isodoc 1.6.3 → 1.6.7.1

data/lib/isodoc/pdf_convert.rb

@@ -1,11 +1,10 @@
-require_relative "html_function/comments.rb"
-require_relative "html_function/footnotes.rb"
-require_relative "html_function/html.rb"
+require_relative "html_function/comments"
+require_relative "html_function/footnotes"
+require_relative "html_function/html"
 require "metanorma"
 
 module IsoDoc
   class PdfConvert < ::IsoDoc::Convert
-
     include HtmlFunction::Comments
     include HtmlFunction::Footnotes
     include HtmlFunction::Html
@@ -13,6 +12,8 @@ module IsoDoc
     def initialize(options)
       @standardstylesheet = nil
       super
+      @format = :pdf
+      @suffix = "pdf"
       @scripts = @scripts_pdf if @scripts_pdf
       @maxwidth = 500
       @maxheight = 800
@@ -22,22 +23,19 @@ module IsoDoc
       "_pdfimages"
     end
 
-    def initialize(options)
-      @format = :pdf
-      @suffix = "pdf"
-      super
-    end
-
     def convert(input_filename, file = nil, debug = false, output_filename = nil)
       file = File.read(input_filename, encoding: "utf-8") if file.nil?
       @openmathdelim, @closemathdelim = extract_delims(file)
       docxml, filename, dir = convert_init(file, input_filename, debug)
       result = convert1(docxml, filename, dir)
       return result if debug
-      postprocess(result, filename + ".tmp.html", dir)
+
+      postprocess(result, "#{filename}.tmp.html", dir)
       FileUtils.rm_rf dir
-      ::Metanorma::Output::Pdf.new.convert("#{filename}.tmp.html",
-                                           output_filename || "#{filename}.#{@suffix}")
+      ::Metanorma::Output::Pdf.new.convert(
+        "#{filename}.tmp.html",
+        output_filename || "#{filename}.#{@suffix}",
+      )
       FileUtils.rm_rf ["#{filename}.tmp.html", tmpimagedir]
     end
 

data/lib/isodoc/presentation_function/bibdata.rb

@@ -1,13 +1,40 @@
 module IsoDoc
   class PresentationXMLConvert < ::IsoDoc::Convert
     def bibdata(docxml)
+      docid_prefixes(docxml)
       a = bibdata_current(docxml) or return
+      address_precompose(a)
       bibdata_i18n(a)
       a.next =
         "<localized-strings>#{i8n_name(trim_hash(@i18n.get), '').join('')}"\
         "</localized-strings>"
     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 address_precompose(bib)
+      bib.xpath(ns("//bibdata//address")).each do |b|
+        next if b.at(ns("./formattedAddress"))
+
+        x = address_precompose1(b)
+        b.children = "<formattedAddress>#{x}</formattedAddress>"
+      end
+    end
+
+    def address_precompose1(addr)
+      ret = []
+      addr.xpath(ns("./street")).each { |s| ret << s.children.to_xml }
+      a = addr.at(ns("./city")) and ret << a.children.to_xml
+      addr.xpath(ns("./state")).each { |s| ret << s.children.to_xml }
+      a = addr.at(ns("./country")) and ret << a.children.to_xml
+      a = addr.at(ns("./postcode")) and ret[-1] += " #{a.children.to_xml}"
+      ret.join("<br/>")
+    end
+
     def bibdata_current(docxml)
       a = docxml.at(ns("//bibdata")) or return
       a.xpath(ns("./language")).each do |l|
@@ -35,27 +62,28 @@ module IsoDoc
       x.next.children = hash[x.text]
     end
 
-    def i18n_tag(k, v)
-      "<localized-string key='#{k}' language='#{@lang}'>#{v}</localized-string>"
+    def i18n_tag(key, value)
+      "<localized-string key='#{key}' language='#{@lang}'>#{value}"\
+        "</localized-string>"
     end
 
-    def i18n_safe(k)
-      k.to_s.gsub(/\s|\./, "_")
+    def i18n_safe(key)
+      key.to_s.gsub(/\s|\./, "_")
     end
 
-    def i8n_name(h, pref)
-      if h.is_a? Hash then i8n_name1(h, pref)
-      elsif h.is_a? Array
-        h.reject { |a| blank?(a) }.each_with_object([])
+    def i8n_name(hash, pref)
+      if hash.is_a? Hash then i8n_name1(hash, pref)
+      elsif hash.is_a? Array
+        hash.reject { |a| blank?(a) }.each_with_object([])
           .with_index do |(v1, g), i|
           i8n_name(v1, "#{i18n_safe(k)}.#{i}").each { |x| g << x }
         end
-      else [i18n_tag(pref, h)]
+      else [i18n_tag(pref, hash)]
       end
     end
 
-    def i8n_name1(h, pref)
-      h.reject { |k, v| blank?(v) }.each_with_object([]) do |(k, v), g|
+    def i8n_name1(hash, pref)
+      hash.reject { |_k, v| blank?(v) }.each_with_object([]) do |(k, v), g|
         if v.is_a? Hash then i8n_name(v, i18n_safe(k)).each { |x| g << x }
         elsif v.is_a? Array
           v.reject { |a| blank?(a) }.each_with_index do |v1, i|
@@ -68,28 +96,28 @@ module IsoDoc
     end
 
     # https://stackoverflow.com/a/31822406
-    def blank?(v)
-      v.nil? || v.respond_to?(:empty?) && v.empty?
+    def blank?(elem)
+      elem.nil? || elem.respond_to?(:empty?) && elem.empty?
     end
 
-    def trim_hash(h)
+    def trim_hash(hash)
       loop do
-        h_new = trim_hash1(h)
-        break h if h==h_new
+        h_new = trim_hash1(hash)
+        break hash if hash == h_new
 
-        h = h_new
+        hash = h_new
       end
     end
 
-    def trim_hash1(h)
-      return h unless h.is_a? Hash
+    def trim_hash1(hash)
+      return hash unless hash.is_a? Hash
 
-      h.each_with_object({}) do |(k, v), g|
+      hash.each_with_object({}) do |(k, v), g|
         next if blank?(v)
 
-        g[k] = if v.is_a? Hash then trim_hash1(h[k])
+        g[k] = if v.is_a? Hash then trim_hash1(hash[k])
                elsif v.is_a? Array
-                 h[k].map { |a| trim_hash1(a) }.reject { |a| blank?(a) }
+                 hash[k].map { |a| trim_hash1(a) }.reject { |a| blank?(a) }
                else
                  v
                end

data/lib/isodoc/presentation_function/inline.rb

@@ -9,8 +9,8 @@ module IsoDoc
         return @xrefs.anchor(node["bibitemid"], :xref) || "???"
       elsif node["target"] && node["droploc"]
         return @xrefs.anchor(node["target"], :value) ||
-          @xrefs.anchor(node["target"], :label) ||
-          @xrefs.anchor(node["target"], :xref) || "???"
+            @xrefs.anchor(node["target"], :label) ||
+            @xrefs.anchor(node["target"], :xref) || "???"
       elsif node["target"] && !/.#./.match(node["target"])
         linkend = anchor_linkend1(node)
       end
@@ -33,6 +33,10 @@ module IsoDoc
       return linkend&.downcase if node["case"] == "lowercase"
       return linkend if linkend[0, 1].match?(/\p{Upper}/)
 
+      capitalise_xref1(node, linkend)
+    end
+
+    def capitalise_xref1(node, linkend)
       prec = nearest_block_parent(node).xpath("./descendant-or-self::text()") &
         node.xpath("./preceding::text()")
       if prec.empty? || /(?!<[^.].)\.\s+$/.match(prec.map(&:text).join)
@@ -43,8 +47,8 @@ module IsoDoc
 
     def nearest_block_parent(node)
       until %w(p title td th name formula li dt dd sourcecode pre)
-        .include?(node.name)
-      node = node.parent
+          .include?(node.name)
+        node = node.parent
       end
       node
     end
@@ -90,7 +94,7 @@ module IsoDoc
       ret
     end
 
-    def eref_localities0(ref, _i, target, delim, node)
+    def eref_localities0(ref, _idx, target, delim, node)
       if ref["type"] == "whole" then l10n("#{delim} #{@i18n.wholeoftext}")
       else
         eref_localities1(target, ref["type"], ref.at(ns("./referenceFrom")),
@@ -99,24 +103,24 @@ module IsoDoc
     end
 
     # TODO: move to localization file
-    def eref_localities1_zh(_target, type, from, to, node, delim)
+    def eref_localities1_zh(_target, type, from, upto, node, delim)
       ret = "#{delim} 第#{from.text}" if from
-      ret += "&ndash;#{to.text}" if to
+      ret += "&ndash;#{upto.text}" if upto
       loc = (@i18n.locality[type] || type.sub(/^locality:/, "").capitalize)
       ret += " #{loc}" unless node["droploc"] == "true"
       ret
     end
 
     # TODO: move to localization file
-    def eref_localities1(target, type, from, to, delim, node, lang = "en")
+    def eref_localities1(target, type, from, upto, delim, node, lang = "en")
       return "" if type == "anchor"
 
       lang == "zh" and
-        return l10n(eref_localities1_zh(target, type, from, to, node, delim))
+        return l10n(eref_localities1_zh(target, type, from, upto, node, delim))
       ret = delim
       ret += eref_locality_populate(type, node)
       ret += " #{from.text}" if from
-      ret += "&ndash;#{to.text}" if to
+      ret += "&ndash;#{upto.text}" if upto
       l10n(ret)
     end
 
@@ -161,11 +165,12 @@ module IsoDoc
       content = node.first_element_child.children.reject do |c|
         %w{locality localityStack}.include? c.name
       end.select { |c| !c.text? || /\S/.match(c) }
-      if node.replace content.empty?
-        @i18n.term_defined_in.sub(/%/, node.first_element_child.to_xml)
-      else
-        "<em>#{node.children.to_xml}</em>"
-      end
+      n = if content.empty?
+            @i18n.term_defined_in.sub(/%/, node.first_element_child.to_xml)
+          else
+            "<em>#{node.children.to_xml}</em>"
+          end
+      node.replace(n)
     end
 
     def variant(docxml)

data/lib/isodoc/presentation_function/section.rb

@@ -44,10 +44,47 @@ module IsoDoc
       prefix_name(elem, "", "#{lbl}#{clausedelim}", "name")
     end
 
-    def references(docxml); end
+    def references(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(&: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

@@ -22,12 +22,14 @@ module IsoDoc
 
     def conversions(docxml)
       bibdata docxml
+      @xrefs.parse docxml
       section docxml
       block docxml
       inline docxml
     end
 
     def section(docxml)
+      display_order docxml
       clause docxml
       annex docxml
       term docxml

data/lib/isodoc/version.rb

@@ -1,3 +1,3 @@
 module IsoDoc
-  VERSION = "1.6.3".freeze
+  VERSION = "1.6.7.1".freeze
 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