metanorma-iso 1.10.3 → 2.0.0

data/lib/asciidoctor/iso/front_id.rb

@@ -1,222 +1,3 @@
-require "date"
-require "nokogiri"
-require "htmlentities"
-require "json"
-require "pathname"
-require "open-uri"
-require "twitter_cldr"
+require "asciidoctor/iso/deprecated"
+require "metanorma/iso/front_id"
 
-module Asciidoctor
-  module ISO
-    class Converter < Standoc::Converter
-      STAGE_ABBRS = {
-        "00": "PWI",
-        "10": "NP",
-        "20": "WD",
-        "30": "CD",
-        "40": "DIS",
-        "50": "FDIS",
-        "60": "IS",
-        "90": "(Review)",
-        "95": "(Withdrawal)",
-      }.freeze
-
-      STAGE_NAMES = {
-        "00": "Preliminary work item",
-        "10": "New work item proposal",
-        "20": "Working draft",
-        "30": "Committee draft",
-        "40": "Draft",
-        "50": "Final draft",
-        "60": "International standard",
-        "90": "Review",
-        "95": "Withdrawal",
-      }.freeze
-
-      def stage_abbr(stage, substage, doctype)
-        return nil if stage.to_i > 60
-
-        ret = STAGE_ABBRS[stage.to_sym]
-        ret = "PRF" if stage == "60" && substage == "00"
-        ret = "AWI" if stage == "10" && substage == "99"
-        if %w(amendment technical-corrigendum technical-report
-              technical-specification).include?(doctype)
-          ret = "D" if stage == "40" && doctype == "amendment"
-          ret = "FD" if stage == "50" && %w(amendment technical-corrigendum)
-            .include?(doctype)
-        end
-        ret
-      end
-
-      def stage_name(stage, substage, doctype, iteration = nil)
-        return "Proof" if stage == "60" && substage == "00"
-
-        ret = STAGE_NAMES[stage.to_sym]
-        if iteration && %w(20 30).include?(stage)
-          prefix = iteration.to_i.localize(@lang.to_sym)
-            .to_rbnf_s("SpelloutRules", "spellout-ordinal")
-          ret = "#{prefix.capitalize} #{ret.downcase}"
-        end
-        ret
-      end
-
-      def metadata_id(node, xml)
-        iso_id(node, xml)
-        node&.attr("tc-docnumber")&.split(/,\s*/)&.each do |n|
-          xml.docidentifier(n, **attr_code(type: "iso-tc"))
-        end
-        xml.docnumber node&.attr("docnumber")
-      end
-
-      def iso_id(node, xml)
-        !@amd && node.attr("docnumber") || @amd && node.attr("updates") or
-          return
-
-        dn = iso_id1(node)
-        dn1 = id_stage_prefix(dn, node, false)
-        dn2 = id_stage_prefix(dn, node, true)
-        xml.docidentifier dn1, **attr_code(type: "ISO")
-        xml.docidentifier(id_langsuffix(dn1, node),
-                          **attr_code(type: "iso-with-lang"))
-        xml.docidentifier(id_langsuffix(dn2, node),
-                          **attr_code(type: "iso-reference"))
-      end
-
-      def iso_id1(node)
-        if @amd
-          dn = node.attr("updates")
-          add_amd_parts(dn, node)
-        else
-          part, subpart = node&.attr("partnumber")&.split(/-/)
-          add_id_parts(node.attr("docnumber"), part, subpart)
-        end
-      end
-
-      def add_amd_parts(docnum, node)
-        case doctype(node)
-        when "amendment"
-          "#{docnum}/Amd #{node.attr('amendment-number')}"
-        when "technical-corrigendum"
-          "#{docnum}/Cor.#{node.attr('corrigendum-number')}"
-        end
-      end
-
-      def id_langsuffix(docnum, node)
-        lang = node.attr("language") || "en"
-        suffix = case lang
-                 when "en" then "(E)"
-                 when "fr" then "(F)"
-                 else
-                   "(X)"
-                 end
-        "#{docnum}#{suffix}"
-      end
-
-      def structured_id(node, xml)
-        return unless node.attr("docnumber")
-
-        part, subpart = node&.attr("partnumber")&.split(/-/)
-        xml.structuredidentifier do |i|
-          i.project_number(node.attr("docnumber"), **attr_code(
-            part: part, subpart: subpart,
-            amendment: node.attr("amendment-number"),
-            corrigendum: node.attr("corrigendum-number"),
-            origyr: node.attr("created-date")
-          ))
-        end
-      end
-
-      def add_id_parts(docnum, part, subpart)
-        docnum += "-#{part}" if part
-        docnum += "-#{subpart}" if subpart
-        docnum
-      end
-
-      def id_stage_abbr(stage, substage, node, bare = false)
-        ret = if bare
-                IsoDoc::Iso::Metadata.new("en", "Latn", @i18n)
-                  .status_abbrev(stage_abbr(stage, substage, doctype(node)),
-                substage, nil, nil, doctype(node))
-              else
-                IsoDoc::Iso::Metadata.new("en", "Latn", @i18n)
-                  .status_abbrev(stage_abbr(stage, substage, doctype(node)),
-                substage, node.attr("iteration"),
-                node.attr("draft"), doctype(node))
-              end
-        if %w(amendment technical-corrigendum technical-report
-              technical-specification).include?(doctype(node))
-          ret = "#{ret} " unless %w(D FD).include?(ret)
-        end
-        ret
-      end
-
-      def cover_stage_abbr(node)
-        stage = get_stage(node)
-        abbr = id_stage_abbr(get_stage(node), get_substage(node), node, true)
-        typeabbr = get_typeabbr(node, true)
-        if stage.to_i > 50 || stage.to_i == 60 && get_substage(node).to_i < 60
-          typeabbr = ""
-        end
-        "#{abbr}#{typeabbr}".strip
-      end
-
-      def id_stage_prefix(docnum, node, force_year)
-        stage = get_stage(node)
-        typeabbr = get_typeabbr(node)
-        if stage && (stage.to_i < 60)
-          docnum = unpub_stage_prefix(docnum, stage, typeabbr, node)
-        elsif typeabbr == "DIR " then docnum = "#{typeabbr}#{docnum}"
-        elsif typeabbr && !@amd then docnum = "/#{typeabbr}#{docnum}"
-        end
-        (force_year || !(stage && (stage.to_i < 60))) and
-          docnum = id_add_year(docnum, node)
-        docnum
-      end
-
-      def unpub_stage_prefix(docnum, stage, typeabbr, node)
-        abbr = id_stage_abbr(stage, get_substage(node), node)
-        %w(40 50).include?(stage) && i = node.attr("iteration") and
-          itersuffix = ".#{i}"
-        return docnum if abbr.nil? || abbr.empty? # prefixes added in cleanup
-        return "/#{abbr}#{typeabbr} #{docnum}#{itersuffix}" unless @amd
-
-        a = docnum.split(%r{/})
-        a[-1] = "#{abbr}#{a[-1]}#{itersuffix}"
-        a.join("/")
-      end
-
-      def id_add_year(docnum, node)
-        year = node.attr("copyright-year")
-        @amd and year ||= node.attr("updated-date")&.sub(/-.*$/, "")
-        docnum += ":#{year}" if year
-        docnum
-      end
-
-      def get_stage(node)
-        a = node.attr("status")
-        a = node.attr("docstage") if a.nil? || a.empty?
-        a = "60" if a.nil? || a.empty?
-        a
-      end
-
-      def get_substage(node)
-        stage = get_stage(node)
-        ret = node.attr("docsubstage")
-        ret = (stage == "60" ? "60" : "00") if ret.nil? || ret.empty?
-        ret
-      end
-
-      def get_typeabbr(node, amd = false)
-        case doctype(node)
-        when "directive" then "DIR "
-        when "technical-report" then "TR "
-        when "technical-specification" then "TS "
-        when "amendment" then (amd ? "Amd " : "")
-        when "technical-corrigendum" then (amd ? "Cor " : "")
-        else
-          nil
-        end
-      end
-    end
-  end
-end

data/lib/asciidoctor/iso/section.rb

@@ -1,49 +1,3 @@
-require "htmlentities"
-require "uri" if /^2\./.match?(RUBY_VERSION)
+require "asciidoctor/iso/deprecated"
+require "metanorma/iso/section"
 
-module Asciidoctor
-  module ISO
-    class Converter < Standoc::Converter
-      def clause_parse(attrs, xml, node)
-        node.option? "appendix" and return appendix_parse(attrs, xml, node)
-        super
-      end
-
-      def scope_parse(attrs, xml, node)
-        attrs = attrs.merge(type: "scope") unless @amd
-        clause_parse(attrs, xml, node)
-      end
-
-      def appendix_parse(attrs, xml, node)
-        attrs[:"inline-header"] = node.option? "inline-header"
-        set_obligation(attrs, node)
-        xml.appendix **attr_code(attrs) do |xml_section|
-          xml_section.title { |name| name << node.title }
-          xml_section << node.content
-        end
-      end
-
-      def patent_notice_parse(xml, node)
-        # xml.patent_notice do |xml_section|
-        #  xml_section << node.content
-        # end
-        xml << node.content
-      end
-
-      def sectiontype(node, level = true)
-        return nil if @amd
-
-        ret = sectiontype_streamline(sectiontype1(node))
-        return ret if ret == "terms and definitions" && @vocab
-
-        super
-      end
-
-      def term_def_subclause_parse(attrs, xml, node)
-        node.role == "term" and
-          return term_def_subclause_parse1(attrs, xml, node)
-        super
-      end
-    end
-  end
-end

data/lib/asciidoctor/iso/validate.rb

@@ -1,172 +1,3 @@
-require "metanorma-standoc"
-require_relative "./validate_style"
-require_relative "./validate_requirements"
-require_relative "./validate_section"
-require_relative "./validate_title"
-require_relative "./validate_image"
-require "nokogiri"
-require "jing"
-require "iev"
+require "asciidoctor/iso/deprecated"
+require "metanorma/iso/validate"
 
-module Asciidoctor
-  module ISO
-    class Converter < Standoc::Converter
-      def isosubgroup_validate(root)
-        root.xpath("//technical-committee/@type").each do |t|
-          unless %w{TC PC JTC JPC}.include? t.text
-            @log.add("Document Attributes", nil,
-                     "invalid technical committee type #{t}")
-          end
-        end
-        root.xpath("//subcommittee/@type").each do |t|
-          unless %w{SC JSC}.include? t.text
-            @log.add("Document Attributes", nil,
-                     "invalid subcommittee type #{t}")
-          end
-        end
-      end
-
-      # ISO/IEC DIR 2, 15.5.3
-      # does not deal with preceding text marked up
-      def see_xrefs_validate(root)
-        root.xpath("//xref").each do |t|
-          preceding = t.at("./preceding-sibling::text()[last()]")
-          next unless !preceding.nil? &&
-            /\b(see| refer to)\s*\Z/mi.match(preceding)
-
-          (target = root.at("//*[@id = '#{t['target']}']")) || next
-          if target&.at("./ancestor-or-self::*[@obligation = 'normative']")
-            @log.add("Style", t,
-                     "'see #{t['target']}' is pointing to a normative section")
-          end
-        end
-      end
-
-      # ISO/IEC DIR 2, 15.5.3
-      def see_erefs_validate(root)
-        root.xpath("//eref").each do |t|
-          prec = t.at("./preceding-sibling::text()[last()]")
-          next unless !prec.nil? && /\b(see|refer to)\s*\Z/mi.match(prec)
-
-          unless target = root.at("//*[@id = '#{t['bibitemid']}']")
-            @log.add("Bibliography", t,
-                     "'#{t} is not pointing to a real reference")
-            next
-          end
-          target.at("./ancestor::references[@normative = 'true']") and
-            @log.add("Style", t,
-                     "'see #{t}' is pointing to a normative reference")
-        end
-      end
-
-      # ISO/IEC DIR 2, 10.4
-      def locality_erefs_validate(root)
-        root.xpath("//eref[descendant::locality]").each do |t|
-          if /^(ISO|IEC)/.match?(t["citeas"]) &&
-              !/: ?(\d+{4}|–)$/.match?(t["citeas"])
-            @log.add("Style", t,
-                     "undated reference #{t['citeas']} should not contain "\
-                     "specific elements")
-          end
-        end
-      end
-
-      def termdef_warn(text, regex, elem, term, msg)
-        regex.match(text) && @log.add("Style", elem, "#{term}: #{msg}")
-      end
-
-      # ISO/IEC DIR 2, 16.5.6
-      def termdef_style(xmldoc)
-        xmldoc.xpath("//term").each do |t|
-          para = t.at("./definition/verbal-definition") || return
-          term = t.at("./preferred//name").text
-          termdef_warn(para.text, /\A(the|a)\b/i, t, term,
-                       "term definition starts with article")
-          termdef_warn(para.text, /\.\Z/i, t, term,
-                       "term definition ends with period")
-        end
-      end
-
-      def doctype_validate(xmldoc)
-        doctype = xmldoc&.at("//bibdata/ext/doctype")&.text
-        %w(international-standard technical-specification technical-report
-           publicly-available-specification international-workshop-agreement
-           guide amendment technical-corrigendum).include? doctype or
-          @log.add("Document Attributes", nil,
-                   "#{doctype} is not a recognised document type")
-      end
-
-      def script_validate(xmldoc)
-        script = xmldoc&.at("//bibdata/script")&.text
-        script == "Latn" or
-          @log.add("Document Attributes", nil,
-                   "#{script} is not a recognised script")
-      end
-
-      def stage_validate(xmldoc)
-        stage = xmldoc&.at("//bibdata/status/stage")&.text
-        %w(00 10 20 30 40 50 60 90 95).include? stage or
-          @log.add("Document Attributes", nil,
-                   "#{stage} is not a recognised stage")
-      end
-
-      def substage_validate(xmldoc)
-        substage = xmldoc&.at("//bibdata/status/substage")&.text or return
-        %w(00 20 60 90 92 93 98 99).include? substage or
-          @log.add("Document Attributes", nil,
-                   "#{substage} is not a recognised substage")
-      end
-
-      def iteration_validate(xmldoc)
-        iteration = xmldoc&.at("//bibdata/status/iteration")&.text or return
-        /^\d+/.match(iteration) or
-          @log.add("Document Attributes", nil,
-                   "#{iteration} is not a recognised iteration")
-      end
-
-      def bibdata_validate(doc)
-        doctype_validate(doc)
-        script_validate(doc)
-        stage_validate(doc)
-        substage_validate(doc)
-        iteration_validate(doc)
-      end
-
-      def content_validate(doc)
-        super
-        title_validate(doc.root)
-        isosubgroup_validate(doc.root)
-        onlychild_clause_validate(doc.root)
-        termdef_style(doc.root)
-        see_xrefs_validate(doc.root)
-        see_erefs_validate(doc.root)
-        locality_erefs_validate(doc.root)
-        bibdata_validate(doc.root)
-        bibitem_validate(doc.root)
-        figure_validate(doc.root)
-      end
-
-      def bibitem_validate(xmldoc)
-        xmldoc.xpath("//bibitem[date/on = '–']").each do |b|
-          b.at("./note[@type = 'Unpublished-Status']") or
-            @log.add("Style", b,
-                     "Reference #{b&.at('./@id')&.text} does not have an "\
-                     "associated footnote indicating unpublished status")
-        end
-      end
-
-      def validate(doc)
-        content_validate(doc)
-        doctype = doc&.at("//bibdata/ext/doctype")&.text
-        schema = case doctype
-                 when "amendment", "technical-corrigendum" # @amd
-                   "isostandard-amd.rng"
-                 else
-                   "isostandard.rng"
-                 end
-        schema_validate(formattedstr_strip(doc.dup),
-                        File.join(File.dirname(__FILE__), schema))
-      end
-    end
-  end
-end

data/lib/asciidoctor/iso/validate_image.rb

@@ -1,97 +1,3 @@
-module Asciidoctor
-  module ISO
-    class Converter < Standoc::Converter
-      # DRG directives 3.7; but anticipated by standoc
-      def subfigure_validate(xmldoc)
-        xmldoc.xpath("//figure//figure").each do |f|
-          { footnote: "fn", note: "note", key: "dl" }.each do |k, v|
-            f.xpath(".//#{v}").each do |n|
-              @log.add("Style", n, "#{k} is not permitted in a subfigure")
-            end
-          end
-        end
-      end
+require "asciidoctor/iso/deprecated"
+require "metanorma/iso/validate_image"
 
-      def image_name_prefix(xmldoc)
-        std = xmldoc&.at("//bibdata/ext/structuredidentifier/project-number") or
-          return
-        num = xmldoc&.at("//bibdata/docnumber")&.text or return
-        ed = xmldoc&.at("//bibdata/edition")&.text || "1"
-        prefix = num
-        std["part"] and prefix += "-#{std['part']}"
-        prefix += "_ed#{ed}"
-        amd = std["amendment"] and prefix += "amd#{amd}"
-        prefix
-      end
-
-      def image_name_suffix(xmldoc)
-        case xmldoc&.at("//bibdata/language")&.text
-        when "fr" then "_f"
-        when "de" then "_d"
-        when "ru" then "_r"
-        when "es" then "_s"
-        when "ar" then "_a"
-        when "en" then "_e"
-        else
-          "_e"
-        end
-      end
-
-      def disjunct_error(img, cond1, cond2, msg1, msg2)
-        cond1 && !cond2 and
-          @log.add("Style", img, "image name #{img['src']} #{msg1}")
-        !cond1 && cond2 and
-          @log.add("Style", img, "image name #{img['src']} #{msg2}")
-      end
-
-      def image_name_parse(img, prefix)
-        m = %r[(SL)?#{prefix}fig(?<tab>Tab)?(?<annex>[A-Z])?(Text)?(?<num>\d+)
-            (?<subfig>[a-z])?(?<key>_key\d+)?(?<lang>_[a-z])?$]x
-          .match(File.basename(img["src"], ".*"))
-        m.nil? and
-          @log.add("Style", img,
-                   "image name #{img['src']} does not match DRG requirements")
-        m
-      end
-
-      def image_name_validate1(i, prefix)
-        m = image_name_parse(i, prefix) or return
-        warn i["src"]
-        disjunct_error(i, i.at("./ancestor::table"), !m[:tab].nil?,
-                       "is under a table but is not so labelled",
-                       "is labelled as under a table but is not")
-        disjunct_error(i, i.at("./ancestor::annex"), !m[:annex].nil?,
-                       "is under an annex but is not so labelled",
-                       "is labelled as under an annex but is not")
-        disjunct_error(i, i.xpath("./ancestor::figure").size > 1, !m[:subfig].nil?,
-                       "does not have a subfigure letter but is a subfigure",
-                       "has a subfigure letter but is not a subfigure")
-        lang = image_name_suffix(i.document.root)
-        (m[:lang] || "_e") == lang or
-          @log.add("Style", i,
-                   "image name #{i['src']} expected to have suffix #{lang}")
-      end
-
-      # DRG directives 3.2
-      def image_name_validate(xmldoc)
-        prefix = image_name_prefix(xmldoc) or return
-        xmldoc.xpath("//image").each do |i|
-          next if i["src"].start_with?("data:")
-
-          if /^ISO_\d+_/.match?(File.basename(i["src"]))
-          elsif /^(SL)?#{prefix}fig/.match?(File.basename(i["src"]))
-            image_name_validate1(i, prefix)
-          else
-            @log.add("Style", i,
-                     "image name #{i['src']} does not match DRG requirements: expect #{prefix}fig")
-          end
-        end
-      end
-
-      def figure_validate(xmldoc)
-        image_name_validate(xmldoc)
-        subfigure_validate(xmldoc)
-      end
-    end
-  end
-end

data/lib/asciidoctor/iso/validate_requirements.rb

@@ -1,111 +1,3 @@
-require "metanorma-standoc"
+require "asciidoctor/iso/deprecated"
+require "metanorma/iso/validate_requirements"
 
-module Asciidoctor
-  module ISO
-    class Converter < Standoc::Converter
-      REQUIREMENT_RE_STR = <<~REGEXP.freeze
-        \\b
-         ( shall | (is|are)_to |
-           (is|are)_required_(not_)?to |
-           (is|are)_required_that |
-           has_to |
-           only\\b[^.,]+\\b(is|are)_permitted |
-           it_is_necessary |
-           (is|are)_not_(allowed | permitted |
-                         acceptable | permissible) |
-           (is|are)_not_to_be |
-           [.,:;]_do_not )
-        \\b
-      REGEXP
-
-      def requirement_re
-        Regexp.new(self.class::REQUIREMENT_RE_STR.gsub(/\s/, "")
-          .gsub(/_/, "\\s"), Regexp::IGNORECASE)
-      end
-
-      def requirement_check(text)
-        text.split(/\.\s+/).each do |t|
-          return t if requirement_re.match t
-        end
-        nil
-      end
-
-      RECOMMENDATION_RE_STR = <<~REGEXP.freeze
-        \\b
-            should |
-            ought_(not_)?to |
-            it_is_(not_)?recommended_that
-        \\b
-      REGEXP
-
-      def recommendation_re
-        Regexp.new(self.class::RECOMMENDATION_RE_STR.gsub(/\s/, "")
-          .gsub(/_/, "\\s"), Regexp::IGNORECASE)
-      end
-
-      def recommendation_check(text)
-        text.split(/\.\s+/).each do |t|
-          return t if recommendation_re.match t
-        end
-        nil
-      end
-
-      PERMISSION_RE_STR = <<~REGEXP.freeze
-        \\b
-             may |
-            (is|are)_(permitted | allowed | permissible ) |
-            it_is_not_required_that |
-            no\\b[^.,]+\\b(is|are)_required
-        \\b
-      REGEXP
-
-      def permission_re
-        Regexp.new(self.class::PERMISSION_RE_STR.gsub(/\s/, "")
-          .gsub(/_/, "\\s"), Regexp::IGNORECASE)
-      end
-
-      def permission_check(text)
-        text.split(/\.\s+/).each do |t|
-          return t if permission_re.match t
-        end
-        nil
-      end
-
-      POSSIBILITY_RE_STR = <<~REGEXP.freeze
-        \\b
-           can | cannot | be_able_to |
-           there_is_a_possibility_of |
-           it_is_possible_to | be_unable_to |
-           there_is_no_possibility_of |
-           it_is_not_possible_to
-        \\b
-      REGEXP
-
-      def possibility_re
-        Regexp.new(self.class::POSSIBILITY_RE_STR.gsub(/\s/, "")
-          .gsub(/_/, "\\s"), Regexp::IGNORECASE)
-      end
-
-      def possibility_check(text)
-        text.split(/\.\s+/).each { |t| return t if possibility_re.match t }
-        nil
-      end
-
-      def external_constraint(text)
-        text.split(/\.\s+/).each do |t|
-          return t if /\b(must)\b/xi.match? t
-        end
-        nil
-      end
-
-      def style_no_guidance(node, text, docpart)
-        r = requirement_check(text)
-        style_warning(node, "#{docpart} may contain requirement", r) if r
-        r = permission_check(text)
-        style_warning(node, "#{docpart} may contain permission", r) if r
-        r = recommendation_check(text)
-        style_warning(node, "#{docpart} may contain recommendation", r) if r
-      end
-    end
-  end
-end