metanorma-standoc 1.10.8 → 1.11.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 2cc836755aed6cfff989fdcbc9cf8123ccfda29418247d93fdd75ba71660cee7
-  data.tar.gz: d1c051429283a6e4153a6a3453b839786561c0975c2acda0586cb0ca787ae26a
+  metadata.gz: 6a5cc91caf1f8d674aeff3b46209557d7be11087bf59728df07a73b26cec880a
+  data.tar.gz: 7b674d7c013a3e5aee09394c085ee40dbbed6e241ffb14a14b363ca5956636f5
 SHA512:
-  metadata.gz: 1e17a3351bf46679b587a82498d5f58d97e43743bd2e6906c929aa8dcbb8ca29fdd6e38acb82252375b40e5fff520f7d6a001b023c9c79681ad61fea949c0799
-  data.tar.gz: 01dd1e74b7990b44c526616611155067c0725b0b0bcaeebe9d728c341d26acdab64c2c5be7519b22b94fd641015aec504c333c3b3da8cf6067c19999c20ab0ff
+  metadata.gz: dab0eafeeb100111eecdd7ae0eeb3a23dd1b60acdbf1fc884a7fba6084db22bc816c8255c230a16eb4ab0fc68555378586106145545672a5b39d444e8a3f97c8
+  data.tar.gz: 1f6ffc49435ffebec0441fafbf4a6eb629216270d0d8fd38d68ad15a5d99e4e3162f3d685229827e0eb1df2a2c6d43aaf475795cbcdb143b772d5589787248ff

data/Rakefile

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

data/lib/asciidoctor/standoc/base.rb

@@ -14,6 +14,7 @@ module Asciidoctor
     module Base
       XML_ROOT_TAG = "standard-document".freeze
       XML_NAMESPACE = "https://www.metanorma.org/ns/standoc".freeze
+      FONTS_MANIFEST = "fonts-manifest".freeze
 
       def xml_root_tag
         self.class::XML_ROOT_TAG
@@ -38,7 +39,7 @@ module Asciidoctor
           scripts: node.attr("scripts"),
           scripts_override: node.attr("scripts-override"),
           scripts_pdf: node.attr("scripts-pdf"),
-          datauriimage: node.attr("data-uri-image"),
+          datauriimage: node.attr("data-uri-image") != "false",
           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"),
@@ -85,9 +86,9 @@ module Asciidoctor
           aligncrosselements: node.attr("align-cross-elements"),
         }
 
-        if font_manifest_file = node.attr("mn2pdf-font-manifest-file")
+        if fonts_manifest = node.attr(FONTS_MANIFEST)
           attrs[IsoDoc::XslfoPdfConvert::MN2PDF_OPTIONS] = {
-            IsoDoc::XslfoPdfConvert::MN2PDF_FONT_MANIFEST => font_manifest_file,
+            IsoDoc::XslfoPdfConvert::MN2PDF_FONT_MANIFEST => fonts_manifest,
           }
         end
 
@@ -127,7 +128,7 @@ module Asciidoctor
         @sourcecode_markup_end = node.attr("sourcecode-markup-end") || "}}}"
         @bibdb = nil
         @seen_headers = []
-        @datauriimage = node.attr("data-uri-image")
+        @datauriimage = node.attr("data-uri-image") != "false"
         @boilerplateauthority = node.attr("boilerplate-authority")
         @sourcecode_markup_start = node.attr("sourcecode-markup-start") || "{{{"
         @sourcecode_markup_end = node.attr("sourcecode-markup-end") || "}}}"

data/lib/asciidoctor/standoc/blocks.rb

@@ -1,5 +1,5 @@
 require "htmlentities"
-require "uri"
+require "uri" if /^2\./.match?(RUBY_VERSION)
 require_relative "./blocks_notes"
 
 module Asciidoctor

data/lib/asciidoctor/standoc/cleanup.rb

@@ -9,6 +9,7 @@ require_relative "./cleanup_ref_dl"
 require_relative "./cleanup_boilerplate"
 require_relative "./cleanup_section"
 require_relative "./cleanup_terms"
+require_relative "./cleanup_symbols"
 require_relative "./cleanup_xref"
 require_relative "./cleanup_inline"
 require_relative "./cleanup_amend"
@@ -41,6 +42,7 @@ module Asciidoctor
         symbols_cleanup(xmldoc)
         xref_cleanup(xmldoc)
         concept_cleanup(xmldoc)
+        related_cleanup(xmldoc)
         origin_cleanup(xmldoc)
         bookmark_cleanup(xmldoc)
         termdef_cleanup(xmldoc)
@@ -73,7 +75,8 @@ module Asciidoctor
         %w{status language script version author name callout phone email
            street city state country postcode identifier referenceFrom surname
            referenceTo docidentifier docnumber prefix initial addition forename
-           title draft secretariat title-main title-intro title-part}.freeze
+           title draft secretariat title-main title-intro title-part
+           verbal-definition non-verbal-representation}.freeze
 
       # it seems Nokogiri::XML is treating the content of <script> as cdata,
       # because of its use in HTML. Bad nokogiri. Undoing that, since we use
@@ -83,7 +86,9 @@ module Asciidoctor
       end
 
       def empty_element_cleanup(xmldoc)
-        xmldoc.xpath("//" + TEXT_ELEMS.join(" | //")).each do |x|
+        xmldoc.xpath("//#{TEXT_ELEMS.join(' | //')}").each do |x|
+          next if x.name == "name" && x.parent.name == "expression"
+
           x.remove if x.children.empty?
         end
       end
@@ -108,19 +113,23 @@ module Asciidoctor
             n.name != "variant" && (!n.text? || !n.text.gsub(/\s/, "").empty?)
           end
 
-          c.xpath("./variant").each do |n|
-            if n.at_xpath("preceding-sibling::node()"\
-                          "[not(self::text()[not(normalize-space())])][1]"\
-                          "[self::variantwrap]")
-              n.previous_element << n
-            else
-              n.replace("<variantwrap/>").first << n
-            end
-          end
+          variant_cleanup1(c)
         end
         xmldoc.xpath("//variantwrap").each { |n| n.name = "variant" }
       end
 
+      def variant_cleanup1(elem)
+        elem.xpath("./variant").each do |n|
+          if n.at_xpath("preceding-sibling::node()"\
+                        "[not(self::text()[not(normalize-space())])][1]"\
+                        "[self::variantwrap]")
+            n.previous_element << n
+          else
+            n.replace("<variantwrap/>").first << n
+          end
+        end
+      end
+
       def variant_space_cleanup(xmldoc)
         xmldoc.xpath("//*[variant]").each do |c|
           if c&.next&.text? && c&.next&.next&.name == "variant"

data/lib/asciidoctor/standoc/cleanup_boilerplate.rb

@@ -15,15 +15,18 @@ module Asciidoctor
         )
       end
 
-      def term_defs_boilerplate(div, source, term, preface, isodoc)
+      def term_defs_boilerplate(div, source, term, _preface, isodoc)
         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
-        a = source.empty? && term.nil? ?  @i18n.no_terms_boilerplate :
-          term_defs_boilerplate_cont(source, term, isodoc)
+        a = if source.empty? && term.nil?
+              @i18n.no_terms_boilerplate
+            else
+              term_defs_boilerplate_cont(source, term, isodoc)
+            end
         a and div.next = a
       end
 
@@ -51,10 +54,11 @@ module Asciidoctor
       end
 
       TERM_CLAUSE = "//sections/terms | "\
-        "//sections/clause[descendant::terms]".freeze
+                    "//sections/clause[descendant::terms]".freeze
 
       NORM_REF = "//bibliography/references[@normative = 'true'] | "\
-        "//bibliography/clause[.//references[@normative = 'true']]".freeze
+                 "//bibliography/clause[.//references[@normative = 'true']]"
+        .freeze
 
       def boilerplate_isodoc(xmldoc)
         x = xmldoc.dup
@@ -118,8 +122,11 @@ module Asciidoctor
 
       def boilerplate(xml, conv)
         file = boilerplate_file(xml)
-        file = File.join(@localdir, @boilerplateauthority) if @boilerplateauthority
-        !file.nil? and File.exists?(file) or return
+        if @boilerplateauthority
+          file = File.join(@localdir,
+                           @boilerplateauthority)
+        end
+        (!file.nil? and File.exists?(file)) or return
         conv.populate_template(File.read(file, encoding: "UTF-8"), nil)
       end
 
@@ -166,28 +173,29 @@ module Asciidoctor
         end
       end
 
-      def indirect_eref_to_xref(e, id)
-        loc = e&.at("./localityStack[locality[@type = 'anchor']]")&.remove&.text ||
-          e&.at("./locality[@type = 'anchor']")&.remove&.text || id
-        e.name = "xref"
-        e.delete("bibitemid")
-        e.delete("citeas")
-        e["target"] = loc
-        unless e.document.at("//*[@id = '#{loc}']")
-          e.children = %(** Missing target #{loc})
-          e["target"] = id
+      def indirect_eref_to_xref(eref, ident)
+        loc = eref&.at("./localityStack[locality[@type = 'anchor']]")
+          &.remove&.text ||
+          eref&.at("./locality[@type = 'anchor']")&.remove&.text || ident
+        eref.name = "xref"
+        eref.delete("bibitemid")
+        eref.delete("citeas")
+        eref["target"] = loc
+        unless eref.document.at("//*[@id = '#{loc}']")
+          eref.children = %(** Missing target #{loc})
+          eref["target"] = ident
         end
       end
 
       def resolve_local_indirect_erefs(xmldoc, refs, prefix)
         refs.each_with_object([]) do |r, m|
           id = r.sub(/^#{prefix}_/, "")
-          if n = xmldoc.at("//*[@id = '#{id}']") and n.at("./ancestor-or-self::*[@type = '#{prefix}']")
+          if n = xmldoc.at("//*[@id = '#{id}']") and
+              n.at("./ancestor-or-self::*[@type = '#{prefix}']")
             xmldoc.xpath("//eref[@bibitemid = '#{r}']").each do |e|
               indirect_eref_to_xref(e, id)
             end
-          else
-            m << r
+          else m << r
           end
         end
       end

data/lib/asciidoctor/standoc/cleanup_inline.rb

@@ -60,13 +60,26 @@ module Asciidoctor
         xmldoc.xpath("//concept[not(termxref)]").each do |x|
           term = x.at("./refterm")
           term&.remove if term&.text&.empty?
-          x.children.remove if x&.children&.text&.strip&.empty?
-          key_extract_locality(x)
-          if /:/.match?(x["key"]) then concept_termbase_cleanup(x)
-          elsif refid? x["key"] then concept_eref_cleanup(x)
-          else concept_xref_cleanup(x)
-          end
-          x.delete("key")
+          concept_cleanup1(x)
+        end
+      end
+
+      def concept_cleanup1(elem)
+        elem.children.remove if elem&.children&.text&.strip&.empty?
+        key_extract_locality(elem)
+        if /:/.match?(elem["key"]) then concept_termbase_cleanup(elem)
+        elsif refid? elem["key"] then concept_eref_cleanup(elem)
+        else concept_xref_cleanup(elem)
+        end
+        elem.delete("key")
+      end
+
+      def related_cleanup(xmldoc)
+        xmldoc.xpath("//related[not(termxref)]").each do |x|
+          term = x.at("./refterm")
+          term.replace("<preferred>#{term_expr(term.children.to_xml)}"\
+                       "</preferred>")
+          concept_cleanup1(x)
         end
       end
 

data/lib/asciidoctor/standoc/cleanup_maths.rb

@@ -69,13 +69,12 @@ module Asciidoctor
         return false if char.length > 1
 
         if /\p{Greek}/.match?(char)
-          /\p{Lower}/.match(char) && !mathml_mi_italics[:lowergreek] ||
-            /\p{Upper}/.match(char) && !mathml_mi_italics[:uppergreek]
+          (/\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
+          (/\p{Lower}/.match(char) && !mathml_mi_italics[:lowerroman]) ||
+            (/\p{Upper}/.match(char) && !mathml_mi_italics[:upperroman])
+        else false
         end
       end
 

data/lib/asciidoctor/standoc/cleanup_ref_dl.rb

@@ -17,45 +17,53 @@ module Asciidoctor
 
       def validate_ref_dl(bib, c)
         id = bib["id"]
-        id ||= c["id"] unless /^_/.match(c["id"]) # do not accept implicit 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)
+          @log.add("Anchors", c,
+                   "The following reference is missing an anchor:\n" + c.to_xml)
           return
         end
         @refids << id
-        bib["title"] or @log.add("Bibliography", c, "Reference #{id} is missing a title")
-        bib["docid"] or @log.add("Bibliography", c, "Reference #{id} is missing a document identifier (docid)")
+        bib["title"] or
+          @log.add("Bibliography", c, "Reference #{id} is missing a title")
+        bib["docid"] or
+          @log.add("Bibliography", c,
+                   "Reference #{id} is missing a document identifier (docid)")
       end
 
       def extract_from_p(tag, bib, key)
         return unless bib[tag]
+
         "<#{key}>#{bib[tag].at('p').children}</#{key}>"
       end
 
       # if the content is a single paragraph, replace it with its children
       # single links replaced with uri
-      def p_unwrap(p)
-        elems = p.elements
+      def p_unwrap(para)
+        elems = para.elements
         if elems.size == 1 && elems[0].name == "p"
           link_unwrap(elems[0]).children.to_xml.strip
         else
-          p.to_xml.strip
+          para.to_xml.strip
         end
       end
 
-      def link_unwrap(p)
-        elems = p.elements
+      def link_unwrap(para)
+        elems = para.elements
         if elems.size == 1 && elems[0].name == "link"
-          p.at("./link").replace(elems[0]["target"].strip)
+          para.at("./link").replace(elems[0]["target"].strip)
         end
-        p
+        para
       end
 
       def dd_bib_extract(dtd)
         return nil if dtd.children.empty?
+
         dtd.at("./dl") and return dl_bib_extract(dtd)
         elems = dtd.remove.elements
-        return p_unwrap(dtd) unless elems.size == 1 && %w(ol ul).include?(elems[0].name)
+        return p_unwrap(dtd) unless elems.size == 1 &&
+          %w(ol ul).include?(elems[0].name)
+
         ret = []
         elems[0].xpath("./li").each do |li|
           ret << p_unwrap(li)
@@ -64,7 +72,7 @@ module Asciidoctor
       end
 
       def add_to_hash(bib, key, val)
-        Metanorma::Utils::set_nested_value(bib, key.split(/\./), val)
+        Metanorma::Utils::set_nested_value(bib, key.split("."), val)
       end
 
       # definition list, with at most one level of unordered lists
@@ -73,14 +81,16 @@ module Asciidoctor
         bib = {}
         key = ""
         dl.xpath("./dt | ./dd").each do |dtd|
-          dtd.name == "dt" and key = dtd.text.sub(/:+$/, "") or add_to_hash(bib, key, dd_bib_extract(dtd))
+          (dtd.name == "dt" and key = dtd.text.sub(/:+$/, "")) or
+            add_to_hash(bib, key, dd_bib_extract(dtd))
         end
         c.xpath("./clause").each do |c1|
           key = c1&.at("./title")&.text&.downcase&.strip
           next unless %w(contributor relation series).include? key
+
           add_to_hash(bib, key, dl_bib_extract(c1, true))
         end
-        if !nested and c.at("./title")
+        if !nested && c.at("./title")
           title = c.at("./title").remove.children.to_xml
           bib["title"] = [bib["title"]] if bib["title"].is_a? Hash
           bib["title"] = [bib["title"]] if bib["title"].is_a? String

data/lib/asciidoctor/standoc/cleanup_reqt.rb

@@ -86,33 +86,14 @@ module Asciidoctor
           ins = reqt.children.first
         end
         %w(obligation model type).each do |a|
-          reqt_dl_to_attrs(reqt, dlist, a)
+          dl_to_attrs(reqt, dlist, a)
         end
         requirement_metadata1_tags.each do |a|
-          ins = reqt_dl_to_elems(ins, reqt, dlist, a)
+          ins = dl_to_elems(ins, reqt, dlist, a)
         end
         reqt_dl_to_classif(ins, reqt, dlist)
       end
 
-      def reqt_dl_to_attrs(reqt, dlist, name)
-        e = dlist.at("./dt[text()='#{name}']") or return
-        val = e.at("./following::dd/p") || e.at("./following::dd") or return
-        reqt[name] = val.text
-      end
-
-      def reqt_dl_to_elems(ins, reqt, dlist, name)
-        if a = reqt.at("./#{name}[last()]")
-          ins = a
-        end
-        dlist.xpath("./dt[text()='#{name}']").each do |e|
-          val = e.at("./following::dd/p") || e.at("./following::dd")
-          val.name = name
-          ins.next = val
-          ins = ins.next
-        end
-        ins
-      end
-
       def reqt_dl_to_classif(ins, reqt, dlist)
         if a = reqt.at("./classification[last()]") then ins = a end
         dlist.xpath("./dt[text()='classification']").each do |e|

data/lib/asciidoctor/standoc/cleanup_section_names.rb

@@ -21,7 +21,7 @@ module Asciidoctor
           title = get_or_make_title(node)
           fn = title.xpath("./fn")
           fn.each(&:remove)
-          title.content = text
+          title.children = text
           fn.each { |n| title << n }
         end
       end
@@ -82,7 +82,7 @@ module Asciidoctor
           p.delete("id")
           p.delete("variant_title")
           p.xpath("(#{path})[last()]").each do |sect|
-            ins = sect.at("./title") and ins.next = p or
+            (ins = sect.at("./title") and ins.next = p) or
               sect.children.first.previous = p
           end
         end

data/lib/asciidoctor/standoc/cleanup_symbols.rb

@@ -0,0 +1,48 @@
+module Asciidoctor
+  module Standoc
+    module Cleanup
+      # Indices sort after letter but before any following
+      # letter (x, x_m, x_1, xa); we use colon to force that sort order.
+      # Numbers sort *after* letters; we use thorn to force that sort order.
+      def symbol_key(sym)
+        key = sym.dup
+        key.traverse do |n|
+          n.name == "math" and
+            n.replace(grkletters(MathML2AsciiMath.m2a(n.to_xml)))
+        end
+        ret = Nokogiri::XML(key.to_xml)
+        HTMLEntities.new.decode(ret.text.downcase)
+          .gsub(/[\[\]{}<>()]/, "").gsub(/\s/m, "")
+          .gsub(/[[:punct:]]|[_^]/, ":\\0").gsub(/`/, "")
+          .gsub(/[0-9]+/, "þ\\0")
+      end
+
+      def grkletters(text)
+        text.gsub(/\b(alpha|beta|gamma|delta|epsilon|zeta|eta|theta|iota|kappa|
+                      lambda|mu|nu|xi|omicron|pi|rho|sigma|tau|upsilon|phi|chi|
+                      psi|omega)\b/xi, "&\\1;")
+      end
+
+      def extract_symbols_list(dlist)
+        dl_out = []
+        dlist.xpath("./dt | ./dd").each do |dtd|
+          if dtd.name == "dt"
+            dl_out << { dt: dtd.remove, key: symbol_key(dtd) }
+          else
+            dl_out.last[:dd] = dtd.remove
+          end
+        end
+        dl_out
+      end
+
+      def symbols_cleanup(docxml)
+        docxml.xpath("//definitions/dl").each do |dl|
+          dl_out = extract_symbols_list(dl)
+          dl_out.sort! { |a, b| a[:key] <=> b[:key] || a[:dt] <=> b[:dt] }
+          dl.children = dl_out.map { |d| d[:dt].to_s + d[:dd].to_s }.join("\n")
+        end
+        docxml
+      end
+    end
+  end
+end