metanorma-gb 1.0.0

data/lib/asciidoctor/gb/section_input.rb

@@ -0,0 +1,150 @@
+require "gbbib"
+
+module Asciidoctor
+  module Gb
+
+    # A {Converter} implementation that generates GB output, and a document
+    # schema encapsulation of the document for validation
+    class Converter < ISO::Converter
+
+      def term_def_subclause_parse(attrs, xml, node)
+        # subclause contains subclauses
+        sub = node.find_by(context: :section) {|s| s.level == node.level + 1 }
+        sub.empty? || (return term_def_parse(attrs, xml, node, false))
+        (node.title.downcase == "symbols and abbreviated terms" ||
+        node.title == "符号、代号和缩略语") &&
+          (return symbols_parse(attrs, xml, node))
+        xml.term **attr_code(attrs) do |xml_section|
+          xml_section.preferred { |name| name << node.title }
+          xml_section << node.content
+        end
+      end
+
+      def section(node)
+        a = { id: Asciidoctor::Standoc::Utils::anchor_or_uuid(node) }
+        noko do |xml|
+          case sectiontype(node)
+          when "引言", "introduction" then
+            if node.level == 1 then introduction_parse(a, xml, node)
+            else
+              clause_parse(a, xml, node)
+            end
+          when "patent notice" then patent_notice_parse(xml, node)
+          when "范围", "scope" then scope_parse(a, xml, node)
+          when "规范性引用文件", "normative references"
+            norm_ref_parse(a, xml, node)
+          when "术语和定义", "terms and definitions",
+            "术语、定义、符号、代号和缩略语",
+            "terms, definitions, symbols and abbreviated terms"
+            @term_def = true
+            term_def_parse(a, xml, node, true)
+            @term_def = false
+          when "符号、代号和缩略语", "symbols and abbreviated terms"
+            symbols_parse(a, xml, node)
+          when "参考文献", "bibliography"
+            bibliography_parse(a, xml, node)
+          else
+            if @term_def then term_def_subclause_parse(a, xml, node)
+            elsif @biblio then bibliography_parse(a, xml, node)
+                          elsif node.attr("style") == "bibliography" && node.level == 1
+              bibliography_parse(a, xml, node)
+            elsif node.attr("style") == "appendix" && node.level == 1
+              annex_parse(a, xml, node)
+            else
+              clause_parse(a, xml, node)
+            end
+          end
+        end.join("\n")
+      end
+
+      # @param xml [Nokogiri::XML::Builder]
+      # @param code [String]
+      #def fetch_ref(xml, code, _year, **opts)
+        #warn "fetching #{code}..."
+        #result = Gbbib::GbBibliography.search code
+        #hit = result.first
+        #if hit&.title&.match(%r{^[^\s]+\s[\d-]+}).to_s == code
+          ## hit.fetch.to_xml xml, opts
+          #xml.parent.add_child hit.fetch.to_xml(xml, opts)
+          #xml
+        #end
+      #end
+
+=begin
+      # spec of permissible section sequence
+      SEQ = [
+        { msg: "Initial section must be (content) 前言",
+          val:  [{ tag: "foreword", title: "前言" }], },
+      { msg: "Prefatory material must be followed by (clause) 范围",
+        val:  [{ tag: "introduction", title: "引言" },
+               { tag: "clause", title: "范围" }], },
+      { msg: "Prefatory material must be followed by (clause) 范围",
+        val: [{ tag: "clause", title: "范围" }], },
+      { msg: "规范性引用文件 must be followed by "\
+        "术语和定义",
+        val: [
+          { tag: "terms", title: "术语和定义" },
+          { tag: "clause", title: "术语和定义" },
+          { tag: "clause",
+            title: "术语、定义、符号、代号和缩略语" },
+          { tag: "terms",
+            title: "术语、定义、符号、代号和缩略语" }
+        ] },
+      ]
+
+      SECTIONS_XPATH =
+        "//foreword | //introduction | //sections/terms | .//annex | "\
+        "//definitions | //sections/clause | //references[not(parent::clause)] | "\
+        "//clause[descendant::references][not(parent::clause)]".freeze
+
+      def sections_sequence_validate(root)
+        f = root.xpath(SECTIONS_XPATH)
+        names = f.map { |s| { tag: s.name, title: s&.at("./title")&.text } }
+        names = seqcheck(names, SEQ[0][:msg], SEQ[0][:val]) || return
+        n = names[0]
+        names = seqcheck(names, SEQ[1][:msg], SEQ[1][:val]) || return
+        if n == { tag: "introduction", title: "引言" }
+          names = seqcheck(names, SEQ[2][:msg], SEQ[2][:val]) || return
+        end
+        names = seqcheck(names, SEQ[3][:msg], SEQ[3][:val]) || return
+        n = names.shift
+        if n == { tag: "definitions", title: nil }
+          n = names.shift || return
+        end
+        unless n
+          warn "ISO style: Document must contain at least one clause"
+          return
+        end
+        n[:tag] == "clause" or
+          warn "ISO style: Document must contain clause after Terms and Definitions"
+        (n == { tag: "clause", title: "范围" }) &&
+          warn("ISO style: 范围 must occur before 术语和定义")
+        n = names.shift or return
+        while n[:tag] == "clause"
+          (n[:title] == "范围") &&
+            warn("ISO style: 范围 must occur before 术语和定义")
+          n = names.shift or return
+        end
+        unless n[:tag] == "annex" or n[:tag] == "references"
+          warn "ISO style: Only annexes and references can follow clauses"
+        end
+        while n[:tag] == "annex"
+          n = names.shift
+          if n.nil?
+            warn("ISO style: Document must include (references) "\
+                 "Normative References")
+            return
+          end
+        end
+        n == { tag: "references", title: "规范性引用文件" } or
+          warn "ISO style: Document must include (references) 规范性引用文件"
+        n = names.shift
+        n == { tag: "references", title: "参考文献" } or
+          warn "ISO style: Final section must be (references) 参考文献"
+        names.empty? or
+          warn "ISO style: There are sections after the final Bibliography"
+      end
+=end
+    end
+  end
+end

data/lib/asciidoctor/gb/validate.rb

@@ -0,0 +1,115 @@
+module Asciidoctor
+  module Gb
+    class Converter < ISO::Converter
+
+      def validate(doc)
+        content_validate(doc)
+        schema_validate(formattedstr_strip(doc.dup),
+                        File.join(File.dirname(__FILE__), "gbstandard.rng"))
+      end
+
+      def content_validate(doc)
+        super
+        bilingual_terms_validate(doc.root)
+        issuer_validate(doc.root)
+        prefix_validate(doc.root)
+        @agencyclass.gbtype_validate(doc.root.at("//gbscope")&.text, doc.root.at("//gbprefix")&.text)
+      end
+
+      def prefix_validate(root)
+        prefix = root&.at("//gbprefix")&.text
+        scope = root&.at("//gbscope")&.text
+        case scope
+        when "social-group"
+          /^[A-Za-z]{3,6}$/.match? prefix or
+            warn("#{prefix} is improperly formatted for social standards")
+        when "enterprise"
+          /^[A-Z0-9]{3,}$/.match? prefix or
+            warn("#{prefix} is improperly formatted for enterprise standards")
+        when "sector"
+          %w(AQ BB CB CH CJ CY DA DB DL DZ EJ FZ GA GH GM GY HB HG HJ HS HY
+             JB JC JG JR JT JY LB LD LS LY MH MT MZ NY QB QC QJ QX SB SC SH
+             SJ SL SN SY TB TD TJ TY WB WH WJ WM WS WW XB YB YC YD YS YY YZ
+             ZY).include? prefix or
+             warn("#{prefix} is not a legal sector standard prefix")
+        when "local"
+          %w(11 12 13 14 15 21 22 23 31 32 33 34 35 36 37 41 42 43 44 45 46
+             50 51 52 53 54 61 62 63 64 65 71 81 82 end).include? prefix or
+             warn("#{prefix} is not a legal local standard prefix")
+        when "national"
+          %w(GB GBZ GJB GBn GHZB GWPB JJF JJG).include? prefix or
+            warn("#{prefix} is not a legal national standard prefix")
+        end
+      end
+
+      def issuer_validate(root)
+        issuer = root&.at("//bibdata/contributor[role/@type = 'issuer']/"\
+                          "organization/name")&.text
+        scope = root&.at("//gbscope")&.text
+        if %w(enterprise social).include?(scope) && issuer == "GB"
+          warn "No issuer provided for #{scope} standard"
+        end
+      end
+
+      def check_bilingual(t, element)
+        zh = t.at(".//#{element}[@language = 'zh']")
+        en = t.at(".//#{element}[@language = 'en']")
+        (en.nil? || en.text.empty?) && !(zh.nil? || zh.text.empty?) &&
+          warn("GB: #{element} term #{zh.text} has no English counterpart")
+        !(en.nil? || en.text.empty?) && (zh.nil? || zh.text.empty?) &&
+          warn("GB: #{element} term #{en.text} has no Chinese counterpart")
+      end
+
+      def bilingual_terms_validate(root)
+        root.xpath("//term").each do |t|
+          check_bilingual(t, "preferred")
+          check_bilingual(t, "admitted")
+          check_bilingual(t, "deprecates")
+        end
+      end
+
+      def title_intro_validate(root)
+        title_intro_en = root.at("//title-intro[@language='en']")
+        title_intro_zh = root.at("//title-intro[@language='zh']")
+        if title_intro_en.nil? && !title_intro_zh.nil?
+          warn "No English Title Intro!"
+        end
+        if !title_intro_en.nil? && title_intro_zh.nil?
+          warn "No Chinese Title Intro!"
+        end
+      end
+
+      def title_main_validate(root)
+        title_main_en = root.at("//title-main[@language='en']")
+        title_main_zh = root.at("//title-main[@language='zh']")
+        if title_main_en.nil? && !title_main_zh.nil?
+          warn "No English Title!"
+        end
+        if !title_main_en.nil? && title_main_zh.nil?
+          warn "No Chinese Title!"
+        end
+      end
+
+      def title_part_validate(root)
+        title_part_en = root.at("//title-part[@language='en']")
+        title_part_zh = root.at("//title-part[@language='zh']")
+        if title_part_en.nil? && !title_part_zh.nil?
+          warn "No English Title Part!"
+        end
+        if !title_part_en.nil? && title_part_zh.nil?
+          warn "No Chinese Title Part!"
+        end
+      end
+
+      def norm_bibitem_style(root)
+        root.xpath(NORM_BIBITEMS).each do |b|
+          if b.at(Asciidoctor::Standoc::Converter::ISO_PUBLISHER_XPATH).nil?
+            unless /^#{GBCODE}(?![A-Z])/.match? b.at("./docidentifier").text
+              Asciidoctor::Standoc::Utils::warning(b, NORM_ISO_WARN, b.text)
+            end
+          end
+        end
+      end
+    end
+  end
+end

data/lib/asciidoctor/gb/version.rb

@@ -0,0 +1,5 @@
+module Asciidoctor
+  module Gb
+    VERSION = "1.0.0"
+  end
+end

data/lib/isodoc/gb/gbcleanup.rb

@@ -0,0 +1,90 @@
+module IsoDoc
+  module Gb
+    class Cleanup
+      def initialize(script, deprecated_lbl)
+        @script = script
+        @deprecated_lbl = deprecated_lbl
+      end
+
+      def cleanup(docxml)
+        terms_cleanup(docxml)
+        formula_cleanup(docxml)
+        title_cleanup(docxml)
+        docxml
+      end
+
+      def formula_cleanup(docxml)
+        docxml.xpath("//table[@class = 'dl']//p[not(@class)]").each do |p|
+          p["class"] = "dl"
+        end
+        docxml
+      end
+
+      def example_cleanup(docxml)
+        docxml.xpath("//table[@class = 'Note']//p[not(@class)]").each do |p|
+          p["class"] = "Note"
+        end
+        docxml
+      end
+
+      def spaerdruck(x, return_on_br)
+        x.traverse do |n|
+          n.text? and n.content = n.text.gsub(/(.)/, "\\1\u00a0\u00a0").
+            gsub(/\u00a0+$/, "")
+          return_on_br and n.element? and n.name == "br" and return
+        end
+      end
+
+      def title_cleanup(docxml)
+        @script == "Hans" or return
+        docxml.xpath("//*[@class = 'zzContents' or @class = 'ForewordTitle' or "\
+                     "@class = 'IntroTitle'] | "\
+                     "//h1[@class = 'Sections3']").each do |x|
+          spaerdruck(x, false)
+        end
+        docxml.xpath("//h1[@class = 'Annex']").each do |x|
+          spaerdruck(x, true)
+        end
+        docxml
+      end
+
+      def term_merge(docxml, term_class)
+        docxml.xpath("//p[@class = '#{term_class}']").each do |t|
+          t1 = t.next_element || next
+          if t1.name == "p" && t1["class"] == term_class
+            t.add_child("　")
+            t.add_child(t1.remove.children)
+          end
+        end
+      end
+
+      def deprecated_single_label(docxml)
+        docxml.xpath("//p[@class = 'DeprecatedTerms']").each do |d|
+          t1 = d.previous_element
+          next unless t1 && t1.name == "p" && t1["class"] == "DeprecatedTerms"
+          d.children.first.content =
+            d.children.first.content.sub(/^#{@deprecated_lbl}:\s*/, "")
+        end
+      end
+
+      def terms_cleanup(docxml)
+        term_merge(docxml, "Terms")
+        term_merge(docxml, "AltTerms")
+        deprecated_single_label(docxml)
+        term_merge(docxml, "DeprecatedTerms")
+        docxml
+      end
+
+=begin
+      def intro_cleanup(docxml)
+        # insert tab for purposes of ToC lining up
+        docxml.xpath("//h1[@class = 'IntroTitle']").each do |h1|
+          if h1.content == "引言"
+            h1.add_child('<span style="mso-tab-count:1">&#xA0; </span>')
+          end
+        end
+      end
+=end
+    end
+  end
+end

data/lib/isodoc/gb/gbconvert.rb

@@ -0,0 +1,66 @@
+require "isodoc"
+require_relative "./gbcleanup.rb"
+require_relative "./metadata.rb"
+require "fileutils"
+
+module IsoDoc
+  module Gb
+    # A {Converter} implementation that generates GB output, and a document
+    # schema encapsulation of the document for validation
+    class Common < IsoDoc::Common
+      def initialize(options)
+        @meta = options[:meta]
+      end
+
+      def fileloc(loc)
+        File.join(File.dirname(__FILE__), loc)
+      end
+
+      def format_agency(agency, format)
+        return agency unless agency.is_a?(Array)
+        if agency == ["中华人民共和国国家质量监督检验检疫总局", "中国国家标准化管理委员会"]
+          logo = "gb-issuer-default.gif"
+          #system "cp #{fileloc(File.join('html/gb-logos', logo))}  #{logo}"
+          FileUtils.cp fileloc(File.join('html/gb-logos', logo)), logo
+          return "<img src='#{logo}' alt='#{agency.join(",")}'></img>"
+        end
+        format_agency1(agency, format)
+      end
+
+      def format_agency1(agency, format)
+        ret = "<table>"
+        agency.each { |a| ret += "<tr><td>#{a}</td></tr>" }
+        ret += "</table>"
+        ret.gsub!(/<table>/, "<table width='100%'>") if format == :word
+        ret
+      end
+
+      def format_logo(prefix, scope, _format)
+        return "" if %w(enterprise social-group).include? scope
+        logo = @meta.standard_logo(prefix)
+        if logo.nil?
+          "<span style='font-size:36pt;font-weight:bold'>#{prefix}</span>"
+        else
+          format_logo1(logo, prefix, scope)
+        end
+      end
+
+      def local_logo_suffix(scope)
+        return "" if scope != "local"
+        local = @meta.get[:gblocalcode]
+        "<span style='font-weight:bold'>#{local}</span>"
+      end
+
+
+      def format_logo1(logo, prefix, scope)
+        logo += ".gif"
+        #system "cp #{fileloc(File.join('html/gb-logos', logo))}  #{logo}"
+        FileUtils.cp fileloc(File.join('html/gb-logos', logo)), logo
+        local = local_logo_suffix(scope)
+        #@files_to_delete << logo
+        "<img width='113' height='56' src='#{logo}' alt='#{prefix}'></img>"\
+          "#{local}"
+      end
+    end
+  end
+end

data/lib/isodoc/gb/gbhtmlconvert.rb

@@ -0,0 +1,84 @@
+require_relative "gbconvert"
+require "gb_agencies"
+require_relative "gbcleanup"
+require_relative "metadata"
+require_relative "gbhtmlrender"
+
+module IsoDoc
+  module Gb
+    # A {Converter} implementation that generates GB output, and a document
+    # schema encapsulation of the document for validation
+    class HtmlConvert < IsoDoc::HtmlConvert
+      def initialize(options)
+        @common = IsoDoc::Gb::Common.new(options)
+        @libdir = File.dirname(__FILE__)
+        super
+        @lang = "zh"
+        @script = "Hans"
+      end
+
+      def default_fonts(options)
+        script = options[:script] || "Hans"
+        scope = options[:scope] || "national"
+        {
+          bodyfont: (script == "Hans" ? '"SimSun",serif' : '"Cambria",serif'),
+          headerfont: (script == "Hans" ? '"SimHei",sans-serif' : '"Calibri",sans-serif'),
+          monospacefont: '"Courier New",monospace',
+          titlefont: (scope == "national" ? (script != "Hans" ? '"Cambria",serif' : '"SimSun",serif' ) :
+           (script == "Hans" ? '"SimHei",sans-serif' : '"Calibri",sans-serif' ))
+        }
+      end
+
+      def default_file_locations(options)
+        {
+          htmlstylesheet: options[:compliant] ? html_doc_path("htmlcompliantstyle.scss") : html_doc_path("htmlstyle.scss"),
+          htmlcoverpage: html_doc_path("html_compliant_gb_titlepage.html"),
+          htmlintropage: html_doc_path("html_gb_intro.html"),
+          scripts: html_doc_path("scripts.html"),
+        }
+      end
+
+      def extract_fonts(options)
+        b = options[:bodyfont] || "Arial"
+        h = options[:headerfont] || "Arial"
+        m = options[:monospacefont] || "Courier"
+        t = options[:titlefont] || "Arial"
+        "$bodyfont: #{b};\n$headerfont: #{h};\n$monospacefont: #{m};\n$titlefont: #{t};\n"
+      end
+
+      def metadata_init(lang, script, labels)
+        unless ["en", "zh"].include? lang
+          lang = "zh"
+          script = "Hans"
+        end
+        @meta = Metadata.new(lang, script, labels)
+        @common = IsoDoc::Gb::Common.new(meta: @meta)
+      end
+
+      def cleanup(docxml)
+        @cleanup = Cleanup.new(@script, @deprecated_lbl)
+        super
+        @cleanup.cleanup(docxml)
+        docxml
+      end
+
+      def example_cleanup(docxml)
+        super
+        @cleanup.example_cleanup(docxml)
+      end
+
+      def i18n_init(lang, script)
+        super
+        y = if lang == "en"
+              YAML.load_file(File.join(File.dirname(__FILE__), "i18n-en.yaml"))
+            elsif lang == "zh" && script == "Hans"
+              YAML.load_file(File.join(File.dirname(__FILE__),
+                                       "i18n-zh-Hans.yaml"))
+            else
+              YAML.load_file(File.join(File.dirname(__FILE__), "i18n-zh-Hans.yaml"))
+            end
+        @labels = @labels.merge(y)
+      end
+    end
+  end
+end