metanorma-standoc 1.10.4.1 → 1.10.8

data/lib/asciidoctor/standoc/cleanup_text.rb

@@ -0,0 +1,73 @@
+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

data/lib/asciidoctor/standoc/cleanup_xref.rb

@@ -0,0 +1,107 @@
+module Asciidoctor
+  module Standoc
+    module Cleanup
+      # extending localities to cover ISO referencing
+      LOCALITY_REGEX_STR = <<~REGEXP.freeze
+        ^((?<locality>section|clause|part|paragraph|chapter|page|
+                      table|annex|figure|example|note|formula|list|time|anchor|
+                      locality:[^ \\t\\n\\r:,;=]+)(\\s+|=)
+               (?<ref>[^"][^ \\t\\n,:-]*|"[^"]+")
+                 (-(?<to>[^"][^ \\t\\n,:-]*|"[^"]"))?|
+          (?<locality2>whole|locality:[^ \\t\\n\\r:,;=]+))(?<punct>[,:;]?)\\s*
+         (?<text>.*)$
+      REGEXP
+      LOCALITY_RE = Regexp.new(LOCALITY_REGEX_STR.gsub(/\s/, ""),
+                               Regexp::IGNORECASE | Regexp::MULTILINE)
+
+      def tq(text)
+        text.sub(/^"/, "").sub(/"$/, "")
+      end
+
+      def extract_localities(elem)
+        f = elem&.children&.first or return
+        f.text? or return
+        head = f.remove.text
+        tail = elem&.children&.remove
+        extract_localities1(elem, head)
+        tail and elem << tail
+      end
+
+      def extract_localities1(elem, text)
+        b = elem.add_child("<localityStack/>").first if LOCALITY_RE.match text
+        while (m = LOCALITY_RE.match text)
+          ref = m[:ref] ? "<referenceFrom>#{tq m[:ref]}</referenceFrom>" : ""
+          refto = m[:to] ? "<referenceTo>#{tq m[:to]}</referenceTo>" : ""
+          b.add_child("<locality type='#{locality_label(m)}'>#{ref}#{refto}"\
+                      "</locality>")
+          text = m[:text]
+          b = elem.add_child("<localityStack/>").first if m[:punct] == ";"
+        end
+        elem.add_child(text) if text
+      end
+
+      def locality_label(match)
+        loc = match[:locality] || match[:locality2]
+        /^locality:/.match?(loc) ? loc : loc&.downcase
+      end
+
+      def xref_to_eref(elem)
+        elem["bibitemid"] = elem["target"]
+        unless elem["citeas"] = @anchors&.dig(elem["target"], :xref)
+          @internal_eref_namespaces.include?(elem["type"]) or
+            @log.add("Crossreferences", elem,
+                     "#{elem['target']} does not have a corresponding "\
+                     "anchor ID in the bibliography!")
+        end
+        elem.delete("target")
+        extract_localities(elem) unless elem.children.empty?
+      end
+
+      def xref_cleanup(xmldoc)
+        xmldoc.xpath("//xref").each do |x|
+          /:/.match(x["target"]) and xref_to_internal_eref(x)
+          next unless x.name == "xref"
+
+          if refid? x["target"]
+            x.name = "eref"
+            xref_to_eref(x)
+          else x.delete("type")
+          end
+        end
+      end
+
+      def xref_to_internal_eref(elem)
+        a = elem["target"].split(":", 3)
+        unless a.size < 2 || a[0].empty? || a[1].empty?
+          elem["target"] = "#{a[0]}_#{a[1]}"
+          a.size > 2 and
+            elem.children = %{anchor="#{a[2..-1].join}",#{elem&.children&.text}}
+          elem["type"] = a[0]
+          @internal_eref_namespaces << a[0]
+          elem.name = "eref"
+          xref_to_eref(elem)
+        end
+      end
+
+      def quotesource_cleanup(xmldoc)
+        xmldoc.xpath("//quote/source | //terms/source").each do |x|
+          xref_to_eref(x)
+        end
+      end
+
+      def origin_cleanup(xmldoc)
+        xmldoc.xpath("//origin/concept[termref]").each do |x|
+          t = x.at("./termref")
+          x.replace(t)
+        end
+        xmldoc.xpath("//origin").each do |x|
+          x["citeas"] = @anchors&.dig(x["bibitemid"], :xref) or
+            @log.add("Crossreferences", x,
+                     "#{x['bibitemid']} does not have a corresponding anchor "\
+                     "ID in the bibliography!")
+          extract_localities(x) unless x.children.empty?
+        end
+      end
+    end
+  end
+end

data/lib/asciidoctor/standoc/converter.rb

@@ -49,7 +49,9 @@ module Asciidoctor
         inline_macro Asciidoctor::Standoc::FormSelectMacro
         inline_macro Asciidoctor::Standoc::FormOptionMacro
         inline_macro Asciidoctor::Standoc::ToCInlineMacro
+        inline_macro Asciidoctor::Standoc::PassInlineMacro
         inline_macro Metanorma::Plugin::Lutaml::LutamlFigureInlineMacro
+        inline_macro Metanorma::Plugin::Lutaml::LutamlTableInlineMacro
         block_macro Metanorma::Plugin::Lutaml::LutamlDiagramBlockMacro
         block Asciidoctor::Standoc::ToDoAdmonitionBlock
         treeprocessor Asciidoctor::Standoc::ToDoInlineAdmonitionBlock
@@ -97,6 +99,17 @@ module Asciidoctor
         File.join(@libdir, "../../isodoc/html", file)
       end
 
+      def content(node)
+        node.content
+      end
+
+      def skip(node, name = nil)
+        name = name || node.node_name
+        w = "converter missing for #{name} node in Metanorma backend"
+        @log.add("AsciiDoc Input", node, w)
+        nil
+      end
+
       alias_method :embedded, :content
       alias_method :verse, :quote
       alias_method :audio, :skip