wcc-scripture 0.1.0

data/lib/wcc/scripture/esv.rb

@@ -0,0 +1,326 @@
+# frozen_string_literal: true
+
+require 'nokogiri'
+require 'pericope'
+require 'forwardable'
+require 'rails-html-sanitizer'
+
+class WCC::Scripture::Esv # rubocop:disable Metrics/ClassLength
+  attr_reader :parsed_ref
+
+  DATA_LIB = File.join(__dir__, '../../../data/esv')
+
+  class Reference
+    extend Forwardable
+
+    SINGLE_CHAPTER_BOOK_REGEX = /^(obadiah|philemon|2 john|3 john|jude)$/i.freeze
+
+    attr_reader :pericope
+    def_delegators :pericope, :ranges, :book_name
+
+    def initialize(pericope, book_only = false)
+      @pericope = pericope
+      @book_only = book_only
+    end
+
+    def self.parse(ref)
+      if match = SINGLE_CHAPTER_BOOK_REGEX.match(ref)
+        # Pericope will resolve the upper range to the actual when 100 is used
+        new(Pericope.parse_one("#{match[0]} 1-100"), true)
+      elsif pericope = Pericope.parse_one(ref)
+        new(pericope)
+      end
+    end
+
+    def to_s
+      return book_name if @book_only
+
+      result = pericope.to_s(
+        verse_range_separator: '–',
+        chapter_range_separator: '–'
+      )
+
+      return result unless book_name == 'Psalm' && range_spans_multiple_chapters?
+
+      result.gsub('Psalm', 'Psalms')
+    end
+
+    private
+
+    def range_spans_multiple_chapters?
+      range = ranges.first
+
+      range.begin.chapter != range.end.chapter
+    end
+  end
+
+  def initialize(
+    reference,
+    footnotes: true,
+    data_lib: DATA_LIB
+  )
+    raise WCC::Scripture::ScriptureNotFoundError unless @parsed_ref = Reference.parse(reference)
+
+    @data_lib = data_lib
+    @body_nodes = []
+    @footnote_nodes = []
+    @display_options = { footnotes: footnotes }
+  end
+
+  def render_html
+    parse_nodes
+    [
+      render_body,
+      render_footnotes
+    ].join
+  end
+
+  # rubocop:disable Metrics/MethodLength
+  # rubocop:disable Metrics/CyclomaticComplexity
+  # rubocop:disable Metrics/AbcSize
+  def render_body
+    marker = nil
+    body = []
+    para_open = false
+
+    @body_nodes.each do |node|
+      marker = node if verse_marker?(node)
+      if node.name == 'heading'
+        body.push process_heading(marker, node)
+      elsif node.name == 'subheading'
+        body.push process_heading(marker, node)
+      elsif node.name == 'begin-paragraph'
+        if node.attributes['class']&.value == 'line-group'
+          body.push('<p class="block-indent">')
+        else
+          body.push '<p>'
+        end
+        para_open = true
+      elsif node.name == 'end-paragraph'
+        body.push '</p>'
+        para_open = false
+      elsif node.name == 'verse'
+        unless para_open
+          body.push '<p>'
+          para_open = true
+        end
+        body.push process_verse(marker, node)
+      end
+    end
+
+    # In case verse range didn't include end-paragraph
+    body.push('</p>') if para_open
+
+    body.compact.join
+  end
+  # rubocop:enable Metrics/MethodLength
+  # rubocop:enable Metrics/CyclomaticComplexity
+  # rubocop:enable Metrics/AbcSize
+
+  def render_footnotes
+    return '' if @footnote_nodes.empty? || !@display_options[:footnotes]
+
+    <<~HTML
+      <div class="footnotes extra_text">
+        <h3>Footnotes</h3>
+        #{@footnote_nodes.join('<br/>')}
+      </div>
+    HTML
+  end
+
+  def convert_node(node, name, css = nil)
+    Nokogiri::XML::Node.new(name, book_xml).tap do |heading|
+      heading['class'] = css || node['class'] if css || node['class']
+      heading.children = node.children
+    end
+  end
+
+  def parse_nodes
+    @parsed_ref.ranges.each do |range|
+      first, *_, last = range.to_a
+
+      link_traverse(last || first, book_xml.at_css("marker.begin-verse[mid*=\"#{first.to_id}\"]"))
+    end
+  end
+
+  def link_traverse(bounds, node = nil)
+    return unless node
+    return if out_of_bounds?(bounds, node)
+
+    @body_nodes.push(node) if node.name =~ /marker|heading|paragraph|verse/
+
+    link_traverse(bounds, node.first_element_child) if node.name == 'chapter'
+    link_traverse(bounds, node.next)
+  end
+
+  def process_heading(marker, node)
+    heading = convert_node(node, node.name == 'heading' ? 'h3' : 'h4')
+
+    preprocess(heading)
+
+    parse_footnotes(marker, heading)
+
+    postprocess(heading.to_xml)
+  end
+
+  def process_verse(marker_node, verse_node)
+    preprocess(verse_node)
+    parse_footnotes(marker_node, verse_node)
+
+    [
+      %(<b class="verse-num">#{verse_node.attributes['num'].value}&nbsp;</b>),
+      # We have to replace these strings in this fashion instead of using Nokogiri because the source markup
+      # is not well-formed. The nodes do not encapsulate the text and children they are intending to designate as children,
+      # but instead self-closing which presents a parsing nightmare. In an ideal world, we would be able to replace the
+      # pseudo-html markup with real html and be done, but alas. So, for now, this post-processing step is acheived by
+      # string replacement.
+      #
+      # Nokogiri HTML Serialization Options
+      # 2 - exclude XML Declaration tag
+      # 32 - output XML - prevents Nokogiri from closing our tags for us
+      #
+      # No option passed would assume HTML options, and disrupt our markup scheme, producing something like:
+      # '<begin-line/>' => '<begin-line></begin-line>'
+      postprocess(verse_node.inner_html(save_with: 2 | 32)),
+      ' '
+    ].join
+  end
+
+  def preprocess(node)
+    node.tap do |n|
+      n.search('crossref, crossrefs, begin-block-indent, end-block-indent, q.continue-double').remove
+      translate_quotes(n)
+      n.search('heading, subheading').each { |h| h.replace(convert_node(h, node.name == 'heading' ? 'h3' : 'h4')) }
+      n.search('span.divine-name').each { |q| q.replace('LORD') }
+      n.search('woc, selah').each { |span| span.replace(convert_node(span, 'span', span.name)) }
+    end
+  end
+
+  # (
+  #   begin-double|continue-double|end-double
+  #   begin-inner-double|continue-inner-double|end-inner-double
+  #   begin-single|continue-single|end-single
+  #   begin-inner-single|end-inner-single
+  # )
+  def translate_quotes(node)
+    node.tap do |n|
+      n.search('q.begin-double, q.continue-double, q.begin-inner-double, q.continue-inner-double')
+        .each { |q| q.replace('&#x201C;') }
+      n.search('q.end-double, q.end-inner-double').each { |q| q.replace('&#x201D;') }
+      n.search('q.begin-single, q.continue-single, q.begin-inner-single').each { |q| q.replace('&#x2018;') }
+      n.search('q.end-single, q.end-inner-single').each { |q| q.replace('&#x2019;') }
+    end
+  end
+
+  def postprocess(markup)
+    translate_entities(
+      translate_pseudo_markup(
+        markup
+      )
+    )
+  end
+
+  def translate_pseudo_markup(markup)
+    markup
+      .gsub(%r{<begin-paragraph class="line-group"/>}, '<p class="block-indent">')
+      .gsub(%r{<begin-paragraph(?:\s+class=".+")?/>}, '<p>')
+      .gsub(%r{<end-paragraph/>}, '</p>')
+      .gsub(%r{<end-line(?:\s+class=".+")?/>}, '</span><br/>')
+      .gsub(%r{<begin-line\s?/>}, '<span class="line">')
+      .gsub(%r{<begin-line\s+class="(.+)"/>}, '<span class="line \1">&nbsp;&nbsp;&nbsp;&nbsp;')
+  end
+
+  def translate_entities(markup)
+    markup
+      .gsub('&ldblquot;', '&#8220;')
+      .gsub('&rdblquot;', '&#8221;')
+      .gsub('&lquot;', '&#8216;')
+      .gsub('&rquot;', '&#8217;')
+      .gsub('&apos;', '&#8217;')
+      .gsub('&emdash;', '&#8212;')
+      .gsub('&endash;', '&#8211;')
+      .gsub('&ellipsis;', '&nbsp;.&nbsp;.&nbsp;.')
+      .gsub('&ellipsis4;', '.&nbsp;.&nbsp;.&nbsp;.')
+  end
+
+  def parse_footnotes(marker, node)
+    notes = node.search('note')
+
+    return if notes.empty?
+    return notes.remove unless @display_options[:footnotes]
+
+    notes.each do |note|
+      footnote_node = note_xml.at_css("note[id=\"#{note.attributes['nid'].value}\"]")
+
+      if footnote_node
+        footnote_id = @footnote_nodes.size + 1
+        @footnote_nodes.push(
+          footnote(marker, footnote_node, footnote_id)
+        )
+        note.replace(
+          footnote_anchor(footnote_node, footnote_id)
+        )
+      else
+        note.remove
+      end
+    end
+  end
+
+  FULL_SANITIZER = Rails::Html::FullSanitizer.new
+
+  def footnote_anchor(note_node, id)
+    <<~HTML
+      <sup class="footnote">
+        <a class="fn" href="#f#{id}-1" id="fb#{id}-1" title="#{FULL_SANITIZER.sanitize(note_node.inner_html)}">#{id}</a>
+      </sup>
+    HTML
+  end
+
+  def footnote(marker, note_node, id)
+    preprocess(note_node)
+
+    verse_ref = Pericope::Verse.parse(marker_numeric_value(marker))
+
+    postprocess(<<~HTML)
+      <span class="footnote">
+        <a href="#fb#{id}-1" id="f#{id}-1">[#{id}]</a>
+      </span>
+      <span class="footnote-ref">#{verse_ref.to_s(with_chapter: true)}</span>
+      #{note_node}
+    HTML
+  end
+
+  def out_of_bounds?(bounds, node)
+    return unless verse_marker?(node)
+
+    bounds.to_i < marker_numeric_value(node)
+  end
+
+  def verse_marker?(node)
+    node.name == 'marker' && node.attributes['class'].value == 'begin-verse'
+  end
+
+  def marker_numeric_value(node)
+    node.attributes['mid'].value.sub(/^v/, '').to_i
+  end
+
+  XML_LOOKUP = {
+    'Psalm' => 'Psalms'
+  }.freeze
+
+  def self.lookup_xml(book_name, data_lib = DATA_LIB)
+    Nokogiri::XML(
+      File.open(File.join(data_lib, "#{XML_LOOKUP.fetch(book_name, book_name)}.xml")),
+      &:huge
+    )
+  end
+
+  def book_xml
+    @book_xml ||= self.class.lookup_xml(@parsed_ref.book_name, @data_lib)
+  end
+
+  def note_xml
+    @note_xml ||=
+      Nokogiri::XML(File.open(File.join(@data_lib, '_notes.text.xml')), &:huge)
+  end
+end

data/lib/wcc/scripture/exceptions.rb

@@ -0,0 +1,4 @@
+module WCC::Scripture
+  class ScriptureNotFoundError < StandardError
+  end
+end

data/lib/wcc/scripture/version.rb

@@ -0,0 +1,5 @@
+module WCC
+  module Scripture
+    VERSION = '0.1.0'
+  end
+end

data/lib/wcc/scripture.rb

@@ -0,0 +1,4 @@
+
+require_relative './scripture/version'
+require_relative './scripture/exceptions'
+require_relative './scripture/esv'

data/lib/wcc-scripture.rb

@@ -0,0 +1,2 @@
+
+require_relative './wcc/scripture'

data/wcc-scripture.gemspec

@@ -0,0 +1,29 @@
+# frozen_string_literal: true
+
+lib = File.expand_path('lib', __dir__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'wcc/scripture/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = 'wcc-scripture'
+  spec.version       = WCC::Scripture::VERSION
+  spec.authors       = ['Watermark Dev']
+  spec.email         = ['dev@watermark.org']
+
+  spec.summary       = File.readlines(File.expand_path('README.md', __dir__)).join
+  spec.description   = ''
+  spec.license       = 'Not licensed for external use'
+
+  spec.required_ruby_version = '>= 2.3'
+
+  spec.files         =
+    `git ls-files -z`.split("\x0").reject do |f|
+      f.match(%r{^(test|spec|features)/})
+    end
+
+  spec.require_paths = ['lib']
+
+  spec.add_runtime_dependency 'nokogiri', '>= 1.0'
+  spec.add_runtime_dependency 'pericope', '>= 1.0'
+  spec.add_runtime_dependency 'rails-html-sanitizer', '>= 1.0'
+end

metadata

@@ -0,0 +1,162 @@
+--- !ruby/object:Gem::Specification
+name: wcc-scripture
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Watermark Dev
+autorequire:
+bindir: bin
+cert_chain: []
+date: 2022-02-07 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '1.0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '1.0'
+- !ruby/object:Gem::Dependency
+  name: pericope
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '1.0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '1.0'
+- !ruby/object:Gem::Dependency
+  name: rails-html-sanitizer
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '1.0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '1.0'
+description: ''
+email:
+- dev@watermark.org
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".rubocop.yml"
+- Gemfile
+- README.md
+- Rakefile
+- data/esv/1 Chronicles.xml
+- data/esv/1 Corinthians.xml
+- data/esv/1 John.xml
+- data/esv/1 Kings.xml
+- data/esv/1 Peter.xml
+- data/esv/1 Samuel.xml
+- data/esv/1 Thessalonians.xml
+- data/esv/1 Timothy.xml
+- data/esv/2 Chronicles.xml
+- data/esv/2 Corinthians.xml
+- data/esv/2 John.xml
+- data/esv/2 Kings.xml
+- data/esv/2 Peter.xml
+- data/esv/2 Samuel.xml
+- data/esv/2 Thessalonians.xml
+- data/esv/2 Timothy.xml
+- data/esv/3 John.xml
+- data/esv/Acts.xml
+- data/esv/Amos.xml
+- data/esv/Colossians.xml
+- data/esv/Daniel.xml
+- data/esv/Deuteronomy.xml
+- data/esv/Ecclesiastes.xml
+- data/esv/Ephesians.xml
+- data/esv/Esther.xml
+- data/esv/Exodus.xml
+- data/esv/Ezekiel.xml
+- data/esv/Ezra.xml
+- data/esv/Galatians.xml
+- data/esv/Genesis.xml
+- data/esv/Habakkuk.xml
+- data/esv/Haggai.xml
+- data/esv/Hebrews.xml
+- data/esv/Hosea.xml
+- data/esv/Isaiah.xml
+- data/esv/James.xml
+- data/esv/Jeremiah.xml
+- data/esv/Job.xml
+- data/esv/Joel.xml
+- data/esv/John.xml
+- data/esv/Jonah.xml
+- data/esv/Joshua.xml
+- data/esv/Jude.xml
+- data/esv/Judges.xml
+- data/esv/Lamentations.xml
+- data/esv/Leviticus.xml
+- data/esv/Luke.xml
+- data/esv/Malachi.xml
+- data/esv/Mark.xml
+- data/esv/Matthew.xml
+- data/esv/Micah.xml
+- data/esv/Nahum.xml
+- data/esv/Nehemiah.xml
+- data/esv/Numbers.xml
+- data/esv/Obadiah.xml
+- data/esv/Philemon.xml
+- data/esv/Philippians.xml
+- data/esv/Proverbs.xml
+- data/esv/Psalms.xml
+- data/esv/Revelation.xml
+- data/esv/Romans.xml
+- data/esv/Ruth.xml
+- data/esv/Song of Solomon.xml
+- data/esv/Titus.xml
+- data/esv/Zechariah.xml
+- data/esv/Zephaniah.xml
+- data/esv/_notes.text.xml
+- lib/wcc-scripture.rb
+- lib/wcc/scripture.rb
+- lib/wcc/scripture/esv.rb
+- lib/wcc/scripture/exceptions.rb
+- lib/wcc/scripture/version.rb
+- wcc-scripture.gemspec
+homepage:
+licenses:
+- Not licensed for external use
+metadata: {}
+post_install_message:
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '2.3'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.0.3
+signing_key:
+specification_version: 4
+summary: Internal Watermark.org gem, not licensed for external use.
+test_files: []