(::File.dirname(opf_file_path), toc_reference(opf_doc))
+          toc_file = zip_file.find_entry toc_file_path
+          raise ::EpubWorm::Error, "toc file not found" unless toc_file
+
+          toc_doc = as_xml toc_file
+          nav_points = elements_at(toc_doc, "//ncx:navMap/ncx:navPoint")
+          build_navigation nav_points
+        end
+      end
+
+      def self.toc_reference(opf_doc)
+        id = element_at(opf_doc, "//opf:spine")&.[]("toc")
+        raise ::EpubWorm::Error, "toc file reference id not found" unless id
+
+        reference = element_at(opf_doc, "//opf:manifest/opf:item[@id='#{id}']")&.[]("href")
+        return reference if reference
+
+        raise ::EpubWorm::Error, "toc file reference not found"
+      end
+
+      def self.build_navigation(nav_points)
+        navigation = ::EpubWorm::Navigation.new
+        nav_points.each do |nav_point|
+          navigation.children << as_navigation(nav_point)
+        end
+        navigation
+      end
+
+      def self.as_navigation(nav_point)
+        ::EpubWorm::Navigation.new(
+          title: text_at(nav_point, "ncx:navLabel/ncx:text"),
+          reference: element_at(nav_point, "ncx:content")["src"],
+          children: elements_at(nav_point, "ncx:navPoint").map { |e| as_navigation(e) }
+        )
+      end
+
+      private_class_method :toc_reference
+      private_class_method :build_navigation
+    end
+  end
+end

data/lib/epub_worm/extractors/spine.rb

@@ -0,0 +1,38 @@
+# frozen_string_literal: true
+
+module EpubWorm
+  module Extractors
+    class Spine
+      extend ::EpubWorm::Extractors::Base
+
+      ns_entry :opf, "http://www.idpf.org/2007/opf"
+
+      def self.extract(path)
+        open_opf(path) do |opf_doc|
+          spine_items = elements_at(opf_doc, "//opf:spine/opf:itemref")
+          build_spine(spine_items, opf_doc, path)
+        end
+      end
+
+      def self.build_spine(spine_items, opf_doc, path)
+        ::EpubWorm::Spine.new(
+          manifest_items: spine_items.map { |e| as_manifest_item(e, opf_doc, path) }
+        )
+      end
+
+      def self.as_manifest_item(spine_entry, opf_doc, path)
+        id_reference = spine_entry["idref"]
+        manifest_entry = element_at(opf_doc, "//opf:manifest/opf:item[@id='#{id_reference}']")
+        ::EpubWorm::ManifestItem.new(
+          id: manifest_entry["id"],
+          reference: manifest_entry["href"],
+          media_type: manifest_entry["media-type"],
+          path: path
+        )
+      end
+
+      private_class_method :build_spine
+      private_class_method :as_manifest_item
+    end
+  end
+end

data/lib/epub_worm/extractors/version.rb

@@ -0,0 +1,17 @@
+# frozen_string_literal: true
+
+module EpubWorm
+  module Extractors
+    class Version
+      extend ::EpubWorm::Extractors::Base
+
+      ns_entry :opf, "http://www.idpf.org/2007/opf"
+
+      def self.extract(path)
+        open_opf(path) do |opf_doc|
+          element_at(opf_doc, "/opf:package")["version"].to_f
+        end
+      end
+    end
+  end
+end

data/lib/epub_worm/extractors/xhtml_navigation.rb

@@ -0,0 +1,51 @@
+# frozen_string_literal: true
+
+module EpubWorm
+  module Extractors
+    class XhtmlNavigation
+      extend ::EpubWorm::Extractors::Base
+
+      ns_entry :opf, "http://www.idpf.org/2007/opf"
+      ns_entry :epub, "http://www.idpf.org/2007/ops"
+      ns_entry :xhtml, "http://www.w3.org/1999/xhtml"
+
+      def self.extract(path)
+        open_opf(path) do |opf_doc, opf_file_path, zip_file|
+          nav_file_path = ::File.join(::File.dirname(opf_file_path), nav_reference(opf_doc))
+          nav_file = zip_file.find_entry nav_file_path
+          raise ::EpubWorm::Error, "nav file not found" unless nav_file
+
+          nav_doc = as_xml nav_file
+          nav_points = elements_at(nav_doc, "//xhtml:nav[@epub:type='toc']/xhtml:ol/xhtml:li")
+          build_navigation nav_points
+        end
+      end
+
+      def self.nav_reference(opf_doc)
+        reference = element_at(opf_doc, "//opf:manifest/opf:item[@properties='nav']")&.[]("href")
+        return reference if reference
+
+        raise ::EpubWorm::Error, "nav file reference not found"
+      end
+
+      def self.build_navigation(nav_points)
+        navigation = ::EpubWorm::Navigation.new
+        nav_points.each do |nav_point|
+          navigation.children << as_navigation(nav_point)
+        end
+        navigation
+      end
+
+      def self.as_navigation(nav_point)
+        ::EpubWorm::Navigation.new(
+          title: text_at(nav_point, "xhtml:a"),
+          reference: element_at(nav_point, "xhtml:a")["href"],
+          children: elements_at(nav_point, "xhtml:ol/xhtml:li").map { |e| as_navigation(e) }
+        )
+      end
+
+      private_class_method :nav_reference
+      private_class_method :build_navigation
+    end
+  end
+end

data/lib/epub_worm/manifest.rb

@@ -0,0 +1,17 @@
+# frozen_string_literal: true
+
+module EpubWorm
+  class Manifest
+    include Enumerable
+
+    attr_accessor :manifest_items
+
+    def initialize(manifest_items: [])
+      @manifest_items = manifest_items
+    end
+
+    def each(&block)
+      manifest_items.each(&block)
+    end
+  end
+end

data/lib/epub_worm/manifest_item.rb

@@ -0,0 +1,30 @@
+# frozen_string_literal: true
+
+module EpubWorm
+  class ManifestItem
+    attr_accessor :id, :reference, :media_type
+
+    def initialize(id: nil, reference: nil, media_type: nil, path: nil)
+      @id = id
+      @reference = reference
+      @media_type = media_type
+      @path = path
+    end
+
+    def file
+      ::EpubWorm::Extractors::File.extract(path, reference)
+    end
+
+    def to_h
+      {
+        id: id,
+        reference: reference,
+        media_type: media_type
+      }
+    end
+
+    private
+
+    attr_reader :path
+  end
+end

data/lib/epub_worm/metadata.rb

@@ -0,0 +1,37 @@
+# frozen_string_literal: true
+
+module EpubWorm
+  class Metadata
+    attr_accessor :title, :authors, :language, :publisher, :description, :published_at, :subjects
+
+    def initialize(
+      title: nil,
+      authors: [],
+      language: nil,
+      publisher: nil,
+      description: nil,
+      published_at: nil,
+      subjects: []
+    )
+      @title = title
+      @authors = authors
+      @language = language
+      @publisher = publisher
+      @description = description
+      @published_at = published_at
+      @subjects = subjects
+    end
+
+    def to_h
+      {
+        title: title,
+        authors: authors,
+        language: language,
+        publisher: publisher,
+        description: description,
+        published_at: published_at,
+        subjects: subjects
+      }
+    end
+  end
+end

data/lib/epub_worm/navigation.rb

@@ -0,0 +1,19 @@
+# frozen_string_literal: true
+
+module EpubWorm
+  class Navigation
+    include Enumerable
+
+    attr_accessor :title, :reference, :children
+
+    def initialize(title: nil, reference: nil, children: [])
+      @title = title
+      @reference = reference
+      @children = children
+    end
+
+    def each(&block)
+      children.each(&block)
+    end
+  end
+end

data/lib/epub_worm/reader.rb

@@ -0,0 +1,43 @@
+# frozen_string_literal: true
+
+module EpubWorm
+  class Reader
+    attr_reader :path
+
+    def initialize(path:)
+      @path = path
+    end
+
+    def content(reference)
+      ::EpubWorm::Extractors::Content.extract(path, reference)
+    end
+
+    def cover
+      manifest.find { |manifest_item| manifest_item.reference == cover_reference }
+    end
+
+    def cover_reference
+      @cover_reference ||= ::EpubWorm::Extractors::CoverReference.extract(path)
+    end
+
+    def manifest
+      @manifest ||= ::EpubWorm::Extractors::Manifest.extract(path)
+    end
+
+    def metadata
+      @metadata ||= ::EpubWorm::Extractors::Metadata.extract(path)
+    end
+
+    def navigation
+      @navigation ||= ::EpubWorm::Extractors::Navigation.extract(path, version: version)
+    end
+
+    def spine
+      @spine ||= ::EpubWorm::Extractors::Spine.extract(path)
+    end
+
+    def version
+      @version ||= ::EpubWorm::Extractors::Version.extract(path)
+    end
+  end
+end

data/lib/epub_worm/spine.rb

@@ -0,0 +1,17 @@
+# frozen_string_literal: true
+
+module EpubWorm
+  class Spine
+    include Enumerable
+
+    attr_accessor :manifest_items
+
+    def initialize(manifest_items: [])
+      @manifest_items = manifest_items
+    end
+
+    def each(&block)
+      manifest_items.each(&block)
+    end
+  end
+end

data/lib/epub_worm/version.rb

@@ -0,0 +1,5 @@
+# frozen_string_literal: true
+
+module EpubWorm
+  VERSION = "0.1.0"
+end

data/lib/epub_worm.rb

@@ -0,0 +1,27 @@
+# frozen_string_literal: true
+
+require_relative "epub_worm/manifest"
+require_relative "epub_worm/manifest_item"
+require_relative "epub_worm/metadata"
+require_relative "epub_worm/navigation"
+require_relative "epub_worm/spine"
+require_relative "epub_worm/version"
+
+require_relative "epub_worm/extractors/base"
+require_relative "epub_worm/extractors/file"
+require_relative "epub_worm/extractors/content"
+require_relative "epub_worm/extractors/cover_reference"
+require_relative "epub_worm/extractors/manifest"
+require_relative "epub_worm/extractors/metadata"
+require_relative "epub_worm/extractors/spine"
+require_relative "epub_worm/extractors/version"
+
+require_relative "epub_worm/extractors/xhtml_navigation"
+require_relative "epub_worm/extractors/ncx_navigation"
+require_relative "epub_worm/extractors/navigation"
+
+require_relative "epub_worm/reader"
+
+module EpubWorm
+  class Error < StandardError; end
+end

metadata

@@ -0,0 +1,100 @@
+--- !ruby/object:Gem::Specification
+name: epub_worm
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Luis Adrián Chávez Fregoso
+autorequire:
+bindir: exe
+cert_chain: []
+date: 2025-07-13 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.18'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.18'
+- !ruby/object:Gem::Dependency
+  name: rubyzip
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.4'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.4'
+description: 'EpubWorm is just another EPUB parser gem, with only two dependencies:
+  "rubyzip" and "nokogiri".'
+email:
+- biolacf@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".standard.yml"
+- CHANGELOG.md
+- CODE_OF_CONDUCT.md
+- LICENSE.txt
+- README.md
+- Rakefile
+- lib/epub_worm.rb
+- lib/epub_worm/extractors/base.rb
+- lib/epub_worm/extractors/content.rb
+- lib/epub_worm/extractors/cover_reference.rb
+- lib/epub_worm/extractors/file.rb
+- lib/epub_worm/extractors/manifest.rb
+- lib/epub_worm/extractors/metadata.rb
+- lib/epub_worm/extractors/navigation.rb
+- lib/epub_worm/extractors/ncx_navigation.rb
+- lib/epub_worm/extractors/spine.rb
+- lib/epub_worm/extractors/version.rb
+- lib/epub_worm/extractors/xhtml_navigation.rb
+- lib/epub_worm/manifest.rb
+- lib/epub_worm/manifest_item.rb
+- lib/epub_worm/metadata.rb
+- lib/epub_worm/navigation.rb
+- lib/epub_worm/reader.rb
+- lib/epub_worm/spine.rb
+- lib/epub_worm/version.rb
+homepage: https://github.com/lacf95/epub_worm
+licenses:
+- MIT
+metadata:
+  homepage_uri: https://github.com/lacf95/epub_worm
+  source_code_uri: https://github.com/lacf95/epub_worm
+  changelog_uri: https://github.com/lacf95/epub_worm/blob/main/CHANGELOG.md
+post_install_message:
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: 3.0.0
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.5.17
+signing_key:
+specification_version: 4
+summary: Another Ruby epub reader
+test_files: []