stepmod-utils 0.1.6 → 0.2.4

data/lib/stepmod/utils/converters/ol.rb

@@ -9,8 +9,9 @@ module Stepmod
           anchor = id ? "[[#{id}]]\n" : ""
           ol_count = state.fetch(:ol_count, 0) + 1
           attrs = ol_attrs(node)
-          res = "\n#{anchor}#{attrs}#{treat_children(node, state.merge(ol_count: ol_count))}"
-          res = "\n" + res if node.parent && node.parent.name == 'note'
+          res = "\n\n#{anchor}#{attrs}#{treat_children(node, state.merge(ol_count: ol_count))}\n"
+          # Why do we add this?
+          # res = "\n" + res if node.parent && node.parent.name == 'note'
           res
         end
 

data/lib/stepmod/utils/converters/p.rb

@@ -0,0 +1,21 @@
+# frozen_string_literal: true
+
+module Stepmod
+  module Utils
+    module Converters
+      class P < ReverseAdoc::Converters::Base
+        def convert(node, state = {})
+          id = node['id']
+          anchor = id ? "[[#{id}]]\n" : ""
+          if state[:tdsinglepara]
+            "#{anchor}#{treat_children(node, state).strip}"
+          else
+            "\n\n#{anchor}#{treat_children(node, state).strip}\n\n"
+          end
+        end
+      end
+
+      ReverseAdoc::Converters.register :p, P.new
+    end
+  end
+end

data/lib/stepmod/utils/converters/pass_through.rb

@@ -0,0 +1,13 @@
+# frozen_string_literal: true
+
+module Stepmod
+  module Utils
+    module Converters
+      class PassThrough < ReverseAdoc::Converters::Base
+        def convert(node, state = {})
+          node.to_s
+        end
+      end
+    end
+  end
+end

data/lib/stepmod/utils/converters/q.rb

@@ -0,0 +1,16 @@
+# frozen_string_literal: true
+
+module Stepmod
+  module Utils
+    module Converters
+      class Q < ReverseAdoc::Converters::Base
+        def convert(node, state = {})
+          content = treat_children(node, state)
+          "#{content[/^\s*/]}\"#{content.strip}\"#{content[/\s*$/]}"
+        end
+      end
+
+      ReverseAdoc::Converters.register :q, Q.new
+    end
+  end
+end

data/lib/stepmod/utils/converters/resource.rb

@@ -0,0 +1,14 @@
+# frozen_string_literal: true
+
+module Stepmod
+  module Utils
+    module Converters
+      class Resource < ReverseAdoc::Converters::Base
+        def convert(node, state = {})
+          treat_children(node, state)
+        end
+      end
+      ReverseAdoc::Converters.register :resource, Resource.new
+    end
+  end
+end

data/lib/stepmod/utils/converters/schema.rb

@@ -0,0 +1,18 @@
+# frozen_string_literal: true
+
+module Stepmod
+  module Utils
+    module Converters
+      class Schema < ReverseAdoc::Converters::Base
+        def convert(node, state = {})
+          <<~TEMPLATE
+            (*"#{node['name']}"
+            #{treat_children(node, state).strip}
+            *)
+          TEMPLATE
+        end
+      end
+      ReverseAdoc::Converters.register :schema, Schema.new
+    end
+  end
+end

data/lib/stepmod/utils/converters/schema_diag.rb

@@ -0,0 +1,14 @@
+# frozen_string_literal: true
+
+module Stepmod
+  module Utils
+    module Converters
+      class SchemaDiag < ReverseAdoc::Converters::Base
+        def convert(node, state = {})
+          treat_children(node, state).strip
+        end
+      end
+      ReverseAdoc::Converters.register :schema_diag, SchemaDiag.new
+    end
+  end
+end

data/lib/stepmod/utils/converters/strong.rb

@@ -0,0 +1,21 @@
+# frozen_string_literal: true
+
+module Stepmod
+  module Utils
+    module Converters
+      class Strong < ReverseAdoc::Converters::Base
+        def convert(node, state = {})
+          content = treat_children(node, state.merge(already_strong: true))
+          if content.strip.empty? || state[:already_strong]
+            content
+          else
+            "#{content[/^\s*/]}*#{content.strip}*#{content[/\s*$/]}"
+          end
+        end
+      end
+
+      ReverseAdoc::Converters.register :strong, Strong.new
+      ReverseAdoc::Converters.register :b,      Strong.new
+    end
+  end
+end

data/lib/stepmod/utils/converters/sub.rb

@@ -0,0 +1,16 @@
+# frozen_string_literal: true
+
+module Stepmod
+  module Utils
+    module Converters
+      class Sub < ReverseAdoc::Converters::Base
+        def convert(node, state = {})
+          content = treat_children(node, state)
+          "#{content[/^\s*/]}~#{content.strip}~#{content[/\s*$/]}"
+        end
+      end
+
+      ReverseAdoc::Converters.register :sub, Sub.new
+    end
+  end
+end

data/lib/stepmod/utils/converters/sup.rb

@@ -0,0 +1,16 @@
+# frozen_string_literal: true
+
+module Stepmod
+  module Utils
+    module Converters
+      class Sup < ReverseAdoc::Converters::Base
+        def convert(node, state = {})
+          content = treat_children(node, state)
+          "#{content[/^\s*/]}^#{content.strip}^#{content[/\s*$/]}"
+        end
+      end
+
+      ReverseAdoc::Converters.register :sup, Sup.new
+    end
+  end
+end

data/lib/stepmod/utils/converters/text.rb

@@ -0,0 +1,68 @@
+# frozen_string_literal: true
+
+module Stepmod
+  module Utils
+    module Converters
+      class Text < ReverseAdoc::Converters::Base
+        def convert(node, state = {})
+          if node.text.strip.empty?
+            treat_empty(node, state)
+          else
+            treat_text(node)
+          end
+        end
+
+        private
+
+        def treat_empty(node, state)
+          parent = node.parent.name.to_sym
+          if [:ol, :ul].include?(parent)  # Otherwise the identation is broken
+            ''
+          elsif state[:tdsinglepara]
+            ''
+          elsif node.text == ' '          # Regular whitespace text node
+            ' '
+          else
+            ''
+          end
+        end
+
+        def treat_text(node)
+          text = node.text
+          text = preserve_nbsp(text)
+          # text = remove_border_newlines(text)
+          text = remove_inner_newlines(text)
+
+          text = preserve_keychars_within_backticks(text)
+          text = preserve_tags(text)
+
+          text
+        end
+
+        def preserve_nbsp(text)
+          text.gsub(/\u00A0/, "&nbsp;")
+        end
+
+        def preserve_tags(text)
+          text.gsub(/[<>]/, '>' => '\>', '<' => '\<')
+        end
+
+        def remove_border_newlines(text)
+          text.gsub(/\A\n+/, '').gsub(/\n+\z/, '')
+        end
+
+        def remove_inner_newlines(text)
+          text.tr("\n\t", ' ').squeeze(' ')
+        end
+
+        def preserve_keychars_within_backticks(text)
+          text.gsub(/`.*?`/) do |match|
+            match.gsub('\_', '_').gsub('\*', '*')
+          end
+        end
+      end
+
+      ReverseAdoc::Converters.register :text, Text.new
+    end
+  end
+end

data/lib/stepmod/utils/html_to_asciimath.rb

@@ -0,0 +1,157 @@
+module Stepmod
+  module Utils
+    class HtmlToAsciimath
+      def call(input)
+        return input if input.nil? || input.empty?
+
+        to_asciimath = Nokogiri::HTML.fragment(input, "UTF-8")
+
+        to_asciimath.css('i').each do |math_element|
+          # puts "HTML MATH!!  #{math_element.to_xml}"
+          # puts "HTML MATH!!  #{math_element.text}"
+          decoded = text_to_asciimath(math_element.text)
+          case decoded.length
+          when 1..12
+            # puts "(#{math_element.text} to => #{decoded})"
+            math_element.replace "stem:[#{decoded}]"
+          when 0
+            math_element.remove
+          else
+            math_element.replace "_#{decoded}_"
+          end
+        end
+
+        to_asciimath.css('sub').each do |math_element|
+          case math_element.text.length
+          when 0
+            math_element.remove
+          else
+            math_element.replace "~#{text_to_asciimath(math_element.text)}~"
+          end
+        end
+
+        to_asciimath.css('sup').each do |math_element|
+          case math_element.text.length
+          when 0
+            math_element.remove
+          else
+            math_element.replace "^#{text_to_asciimath(math_element.text)}^"
+          end
+        end
+
+        to_asciimath.css('ol').each do |element|
+          element.css('li').each do |li|
+            li.replace ". #{li.text}"
+          end
+        end
+
+        to_asciimath.css('ul').each do |element|
+          element.css('li').each do |li|
+            li.replace "* #{li.text}"
+          end
+        end
+
+        # Replace sans-serif font with monospace
+        to_asciimath.css('font[style*="sans-serif"]').each do |x|
+          x.replace "`#{x.text}`"
+        end
+
+        html_entities_to_stem(
+          to_asciimath.children.to_s.gsub(/\]stem:\[/, '').gsub(/<\/?[uo]l>/, '')
+        )
+      end
+
+      def text_to_asciimath(text)
+        html_entities_to_asciimath(text.decode_html)
+      end
+
+      def html_entities_to_asciimath(x)
+        x.gsub("&alpha;", "alpha").
+          gsub("&beta;", "beta").
+          gsub("&gamma;", "gamma").
+          gsub("&Gamma;", "Gamma").
+          gsub("&delta;", "delta").
+          gsub("&Delta;", "Delta").
+          gsub("&epsilon;", "epsilon").
+          gsub("&varepsilon;", "varepsilon").
+          gsub("&zeta;", "zeta").
+          gsub("&eta;", "eta").
+          gsub("&theta;", "theta").
+          gsub("&Theta;", "Theta").
+          gsub("&vartheta;", "vartheta").
+          gsub("&iota;", "iota").
+          gsub("&kappa;", "kappa").
+          gsub("&lambda;", "lambda").
+          gsub("&Lambda;", "Lambda").
+          gsub("&mu;", "mu").
+          gsub("&nu;", "nu").
+          gsub("&xi;", "xi").
+          gsub("&Xi;", "Xi").
+          gsub("&pi;", "pi").
+          gsub("&Pi;", "Pi").
+          gsub("&rho;", "rho").
+          gsub("&beta;", "beta").
+          gsub("&sigma;", "sigma").
+          gsub("&Sigma;", "Sigma").
+          gsub("&tau;", "tau").
+          gsub("&upsilon;", "upsilon").
+          gsub("&phi;", "phi").
+          gsub("&Phi;", "Phi").
+          gsub("&varphi;", "varphi").
+          gsub("&chi;", "chi").
+          gsub("&psi;", "psi").
+          gsub("&Psi;", "Psi").
+          gsub("&omega;", "omega")
+          gsub("&#967", "χ").
+          gsub("&#215", "×").
+          gsub("&#931", "Σ").
+          gsub("&#961", "ρ").
+          gsub("&#963", "σ").
+          gsub("&#955", "λ").
+          gsub("&#964", "τ").
+          gsub("&#8706", "∂").
+          gsub("&#8804", "≤").
+          gsub("&#8805", "≥")
+      end
+
+      def html_entities_to_stem(x)
+        x.gsub("&alpha;", "stem:[alpha]").
+          gsub("&beta;", "stem:[beta]").
+          gsub("&gamma;", "stem:[gamma]").
+          gsub("&Gamma;", "stem:[Gamma]").
+          gsub("&delta;", "stem:[delta]").
+          gsub("&Delta;", "stem:[Delta]").
+          gsub("&epsilon;", "stem:[epsilon]").
+          gsub("&varepsilon;", "stem:[varepsilon]").
+          gsub("&zeta;", "stem:[zeta]").
+          gsub("&eta;", "stem:[eta]").
+          gsub("&theta;", "stem:[theta]").
+          gsub("&Theta;", "stem:[Theta]").
+          gsub("&vartheta;", "stem:[vartheta]").
+          gsub("&iota;", "stem:[iota]").
+          gsub("&kappa;", "stem:[kappa]").
+          gsub("&lambda;", "stem:[lambda]").
+          gsub("&Lambda;", "stem:[Lambda]").
+          gsub("&mu;", "stem:[mu]").
+          gsub("&nu;", "stem:[nu]").
+          gsub("&xi;", "stem:[xi]").
+          gsub("&Xi;", "stem:[Xi]").
+          gsub("&pi;", "stem:[pi]").
+          gsub("&Pi;", "stem:[Pi]").
+          gsub("&rho;", "stem:[rho]").
+          gsub("&beta;", "stem:[beta]").
+          gsub("&sigma;", "stem:[sigma]").
+          gsub("&Sigma;", "stem:[Sigma]").
+          gsub("&tau;", "stem:[tau]").
+          gsub("&upsilon;", "stem:[upsilon]").
+          gsub("&phi;", "stem:[phi]").
+          gsub("&Phi;", "stem:[Phi]").
+          gsub("&varphi;", "stem:[varphi]").
+          gsub("&chi;", "stem:[chi]").
+          gsub("&psi;", "stem:[psi]").
+          gsub("&Psi;", "stem:[Psi]").
+          gsub("&omega;", "stem:[omega]")
+      end
+    end
+  end
+end

data/lib/stepmod/utils/smrl_description_converter.rb

@@ -0,0 +1,49 @@
+# frozen_string_literal: true
+
+require 'reverse_adoc'
+require 'stepmod/utils/converters/a'
+require 'stepmod/utils/converters/blockquote'
+require 'stepmod/utils/converters/br'
+require 'stepmod/utils/converters/bypass'
+require 'stepmod/utils/converters/code'
+require 'stepmod/utils/converters/drop'
+require 'stepmod/utils/converters/em_express_description'
+require 'stepmod/utils/converters/example'
+require 'stepmod/utils/converters/express_ref_express_description'
+require 'stepmod/utils/converters/ext_description'
+require 'stepmod/utils/converters/ext_descriptions'
+require 'stepmod/utils/converters/head'
+require 'stepmod/utils/converters/hr'
+require 'stepmod/utils/converters/ignore'
+require 'stepmod/utils/converters/note'
+require 'stepmod/utils/converters/p'
+require 'stepmod/utils/converters/pass_through'
+require 'stepmod/utils/converters/q'
+require 'stepmod/utils/converters/strong'
+require 'stepmod/utils/converters/sub'
+require 'stepmod/utils/converters/sup'
+require 'stepmod/utils/converters/text'
+require 'stepmod/utils/cleaner'
+
+module Stepmod
+  module Utils
+    class SmrlDescriptionConverter
+      def self.convert(input, options = {})
+        root = if input.is_a?(String)
+                  then Nokogiri::XML(input).root
+                elsif input.is_a?(Nokogiri::XML::Document)
+                  then input.root
+                elsif input.is_a?(Nokogiri::XML::Node)
+                  then input
+                end
+
+        root || (return '')
+
+        ReverseAdoc.config.with(options) do
+          result = ReverseAdoc::Converters.lookup(root.name).convert(root)
+          Stepmod::Utils::Cleaner.new.tidy(result)
+        end
+      end
+    end
+  end
+end