metanorma-standoc 1.10.4.1 → 1.10.5

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 4de5b7f8779dae7c359b93ce364ffa7cc406156bf1437c7cdccb6595b7bd958a
-  data.tar.gz: c35902148b405e451af8487faff391b6eddbbd7b07cd2b6c8d565cd515e4515c
+  metadata.gz: dd98ba81df1c144552167e677b04d6152d838de0ea2d539a6bc7bde2a4b7f235
+  data.tar.gz: 68d9afff164047bf12f97ac23735cc1d61503172ae8656795393314d127223b6
 SHA512:
-  metadata.gz: 6e33b33321d6826a65257a3440c63218021d5d40b69fa58b268d0a2c5e8436aed951e05c7f44ab97c74b5ce916c25ad7040cc962cf38be15ee2ebaf0c6858529
-  data.tar.gz: f8f719f8062c3c71ebd2883617b984d7432134cb94da1be308e9ede34bf74def5be6267570c76ff9f248e628e443d6b71a60b9f71e1ba436b7c64eb2c2b25c13
+  metadata.gz: 611ba153c4160486b0ea51eb1564e09cd81d02f6ca6d5a075e3f38cf321321f2e019ba538341786bd4fe01eac9ef53e71ddc5cc19fdccb4e69189d9e7a720955
+  data.tar.gz: 0acb358132209888abe3a276c16abcfdf142570fd271712960e64e02db487df9bb39081a1f4e08da7347777a71240b57b2d8f6dda7d980523981efe5a838495c

data/lib/asciidoctor/standoc/base.rb

@@ -53,6 +53,7 @@ module Asciidoctor
           htmltoclevels: node.attr("htmltoclevels") || node.attr("toclevels"),
           doctoclevels: node.attr("doctoclevels") || node.attr("toclevels"),
           break_up_urls_in_tables: node.attr("break-up-urls-in-tables"),
+          suppressasciimathdup: node.attr("suppress-asciimath-dup"),
           bare: node.attr("bare"),
           sectionsplit: node.attr("sectionsplit"),
         }
@@ -87,6 +88,7 @@ module Asciidoctor
           htmltoclevels: node.attr("htmltoclevels") || node.attr("toclevels"),
           doctoclevels: node.attr("doctoclevels") || node.attr("toclevels"),
           break_up_urls_in_tables: node.attr("break-up-urls-in-tables"),
+          suppressasciimathdup: node.attr("suppress-asciimath-dup"),
           bare: node.attr("bare"),
         }
 

data/lib/asciidoctor/standoc/blocks.rb

@@ -161,6 +161,8 @@ module Asciidoctor
       def para_attrs(node)
         attr_code(keep_attrs(node)
           .merge(align: node.attr("align"),
+                 variant_title: node.role == "variant-title" ? true : nil,
+                 type: node.attr("type"),
                  id: Metanorma::Utils::anchor_or_uuid(node)))
       end
 

data/lib/asciidoctor/standoc/cleanup.rb

@@ -13,19 +13,12 @@ require_relative "./cleanup_amend"
 require_relative "./cleanup_maths"
 require_relative "./cleanup_image"
 require_relative "./cleanup_reqt"
+require_relative "./cleanup_text"
 require "relaton_iev"
 
 module Asciidoctor
   module Standoc
     module Cleanup
-      def textcleanup(result)
-        text = result.flatten.map { |l| l.sub(/\s*$/, "") } * "\n"
-        !@keepasciimath and text = asciimath2mathml(text)
-        text = text.gsub(/\s+<fn /, "<fn ")
-        text.gsub(%r{<passthrough\s+formats="metanorma">([^<]*)
-                  </passthrough>}mx) { HTMLEntities.new.decode($1) }
-      end
-
       def cleanup(xmldoc)
         element_name_cleanup(xmldoc)
         sections_cleanup(xmldoc)
@@ -72,63 +65,6 @@ module Asciidoctor
         xmldoc
       end
 
-      IGNORE_DUMBQUOTES = "//pre | //pre//* | //tt | //tt//* | "\
-        "//sourcecode | //sourcecode//* | //bibdata//* | //stem | "\
-        "//stem//* | //figure[@class = 'pseudocode'] | "\
-        "//figure[@class = 'pseudocode']//*".freeze
-
-      def smartquotes_cleanup(xmldoc)
-        xmldoc.xpath("//date").each { |d| Metanorma::Utils::endash_date(d) }
-        if @smartquotes then smartquotes_cleanup1(xmldoc)
-        else dumbquote_cleanup(xmldoc)
-        end
-      end
-
-      def smartquotes_cleanup1(xmldoc)
-        uninterrupt_quotes_around_xml(xmldoc)
-        dumb2smart_quotes(xmldoc)
-      end
-
-      # "abc<tag/>", def => "abc",<tag/> def
-      def uninterrupt_quotes_around_xml(xmldoc)
-        xmldoc.xpath("//*[following::text()[1]"\
-                     "[starts-with(., '\"') or starts-with(., \"'\")]]")
-          .each do |x|
-          next if !x.ancestors("pre, tt, sourcecode, stem, figure").empty?
-          uninterrupt_quotes_around_xml1(x)
-        end
-      end
-
-      def uninterrupt_quotes_around_xml1(elem)
-        prev = elem.at(".//preceding::text()[1]") or return
-        /\S$/.match?(prev.text) or return
-        foll = elem.at(".//following::text()[1]")
-        m = /^(["'][[:punct:]]*)(\s|$)/.match(HTMLEntities.new.decode(foll&.text)) or return
-        foll.content = foll.text.sub(/^(["'][[:punct:]]*)/, "")
-        prev.content = "#{prev.text}#{m[1]}"
-      end
-
-      def dumb2smart_quotes(xmldoc)
-        (xmldoc.xpath("//*[child::text()]") - xmldoc.xpath(IGNORE_DUMBQUOTES))
-          .each do |x|
-          x.children.each do |n|
-            next unless n.text?
-
-            /[-'"(<>]|\.\.|\dx/.match(n) or next
-
-            n.replace(Metanorma::Utils::smartformat(n.text))
-          end
-        end
-      end
-
-      def dumbquote_cleanup(xmldoc)
-        xmldoc.traverse do |n|
-          next unless n.text?
-
-          n.replace(n.text.gsub(/(?<=\p{Alnum})\u2019(?=\p{Alpha})/, "'")) # .
-        end
-      end
-
       def docidentifier_cleanup(xmldoc); end
 
       TEXT_ELEMS =
@@ -172,8 +108,8 @@ module Asciidoctor
 
           c.xpath("./variant").each do |n|
             if n.at_xpath("preceding-sibling::node()"\
-                "[not(self::text()[not(normalize-space())])][1]"\
-                "[self::variantwrap]")
+                          "[not(self::text()[not(normalize-space())])][1]"\
+                          "[self::variantwrap]")
               n.previous_element << n
             else
               n.replace("<variantwrap/>").first << n
@@ -203,11 +139,11 @@ module Asciidoctor
       end
 
       def toc_index(toc, xmldoc)
-        depths = toc.xpath("./toc-xpath").each_with_object({}) do |x, m|
-          m[x.text] = x["depth"]
-        end
+        depths = toc_index_depths(toc)
         depths.keys.each_with_object([]) do |key, arr|
           xmldoc.xpath(key).each do |x|
+            t = x.at("./following-sibling::variant-title[@type = 'toc']") and
+              x = t
             arr << { text: x.children.to_xml, depth: depths[key].to_i,
                      target: x.xpath("(./ancestor-or-self::*/@id)[last()]")[0].text,
                      line: x.line }
@@ -215,6 +151,12 @@ module Asciidoctor
         end.sort_by { |a| a[:line] }
       end
 
+      def toc_index_depths(toc)
+        toc.xpath("./toc-xpath").each_with_object({}) do |x, m|
+          m[x.text] = x["depth"]
+        end
+      end
+
       def toc_cleanup1(toc, xmldoc)
         depth = 1
         ret = ""

data/lib/asciidoctor/standoc/cleanup_maths.rb

@@ -29,19 +29,19 @@ module Asciidoctor
         x.to_xml
       end
 
-      def xml_unescape_mathml(x)
-        return if x.children.any? { |y| y.element? }
+      def xml_unescape_mathml(xml)
+        return if xml.children.any? { |y| y.element? }
 
-        math = x.text.gsub(/&lt;/, "<").gsub(/&gt;/, ">")
+        math = xml.text.gsub(/&lt;/, "<").gsub(/&gt;/, ">")
           .gsub(/&quot;/, '"').gsub(/&apos;/, "'").gsub(/&amp;/, "&")
           .gsub(/<[^: \r\n\t\/]+:/, "<").gsub(/<\/[^ \r\n\t:]+:/, "</")
-        x.children = math
+        xml.children = math
       end
 
       MATHML_NS = "http://www.w3.org/1998/Math/MathML".freeze
 
-      def mathml_preserve_space(m)
-        m.xpath(".//m:mtext", "m" => MATHML_NS).each do |x|
+      def mathml_preserve_space(math)
+        math.xpath(".//m:mtext", "m" => MATHML_NS).each do |x|
           x.children = x.children.to_xml
             .gsub(/^\s/, "&#xA0;").gsub(/\s$/, "&#xA0;")
         end
@@ -57,23 +57,23 @@ module Asciidoctor
       end
 
       # presuppose multichar mi upright, singlechar mi MathML default italic
-      def mathml_italicise(x)
-        x.xpath(".//m:mi[not(ancestor::*[@mathvariant])]",
-                "m" => MATHML_NS).each do |i|
+      def mathml_italicise(xml)
+        xml.xpath(".//m:mi[not(ancestor::*[@mathvariant])]",
+                  "m" => MATHML_NS).each do |i|
           char = HTMLEntities.new.decode(i.text)
           i["mathvariant"] = "normal" if mi_italicise?(char)
         end
       end
 
-      def mi_italicise?(c)
-        return false if c.length > 1
+      def mi_italicise?(char)
+        return false if char.length > 1
 
-        if /\p{Greek}/.match?(c)
-          /\p{Lower}/.match(c) && !mathml_mi_italics[:lowergreek] ||
-            /\p{Upper}/.match(c) && !mathml_mi_italics[:uppergreek]
-        elsif /\p{Latin}/.match?(c)
-          /\p{Lower}/.match(c) && !mathml_mi_italics[:lowerroman] ||
-            /\p{Upper}/.match(c) && !mathml_mi_italics[:upperroman]
+        if /\p{Greek}/.match?(char)
+          /\p{Lower}/.match(char) && !mathml_mi_italics[:lowergreek] ||
+            /\p{Upper}/.match(char) && !mathml_mi_italics[:uppergreek]
+        elsif /\p{Latin}/.match?(char)
+          /\p{Lower}/.match(char) && !mathml_mi_italics[:lowerroman] ||
+            /\p{Upper}/.match(char) && !mathml_mi_italics[:upperroman]
         else
           false
         end
@@ -100,14 +100,14 @@ module Asciidoctor
         end
       end
 
-      def gather_unitsml(unitsml, xmldoc, t)
-        tags = xmldoc.xpath(".//m:#{t}", "m" => UNITSML_NS)
+      def gather_unitsml(unitsml, xmldoc, tag)
+        tags = xmldoc.xpath(".//m:#{tag}", "m" => UNITSML_NS)
           .each_with_object({}) do |x, m|
           m[x["id"]] = x.remove
         end
         return if tags.empty?
 
-        set = unitsml.add_child("<#{t}Set/>").first
+        set = unitsml.add_child("<#{tag}Set/>").first
         tags.each_value { |v| set << v }
       end
 
@@ -115,14 +115,106 @@ module Asciidoctor
         { multiplier: :space }
       end
 
+      def mathvariant_override(inner, outer)
+        case outer
+        when "bold"
+          case inner
+          when "normal" then "bold"
+          when "italic" then "bold-italic"
+          when "fraktur" then "bold-fraktur"
+          when "script" then "bold-script"
+          when "sans-serif" then "bold-sans-serif"
+          when "sans-serif-italic" then "sans-serif-bold-italic"
+          else inner
+          end
+        when "italic"
+          case inner
+          when "normal" then "italic"
+          when "bold" then "bold-italic"
+          when "sans-serif" then "sans-serif-italic"
+          when "bold-sans-serif" then "sans-serif-bold-italic"
+          else inner
+          end
+        when "bold-italic"
+          case inner
+          when "normal", "bold", "italic" then "bold-italic"
+          when "sans-serif", "bold-sans-serif", "sans-serif-italic"
+            "sans-serif-bold-italic"
+          else inner
+          end
+        when "fraktur"
+          case inner
+          when "normal" then "fraktur"
+          when "bold" then "bold-fraktur"
+          else inner
+          end
+        when "bold-fraktur"
+          case inner
+          when "normal", "fraktur" then "bold-fraktur"
+          else inner
+          end
+        when "script"
+          case inner
+          when "normal" then "script"
+          when "bold" then "bold-script"
+          else inner
+          end
+        when "bold-script"
+          case inner
+          when "normal", "script" then "bold-script"
+          else inner
+          end
+        when "sans-serif"
+          case inner
+          when "normal" then "sans-serif"
+          when "bold" then "bold-sans-serif"
+          when "italic" then "sans-serif-italic"
+          when "bold-italic" then "sans-serif-bold-italic"
+          else inner
+          end
+        when "bold-sans-serif"
+          case inner
+          when "normal", "bold", "sans-serif" then "bold-sans-serif"
+          when "italic", "bold-italic", "sans-serif-italic"
+            "sans-serif-bold-italic"
+          else inner
+          end
+        when "sans-serif-italic"
+          case inner
+          when "normal", "italic", "sans-serif" then "sans-serif-italic"
+          when "bold", "bold-italic", "sans-serif-bold"
+            "sans-serif-bold-italic"
+          else inner
+          end
+        when "sans-serif-bold-italic"
+          case inner
+          when "normal", "italic", "sans-serif", "sans-serif-italic",
+          "bold", "bold-italic", "sans-serif-bold"
+            "sans-serif-bold-italic"
+          else inner
+          end
+        else inner
+        end
+      end
+
+      def mathml_mathvariant(math)
+        math.xpath(".//*[@mathvariant]").each do |outer|
+          outer.xpath(".//*[@mathvariant]").each do |inner|
+            inner["mathvariant"] =
+              mathvariant_override(outer["mathvariant"], inner["mathvariant"])
+          end
+        end
+      end
+
       def mathml_cleanup(xmldoc)
         unitsml = Asciimath2UnitsML::Conv.new(asciimath2unitsml_options)
         xmldoc.xpath("//stem[@type = 'MathML']").each do |x|
           xml_unescape_mathml(x)
           mathml_namespace(x)
           mathml_preserve_space(x)
-          mathml_italicise(x)
           unitsml.MathML2UnitsML(x)
+          mathml_mathvariant(x)
+          mathml_italicise(x)
         end
         mathml_unitsML(xmldoc)
       end

data/lib/asciidoctor/standoc/cleanup_reqt.rb

@@ -24,6 +24,7 @@ module Asciidoctor
           r.children.each do |e|
             unless e.element? && (reqt_subpart(e.name) ||
                 %w(requirement recommendation permission).include?(e.name))
+              next if e.text.strip.empty?
               t = Nokogiri::XML::Element.new("description", r)
               e.before(t)
               t.children = e.remove

data/lib/asciidoctor/standoc/cleanup_section.rb

@@ -114,6 +114,7 @@ module Asciidoctor
         sections_order_cleanup(xml)
         sections_level_cleanup(xml)
         sections_names_cleanup(xml)
+        sections_variant_title_cleanup(xml)
         change_clauses(xml)
       end
 

data/lib/asciidoctor/standoc/cleanup_section_names.rb

@@ -37,39 +37,56 @@ module Asciidoctor
       end
 
       def section_names_refs_cleanup(xml)
-        replace_title(xml, "//references[@normative = 'true']",
+        replace_title(xml, "//bibliography/references[@normative = 'true']",
                       @i18n&.normref, true)
-        replace_title(xml, "//references[@normative = 'false']",
+        replace_title(xml, "//bibliography/references[@normative = 'false']",
                       @i18n&.bibliography, true)
       end
 
       NO_SYMABBR = "[.//definitions[not(@type)]]".freeze
       SYMABBR = "[.//definitions[@type = 'symbols']]"\
-        "[.//definitions[@type = 'abbreviated_terms']]".freeze
+                "[.//definitions[@type = 'abbreviated_terms']]".freeze
       SYMnoABBR = "[.//definitions[@type = 'symbols']]"\
-        "[not(.//definitions[@type = 'abbreviated_terms'])]".freeze
+                  "[not(.//definitions[@type = 'abbreviated_terms'])]".freeze
       ABBRnoSYM = "[.//definitions[@type = 'abbreviated_terms']]"\
-        "[not(.//definitions[@type = 'symbols'])]".freeze
+                  "[not(.//definitions[@type = 'symbols'])]".freeze
 
-      def section_names_terms_cleanup(x)
-        replace_title(x, "//definitions[@type = 'symbols']", @i18n&.symbols)
-        replace_title(x, "//definitions[@type = 'abbreviated_terms']",
+      def section_names_terms_cleanup(xml)
+        replace_title(xml, "//definitions[@type = 'symbols']", @i18n&.symbols)
+        replace_title(xml, "//definitions[@type = 'abbreviated_terms']",
                       @i18n&.abbrev)
-        replace_title(x, "//definitions[not(@type)]", @i18n&.symbolsabbrev)
-        replace_title(x, "//terms#{SYMnoABBR} | //clause[.//terms]#{SYMnoABBR}",
+        replace_title(xml, "//definitions[not(@type)]", @i18n&.symbolsabbrev)
+        replace_title(xml, "//terms#{SYMnoABBR} | //clause[.//terms]#{SYMnoABBR}",
                       @i18n&.termsdefsymbols, true)
-        replace_title(x, "//terms#{ABBRnoSYM} | //clause[.//terms]#{ABBRnoSYM}",
+        replace_title(xml, "//terms#{ABBRnoSYM} | //clause[.//terms]#{ABBRnoSYM}",
                       @i18n&.termsdefabbrev, true)
-        replace_title(x, "//terms#{SYMABBR} | //clause[.//terms]#{SYMABBR}",
+        replace_title(xml, "//terms#{SYMABBR} | //clause[.//terms]#{SYMABBR}",
                       @i18n&.termsdefsymbolsabbrev, true)
-        replace_title(x, "//terms#{NO_SYMABBR} | //clause[.//terms]#{NO_SYMABBR}",
+        replace_title(xml, "//terms#{NO_SYMABBR} | //clause[.//terms]#{NO_SYMABBR}",
                       @i18n&.termsdefsymbolsabbrev, true)
         replace_title(
-          x,
+          xml,
           "//terms[not(.//definitions)] | //clause[.//terms][not(.//definitions)]",
           @i18n&.termsdef, true
         )
       end
+
+      SECTION_CONTAINERS = %w(foreword introduction acknowledgements abstract
+                              clause clause references terms definitions annex
+                              appendix).freeze
+
+      def sections_variant_title_cleanup(xml)
+        path = SECTION_CONTAINERS.map { |x| "./ancestor::#{x}" }.join(" | ")
+        xml.xpath("//p[@variant_title]").each do |p|
+          p.xpath("(#{path})[last()]").each do |sect|
+            p.name = "variant-title"
+            p.delete("id")
+            if ins = sect.at("./title") then ins.next = p
+            else sect.children.first.previous = p
+            end
+          end
+        end
+      end
     end
   end
 end

data/lib/asciidoctor/standoc/cleanup_text.rb

@@ -0,0 +1,70 @@
+module Asciidoctor
+  module Standoc
+    module Cleanup
+      def textcleanup(result)
+        text = result.flatten.map { |l| l.sub(/\s*$/, "") } * "\n"
+        !@keepasciimath and text = asciimath2mathml(text)
+        text = text.gsub(/\s+<fn /, "<fn ")
+        text.gsub(%r{<passthrough\s+formats="metanorma">([^<]*)
+                  </passthrough>}mx) { HTMLEntities.new.decode($1) }
+      end
+
+            IGNORE_DUMBQUOTES = "//pre | //pre//* | //tt | //tt//* | "\
+        "//sourcecode | //sourcecode//* | //bibdata//* | //stem | "\
+        "//stem//* | //figure[@class = 'pseudocode'] | "\
+        "//figure[@class = 'pseudocode']//*".freeze
+
+      def smartquotes_cleanup(xmldoc)
+        xmldoc.xpath("//date").each { |d| Metanorma::Utils::endash_date(d) }
+        if @smartquotes then smartquotes_cleanup1(xmldoc)
+        else dumbquote_cleanup(xmldoc)
+        end
+      end
+
+      def smartquotes_cleanup1(xmldoc)
+        uninterrupt_quotes_around_xml(xmldoc)
+        dumb2smart_quotes(xmldoc)
+      end
+
+      # "abc<tag/>", def => "abc",<tag/> def
+      def uninterrupt_quotes_around_xml(xmldoc)
+        xmldoc.xpath("//*[following::text()[1]"\
+                     "[starts-with(., '\"') or starts-with(., \"'\")]]")
+          .each do |x|
+          next if !x.ancestors("pre, tt, sourcecode, stem, figure").empty?
+          uninterrupt_quotes_around_xml1(x)
+        end
+      end
+
+      def uninterrupt_quotes_around_xml1(elem)
+        prev = elem.at(".//preceding::text()[1]") or return
+        /\S$/.match?(prev.text) or return
+        foll = elem.at(".//following::text()[1]")
+        m = /^(["'][[:punct:]]*)(\s|$)/.match(HTMLEntities.new.decode(foll&.text)) or return
+        foll.content = foll.text.sub(/^(["'][[:punct:]]*)/, "")
+        prev.content = "#{prev.text}#{m[1]}"
+      end
+
+      def dumb2smart_quotes(xmldoc)
+        (xmldoc.xpath("//*[child::text()]") - xmldoc.xpath(IGNORE_DUMBQUOTES))
+          .each do |x|
+          x.children.each do |n|
+            next unless n.text?
+
+            /[-'"(<>]|\.\.|\dx/.match(n) or next
+
+            n.replace(Metanorma::Utils::smartformat(n.text))
+          end
+        end
+      end
+
+      def dumbquote_cleanup(xmldoc)
+        xmldoc.traverse do |n|
+          next unless n.text?
+
+          n.replace(n.text.gsub(/(?<=\p{Alnum})\u2019(?=\p{Alpha})/, "'")) # .
+        end
+      end
+    end
+  end
+end