metanorma-un 0.3.1

data/lib/isodoc/un/html_convert.rb

@@ -0,0 +1,121 @@
+require_relative "base_convert"
+require "isodoc"
+
+module IsoDoc
+  module UN
+
+    # A {Converter} implementation that generates HTML output, and a document
+    # schema encapsulation of the document for validation
+    #
+    class HtmlConvert < IsoDoc::HtmlConvert
+      def initialize(options)
+        @libdir = File.dirname(__FILE__)
+        super
+      end
+
+      def default_fonts(options)
+        {
+          bodyfont: (
+            options[:script] == "Hans" ?
+            '"SimSun",serif' :
+            '"Roboto", "Helvetica Neue", Helvetica, Arial, sans-serif'
+          ),
+          headerfont: (
+            options[:script] == "Hans" ?
+            '"SimHei",sans-serif' :
+            '"Roboto", "Helvetica Neue", Helvetica, Arial, sans-serif'
+          ),
+          monospacefont: '"Space Mono",monospace'
+        }
+      end
+
+      def default_file_locations(_options)
+        {
+          htmlstylesheet: html_doc_path("htmlstyle.scss"),
+          htmlcoverpage: html_doc_path("html_unece_titlepage.html"),
+          htmlintropage: html_doc_path("html_unece_intro.html"),
+          scripts: html_doc_path("scripts.html"),
+        }
+      end
+
+
+      def googlefonts
+        <<~HEAD.freeze
+    <link href="https://fonts.googleapis.com/css?family=Open+Sans:300,300i,400,400i,600,600i|Space+Mono:400,700" rel="stylesheet">
+    <link href="https://fonts.googleapis.com/css?family=Roboto:300,400,400i,500,700,900" rel="stylesheet">
+        HEAD
+      end
+
+      def make_body(xml, docxml)
+        plenary = docxml.at(ns("//bibdata/ext[doctype = 'plenary']"))
+        body_attr = { lang: "EN-US", link: "blue", vlink: "#954F72", "xml:lang": "EN-US", class: "container" }
+        if plenary && @htmlcoverpage == html_doc_path("html_unece_titlepage.html")
+          @htmlcoverpage = html_doc_path("html_unece_plenary_titlepage.html")
+        end
+        xml.body **body_attr do |body|
+          make_body1(body, docxml)
+          make_body2(body, docxml)
+          make_body3(body, docxml)
+        end
+      end
+
+      def make_body3(body, docxml)
+        body.div **{ class: "main-section" } do |div3|
+          boilerplate docxml, div3
+          abstract docxml, div3
+          foreword docxml, div3
+          introduction docxml, div3
+          middle docxml, div3
+          footnotes div3
+          comments div3
+        end
+      end
+
+      def middle(isoxml, out)
+        clause isoxml, out
+        annex isoxml, out
+        bibliography isoxml, out
+      end
+
+      def clause_parse_title(node, div, c1, out)
+        if node["inline-header"] == "true"
+          inline_header_title(out, node, c1)
+        else
+          div.send "h#{anchor(node['id'], :level, false) || '1'}" do |h|
+            lbl = anchor(node['id'], :label, false)
+            h << "#{lbl}. " if lbl && !@suppressheadingnumbers
+            insert_tab(h, 1) if lbl && !@suppressheadingnumbers
+            c1&.children&.each { |c2| parse(c2, h) }
+          end
+        end
+      end
+
+      def introduction(isoxml, out)
+        f = isoxml.at(ns("//introduction")) || return
+        page_break(out)
+        out.div **{ class: "Section3", id: f["id"] } do |div|
+          div.h1(**{ class: "IntroTitle" }) do |h1|
+            h1 << @introduction_lbl
+          end
+          f.elements.each do |e|
+            parse(e, div) unless e.name == "title"
+          end
+        end
+      end
+
+      def foreword(isoxml, out)
+        f = isoxml.at(ns("//foreword")) || return
+        page_break(out)
+        out.div **attr_code(id: f["id"]) do |s|
+          s.h1(**{ class: "ForewordTitle" }) do |h1|
+            h1 << @foreword_lbl
+          end
+          f.elements.each { |e| parse(e, s) unless e.name == "title" }
+        end
+      end
+
+      include BaseConvert
+    end
+  end
+end
+

data/lib/isodoc/un/metadata.rb

@@ -0,0 +1,115 @@
+require "isodoc"
+require "twitter_cldr"
+require "iso-639"
+
+module IsoDoc
+  module UN
+
+    class Metadata < IsoDoc::Metadata
+      def initialize(lang, script, labels)
+        super
+                here = File.dirname(__FILE__)
+set(:logo, File.expand_path(File.join(here, "html", "logo.jpg")))
+      end
+
+      def title(isoxml, _out)
+        main = isoxml&.at(ns("//bibdata/title[@language='en' and @type='main']"))&.text
+        set(:doctitle, main)
+      end
+
+      def subtitle(isoxml, _out)
+        main = isoxml&.at(ns("//bibdata/title[@language='en' and @type='subtitle']"))&.text
+        set(:docsubtitle, main)
+      end
+
+      def extract_languages(nodeset)
+        lgs = []
+        nodeset.each do |l|
+          l && ISO_639&.find(l.text)&.english_name &&
+            lgs << ISO_639.find(l.text).english_name 
+        end
+        lgs.map { |l| l == "Spanish; Castilian" ? "Spanish" : l }
+      end
+
+      def author(isoxml, _out)
+        tc = isoxml.at(ns("//bibdata/ext/editorialgroup/committee"))
+        set(:tc, tc.text) if tc
+        set(:distribution, isoxml&.at(ns("//bibdata/ext/distribution"))&.text)
+        lgs = extract_languages(isoxml.xpath(ns("//bibdata/language")))
+        lgs = [] if lgs.sort == %w(English French Arabic Chinese Russian Spanish).sort
+        slgs = extract_languages(isoxml.xpath(ns("//bibdata/ext/submissionlanguage")))
+        lgs = [] if slgs.size == 1
+        set(:doclanguage, lgs) unless lgs.empty?
+        set(:submissionlanguage, slgs) unless slgs.empty?
+        session(isoxml, _out)
+      end
+
+      def multival(isoxml, xpath)
+        items = []
+        isoxml.xpath(ns(xpath)).each { |i| items << i.text }
+        items
+      end
+
+      def session(isoxml, _out)
+        set(:session_number, isoxml&.at(ns("//bibdata/ext/session/number"))&.text&.to_i&.
+            localize&.to_rbnf_s("SpelloutRules", "spellout-ordinal")&.capitalize)
+        set(:session_date, isoxml&.at(ns("//bibdata/ext/session/date"))&.text)
+        set(:session_collaborator, isoxml&.at(ns("//bibdata/ext/session/collaborator"))&.text)
+        set(:session_id, isoxml&.at(ns("//bibdata/ext/session/id"))&.text)
+        set(:item_footnote, isoxml&.at(ns("//bibdata/ext/session/item-footnote"))&.text)
+        set(:session_itemnumber, multival(isoxml, "//bibdata/ext/session/item-number"))
+        set(:session_itemname, multival(isoxml, "//bibdata/ext/session/item-name"))
+        set(:session_subitemname, multival(isoxml, "//bibdata/ext/session/subitem-name"))
+      end
+
+      def docid(isoxml, _out)
+        dn = isoxml.at(ns("//bibdata/docidentifier"))&.text
+        set(:docnumber, dn)
+        type = isoxml&.at(ns("//bibdata/ext/doctype"))&.text
+        set(:formatted_docnumber, type == "recommendation" ? "UN/CEFACT Recommendation #{dn}" : dn)
+      end
+
+      def stage_abbr(status)
+        case status
+        when "working-draft" then "wd"
+        when "committee-draft" then "cd"
+        when "draft-standard" then "d"
+        else
+          ""
+        end
+      end
+
+      def unpublished(status)
+        !%w(published withdrawn).include? status.downcase
+      end
+
+      def version(isoxml, _out)
+        super
+        revdate = get[:revdate]
+        set(:revdate_monthyear, monthyr(revdate))
+      end
+
+      MONTHS = {
+        "01": "January",
+        "02": "February",
+        "03": "March",
+        "04": "April",
+        "05": "May",
+        "06": "June",
+        "07": "July",
+        "08": "August",
+        "09": "September",
+        "10": "October",
+        "11": "November",
+        "12": "December",
+      }.freeze
+
+      def monthyr(isodate)
+        m = /(?<yr>\d\d\d\d)-(?<mo>\d\d)/.match isodate
+        return isodate unless m && m[:yr] && m[:mo]
+        return "#{MONTHS[m[:mo].to_sym]} #{m[:yr]}"
+      end
+
+    end
+  end
+end

data/lib/isodoc/un/pdf_convert.rb

@@ -0,0 +1,133 @@
+require_relative "base_convert"
+require "isodoc"
+
+module IsoDoc
+  module UN
+
+    # A {Converter} implementation that generates HTML output, and a document
+    # schema encapsulation of the document for validation
+    #
+    class PdfConvert < IsoDoc::PdfConvert
+      def initialize(options)
+        @libdir = File.dirname(__FILE__)
+        super
+      end
+
+      #def convert1(docxml, filename, dir)
+        #FileUtils.cp html_doc_path('logo.jpg'), File.join(@localdir, "logo.jpg")
+        #@files_to_delete << File.join(@localdir, "logo.jpg")
+        #super
+      #end
+
+      def default_fonts(options)
+        {
+          bodyfont: (
+            options[:script] == "Hans" ?
+            '"SimSun",serif' :
+            '"Roboto", "Helvetica Neue", Helvetica, Arial, sans-serif'
+          ),
+          headerfont: (
+            options[:script] == "Hans" ?
+            '"SimHei",sans-serif' :
+            '"Roboto", "Helvetica Neue", Helvetica, Arial, sans-serif'
+          ),
+          monospacefont: '"Space Mono",monospace'
+        }
+      end
+
+      def default_file_locations(_options)
+        {
+          htmlstylesheet: html_doc_path("htmlstyle.scss"),
+          htmlcoverpage: html_doc_path("html_unece_titlepage.html"),
+          htmlintropage: html_doc_path("html_unece_intro.html"),
+          scripts: html_doc_path("scripts.pdf.html"),
+        }
+      end
+
+
+      def googlefonts
+        <<~HEAD.freeze
+    <link href="https://fonts.googleapis.com/css?family=Open+Sans:300,300i,400,400i,600,600i|Space+Mono:400,700" rel="stylesheet">
+    <link href="https://fonts.googleapis.com/css?family=Roboto:300,400,400i,500,700,900" rel="stylesheet">
+        HEAD
+      end
+
+      def make_body(xml, docxml)
+        plenary = docxml.at(ns("//bibdata/ext[doctype = 'plenary']"))
+        body_attr = { lang: "EN-US", link: "blue", vlink: "#954F72", "xml:lang": "EN-US", class: "container" }
+        if plenary && @htmlcoverpage == html_doc_path("html_unece_titlepage.html")
+          @htmlcoverpage = html_doc_path("html_unece_plenary_titlepage.html")
+        end
+        #@htmlintropage = nil if plenary
+        xml.body **body_attr do |body|
+          make_body1(body, docxml)
+          make_body2(body, docxml)
+          make_body3(body, docxml)
+        end
+      end
+
+      def make_body3(body, docxml)
+        body.div **{ class: "main-section" } do |div3|
+          boilerplate docxml, div3
+          abstract docxml, div3
+          foreword docxml, div3
+          introduction docxml, div3
+          middle docxml, div3
+          footnotes div3
+          comments div3
+        end
+      end
+
+      def html_preface(docxml)
+        super
+        docxml
+      end
+
+      def middle(isoxml, out)
+        clause isoxml, out
+        annex isoxml, out
+        bibliography isoxml, out
+      end
+
+      def clause_parse_title(node, div, c1, out)
+        if node["inline-header"] == "true"
+          inline_header_title(out, node, c1)
+        else
+          div.send "h#{anchor(node['id'], :level, false) || '1'}" do |h|
+            lbl = anchor(node['id'], :label, false)
+            h << "#{lbl}. " if lbl && !@suppressheadingnumbers
+            insert_tab(h, 1) if lbl && !@suppressheadingnumbers
+            c1&.children&.each { |c2| parse(c2, h) }
+          end
+        end
+      end
+
+      def introduction(isoxml, out)
+        f = isoxml.at(ns("//introduction")) || return
+        page_break(out)
+        out.div **{ class: "Section3", id: f["id"] } do |div|
+          div.h1(**{ class: "IntroTitle" }) do |h1|
+            h1 << @introduction_lbl
+          end
+          f.elements.each do |e|
+            parse(e, div) unless e.name == "title"
+          end
+        end
+      end
+
+      def foreword(isoxml, out)
+        f = isoxml.at(ns("//foreword")) || return
+        page_break(out)
+        out.div **attr_code(id: f["id"]) do |s|
+          s.h1(**{ class: "ForewordTitle" }) do |h1|
+            h1 << @foreword_lbl
+          end
+          f.elements.each { |e| parse(e, s) unless e.name == "title" }
+        end
+      end
+
+      include BaseConvert
+    end
+  end
+end
+

data/lib/isodoc/un/word_convert.rb

@@ -0,0 +1,180 @@
+require_relative "base_convert"
+require "isodoc"
+
+module IsoDoc
+  module UN
+    # A {Converter} implementation that generates Word output, and a document
+    # schema encapsulation of the document for validation
+
+    class WordConvert < IsoDoc::WordConvert
+      def initialize(options)
+        @libdir = File.dirname(__FILE__)
+        super
+        @toc = options[:toc]
+      end
+
+      #def convert1(docxml, filename, dir)
+        #FileUtils.cp html_doc_path('logo.jpg'), File.join(@localdir, "logo.jpg")
+        #super
+      #end
+
+      def default_fonts(options)
+        {
+          bodyfont: (options[:script] == "Hans" ? '"SimSun",serif' : '"Times New Roman",serif'),
+          headerfont: (options[:script] == "Hans" ? '"SimHei",sans-serif' : '"Times New Roman",serif'),
+          monospacefont: '"Courier New",monospace'
+        }
+      end
+
+      def default_file_locations(options)
+        {
+          wordstylesheet: html_doc_path("wordstyle.scss"),
+          standardstylesheet: html_doc_path("unece.scss"),
+          header: html_doc_path("header.html"),
+          wordcoverpage: html_doc_path("word_unece_titlepage.html"),
+          wordintropage: html_doc_path("word_unece_intro.html"),
+          ulstyle: "l3",
+          olstyle: "l2",
+        }
+      end
+
+      def footnotes(div)
+        if @meta.get[:item_footnote]
+          fn = noko do |xml|
+            xml.aside **{ id: "ftnitem" } do |div|
+              div.p @meta.get[:item_footnote]
+            end
+          end.join("\n")
+          @footnotes.unshift fn
+        end
+        super
+      end
+
+      def make_body(xml, docxml)
+        plenary = docxml.at(ns("//bibdata/ext[doctype = 'plenary']"))
+        if plenary && @wordcoverpage == html_doc_path("word_unece_titlepage.html")
+          @wordcoverpage = html_doc_path("word_unece_plenary_titlepage.html")
+        end
+        @wordintropage = nil if plenary && !@toc
+        body_attr = { lang: "EN-US", link: "blue", vlink: "#954F72" }
+        xml.body **body_attr do |body|
+          make_body1(body, docxml)
+          make_body2(body, docxml)
+          make_body3(body, docxml)
+        end
+      end
+
+      def make_body2(body, docxml)
+        body.div **{ class: "WordSection2" } do |div2|
+          info docxml, div2
+          boilerplate docxml, div2
+          abstract docxml, div2
+          foreword docxml, div2
+          introduction docxml, div2
+          div2.p { |p| p << "&nbsp;" } # placeholder
+        end
+        section_break(body)
+      end
+
+      ENDLINE = <<~END.freeze
+      <v:line 
+ alt="" style='position:absolute;left:0;text-align:left;z-index:251662848;
+ mso-wrap-edited:f;mso-width-percent:0;mso-height-percent:0;
+ mso-width-percent:0;mso-height-percent:0'
+ from="6.375cm,20.95pt" to="10.625cm,20.95pt"
+ strokeweight="1.5pt"/>
+      END
+
+      def end_line(_isoxml, out)
+        out.parent.add_child(ENDLINE)
+      end
+
+      def middle(isoxml, out)
+        clause isoxml, out
+        annex isoxml, out
+        bibliography isoxml, out
+        end_line(isoxml, out)
+      end
+
+      def clause_parse_title(node, div, c1, out)
+        if node["inline-header"] == "true"
+          inline_header_title(out, node, c1)
+        else
+          div.send "h#{anchor(node['id'], :level, false) || '1'}" do |h|
+            lbl = anchor(node['id'], :label, false)
+            if lbl && !@suppressheadingnumbers
+              h << "#{lbl}. "
+              insert_tab(h, 1)
+            end
+            c1&.children&.each { |c2| parse(c2, h) }
+          end
+        end
+      end
+
+      def introduction(isoxml, out)
+        f = isoxml.at(ns("//introduction")) || return
+        out.div **{ class: "Section3", id: f["id"] } do |div|
+          page_break(out)
+          div.p(**{ class: "IntroTitle" }) do |h1|
+            h1 << @introduction_lbl
+          end
+          f.elements.each do |e|
+            parse(e, div) unless e.name == "title"
+          end
+        end
+      end
+
+      def foreword(isoxml, out)
+        f = isoxml.at(ns("//foreword")) || return
+        out.div **attr_code(id: f["id"]) do |s|
+          page_break(out)
+          s.p(**{ class: "ForewordTitle" }) do |h1|
+            h1 << @foreword_lbl
+          end
+          f.elements.each { |e| parse(e, s) unless e.name == "title" }
+        end
+      end
+
+      def word_preface(docxml)
+        super
+        preface_container = docxml.at("//div[@id = 'preface_container']") # recommendation
+        abstractbox = docxml.at("//div[@id = 'abstractbox']") # plenary
+        foreword = docxml.at("//p[@class = 'ForewordTitle']/..")
+        intro = docxml.at("//p[@class = 'IntroTitle']/..")
+        abstract = docxml.at("//p[@class = 'AbstractTitle']/..")
+        abstract.parent = (abstractbox || preface_container) if abstract
+        abstractbox and abstract&.xpath(".//p/br")&.each do |a|
+          a.parent.remove if /page-break-before:always/.match(a["style"])
+        end
+        docxml&.at("//p[@class = 'AbstractTitle']")&.remove if abstractbox
+        foreword.parent = preface_container if foreword && preface_container
+        intro.parent = preface_container if intro && preface_container
+        if preface_container && (foreword || intro)
+          preface_container.at("./div/p[br]").remove # remove initial page break
+        end
+        if abstractbox && !intro && !foreword && !@toc
+          sect2 = docxml.at("//div[@class='WordSection2']")
+          sect2.next_element.remove # pagebreak
+          sect2.remove # pagebreak
+        end
+      end
+
+      def abstract(isoxml, out)
+        f = isoxml.at(ns("//abstract")) || return
+        out.div **attr_code(id: f["id"]) do |s|
+          page_break(out)
+          s.p(**{ class: "AbstractTitle" }) { |h1| h1 << @abstract_lbl }
+          f.elements.each { |e| parse(e, s) unless e.name == "title" }
+        end
+      end
+
+      def authority_cleanup(docxml)
+        super
+        a = docxml.at("//div[@id = 'boilerplate-ECEhdr']") and a["class"] = "boilerplate-ECEhdr"
+        docxml&.at("//div[@class = 'authority']")&.remove
+      end
+
+      include BaseConvert
+    end
+  end
+end