openstax_cnx 0.1.0 → 0.1.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 1290e2c41b0cfe6e5f18b3a8d2f5f423d1ecec4d661b589929514a790064683d
-  data.tar.gz: b86557dc8226f2179fcb21990bdc5b6a2c796308943b4aa9eca71a932b258e95
+  metadata.gz: 9157ba0a43475c290a7dfb335ed33b03753b6be00a24af0897108ff376471e6c
+  data.tar.gz: b679d19ea1a362100847dbd59f409d11bd7fb612ec5a2f4b713b2af7fd9884b2
 SHA512:
-  metadata.gz: f704b248e1e7f1710ff6d75af6595171437279131f3f478cd6305ae7797578ce67026b56a8ea37ce4349b63b34023cd1ce9db909d39f51c3725cccf315bdc031
-  data.tar.gz: 2139b21f10a4157e532ca4e92ed071cb2aa4cc3df0a1d7eff86f43e8033d1d07f542b1b36114b43f9acf7892566bc022514467e3c3b74729844059d13b7b3e14
+  metadata.gz: b27fd15c9f37a2b823940825f33b2d9c3c4c0e84fe7991541a60018ec36af69bd0b63c7a42557d5c4970a5d5d9ef27434d9d8fffcbe9ee7110fa4a3c4d8cc53a
+  data.tar.gz: 1c7c17740aecc143cd5bd757a2d97dd00172eff2a0c7ec0192da6f08d7269a81788f8a3cfed16527a6edf2f70fe92fc2ec057a8e660f759f44bc8fc014388590

data/.github/workflows/tests.yml

@@ -0,0 +1,21 @@
+name: Tests
+
+on:
+  pull_request:
+  push:
+    branches:
+      - main
+
+jobs:
+  tests:
+    timeout-minutes: 10
+    runs-on: ubuntu-24.04
+
+    steps:
+      - uses: actions/checkout@v4
+      - uses: ruby/setup-ruby@v1
+        with:
+          ruby-version: 3.1
+          bundler-cache: true
+      - name: Test
+        run: bundle exec rspec

data/.gitignore

@@ -13,3 +13,5 @@
 .env
 
 .byebug_history
+
+Gemfile.lock

data/.travis.yml

@@ -4,4 +4,6 @@ language: ruby
 cache: bundler
 rvm:
   - 2.5.0
+notifications:
+  email: false
 before_install: gem install bundler -v 1.17.2

data/README.md

@@ -1,5 +1,7 @@
 # OpenStax::Cnx
 
+[![Build Status](https://travis-ci.org/openstax/cnx-ruby.svg?branch=master)](https://travis-ci.org/openstax/cnx-ruby)
+
 This gem provides a Ruby interface to OpenStax book content.
 
 ## Installation
@@ -36,7 +38,7 @@ Book
     etc...
 ```
 
-Some OpenStax books organized chapters into units.  The units are BookParts like the chapters are:
+Some OpenStax books organize chapters into units.  The units are BookParts like the chapters are:
 
 ```
 Book
@@ -70,6 +72,12 @@ book.baked # => "2019-03-20T14:24:26.164476-05:00"
 book.url   # => "https://archive.cnx.org/contents/031da8d3-b525-429c-80cf-6c8ed997733a"
 ```
 
+To get all pages in a book:
+
+```ruby
+book.root_book_part.pages.count   # => 460
+```
+
 To dig deeper, get the `root_book_part` and then is `parts`
 
 ```ruby

data/lib/openstax/cnx/v1/book.rb

@@ -1,7 +1,7 @@
 module OpenStax::Cnx::V1
   class Book
 
-    def initialize(id: nil, hash: nil, title: nil, tree: nil, root_book_part: nil)
+    def initialize(id:, hash: nil, title: nil, tree: nil, root_book_part: nil)
       @id             = id
       @hash           = hash
       @title          = title

data/lib/openstax/cnx/v1/book_part.rb

@@ -1,14 +1,16 @@
 module OpenStax::Cnx::V1
   class BookPart
 
+    CONTENTS = 'contents'
+
+    attr_reader :hash, :is_root, :book
+
     def initialize(hash: {}, is_root: false, book: nil)
       @hash = hash
       @is_root = is_root
       @book = book
     end
 
-    attr_reader :hash, :is_root, :book
-
     def parsed_title
       @parsed_title ||= OpenStax::Cnx::V1::Baked.parse_title(
         hash.fetch('title') { |key| raise "#{self.class.name} id=#{@id} is missing #{key}" }
@@ -24,14 +26,14 @@ module OpenStax::Cnx::V1
     end
 
     def contents
-      @contents ||= hash.fetch('contents') do |key|
+      @contents ||= hash.fetch(CONTENTS) do |key|
         raise "#{self.class.name} id=#{@id} is missing #{key}"
       end
     end
 
     def parts
       @parts ||= contents.map do |hash|
-        if hash.has_key? 'contents'
+        if hash.has_key? CONTENTS
           self.class.new(hash: hash, book: book)
         else
           OpenStax::Cnx::V1::Page.new(hash: hash, book: book)
@@ -44,5 +46,11 @@ module OpenStax::Cnx::V1
       @is_chapter ||= parts.none? { |part| part.is_a?(self.class) }
     end
 
+    def pages
+      @pages ||= parts.map do |part|
+        part.is_a?(Page) ? part : part.pages
+      end.flatten
+    end
+
   end
 end

data/lib/openstax/cnx/v1/element.rb

@@ -0,0 +1,9 @@
+module OpenStax::Cnx::V1
+  class Element
+    attr_reader :node
+
+    def initialize(node:)
+      @node = node
+    end
+  end
+end

data/lib/openstax/cnx/v1/figure.rb

@@ -0,0 +1,35 @@
+module OpenStax::Cnx::V1
+  class Figure < Element
+    MATCH_FIGURE = "//*[contains(@class, 'os-figure')]"
+
+    MATCH_FIGURE_CAPTION = ".//*[contains(@class, 'os-caption')]"
+    MATCH_FIGURE_ALT_TEXT = './/*[@alt]'
+    MATCH_FIGURE_DATA_ALT_TEXT = './/*[@data-alt]'
+    MATCH_FIGURE_ELEM = './/figure'
+
+    def initialize(node:)
+      super
+    end
+
+    def caption
+      node.at_xpath(MATCH_FIGURE_CAPTION).try(:text)
+    end
+
+    def id
+      node.at_xpath(MATCH_FIGURE_ELEM).attr('id')
+    end
+
+    def alt_text
+      node.at_xpath(MATCH_FIGURE_ALT_TEXT).try(:attr, 'alt') ||
+      node.at_xpath(MATCH_FIGURE_DATA_ALT_TEXT).try(:attr, 'data-alt')
+    end
+
+    def self.matcher
+      MATCH_FIGURE
+    end
+
+    def self.matches?(node)
+      node.matches?(MATCH_FIGURE)
+    end
+  end
+end

data/lib/openstax/cnx/v1/key_term.rb

@@ -0,0 +1,32 @@
+module OpenStax::Cnx::V1
+  class KeyTerm < Element
+    MATCH_KEY_TERM = "//*[contains(@class, 'os-glossary-container')]//dl"
+
+    MATCH_KEY_TERM_TEXT = ".//dt"
+    MATCH_KEY_TERM_DESCRIPTION = ".//dd"
+
+    def initialize(node:)
+      super
+    end
+
+    def description
+      node.xpath(MATCH_KEY_TERM_DESCRIPTION).text
+    end
+
+    def id
+      node.attr('id')
+    end
+
+    def term
+      node.xpath(MATCH_KEY_TERM_TEXT).text
+    end
+
+    def self.matcher
+      MATCH_KEY_TERM
+    end
+
+    def self.matches?(node)
+      node.matches?(MATCH_KEY_TERM)
+    end
+  end
+end

data/lib/openstax/cnx/v1/page.rb

@@ -67,6 +67,14 @@ module OpenStax::Cnx::V1
       @is_intro = title.start_with?('Introduction')
     end
 
+    def preface?
+      content_dom.xpath('boolean(//html/body/div[@data-type="page"][@class="preface"])')
+    end
+
+    def index?
+      content_dom.xpath('boolean(//div[contains(@class,"os-index-container")])')
+    end
+
     def full_hash
       @full_hash ||= OpenStax::Cnx::V1.fetch(url)
     end
@@ -161,8 +169,48 @@ module OpenStax::Cnx::V1
       @tags.values
     end
 
+    def remove_elements(xpath:)
+      content_dom.xpath(xpath).each do | xpath_element |
+        xpath_element.remove
+      end
+    end
+
+    # Pass the
+    #
+    #   e.g.,
+    #     element classes = [
+    #       OpenStax::Cnx::V1::Figure,
+    #       OpenStax::Cnx::V1::Paragraph,
+    #       OpenStax::Cnx::V1::KeyTerm,
+    #     ]
+    #
+    # you want to retrieve with the page
+    def elements(element_classes:)
+      # This join is important to OR together all the xpaths in order to determine
+      # the matched element's order inside the page. Xpath does this for us.
+      match_all_elements = element_classes.map(&:matcher).join(' | ')
+
+      working_element_index = []
+
+      # Match on all the elements. Create Element objects with the matching xpath node.
+      content_dom.xpath(match_all_elements).each do | xpath_element |
+        element_class = element_classes.detect do | elem_class |
+          elem_class.matches?(xpath_element)
+        end
+
+        element = element_class.new(node: xpath_element)
+        working_element_index << element if element
+      end
+
+      working_element_index
+    end
+
     protected
 
+    def content_dom
+      @content_dom ||= Nokogiri::HTML(content)
+    end
+
     def url_for(path)
       book.nil? ? OpenStax::Cnx::V1.archive_url_for(path) : "#{book.canonical_url}:#{path}"
     end

data/lib/openstax/cnx/v1/paragraph.rb

@@ -0,0 +1,25 @@
+module OpenStax::Cnx::V1
+  class Paragraph < Element
+    MATCH_PARAGRAPH = '//p[@id]'
+
+    def initialize(node:)
+      super
+    end
+
+    def text
+      node.text
+    end
+
+    def id
+      node.attr('id')
+    end
+
+    def self.matcher
+      MATCH_PARAGRAPH
+    end
+
+    def self.matches?(node)
+      node.matches?(MATCH_PARAGRAPH)
+    end
+  end
+end

data/lib/openstax/cnx/v1.rb

@@ -8,6 +8,10 @@ require_relative './v1/http_error'
 
 require_relative './v1/book'
 require_relative './v1/book_part'
+require_relative './v1/element'
+require_relative './v1/figure'
+require_relative './v1/key_term'
+require_relative './v1/paragraph'
 require_relative './v1/page'
 require_relative './v1/baked'
 
@@ -117,7 +121,7 @@ module OpenStax::Cnx::V1
     def fetch(url)
       begin
         OpenStax::Cnx::V1.logger.debug { "Fetching #{url}" }
-        data = JSON.parse open(url, 'ACCEPT' => 'text/json').read
+        data = JSON.parse URI.open(url, 'ACCEPT' => 'text/json').read
         data.delete("history") if configuration.ignore_history
         data
       rescue OpenURI::HTTPError => exception
@@ -125,8 +129,8 @@ module OpenStax::Cnx::V1
       end
     end
 
-    def book(options = {})
-      OpenStax::Cnx::V1::Book.new(options)
+    def book(**options)
+      OpenStax::Cnx::V1::Book.new(**options)
     end
 
   end

data/lib/openstax/cnx/version.rb

@@ -1,5 +1,5 @@
 module OpenStax
   module Cnx
-    VERSION = "0.1.0"
+    VERSION = "0.1.1"
   end
 end

data/openstax_cnx.gemspec

@@ -37,10 +37,11 @@ Gem::Specification.new do |spec|
   spec.require_paths = ["lib"]
 
   spec.add_dependency "nokogiri"
+  spec.add_dependency "addressable"
 
-  spec.add_development_dependency "bundler", "~> 1.17"
-  spec.add_development_dependency "rake", "~> 10.0"
-  spec.add_development_dependency "rspec", "~> 3.0"
+  spec.add_development_dependency "bundler"
+  spec.add_development_dependency "rake"
+  spec.add_development_dependency "rspec"
   spec.add_development_dependency "dotenv"
   spec.add_development_dependency "webmock"
   spec.add_development_dependency "vcr"

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: openstax_cnx
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: 0.1.1
 platform: ruby
 authors:
 - JP Slavinsky
-autorequire: 
+autorequire:
 bindir: exe
 cert_chain: []
-date: 2019-04-06 00:00:00.000000000 Z
+date: 2025-10-21 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
@@ -24,48 +24,62 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
+- !ruby/object:Gem::Dependency
+  name: addressable
+  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'
 - !ruby/object:Gem::Dependency
   name: bundler
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '1.17'
+        version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '1.17'
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '10.0'
+        version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '10.0'
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: rspec
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '3.0'
+        version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '3.0'
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: dotenv
   requirement: !ruby/object:Gem::Requirement
@@ -129,12 +143,12 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
+- ".github/workflows/tests.yml"
 - ".gitignore"
 - ".rspec"
 - ".travis.yml"
 - CODE_OF_CONDUCT.md
 - Gemfile
-- Gemfile.lock
 - LICENSE.txt
 - README.md
 - Rakefile
@@ -144,8 +158,12 @@ files:
 - lib/openstax/cnx/v1/baked.rb
 - lib/openstax/cnx/v1/book.rb
 - lib/openstax/cnx/v1/book_part.rb
+- lib/openstax/cnx/v1/element.rb
+- lib/openstax/cnx/v1/figure.rb
 - lib/openstax/cnx/v1/http_error.rb
+- lib/openstax/cnx/v1/key_term.rb
 - lib/openstax/cnx/v1/page.rb
+- lib/openstax/cnx/v1/paragraph.rb
 - lib/openstax/cnx/version.rb
 - lib/openstax_cnx.rb
 - openstax_cnx.gemspec
@@ -156,7 +174,7 @@ metadata:
   allowed_push_host: https://rubygems.org
   homepage_uri: https://github.com/openstax/cnx-ruby
   source_code_uri: https://github.com/openstax/cnx-ruby
-post_install_message: 
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -171,9 +189,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.7.3
-signing_key: 
+rubygems_version: 3.5.21
+signing_key:
 specification_version: 4
 summary: Bindings to fetch and inspect CNX books
 test_files: []

data/Gemfile.lock

@@ -1,57 +0,0 @@
-PATH
-  remote: .
-  specs:
-    openstax_cnx (0.1.0)
-      nokogiri
-
-GEM
-  remote: https://rubygems.org/
-  specs:
-    addressable (2.6.0)
-      public_suffix (>= 2.0.2, < 4.0)
-    byebug (11.0.1)
-    crack (0.4.3)
-      safe_yaml (~> 1.0.0)
-    diff-lcs (1.3)
-    dotenv (2.7.2)
-    hashdiff (0.3.8)
-    mini_portile2 (2.4.0)
-    nokogiri (1.10.2)
-      mini_portile2 (~> 2.4.0)
-    public_suffix (3.0.3)
-    rake (10.5.0)
-    rspec (3.8.0)
-      rspec-core (~> 3.8.0)
-      rspec-expectations (~> 3.8.0)
-      rspec-mocks (~> 3.8.0)
-    rspec-core (3.8.0)
-      rspec-support (~> 3.8.0)
-    rspec-expectations (3.8.2)
-      diff-lcs (>= 1.2.0, < 2.0)
-      rspec-support (~> 3.8.0)
-    rspec-mocks (3.8.0)
-      diff-lcs (>= 1.2.0, < 2.0)
-      rspec-support (~> 3.8.0)
-    rspec-support (3.8.0)
-    safe_yaml (1.0.5)
-    vcr (4.0.0)
-    webmock (3.5.1)
-      addressable (>= 2.3.6)
-      crack (>= 0.3.2)
-      hashdiff
-
-PLATFORMS
-  ruby
-
-DEPENDENCIES
-  bundler (~> 1.17)
-  byebug
-  dotenv
-  openstax_cnx!
-  rake (~> 10.0)
-  rspec (~> 3.0)
-  vcr
-  webmock
-
-BUNDLED WITH
-   1.17.2