metanorma-standoc 1.4.4 → 1.6.0

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

data/lib/asciidoctor/standoc/cleanup_ref.rb

@@ -49,9 +49,8 @@ module Asciidoctor
       # consecutively, but that standards codes are preserved as is:
       # only numeric references are renumbered
       def biblio_renumber(xmldoc)
-        r = xmldoc.at("//references[@normative = 'false'] | "\
-                      "//clause[.//references[@normative = 'false']] | "\
-                      "//annex[.//references[@normative = 'false']]") or return
+        r = xmldoc.at("//references | //clause[.//references] | "\
+                      "//annex[.//references]") or return
         r.xpath(".//bibitem[not(ancestor::bibitem)]").each_with_index do |b, i|
           next unless docid = b.at("./docidentifier[@type = 'metanorma']")
           next unless  /^\[\d+\]$/.match(docid.text)
@@ -133,14 +132,16 @@ module Asciidoctor
       end
 
       def validate_ref_dl(bib, c)
-        unless bib["id"]
+        id = bib["id"]
+        id ||= c["id"] unless /^_/.match(c["id"]) # do not accept implicit id
+        unless id
           @log.add("Anchors", c, "The following reference is missing "\
                    "an anchor:\n" + c.to_xml)
           return
         end
-        bib["title"] or @log.add("Bibliography", c, "Reference #{bib['id']} "\
+        bib["title"] or @log.add("Bibliography", c, "Reference #{id} "\
                                  "is missing a title")
-        bib["docid"] or @log.add("Bibliography", c, "Reference #{bib['id']} "\
+        bib["docid"] or @log.add("Bibliography", c, "Reference #{id} "\
                                  "is missing a document identifier (docid)")
       end
 
@@ -201,7 +202,9 @@ module Asciidoctor
         end
         if !nested and c.at("./title")
           title = c.at("./title").remove.children.to_xml
-          bib["title"] = bib["title"] ? Array(bib["title"]) : []
+          bib["title"] = [bib["title"]] if bib["title"].is_a? Hash
+          bib["title"] = [bib["title"]] if bib["title"].is_a? String
+          bib["title"] = [] unless bib["title"]
           bib["title"] << title if !title.empty?
         end
         bib

data/lib/asciidoctor/standoc/cleanup_section.rb

@@ -1,8 +1,6 @@
 require "date"
-require "nokogiri"
 require "htmlentities"
 require "json"
-require "pathname"
 require "open-uri"
 require "mathml2asciimath"
 
@@ -39,6 +37,7 @@ module Asciidoctor
           dupabstract.traverse { |n| n.remove_attribute("id") }
           dupabstract.remove_attribute("language")
           dupabstract.remove_attribute("script")
+          dupabstract&.at("./title")&.remove
           bibabstract.next = dupabstract
         end
       end
@@ -105,6 +104,8 @@ module Asciidoctor
       def sections_cleanup(x)
         sections_order_cleanup(x)
         sections_level_cleanup(x)
+        sections_names_cleanup(x)
+        change_clauses(x)
       end
 
       def obligations_cleanup(x)
@@ -118,15 +119,15 @@ module Asciidoctor
         (s = x.at("//introduction")) && s["obligation"] = "informative"
         (s = x.at("//acknowledgements")) && s["obligation"] = "informative"
         x.xpath("//references").each { |r| r["obligation"] = "informative" }
-        x.xpath("//preface//clause").each { |r| r["obligation"] = "informative" }
+        x.xpath("//preface//clause").each do |r|
+          r["obligation"] = "informative"
+        end
       end
 
       def obligations_cleanup_norm(x)
-        (s = x.at("//clause[title = 'Scope']")) && s["obligation"] = "normative"
-        (s = x.at("//clause[title = 'Symbols and Abbreviated Terms']")) &&
-          s["obligation"] = "normative"
+        (s = x.at("//clause[@type = 'scope']")) && s["obligation"] = "normative"
         x.xpath("//terms").each { |r| r["obligation"] = "normative" }
-        x.xpath("//symbols-abbrevs").each { |r| r["obligation"] = "normative" }
+        x.xpath("//definitions").each { |r| r["obligation"] = "normative" }
       end
 
       def obligations_cleanup_inherit(x)
@@ -139,16 +140,98 @@ module Asciidoctor
       end
 
       def clausebefore_cleanup(xmldoc)
+        preface_clausebefore_cleanup(xmldoc)
+        sections_clausebefore_cleanup(xmldoc)
+      end
+
+       def preface_clausebefore_cleanup(xmldoc)
+        return unless xmldoc.at("//preface")
+        unless ins = xmldoc.at("//preface").children.first
+          xmldoc.at("//preface") << " "
+          ins = xmldoc.at("//preface").children.first
+        end
+        xmldoc.xpath("//preface//*[@beforeclauses = 'true']").each do |x|
+          x.delete("beforeclauses")
+          ins.previous = x.remove
+        end
+      end
+
+      def sections_clausebefore_cleanup(xmldoc)
         return unless xmldoc.at("//sections")
         unless ins = xmldoc.at("//sections").children.first
           xmldoc.at("//sections") << " "
           ins = xmldoc.at("//sections").children.first
         end
-        xmldoc.xpath("//*[@beforeclauses = 'true']").each do |x|
+        xmldoc.xpath("//sections//*[@beforeclauses = 'true']").each do |x|
           x.delete("beforeclauses")
           ins.previous = x.remove
         end
       end
+
+      def get_or_make_title(node)
+          unless node.at("./title")
+            if node.children.empty?
+              node << "<title/>"
+            else
+              node.children.first.previous = "<title/>"
+            end
+          end
+          node.at("./title")
+      end
+
+      def replace_title(doc, xpath, text, first = false)
+        return unless text
+        doc.xpath(xpath).each_with_index do |node, i|
+          next if first && !i.zero?
+          title = get_or_make_title(node)
+          fn = title.xpath("./fn")
+          fn.each { |n| n.remove }
+          title.content = text
+          fn.each { |n| title << n }
+        end
+      end
+
+      def sections_names_cleanup(x)
+        replace_title(x, "//clause[@type = 'scope']", @i18n&.scope)
+        replace_title(x, "//preface//abstract", @i18n&.abstract)
+        replace_title(x, "//foreword", @i18n&.foreword)
+        replace_title(x, "//introduction", @i18n&.introduction)
+        replace_title(x, "//acknowledgements", @i18n&.acknowledgements)
+        section_names_refs_cleanup(x)
+        section_names_terms_cleanup(x)
+      end
+
+      def section_names_refs_cleanup(x)
+        replace_title(x, "//references[@normative = 'true']",
+                      @i18n&.normref, true)
+        replace_title(x, "//references[@normative = 'false']",
+                      @i18n&.bibliography, true)
+      end
+
+      NO_SYMABBR = "[.//definitions[not(@type)]]"
+      SYMABBR = "[.//definitions[@type = 'symbols']"\
+        "[@type = 'abbreviated_terms']]".freeze
+      SYMnoABBR = "[.//definitions[@type = 'symbols']"\
+        "[not(@type = 'abbreviated_terms')]]".freeze
+      ABBRnoSYM = "[.//definitions[not(@type = 'symbols')]"\
+        "[@type = 'abbreviated_terms']]".freeze
+
+      def section_names_terms_cleanup(x)
+        replace_title(x, "//definitions[@type = 'symbols']", @i18n&.symbols)
+        replace_title(x, "//definitions[@type = 'abbreviated_terms']", @i18n&.abbrev)
+        replace_title(x, "//definitions[not(@type)]", @i18n&.symbolsabbrev)
+        replace_title(x, "//terms#{SYMnoABBR} | //clause[.//terms]#{SYMnoABBR}",
+                      @i18n&.termsdefsymbols, true)
+        replace_title(x, "//terms#{ABBRnoSYM} | //clause[.//terms]#{ABBRnoSYM}",
+                      @i18n&.termsdefabbrev, true)
+        replace_title(x, "//terms#{SYMABBR} | //clause[.//terms]#{SYMABBR}",
+                      @i18n&.termsdefsymbolsabbrev, true)
+        replace_title(x, "//terms#{NO_SYMABBR} | //clause[.//terms]#{NO_SYMABBR}",
+                      @i18n&.termsdefsymbolsabbrev, true)
+        replace_title(
+          x, "//terms[not(.//definitions)] | //clause[.//terms][not(.//definitions)]",
+          @i18n&.termsdef, true)
+      end
     end
   end
 end

data/lib/asciidoctor/standoc/cleanup_terms.rb

@@ -76,6 +76,15 @@ module Asciidoctor
         end
       end
 
+      def termnote_example_cleanup(xmldoc)
+        xmldoc.xpath("//termnote[not(ancestor::term)]").each do |x|
+          x.name = "note"
+        end
+        xmldoc.xpath("//termexample[not(ancestor::term)]").each do |x|
+          x.name = "note"
+        end
+      end
+
       def termdef_cleanup(xmldoc)
         termdef_from_termbase(xmldoc)
         termdef_unnest_cleanup(xmldoc)
@@ -83,6 +92,7 @@ module Asciidoctor
         termdomain_cleanup(xmldoc)
         termdefinition_cleanup(xmldoc)
         termdomain1_cleanup(xmldoc)
+        termnote_example_cleanup(xmldoc)
         termdef_boilerplate_cleanup(xmldoc)
         termdef_subclause_cleanup(xmldoc)
         term_children_cleanup(xmldoc) 
@@ -100,8 +110,8 @@ module Asciidoctor
         end
         ret = Nokogiri::XML(key.to_xml)
         HTMLEntities.new.decode(ret.text).
-          gsub(/[\[\]\{\}<>\(\)]/, "").strip.
-          gsub(/[[:punct]]|[_^]/, ":\\0").gsub(/`/, "").
+          gsub(/[\[\]\{\}<>\(\)]/, "").gsub(/\s/m, "").
+          gsub(/[[:punct:]]|[_^]/, ":\\0").gsub(/`/, "").
           gsub(/[0-9]+/, "þ\\0")
       end
         

data/lib/asciidoctor/standoc/converter.rb

@@ -11,7 +11,6 @@ require "asciidoctor/standoc/table"
 require "asciidoctor/standoc/validate"
 require "asciidoctor/standoc/utils"
 require "asciidoctor/standoc/cleanup"
-require "asciidoctor/standoc/i18n"
 require "asciidoctor/standoc/reqt"
 require_relative "./macros.rb"
 require_relative "./log.rb"
@@ -25,12 +24,14 @@ module Asciidoctor
         preprocessor Asciidoctor::Standoc::Datamodel::AttributesTablePreprocessor
         preprocessor Asciidoctor::Standoc::Datamodel::DiagramPreprocessor
         preprocessor Asciidoctor::Standoc::Yaml2TextPreprocessor
+        preprocessor Asciidoctor::Standoc::Json2TextPreprocessor
         inline_macro Asciidoctor::Standoc::AltTermInlineMacro
         inline_macro Asciidoctor::Standoc::DeprecatedTermInlineMacro
         inline_macro Asciidoctor::Standoc::DomainTermInlineMacro
         inline_macro Asciidoctor::Standoc::InheritInlineMacro
         inline_macro Asciidoctor::Standoc::HTML5RubyMacro
         inline_macro Asciidoctor::Standoc::ConceptInlineMacro
+        inline_macro Asciidoctor::Standoc::AutonumberInlineMacro
         block Asciidoctor::Standoc::ToDoAdmonitionBlock
         treeprocessor Asciidoctor::Standoc::ToDoInlineAdmonitionBlock
         block Asciidoctor::Standoc::PlantUMLBlockMacro
@@ -48,7 +49,6 @@ module Asciidoctor
       include ::Asciidoctor::Standoc::Section
       include ::Asciidoctor::Standoc::Table
       include ::Asciidoctor::Standoc::Utils
-      include ::Asciidoctor::Standoc::I18n
       include ::Asciidoctor::Standoc::Cleanup
       include ::Asciidoctor::Standoc::Validate
 
@@ -67,7 +67,7 @@ module Asciidoctor
         attr_accessor :_file
       end
 
-      def self.inherited( k )
+      def self.inherited(k)
         k._file = caller_locations.first.absolute_path
       end
 

data/lib/asciidoctor/standoc/front.rb

@@ -25,18 +25,6 @@ module Asciidoctor
         end
       end
 
-      def metadata_copyright(node, xml)
-        publishers = node.attr("publisher") || " "
-        publishers.split(/,[ ]?/).each do |p|
-          xml.copyright do |c|
-            c.from (node.attr("copyright-year") || Date.today.year)
-            p.match(/[A-Za-z]/).nil? or c.owner do |owner|
-              owner.organization { |o| organization(o, p) }
-            end
-          end
-        end
-      end
-
       def metadata_status(node, xml)
         xml.status do |s|
           s.stage ( node.attr("status") || node.attr("docstage") || "published" )

data/lib/asciidoctor/standoc/front_contributor.rb

@@ -3,6 +3,7 @@ require "nokogiri"
 require "htmlentities"
 require "pathname"
 require "open-uri"
+require "csv"
 
 module Asciidoctor
   module Standoc
@@ -21,11 +22,22 @@ module Asciidoctor
       end
 
       def organization(org, orgname)
+        abbrevs = org_abbrev
+        n = abbrevs.invert[orgname] and orgname = n
         org.name orgname
+        a = org_abbrev[orgname] and org.abbreviation a
+      end
+
+      # , " => ," : CSV definition does not deal with space followed by quote
+      # at start of field
+      def csv_split(s, delim = ",")
+        CSV.parse_line(s&.gsub(/, "(?!")/, ',"'),
+                       liberal_parsing: true,
+                       col_sep: delim)&.compact&.map { |x| x.strip }
       end
 
       def metadata_author(node, xml)
-        (node.attr("publisher") || "").split(/,[ ]?/).each do |p|
+        csv_split(node.attr("publisher") || default_publisher || "")&.each do |p|
           xml.contributor do |c|
             c.role **{ type: "author" }
             c.organization { |a| organization(a, p) }
@@ -44,18 +56,26 @@ module Asciidoctor
         end
       end
 
+      def personal_role(node, c, suffix)
+        c.role **{ type: node.attr("role#{suffix}")&.downcase || "author" }
+      end
+
+      def personal_contact(node, suffix, p)
+        node.attr("phone#{suffix}") and p.phone node.attr("phone#{suffix}")
+        node.attr("fax#{suffix}") and
+          p.phone node.attr("fax#{suffix}"), **{type: "fax"}
+        node.attr("email#{suffix}") and p.email node.attr("email#{suffix}")
+        node.attr("contributor-uri#{suffix}") and
+          p.uri node.attr("contributor-uri#{suffix}")
+      end
+
       def personal_author1(node, xml, suffix)
         xml.contributor do |c|
-          c.role **{ type: node.attr("role#{suffix}")&.downcase || "author" }
+          personal_role(node, c, suffix)
           c.person do |p|
             person_name(node, xml, suffix, p)
             person_affiliation(node, xml, suffix, p)
-            node.attr("phone#{suffix}") and p.phone node.attr("phone#{suffix}")
-            node.attr("fax#{suffix}") and
-              p.phone node.attr("fax#{suffix}"), **{type: "fax"}
-            node.attr("email#{suffix}") and p.email node.attr("email#{suffix}")
-            node.attr("contributor-uri#{suffix}") and
-              p.uri node.attr("contributor-uri#{suffix}")
+            personal_contact(node, suffix, p)
           end
         end
       end
@@ -85,15 +105,36 @@ module Asciidoctor
         end
       end
 
+      def default_publisher
+        nil
+      end
+
+      def org_abbrev
+        { }
+      end
+
       def metadata_publisher(node, xml)
-        publishers = node.attr("publisher") || return
-        publishers.split(/,[ ]?/).each do |p|
+        publishers = node.attr("publisher") || default_publisher || return
+        csv_split(publishers)&.each do |p|
           xml.contributor do |c|
             c.role **{ type: "publisher" }
             c.organization { |a| organization(a, p) }
           end
         end
       end
+
+      def metadata_copyright(node, xml)
+        publishers = node.attr("copyright-holder") || node.attr("publisher") || 
+          default_publisher || "-"
+        csv_split(publishers)&.each do |p|
+          xml.copyright do |c|
+            c.from (node.attr("copyright-year") || Date.today.year)
+            p.match(/[A-Za-z]/).nil? or c.owner do |owner|
+              owner.organization { |o| organization(o, p) }
+            end
+          end
+        end
+      end
     end
   end
 end