metanorma-standoc 1.4.3 → 1.5.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: ac225a257c1a5c42ce296ee87ef1d95e378111a82875211969771f7d1756bcf2
-  data.tar.gz: 30ff55c905559089be61b2752cb84c8274a121b4e5359a8cdf547528296a09be
+  metadata.gz: 7503bfc7dd68c2d6a6b2ded8f08611e92067a15aa4088c02f1e5408ff8e027e6
+  data.tar.gz: 65cd5d4d3648788113fd30437fe8d649c6e498b9ebdab8d5b41d2fadb7439056
 SHA512:
-  metadata.gz: e66997f17221a04e57e213a66e16ce0061060c5ffd0708bc9196b2b75ec8081673475890b8745086341196bb30a7832ca7f3c1d5615bd80063e31f6f9e243534
-  data.tar.gz: 1a1e23d189dbb0ef46552e5953cd8568c83b6380d239a68cfab95e8a1cb975583e7697bc6d11babb509ca5a21f9f3c7d4d06e225f8faef39f2c7f3d9d8087f9c
+  metadata.gz: 73510f7d926c6acf395377794a753cef6bb0f0658fb66c606df07e23548c17f010c7120b77765b388fb363a4309051fcf03a601d6ea95cf20aca6e4645b1c674
+  data.tar.gz: bae732755cc47dcae17e0d8ef01bcd35173c8941807b2d5844cf45f008f57c199977756d4fd15b0e3c8c558e73432dd9ba88be2b01f61b32cff180308adcd83d

data/.github/workflows/ubuntu.yml

@@ -43,7 +43,7 @@ jobs:
           polling_interval_seconds: 5
           timeout_minutes: 5
           max_attempts: 3
-          command: sudo bash -c "curl -L https://github.com/metanorma/plantuml-install/raw/master/ubuntu.sh | bash"
+          command: sudo apt-get update -y && sudo bash -c "curl -L https://github.com/metanorma/plantuml-install/raw/master/ubuntu.sh | bash"
       - name: Run specs
         run: |
           bundle exec rake

data/.rubocop.yml

@@ -5,6 +5,6 @@
 inherit_from:
   - https://raw.githubusercontent.com/riboseinc/oss-guides/master/ci/rubocop.yml
 AllCops:
-  TargetRubyVersion: 2.3
+  TargetRubyVersion: 2.6
 Rails:
   Enabled: true

data/Rakefile

@@ -1,6 +1,8 @@
 require "bundler/gem_tasks"
 require "rspec/core/rake_task"
+require 'isodoc/gem_tasks'
 
+IsoDoc::GemTasks.install
 RSpec::Core::RakeTask.new(:spec)
 
 task default: :spec

data/lib/asciidoctor/standoc/base.rb

@@ -111,9 +111,10 @@ module Asciidoctor
         @log = Asciidoctor::Standoc::Log.new
         init_bib_caches(node)
         init_iev_caches(node)
-        lang = (node.attr("language") || "en")
-        script = (node.attr("script") || "en")
-        i18n_init(lang, script)
+        @lang = (node.attr("language") || "en")
+        @script = (node.attr("script") || "Latn")
+        @isodoc = isodoc(@lang, @script, node.attr("i18nyaml"))
+        @i18n = @isodoc.i18n
       end
 
       def default_fonts(node)
@@ -169,7 +170,7 @@ module Asciidoctor
       end
 
       def doctype(node)
-        node.attr("doctype")
+        node.attr("doctype")&.gsub(/\s+/, "-")&.downcase
       end
 
       def front(node, xml)

data/lib/asciidoctor/standoc/base_structured_text_preprocessor.rb

@@ -0,0 +1,123 @@
+# frozen_string_literal: true
+
+require "liquid/custom_blocks/key_iterator"
+require "liquid/custom_filters/values"
+
+Liquid::Template.register_tag("keyiterator", Liquid::CustomBlocks::KeyIterator)
+Liquid::Template.register_filter(Liquid::CustomFilters)
+
+module Asciidoctor
+  module Standoc
+    # Base class for processing structured data blocks(yaml, json)
+    class BaseStructuredTextPreprocessor < Asciidoctor::Extensions::Preprocessor
+      BLOCK_START_REGEXP = /\{(.+?)\.\*,(.+),(.+)\}/
+      BLOCK_END_REGEXP = /\A\{[A-Z]+\}\z/
+
+      def process(document, reader)
+        input_lines = reader.readlines.to_enum
+        Reader.new(processed_lines(document, input_lines))
+      end
+
+      protected
+
+      def content_from_file(_document, _file_path)
+        raise ArgumentError, "Implement `content_from_file` in your class"
+      end
+
+      private
+
+      def processed_lines(document, input_lines)
+        result = []
+        loop do
+          result.push(*process_text_blocks(document, input_lines))
+        end
+        result
+      end
+
+      def relative_file_path(document, file_path)
+        docfile_directory = File.dirname(document.attributes["docfile"] || ".")
+        document
+          .path_resolver
+          .system_path(file_path, docfile_directory)
+      end
+
+      def process_text_blocks(document, input_lines)
+        line = input_lines.next
+        block_match = line.match(/^\[#{config[:block_name]},(.+?),(.+?)\]/)
+        return [line] if block_match.nil?
+
+        mark = input_lines.next
+        current_block = []
+        while (block_line = input_lines.next) != mark
+          current_block.push(block_line)
+        end
+        read_content_and_parse_template(document,
+                                        current_block,
+                                        block_match)
+      end
+
+      def read_content_and_parse_template(document, current_block, block_match)
+        transformed_liquid_lines = current_block
+          .map(&method(:transform_line_liquid))
+        context_items = content_from_file(document, block_match[1])
+        parse_context_block(document: document,
+                            context_lines: transformed_liquid_lines,
+                            context_items: context_items,
+                            context_name: block_match[2])
+      rescue StandardError => exception
+        document.logger
+          .warn("Failed to parse #{config[:block_name]} \
+            block: #{exception.message}")
+        []
+      end
+
+      def transform_line_liquid(line)
+        if line.match?(BLOCK_START_REGEXP)
+          line.gsub!(BLOCK_START_REGEXP,
+                     '{% keyiterator \1, \2 %}')
+        end
+
+        if line.strip.match?(BLOCK_END_REGEXP)
+          line.gsub!(BLOCK_END_REGEXP, "{% endkeyiterator %}")
+        end
+        line
+          .gsub(/(?<!{){(?!%)([^{}]+)(?<!%)}(?!})/, '{{\1}}')
+          .gsub(/[a-z\.]+\#/, "index")
+          .gsub(/{{(.+)\s+\+\s+(\d+)\s*?}}/, '{{ \1 | plus: \2 }}')
+          .gsub(/{{(.+)\s+\-\s+(\d+)\s*?}}/, '{{ \1 | minus: \2 }}')
+          .gsub(/{{(.+).values(.*?)}}/,
+                '{% assign custom_value = \1 | values %}{{custom_value\2}}')
+      end
+
+      def parse_context_block(context_lines:,
+                              context_items:,
+                              context_name:,
+                              document:)
+        render_result, errors = render_liquid_string(
+          template_string: context_lines.join("\n"),
+          context_items: context_items,
+          context_name: context_name
+        )
+        notify_render_errors(document, errors)
+        render_result.split("\n")
+      end
+
+      def render_liquid_string(template_string:, context_items:, context_name:)
+        liquid_template = Liquid::Template.parse(template_string)
+        rendered_string = liquid_template
+          .render(context_name => context_items,
+                  strict_variables: true,
+                  error_mode: :warn)
+        [rendered_string, liquid_template.errors]
+      end
+
+      def notify_render_errors(document, errors)
+        errors.each do |error_obj|
+          document
+            .logger
+            .warn("Liquid render error: #{error_obj.message}")
+        end
+      end
+    end
+  end
+end

data/lib/asciidoctor/standoc/basicdoc.rng

@@ -158,7 +158,17 @@
         <data type="ID"/>
       </attribute>
       <oneOrMore>
-        <ref name="paragraph"/>
+        <choice>
+          <ref name="formula"/>
+          <ref name="ul"/>
+          <ref name="ol"/>
+          <ref name="dl"/>
+          <ref name="quote"/>
+          <ref name="sourcecode"/>
+          <ref name="paragraph"/>
+          <ref name="table"/>
+          <ref name="figure"/>
+        </choice>
       </oneOrMore>
     </element>
   </define>
@@ -402,6 +412,16 @@
           </choice>
         </attribute>
       </optional>
+      <optional>
+        <attribute name="valign">
+          <choice>
+            <value>top</value>
+            <value>middle</value>
+            <value>bottom</value>
+            <value>baseline</value>
+          </choice>
+        </attribute>
+      </optional>
       <choice>
         <zeroOrMore>
           <ref name="TextElement"/>
@@ -429,6 +449,16 @@
           </choice>
         </attribute>
       </optional>
+      <optional>
+        <attribute name="valign">
+          <choice>
+            <value>top</value>
+            <value>middle</value>
+            <value>bottom</value>
+            <value>baseline</value>
+          </choice>
+        </attribute>
+      </optional>
       <choice>
         <zeroOrMore>
           <ref name="TextElement"/>

data/lib/asciidoctor/standoc/cleanup.rb

@@ -9,6 +9,7 @@ require_relative "./cleanup_boilerplate.rb"
 require_relative "./cleanup_section.rb"
 require_relative "./cleanup_terms.rb"
 require_relative "./cleanup_inline.rb"
+require_relative "./cleanup_amend.rb"
 require "relaton_iev"
 
 module Asciidoctor
@@ -71,6 +72,7 @@ module Asciidoctor
         para_cleanup(xmldoc)
         empty_element_cleanup(xmldoc)
         img_cleanup(xmldoc)
+        anchor_cleanup(xmldoc)
         xmldoc
       end
 

data/lib/asciidoctor/standoc/cleanup_amend.rb

@@ -0,0 +1,54 @@
+module Asciidoctor
+  module Standoc
+    module Cleanup
+      def change_clauses(x)
+        x.xpath("//clause[@change]").each do |c|
+          a = create_amend(c)
+        end
+      end
+
+      def create_amend(c)
+        a = c.add_child("<amend id='_#{UUIDTools::UUID.random_create}'/>").first
+        c.elements.each do |e|
+          e.parent = a unless %w(amend title).include? e.name
+        end
+        create_amend1(c, a)
+      end
+
+      def create_amend1(c, a)
+        create_amend2(c, a)
+        d = a.at("./description")
+        d.xpath(".//autonumber").each { |e| d.previous = e }
+        d.xpath(".//p[normalize-space(.)='']").each { |e| e.remove }
+        move_attrs_to_amend(c, a)
+        a
+      end
+
+      def create_amend2(c, a)
+        q = a.at("./quote") and q.name = "newcontent"
+        if q.nil?
+          a.children = "<description>#{a.children.to_xml}</description>"
+        else
+          pre = q&.xpath("./preceding-sibling::*")&.remove
+          post = q&.xpath("./following-sibling::*")&.remove
+          pre.empty? or a << "<description>#{pre.to_xml}</description>"
+          a << q.remove
+          post.empty? or a << "<description>#{post.to_xml}</description>"
+        end
+      end
+
+      def move_attrs_to_amend(c, a)
+        %w(change path path_end title).each do |e|
+          next unless c[e]
+          a[e] = c[e]
+          c.delete(e)
+        end
+        return unless a["locality"]
+        loc = a.children.add_previous_sibling("<location/>")
+        extract_localities1(loc, a["locality"])
+        loc1 = loc.at("./localityStack") and loc.replace(loc1.elements)
+        a.delete("locality")
+      end
+    end
+  end
+end

data/lib/asciidoctor/standoc/cleanup_block.rb

@@ -1,8 +1,6 @@
 require "date"
-require "nokogiri"
 require "htmlentities"
 require "json"
-require "pathname"
 require "open-uri"
 
 module Asciidoctor

data/lib/asciidoctor/standoc/cleanup_boilerplate.rb

@@ -2,25 +2,25 @@ module Asciidoctor
   module Standoc
     module Cleanup
       def external_terms_boilerplate(sources)
-        IsoDoc::Function::I18n::l10n(
-          @external_terms_boilerplate.gsub(/%/, sources || "???"),
+        @i18n.l10n(
+          @i18n.external_terms_boilerplate.gsub(/%/, sources || "???"),
           @lang, @script)
       end
 
       def internal_external_terms_boilerplate(sources)
-        IsoDoc::Function::I18n::l10n(
-          @internal_external_terms_boilerplate.gsub(/%/, sources || "??"),
+        @i18n.l10n(
+          @i18n.internal_external_terms_boilerplate.gsub(/%/, sources || "??"),
           @lang, @script)
       end
 
       def term_defs_boilerplate(div, source, term, preface, isodoc)
-        div.next = @term_def_boilerplate
+        a = @i18n.term_def_boilerplate and div.next = a
         source.each do |s|
           @anchors[s["bibitemid"]] or
             @log.add("Crossreferences", nil, "term source #{s['bibitemid']} not referenced")
         end
         if source.empty? && term.nil?
-          div.next = @no_terms_boilerplate
+          div.next = @i18n.no_terms_boilerplate
         else
           div.next = term_defs_boilerplate_cont(source, term, isodoc)
         end
@@ -30,7 +30,7 @@ module Asciidoctor
         sources = isodoc.sentence_join(src.map do |s|
           %{<eref bibitemid="#{s['bibitemid']}"/>}
         end)
-        if src.empty? then @internal_terms_boilerplate
+        if src.empty? then @i18n.internal_terms_boilerplate
         elsif term.nil? then external_terms_boilerplate(sources)
         else
           internal_external_terms_boilerplate(sources)
@@ -42,7 +42,7 @@ module Asciidoctor
         ["reference", "bibitem"].include? e.name
       end
       f.at("./title").next =
-        "<p>#{(refs.empty? ? @norm_empty_pref : @norm_with_refs_pref)}</p>"
+        "<p>#{(refs.empty? ? @i18n.norm_empty_pref : @i18n.norm_with_refs_pref)}</p>"
     end
 
       TERM_CLAUSE = "//sections/terms | "\
@@ -54,13 +54,9 @@ module Asciidoctor
         x = xmldoc.dup
         x.root.add_namespace(nil, self.class::XML_NAMESPACE)
         xml = Nokogiri::XML(x.to_xml)
-        conv = html_converter(EmptyAttr.new)
-        @lang = xmldoc&.at("//bibdata/language")&.text
-        @script = xmldoc&.at("//bibdata/script")&.text
-        conv.i18n_init(@lang, @script)
-        conv.metadata_init(@lang, @script, conv.labels)
-        conv.info(xml, nil)
-        conv
+        @isodoc ||= isodoc(@lang, @script)
+        @isodoc.info(xml, nil)
+        @isodoc
       end
 
       def boilerplate_cleanup(xmldoc)
@@ -83,15 +79,6 @@ module Asciidoctor
         preface.previous = b
       end
 
-      class EmptyAttr
-        def attr(_x)
-          nil
-        end
-        def attributes
-          {}
-        end
-      end
-
       def boilerplate_file(xmldoc)
         File.join(@libdir, "boilerplate.xml")
       end

data/lib/asciidoctor/standoc/cleanup_footnotes.rb

@@ -1,10 +1,7 @@
 require "date"
-require "nokogiri"
 require "htmlentities"
 require "json"
-require "pathname"
 require "open-uri"
-require "pp"
 
 module Asciidoctor
   module Standoc

data/lib/asciidoctor/standoc/cleanup_inline.rb

@@ -50,6 +50,10 @@ module Asciidoctor
 
       def extract_localities(x)
         text = x&.children&.first&.remove&.text
+        extract_localities1(x, text)
+      end
+
+      def extract_localities1(x, text)
         b = x.add_child("<localityStack/>").first if LOCALITY_RE.match text
         while (m = LOCALITY_RE.match text)
           ref = m[:ref] ? "<referenceFrom>#{tq m[:ref]}</referenceFrom>" : ""
@@ -117,7 +121,8 @@ module Asciidoctor
       def concept_termbase_cleanup(x)
         text = x&.children&.first&.remove&.text
         termbase, key = x["key"].split(/:/, 2)
-        x.add_child(%(<termref base="#{termbase}" target="#{key}">#{text}</termref>))
+        x.add_child(%(<termref base="#{termbase}" target="#{key}">) + 
+                    "#{text}</termref>")
       end
 
       def concept_xref_cleanup(x)
@@ -129,6 +134,62 @@ module Asciidoctor
         x.children = "<eref>#{x.children.to_xml}</eref>"
         extract_localities(x.first_element_child)
       end
+
+      NAMECHAR = "\u0000-\u0022\u0024\u002c\u002f\u003a-\u0040\\u005b-\u005e"\
+        "\u0060\u007b-\u00b6\u00b8-\u00bf\u00d7\u00f7\u037e\u2000-\u200b"\
+        "\u200e-\u203e\u2041-\u206f\u2190-\u2bff\u2ff0-\u3000".freeze
+      #"\ud800-\uf8ff\ufdd0-\ufdef\ufffe-\uffff".freeze
+      NAMESTARTCHAR = "\\u002d\u002e\u0030-\u0039\u00b7\u0300-\u036f"\
+        "\u203f-\u2040".freeze
+
+      def to_ncname(s)
+        start = s[0]
+        ret1 = %r([#{NAMECHAR}#]).match(start) ? "_" :
+          (%r([#{NAMESTARTCHAR}#]).match(start) ? "_#{start}" : start)
+        ret2 = s[1..-1] || ""
+        ret = (ret1 || "") + ret2.gsub(%r([#{NAMECHAR}#]), "_")
+        ret
+      end
+
+      def to_xreftarget(s)
+        return to_ncname(s) unless /^[^#]+#.+$/.match(s)
+          /^(?<pref>[^#]+)#(?<suff>.+)$/ =~ s
+        pref = pref.gsub(%r([#{NAMECHAR}]), "_")
+        suff = suff.gsub(%r([#{NAMECHAR}]), "_")
+        "#{pref}##{suff}"
+      end
+
+      IDREF = "//*/@id | //review/@from | //review/@to | "\
+        "//callout/@target | //citation/@bibitemid | //eref/@bibitemid".freeze
+
+      def anchor_cleanup(x)
+        anchor_cleanup1(x)
+        xreftarget_cleanup(x)
+      end
+
+      def anchor_cleanup1(x)
+        x.xpath(IDREF).each do |s|
+          if (ret = to_ncname(s.value)) != (orig = s.value)
+            s.value = ret
+            output = s.parent.dup
+            output.children.remove
+            @log.add("Anchors", s.parent, "normalised identifier in #{output} "\
+                     "from #{orig}")
+          end
+        end
+      end
+
+      def xreftarget_cleanup(x)
+        x.xpath("//xref/@target").each do |s|
+          if (ret = to_xreftarget(s.value)) != (orig = s.value)
+            s.value = ret
+            output = s.parent.dup
+            output.children.remove
+            @log.add("Anchors", s.parent, "normalised identifier in #{output} "\
+                     "from #{orig}")
+          end
+        end
+      end
     end
   end
 end