isodoc 1.6.1 → 1.6.6

data/lib/isodoc/presentation_function/math.rb

@@ -0,0 +1,84 @@
+require "twitter_cldr"
+require "bigdecimal"
+
+module IsoDoc
+  class PresentationXMLConvert < ::IsoDoc::Convert
+    MATHML = { "m" => "http://www.w3.org/1998/Math/MathML" }.freeze
+
+    def mathml(docxml)
+      locale = twitter_cldr_localiser
+      docxml.xpath("//m:math", MATHML).each do |f|
+        mathml1(f, locale)
+      end
+    end
+
+    # symbols is merged into
+    # TwitterCldr::DataReaders::NumberDataReader.new(locale).symbols
+    def localize_maths(node, locale)
+      node.xpath(".//m:mn", MATHML).each do |x|
+        num = BigDecimal(x.text)
+        precision = /\./.match?(x.text) ? x.text.sub(/^.*\./, "").size : 0
+        x.children = localized_number(num, locale, precision)
+      end
+    end
+
+    # By itself twitter-cldr does not support fraction part digits grouping
+    # and custom delimeter, will decorate fraction part manually
+    def localized_number(num, locale, precision)
+      localized = localized_number1(num, locale, precision)
+      twitter_cldr_reader_symbols = twitter_cldr_reader(locale)
+      return localized unless twitter_cldr_reader_symbols[:decimal]
+
+      integer, fraction = localized.split(twitter_cldr_reader_symbols[:decimal])
+      return localized if fraction.nil? || fraction.length.zero?
+
+      [integer, decorate_fraction_part(fraction, locale)]
+        .join(twitter_cldr_reader_symbols[:decimal])
+    end
+
+    def localized_number1(num, locale, precision)
+      if precision.zero?
+        num.localize(locale).to_s
+      else
+        num.localize(locale).to_decimal.to_s(precision: precision)
+      end
+    end
+
+    def decorate_fraction_part(fract, locale)
+      result = []
+      twitter_cldr_reader_symbols = twitter_cldr_reader(locale)
+      fract = fract.slice(0..(twitter_cldr_reader_symbols[:precision] || -1))
+      fr_group_digits = twitter_cldr_reader_symbols[:fraction_group_digits] || 1
+      until fract.empty?
+        result.push(fract.slice!(0, fr_group_digits))
+      end
+      result.join(twitter_cldr_reader_symbols[:fraction_group].to_s)
+    end
+
+    def twitter_cldr_localiser_symbols
+      {}
+    end
+
+    def twitter_cldr_reader(locale)
+      num = TwitterCldr::DataReaders::NumberDataReader.new(locale)
+      num.symbols.merge!(twitter_cldr_localiser_symbols)
+    end
+
+    def twitter_cldr_localiser
+      locale = TwitterCldr.supported_locale?(@lang.to_sym) ? @lang.to_sym : :en
+      twitter_cldr_reader(locale)
+      locale
+    end
+
+    def mathml1(node, locale)
+      localize_maths(node, locale)
+      return unless node.elements.size == 1 && node.elements.first.name == "mn"
+
+      if node.parent.name == "stem"
+        node.parent.replace(node.at("./m:mn", MATHML).children)
+      else
+        node.replace(node.at("./m:mn", MATHML).children)
+      end
+    end
+  end
+end

data/lib/isodoc/presentation_function/section.rb

@@ -2,20 +2,21 @@ module IsoDoc
   class PresentationXMLConvert < ::IsoDoc::Convert
     def clause(docxml)
       docxml.xpath(ns("//clause | "\
-                      "//terms | //definitions | //references")).
-                     each do |f|
+                      "//terms | //definitions | //references"))
+        .each do |f|
         clause1(f)
       end
     end
 
-    def clause1(f)
-      level = @xrefs.anchor(f['id'], :level, false) || "1"
-      t = f.at(ns("./title")) and t["depth"] = level
-      return if !f.ancestors("boilerplate").empty?
-      return if @suppressheadingnumbers || f["unnumbered"]
-      lbl = @xrefs.anchor(f['id'], :label,
-                          f.parent.name != "sections") or return
-      prefix_name(f, "<tab/>", "#{lbl}#{clausedelim}", "title")
+    def clause1(elem)
+      level = @xrefs.anchor(elem["id"], :level, false) || "1"
+      t = elem.at(ns("./title")) and t["depth"] = level
+      return if !elem.ancestors("boilerplate").empty? ||
+        @suppressheadingnumbers || elem["unnumbered"]
+
+      lbl = @xrefs.anchor(elem["id"], :label,
+                          elem.parent.name != "sections") or return
+      prefix_name(elem, "<tab/>", "#{lbl}#{clausedelim}", "title")
     end
 
     def annex(docxml)
@@ -24,12 +25,12 @@ module IsoDoc
       end
     end
 
-    def annex1(f)
-      lbl = @xrefs.anchor(f['id'], :label)
-      if t = f.at(ns("./title"))
+    def annex1(elem)
+      lbl = @xrefs.anchor(elem["id"], :label)
+      if t = elem.at(ns("./title"))
         t.children = "<strong>#{t.children.to_xml}</strong>"
       end
-      prefix_name(f, "<br/><br/>", lbl, "title")
+      prefix_name(elem, "<br/><br/>", lbl, "title")
     end
 
     def term(docxml)
@@ -38,18 +39,53 @@ module IsoDoc
       end
     end
 
-    def term1(f)
-      lbl = @xrefs.get[f["id"]][:label] or return
-      prefix_name(f, "", "#{lbl}#{clausedelim}", "name")
+    def term1(elem)
+      lbl = @xrefs.get[elem["id"]][:label] or return
+      prefix_name(elem, "", "#{lbl}#{clausedelim}", "name")
     end
 
     def references(docxml)
+      docid_prefixes(docxml)
+    end
+
+    def docid_prefixes(docxml)
+      docxml.xpath(ns("//references/bibitem/docidentifier")).each do |i|
+        i.children = @xrefs.klass.docid_prefix(i["type"], i.text)
+      end
     end
 
     def index(docxml)
-      docxml.xpath(ns("//index | //index-xref | //indexsect")).each do |f|
-        f.remove
+      docxml.xpath(ns("//index | //index-xref | //indexsect")).each(&:remove)
+    end
+
+    def display_order_at(docxml, xpath, idx)
+      return idx unless c = docxml.at(ns(xpath))
+
+      idx += 1
+      c["displayorder"] = idx
+      idx
+    end
+
+    def display_order_xpath(docxml, xpath, idx)
+      docxml.xpath(ns(xpath)).each do |c|
+        idx += 1
+        c["displayorder"] = idx
       end
+      idx
+    end
+
+    def display_order(docxml)
+      i = 0
+      i = display_order_xpath(docxml, "//preface/*", i)
+      i = display_order_at(docxml, "//clause[@type = 'scope']", i)
+      i = display_order_at(docxml, @xrefs.klass.norm_ref_xpath, i)
+      i = display_order_at(docxml, "//sections/terms | "\
+                           "//sections/clause[descendant::terms]", i)
+      i = display_order_at(docxml, "//sections/definitions", i)
+      i = display_order_xpath(docxml, @xrefs.klass.middle_clause(docxml), i)
+      i = display_order_xpath(docxml, "//annex", i)
+      i = display_order_xpath(docxml, @xrefs.klass.bibliography_xpath, i)
+      display_order_xpath(docxml, "//indexsect", i)
     end
   end
 end

data/lib/isodoc/presentation_xml_convert.rb

@@ -1,5 +1,6 @@
 require_relative "presentation_function/block"
 require_relative "presentation_function/inline"
+require_relative "presentation_function/math"
 require_relative "presentation_function/section"
 require_relative "presentation_function/bibdata"
 
@@ -23,10 +24,12 @@ module IsoDoc
       bibdata docxml
       section docxml
       block docxml
+      @xrefs.parse docxml
       inline docxml
     end
 
     def section(docxml)
+      display_order docxml
       clause docxml
       annex docxml
       term docxml

data/lib/isodoc/sassc_importer.rb

@@ -1,6 +1,6 @@
 # frozen_string_literal: true
 
-require 'sassc'
+require "sassc"
 
 class SasscImporter < SassC::Importer
   def imports(path, _parent_path)

data/lib/isodoc/version.rb

@@ -1,3 +1,3 @@
 module IsoDoc
-  VERSION = "1.6.1".freeze
+  VERSION = "1.6.6".freeze
 end

data/lib/isodoc/word_function/body.rb

@@ -1,5 +1,5 @@
-require_relative "./table.rb"
-require_relative "./inline.rb"
+require_relative "./table"
+require_relative "./inline"
 
 module IsoDoc::WordFunction
   module Body
@@ -71,8 +71,8 @@ module IsoDoc::WordFunction
       node.xpath(ns("./note")).each { |n| parse(n, out) }
     end
 
-    WORD_DT_ATTRS = {class: @note ? "Note" : nil, align: "left",
-                     style: "margin-left:0pt;text-align:left;"}.freeze
+    WORD_DT_ATTRS = { class: @note ? "Note" : nil, align: "left",
+                      style: "margin-left:0pt;text-align:left;" }.freeze
 
     def dt_parse(dt, term)
       term.p **attr_code(WORD_DT_ATTRS) do |p|
@@ -102,6 +102,7 @@ module IsoDoc::WordFunction
 
     def dl_parse_notes(node, v)
       return if node.elements.reject { |n| dt_dd? n }.empty?
+
       v.tr do |tr|
         tr.td **{ colspan: 2 } do |td|
           node.elements.reject { |n| dt_dd? n }.each { |n| parse(n, td) }
@@ -109,19 +110,19 @@ module IsoDoc::WordFunction
       end
     end
 
-    def figure_get_or_make_dl(t)
-      dl = t.at(".//table[@class = 'dl']")
+    def figure_get_or_make_dl(node)
+      dl = node.at(".//table[@class = 'dl']")
       if dl.nil?
-        t.add_child("<p><b>#{@i18n.key}</b></p><table class='dl'></table>")
-        dl = t.at(".//table[@class = 'dl']")
+        node.add_child("<p><b>#{@i18n.key}</b></p><table class='dl'></table>")
+        dl = node.at(".//table[@class = 'dl']")
       end
       dl
     end
 
-    def figure_aside_process(f, aside, key)
+    def figure_aside_process(fig, aside, key)
       # get rid of footnote link, it is in diagram
-      f&.at("./a[@class='TableFootnoteRef']")&.remove
-      fnref = f.at(".//span[@class='TableFootnoteRef']/..")
+      fig&.at("./a[@class='TableFootnoteRef']")&.remove
+      fnref = fig.at(".//span[@class='TableFootnoteRef']/..")
       tr = key.add_child("<tr></tr>").first
       dt = tr.add_child("<td valign='top' align='left'></td>").first
       dd = tr.add_child("<td valign='top'></td>").first
@@ -174,31 +175,32 @@ module IsoDoc::WordFunction
         attrs[:align] = node["align"] unless node["align"] == "justify"
         attrs[:style] += "text-align:#{node['align']};"
       end
-      attrs[:style] += "#{keep_style(node)}"
+      attrs[:style] += keep_style(node).to_s
       attrs[:style] = nil if attrs[:style].empty?
       attrs
     end
 
     def example_table_attr(node)
       super.merge({
-        style: "mso-table-lspace:15.0cm;margin-left:423.0pt;"\
-        "mso-table-rspace:15.0cm;margin-right:423.0pt;"\
-        "mso-table-anchor-horizontal:column;"\
-        "mso-table-overlap:never;border-collapse:collapse;"\
-        "#{keep_style(node)}"
-      })
+                    style: "mso-table-lspace:15.0cm;margin-left:423.0pt;"\
+                    "mso-table-rspace:15.0cm;margin-right:423.0pt;"\
+                    "mso-table-anchor-horizontal:column;"\
+                    "mso-table-overlap:never;border-collapse:collapse;"\
+                    "#{keep_style(node)}",
+                  })
     end
 
-    def formula_where(dl, out)
-      return unless dl
+    def formula_where(deflist, out)
+      return unless deflist
+
       out.p { |p| p << @i18n.where }
-      parse(dl, out)
+      parse(deflist, out)
       out.parent.at("./table")["class"] = "formula_dl"
     end
 
     def formula_parse1(node, out)
       out.div **attr_code(class: "formula") do |div|
-        div.p do |p|
+        div.p do |_p|
           parse(node.at(ns("./stem")), div)
           insert_tab(div, 1)
           if lbl = node&.at(ns("./name"))&.text
@@ -209,7 +211,7 @@ module IsoDoc::WordFunction
     end
 
     def li_parse(node, out)
-      out.li  **attr_code(id: node["id"]) do |li|
+      out.li **attr_code(id: node["id"]) do |li|
         if node["uncheckedcheckbox"] == "true"
           li << '<span class="zzMoveToFollowing">&#x2610; </span>'
         elsif node["checkedcheckbox"] == "true"
@@ -220,7 +222,9 @@ module IsoDoc::WordFunction
     end
 
     def suffix_url(url)
-      return url if %r{^http[s]?://}.match(url)
+      return url if %r{^https?://}.match?(url)
+      return url unless File.extname(url).empty?
+
       url.sub(/#{File.extname(url)}$/, ".doc")
     end
   end

data/lib/isodoc/word_function/postprocess.rb

@@ -1,17 +1,17 @@
 require "fileutils"
-require_relative "./postprocess_cover.rb"
+require_relative "./postprocess_cover"
 
 module IsoDoc::WordFunction
   module Postprocess
     # add namespaces for Word fragments
     WORD_NOKOHEAD = <<~HERE.freeze
-    <!DOCTYPE html SYSTEM "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
-    <html xmlns="http://www.w3.org/1999/xhtml"
-xmlns:v="urn:schemas-microsoft-com:vml" xmlns:o="urn:schemas-microsoft-com:office:office"
-xmlns:w="urn:schemas-microsoft-com:office:word"
-xmlns:m="http://schemas.microsoft.com/office/2004/12/omml">
-    <head> <title></title> <meta charset="UTF-8" /> </head>
-    <body> </body> </html>
+      <!DOCTYPE html SYSTEM "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
+      <html xmlns="http://www.w3.org/1999/xhtml"
+      xmlns:v="urn:schemas-microsoft-com:vml" xmlns:o="urn:schemas-microsoft-com:office:office"
+      xmlns:w="urn:schemas-microsoft-com:office:word"
+      xmlns:m="http://schemas.microsoft.com/office/2004/12/omml">
+      <head> <title></title> <meta charset="UTF-8" /> </head>
+      <body> </body> </html>
     HERE
 
     def to_word_xhtml_fragment(xml)
@@ -22,7 +22,8 @@ xmlns:m="http://schemas.microsoft.com/office/2004/12/omml">
     def table_note_cleanup(docxml)
       super
       # preempt html2doc putting MsoNormal there
-      docxml.xpath("//p[not(self::*[@class])][ancestor::*[@class = 'Note']]").each do |p|
+      docxml.xpath("//p[not(self::*[@class])][ancestor::*[@class = 'Note']]")
+        .each do |p|
         p["class"] = "Note"
       end
     end
@@ -38,16 +39,21 @@ xmlns:m="http://schemas.microsoft.com/office/2004/12/omml">
     def toWord(result, filename, dir, header)
       result = from_xhtml(word_cleanup(to_xhtml(result)))
       @wordstylesheet = wordstylesheet_update
-      Html2Doc.process(result, filename: filename, stylesheet: @wordstylesheet&.path,
-                       header_file: header&.path, dir: dir,
-                       asciimathdelims: [@openmathdelim, @closemathdelim],
-                       liststyles: { ul: @ulstyle, ol: @olstyle })
+      Html2Doc.process(
+        result,
+        filename: filename,
+        stylesheet: @wordstylesheet&.path,
+        header_file: header&.path, dir: dir,
+        asciimathdelims: [@openmathdelim, @closemathdelim],
+        liststyles: { ul: @ulstyle, ol: @olstyle }
+      )
       header&.unlink
-      @wordstylesheet&.unlink if @wordstylesheet&.is_a?(Tempfile)
+      @wordstylesheet.unlink if @wordstylesheet.is_a?(Tempfile)
     end
 
-    def wordstylesheet_update()
+    def wordstylesheet_update
       return if @wordstylesheet.nil?
+
       f = File.open(@wordstylesheet.path, "a")
       @landscapestyle.empty? or f.write(@landscapestyle)
       if @wordstylesheet_override && @wordstylesheet
@@ -62,7 +68,8 @@ xmlns:m="http://schemas.microsoft.com/office/2004/12/omml">
 
     def word_admonition_images(docxml)
       docxml.xpath("//div[@class = 'Admonition']//img").each do |i|
-        i["width"], i["height"] = Html2Doc.image_resize(i, image_localfile(i), @maxheight, 300)
+        i["width"], i["height"] =
+          Html2Doc.image_resize(i, image_localfile(i), @maxheight, 300)
       end
     end
 
@@ -88,21 +95,23 @@ xmlns:m="http://schemas.microsoft.com/office/2004/12/omml">
       cells2d = {}
       docxml.xpath("//table[colgroup]").each do |t|
         w = colgroup_widths(t)
-        t.xpath(".//tr").each_with_index { |tr, r| cells2d[r] = {} }
+        t.xpath(".//tr").each_with_index { |_tr, r| cells2d[r] = {} }
         t.xpath(".//tr").each_with_index do |tr, r|
-          tr.xpath("./td | ./th").each_with_index do |td, i|
+          tr.xpath("./td | ./th").each_with_index do |td, _i|
             x = 0
             rs = td&.attr("rowspan")&.to_i || 1
             cs = td&.attr("colspan")&.to_i || 1
-            while cells2d[r][x] do
-              x += 1 
+            while cells2d[r][x]
+              x += 1
             end
-            for y2 in r..(r + rs - 1)
-              for x2 in x..(x + cs - 1)
+            (r..(r + rs - 1)).each do |y2|
+              (x..(x + cs - 1)).each do |x2|
                 cells2d[y2][x2] = 1
               end
             end
-            width = (x..(x+cs-1)).each_with_object({width: 0}) { |z, m| m[:width] += w[z] }
+            width = (x..(x + cs - 1)).each_with_object({ width: 0 }) do |z, m|
+              m[:width] += w[z]
+            end
             td["width"] = "#{width[:width]}%"
             x += cs
           end
@@ -111,8 +120,8 @@ xmlns:m="http://schemas.microsoft.com/office/2004/12/omml">
     end
 
     # assume percentages
-    def colgroup_widths(t)
-      t.xpath("./colgroup/col").each_with_object([]) do |c, m|
+    def colgroup_widths(table)
+      table.xpath("./colgroup/col").each_with_object([]) do |c, m|
         m << c["width"].sub(/%$/, "").to_f
       end
     end
@@ -127,12 +136,13 @@ xmlns:m="http://schemas.microsoft.com/office/2004/12/omml">
 
     def style_update(node, css)
       return unless node
-      node["style"] = node["style"] ?  node["style"].sub(/;?$/, ";#{css}") : css
+
+      node["style"] = node["style"] ? node["style"].sub(/;?$/, ";#{css}") : css
     end
 
     def word_image_caption(docxml)
-      docxml.xpath("//p[@class = 'FigureTitle' or @class = 'SourceTitle']").
-        each do |t|
+      docxml.xpath("//p[@class = 'FigureTitle' or @class = 'SourceTitle']")
+        .each do |t|
         if t&.previous_element&.name == "img"
           img = t.previous_element
           t.previous_element.swap("<p class=\'figure\'>#{img.to_xml}</p>")
@@ -150,7 +160,8 @@ xmlns:m="http://schemas.microsoft.com/office/2004/12/omml">
       xpath.each do |list|
         (list.xpath(".//li") - list.xpath(".//ol//li | .//ul//li")).each do |l|
           l.xpath("./p | ./div | ./table").each_with_index do |p, i|
-            next if i == 0
+            next if i.zero?
+
             p.wrap(%{<div class="ListContLevel#{lvl}"/>})
           end
           list_add(l.xpath(".//ul") - l.xpath(".//ul//ul | .//ol//ul"), lvl + 1)
@@ -162,20 +173,21 @@ xmlns:m="http://schemas.microsoft.com/office/2004/12/omml">
     def word_table_align(docxml)
       docxml.xpath("//td[@align]/p | //th[@align]/p").each do |p|
         next if p["align"]
-        style_update(p, "text-align: #{p.parent["align"]}")
+
+        style_update(p, "text-align: #{p.parent['align']}")
       end
     end
 
     def word_table_separator(docxml)
       docxml.xpath("//p[@class = 'TableTitle']").each do |t|
         next unless t.children.empty?
+
         t["style"] = t["style"].sub(/;?$/, ";font-size:0pt;")
         t.children = "&nbsp;"
       end
     end
 
-    def word_annex_cleanup(docxml)
-    end
+    def word_annex_cleanup(docxml); end
 
     def word_example_cleanup(docxml)
       docxml.xpath("//div[@class = 'example']//p[not(@class)]").each do |p|
@@ -194,19 +206,21 @@ xmlns:m="http://schemas.microsoft.com/office/2004/12/omml">
       docxml.xpath("//div[p/br]").each do |d|
         /^WordSection\d+_\d+$/.match(d["class"]) or next
         d.elements[0].name == "p" && !d.elements[0].elements.empty? or next
-        d.elements[0].elements[0].name == "br" && d.elements[0].elements[0]["style"] ==
-          "mso-special-character:line-break;page-break-before:always" or next
+        d.elements[0].elements[0].name == "br" &&
+          d.elements[0].elements[0]["style"] ==
+            "mso-special-character:line-break;page-break-before:always" or next
         d.elements[0].remove
       end
     end
 
     def word_footnote_format(docxml)
-      # the content is in a[@epub:type = 'footnote']//sup, but in Word, 
+      # the content is in a[@epub:type = 'footnote']//sup, but in Word,
       # we need to inject content around the autonumbered footnote reference
       docxml.xpath("//a[@epub:type = 'footnote']").each do |x|
         footnote_reference_format(x)
       end
-      docxml.xpath("//a[@class = 'TableFootnoteRef'] | //span[@class = 'TableFootnoteRef']").each do |x|
+      docxml.xpath("//a[@class = 'TableFootnoteRef'] | "\
+                   "//span[@class = 'TableFootnoteRef']").each do |x|
         table_footnote_reference_format(x)
       end
       docxml