isodoc 1.7.3 → 1.7.6

data/lib/isodoc/function/cleanup.rb

@@ -1,226 +1,232 @@
-module IsoDoc::Function
-  module Cleanup
-    def textcleanup(docxml)
-      termref_cleanup(passthrough_cleanup(docxml))
-    end
+module IsoDoc
+  module Function
+    module Cleanup
+      def textcleanup(docxml)
+        termref_cleanup(passthrough_cleanup(docxml))
+      end
 
-    def termref_cleanup(docxml)
-      docxml
-        .gsub(/\s*\[MODIFICATION\]\s*\[\/TERMREF\]/,
-              l10n(", #{@i18n.modified} [/TERMREF]"))
-        .gsub(%r{\s*\[/TERMREF\]\s*</p>\s*<p>\s*\[TERMREF\]}, "; ")
-        .gsub(/\[TERMREF\]\s*/, l10n("[#{@i18n.source}: "))
-        .gsub(%r{\s*\[/TERMREF\]\s*}, l10n("]"))
-        .gsub(/\s*\[MODIFICATION\]/, l10n(", #{@i18n.modified} &mdash; "))
-    end
+      def termref_cleanup(docxml)
+        docxml
+          .gsub(/\s*\[MODIFICATION\]\s*\[\/TERMREF\]/,
+                l10n(", #{@i18n.modified} [/TERMREF]"))
+          .gsub(%r{\s*\[/TERMREF\]\s*</p>\s*<p>\s*\[TERMREF\]}, "; ")
+          .gsub(/\[TERMREF\]\s*/, l10n("[#{@i18n.source}: "))
+          .gsub(%r{\s*\[/TERMREF\]\s*}, l10n("]"))
+          .gsub(/\s*\[MODIFICATION\]/, l10n(", #{@i18n.modified} &mdash; "))
+      end
 
-    def passthrough_cleanup(docxml)
-      docxml.split(%r{(<passthrough>|</passthrough>)}).each_slice(4).map do |a|
-        a.size > 2 and a[2] = HTMLEntities.new.decode(a[2])
-        [a[0], a[2]]
-      end.join
-    end
+      def passthrough_cleanup(docxml)
+        docxml.split(%r{(<passthrough>|</passthrough>)}).each_slice(4)
+          .map do |a|
+          a.size > 2 and a[2] = HTMLEntities.new.decode(a[2])
+          [a[0], a[2]]
+        end.join
+      end
 
-    def cleanup(docxml)
-      @i18n ||= i18n_init(@lang, @script)
-      comment_cleanup(docxml)
-      footnote_cleanup(docxml)
-      inline_header_cleanup(docxml)
-      figure_cleanup(docxml)
-      table_cleanup(docxml)
-      symbols_cleanup(docxml)
-      example_cleanup(docxml)
-      admonition_cleanup(docxml)
-    end
+      def cleanup(docxml)
+        @i18n ||= i18n_init(@lang, @script)
+        comment_cleanup(docxml)
+        footnote_cleanup(docxml)
+        inline_header_cleanup(docxml)
+        figure_cleanup(docxml)
+        table_cleanup(docxml)
+        symbols_cleanup(docxml)
+        example_cleanup(docxml)
+        admonition_cleanup(docxml)
+      end
 
-    def table_long_strings_cleanup(docxml)
-      return unless @break_up_urls_in_tables == true
+      def table_long_strings_cleanup(docxml)
+        return unless @break_up_urls_in_tables == true
 
-      docxml.xpath("//td | //th").each do |d|
-        d.traverse do |n|
-          next unless n.text?
+        docxml.xpath("//td | //th").each do |d|
+          d.traverse do |n|
+            next unless n.text?
 
-          n.replace(HTMLEntities.new.encode(
-                      break_up_long_strings(n.text),
-                    ))
+            n.replace(HTMLEntities.new.encode(
+                        break_up_long_strings(n.text),
+                      ))
+          end
         end
       end
-    end
 
-    def break_up_long_strings(text)
-      return text if /^\s*$/.match?(text)
+      def break_up_long_strings(text)
+        return text if /^\s*$/.match?(text)
+
+        text.split(/(?=\s)/).map do |w|
+          if /^\s*$/.match(text) || (w.size < 30) then w
+          else
+            w.scan(/.{,30}/).map do |w1|
+              w1.size < 30 ? w1 : break_up_long_strings1(w1)
+            end.join
+          end
+        end.join
+      end
 
-      text.split(/(?=\s)/).map do |w|
-        if /^\s*$/.match(text) || (w.size < 30) then w
+      def break_up_long_strings1(text)
+        s = text.split(%r{(?<=[,.?+;/=])})
+        if s.size == 1 then "#{text} "
         else
-          w.scan(/.{,30}/).map do |w1|
-            w1.size < 30 ? w1 : break_up_long_strings1(w1)
-          end.join
+          s[-1] = " #{s[-1]}"
+          s.join
         end
-      end.join
-    end
-
-    def break_up_long_strings1(text)
-      s = text.split(%r{(?<=[,.?+;/=])})
-      if s.size == 1 then "#{text} "
-      else
-        s[-1] = " #{s[-1]}"
-        s.join
       end
-    end
 
-    def admonition_cleanup(docxml)
-      docxml.xpath("//div[@class = 'Admonition'][title]").each do |d|
-        title = d.at("./title")
-        n = title.next_element
-        n&.children&.first&.add_previous_sibling(title.remove.text + "&mdash;")
+      def admonition_cleanup(docxml)
+        docxml.xpath("//div[@class = 'Admonition'][title]").each do |d|
+          title = d.at("./title")
+          n = title.next_element
+          n&.children&.first
+            &.add_previous_sibling("#{title.remove.text}&mdash;")
+        end
+        docxml
       end
-      docxml
-    end
 
-    def example_cleanup(docxml)
-      docxml.xpath("//table[@class = 'example']//p[not(@class)]").each do |p|
-        p["class"] = "example"
+      def example_cleanup(docxml)
+        docxml.xpath("//table[@class = 'example']//p[not(@class)]").each do |p|
+          p["class"] = "example"
+        end
+        docxml
       end
-      docxml
-    end
 
-    def figure_get_or_make_dl(elem)
-      dl = elem.at(".//dl")
-      if dl.nil?
-        elem.add_child("<p><b>#{@i18n.key}</b></p><dl></dl>")
+      def figure_get_or_make_dl(elem)
         dl = elem.at(".//dl")
+        if dl.nil?
+          elem.add_child("<p><b>#{@i18n.key}</b></p><dl></dl>")
+          dl = elem.at(".//dl")
+        end
+        dl
       end
-      dl
-    end
 
-    FIGURE_WITH_FOOTNOTES =
-      "//div[@class = 'figure'][descendant::aside]"\
-      "[not(descendant::div[@class = 'figure'])]".freeze
-
-    def figure_aside_process(elem, aside, key)
-      # get rid of footnote link, it is in diagram
-      elem&.at("./a[@class='TableFootnoteRef']")&.remove
-      fnref = elem.at(".//span[@class='TableFootnoteRef']/..")
-      dt = key.add_child("<dt></dt>").first
-      dd = key.add_child("<dd></dd>").first
-      fnref.parent = dt
-      aside.xpath(".//p").each do |a|
-        a.delete("class")
-        a.parent = dd
+      FIGURE_WITH_FOOTNOTES =
+        "//div[@class = 'figure'][descendant::aside]"\
+        "[not(descendant::div[@class = 'figure'])]".freeze
+
+      def figure_aside_process(elem, aside, key)
+        # get rid of footnote link, it is in diagram
+        elem&.at("./a[@class='TableFootnoteRef']")&.remove
+        fnref = elem.at(".//span[@class='TableFootnoteRef']/..")
+        dt = key.add_child("<dt></dt>").first
+        dd = key.add_child("<dd></dd>").first
+        fnref.parent = dt
+        aside.xpath(".//p").each do |a|
+          a.delete("class")
+          a.parent = dd
+        end
       end
-    end
 
-    # move footnotes into key, and get rid of footnote reference
-    # since it is in diagram
-    def figure_cleanup(docxml)
-      docxml.xpath(FIGURE_WITH_FOOTNOTES).each do |f|
-        next unless f.at(".//aside[not(ancestor::p[@class = 'FigureTitle'])]")
+      # move footnotes into key, and get rid of footnote reference
+      # since it is in diagram
+      def figure_cleanup(docxml)
+        docxml.xpath(FIGURE_WITH_FOOTNOTES).each do |f|
+          next unless f.at(".//aside[not(ancestor::p[@class = 'FigureTitle'])]")
 
-        key = figure_get_or_make_dl(f)
-        f.xpath(".//aside").each do |aside|
-          figure_aside_process(f, aside, key)
+          key = figure_get_or_make_dl(f)
+          f.xpath(".//aside").each do |aside|
+            figure_aside_process(f, aside, key)
+          end
         end
+        docxml
       end
-      docxml
-    end
 
-    def inline_header_cleanup(docxml)
-      docxml.xpath('//span[@class="zzMoveToFollowing"]').each do |x|
-        x.delete("class")
-        n = x.next_element
-        if n.nil?
-          x.name = "p"
-        else
-          n.children.first.previous = x.remove
+      def inline_header_cleanup(docxml)
+        docxml.xpath('//span[@class="zzMoveToFollowing"]').each do |x|
+          x.delete("class")
+          n = x.next_element
+          if n.nil?
+            x.name = "p"
+          else
+            n.children.first.previous = x.remove
+          end
         end
+        docxml
       end
-      docxml
-    end
 
-    def footnote_cleanup(docxml)
-      docxml.xpath('//a[@class = "FootnoteRef"]/sup').each_with_index do |x, i|
-        x.content = (i + 1).to_s
+      def footnote_cleanup(docxml)
+        docxml.xpath('//a[@class = "FootnoteRef"]/sup')
+          .each_with_index do |x, i|
+          x.content = (i + 1).to_s
+        end
+        docxml
       end
-      docxml
-    end
 
-    def merge_fnref_into_fn_text(elem)
-      fn = elem.at('.//span[@class="TableFootnoteRef"]/..')
-      n = fn.next_element
-      n&.children&.first&.add_previous_sibling(fn.remove)
-    end
+      def merge_fnref_into_fn_text(elem)
+        fn = elem.at('.//span[@class="TableFootnoteRef"]/..')
+        n = fn.next_element
+        n&.children&.first&.add_previous_sibling(fn.remove)
+      end
 
-    # preempt html2doc putting MsoNormal under TableFootnote class
-    def table_footnote_cleanup(docxml)
-      docxml.xpath("//table[descendant::aside]").each do |t|
-        t.xpath(".//aside").each do |a|
-          merge_fnref_into_fn_text(a)
-          a.name = "div"
-          a["class"] = "TableFootnote"
-          t << a.remove
+      # preempt html2doc putting MsoNormal under TableFootnote class
+      def table_footnote_cleanup(docxml)
+        docxml.xpath("//table[descendant::aside]").each do |t|
+          t.xpath(".//aside").each do |a|
+            merge_fnref_into_fn_text(a)
+            a.name = "div"
+            a["class"] = "TableFootnote"
+            t << a.remove
+          end
+        end
+        docxml.xpath("//p[not(self::*[@class])]"\
+                     "[ancestor::*[@class = 'TableFootnote']]").each do |p|
+          p["class"] = "TableFootnote"
         end
       end
-      docxml.xpath("//p[not(self::*[@class])]"\
-                   "[ancestor::*[@class = 'TableFootnote']]").each do |p|
-        p["class"] = "TableFootnote"
-      end
-    end
 
-    def remove_bottom_border(cell)
-      cell["style"] =
-        cell["style"].gsub(/border-bottom:[^;]+;/, "border-bottom:0pt;")
-    end
+      def remove_bottom_border(cell)
+        cell["style"] =
+          cell["style"].gsub(/border-bottom:[^;]+;/, "border-bottom:0pt;")
+      end
 
-    def table_get_or_make_tfoot(table)
-      tfoot = table.at(".//tfoot")
-      if tfoot.nil?
-        table.add_child("<tfoot></tfoot>")
+      def table_get_or_make_tfoot(table)
         tfoot = table.at(".//tfoot")
-      else
-        tfoot.xpath(".//td | .//th").each { |td| remove_bottom_border(td) }
+        if tfoot.nil?
+          table.add_child("<tfoot></tfoot>")
+          tfoot = table.at(".//tfoot")
+        else
+          tfoot.xpath(".//td | .//th").each { |td| remove_bottom_border(td) }
+        end
+        tfoot
       end
-      tfoot
-    end
 
-    def new_fullcolspan_row(table, tfoot)
-      # how many columns in the table?
-      cols = 0
-      table.at(".//tr").xpath("./td | ./th").each do |td|
-        cols += (td["colspan"] ? td["colspan"].to_i : 1)
+      def new_fullcolspan_row(table, tfoot)
+        # how many columns in the table?
+        cols = 0
+        table.at(".//tr").xpath("./td | ./th").each do |td|
+          cols += (td["colspan"] ? td["colspan"].to_i : 1)
+        end
+        style =
+          %{border-top:0pt;border-bottom:#{IsoDoc::Function::Table::SW} 1.5pt;}
+        tfoot.add_child("<tr><td colspan='#{cols}' style='#{style}'/></tr>")
+        tfoot.xpath(".//td").last
       end
-      style =
-        %{border-top:0pt;border-bottom:#{IsoDoc::Function::Table::SW} 1.5pt;}
-      tfoot.add_child("<tr><td colspan='#{cols}' style='#{style}'/></tr>")
-      tfoot.xpath(".//td").last
-    end
 
-    def table_note_cleanup(docxml)
-      docxml.xpath("//table[div[@class = 'Note' or "\
-                   "@class = 'TableFootnote']]").each do |t|
-        tfoot = table_get_or_make_tfoot(t)
-        insert_here = new_fullcolspan_row(t, tfoot)
-        t.xpath("div[@class = 'Note' or @class = 'TableFootnote']").each do |d|
-          d.parent = insert_here
+      def table_note_cleanup(docxml)
+        docxml.xpath("//table[div[@class = 'Note' or "\
+                     "@class = 'TableFootnote']]").each do |t|
+          tfoot = table_get_or_make_tfoot(t)
+          insert_here = new_fullcolspan_row(t, tfoot)
+          t.xpath("div[@class = 'Note' or @class = 'TableFootnote']")
+            .each do |d|
+            d.parent = insert_here
+          end
         end
       end
-    end
 
-    def table_cleanup(docxml)
-      table_footnote_cleanup(docxml)
-      table_note_cleanup(docxml)
-      table_long_strings_cleanup(docxml)
-      docxml
-    end
+      def table_cleanup(docxml)
+        table_footnote_cleanup(docxml)
+        table_note_cleanup(docxml)
+        table_long_strings_cleanup(docxml)
+        docxml
+      end
 
-    def symbols_cleanup(docxml); end
+      def symbols_cleanup(docxml); end
 
-    def table_footnote_reference_format(link)
-      link
-    end
+      def table_footnote_reference_format(link)
+        link
+      end
 
-    def footnote_reference_format(link)
-      link
+      def footnote_reference_format(link)
+        link
+      end
     end
   end
 end

data/lib/isodoc/function/inline.rb

@@ -1,147 +1,149 @@
 require_relative "inline_simple"
 
-module IsoDoc::Function
-  module Inline
-    def link_parse(node, out)
-      url = node["target"]
-      node["updatetype"] == "true" and url = suffix_url(url)
-      out.a **attr_code(href: url, title: node["alt"]) do |l|
-        if node.text.empty?
-          l << node["target"].sub(/^mailto:/, "")
-        else node.children.each { |n| parse(n, l) }
+module IsoDoc
+  module Function
+    module Inline
+      def link_parse(node, out)
+        url = node["target"]
+        node["updatetype"] == "true" and url = suffix_url(url)
+        out.a **attr_code(href: url, title: node["alt"]) do |l|
+          if node.text.empty?
+            l << node["target"].sub(/^mailto:/, "")
+          else node.children.each { |n| parse(n, l) }
+          end
         end
       end
-    end
 
-    def callout_parse(node, out)
-      out << " &lt;#{node.text}&gt;"
-    end
+      def callout_parse(node, out)
+        out << " &lt;#{node.text}&gt;"
+      end
 
-    def no_locality_parse(node, out)
-      node.children.each do |n|
-        parse(n, out) unless %w{locality localityStack}.include? n.name
+      def no_locality_parse(node, out)
+        node.children.each do |n|
+          parse(n, out) unless %w{locality localityStack}.include? n.name
+        end
       end
-    end
 
-    def xref_parse(node, out)
-      target = if /#/.match?(node["target"])
-                 node["target"].sub(/#/, ".html#")
-               else
-                 "##{node['target']}"
-               end
-      out.a(**{ "href": target }) { |l| no_locality_parse(node, l) }
-    end
+      def xref_parse(node, out)
+        target = if /#/.match?(node["target"])
+                   node["target"].sub(/#/, ".html#")
+                 else
+                   "##{node['target']}"
+                 end
+        out.a(**{ href: target }) { |l| no_locality_parse(node, l) }
+      end
 
-    def suffix_url(url)
-      return url if %r{^https?://}.match?(url)
-      return url unless File.extname(url).empty?
+      def suffix_url(url)
+        return url if %r{^https?://}.match?(url)
+        return url unless File.extname(url).empty?
 
-      url.sub(/#{File.extname(url)}$/, ".html")
-    end
+        url.sub(/#{File.extname(url)}$/, ".html")
+      end
 
-    def eref_target(node)
-      href = "##{node['bibitemid']}"
-      url = node.at(ns("//bibitem[@id = '#{node['bibitemid']}']/"\
-                       "uri[@type = 'citation']"))
-      return href unless url
+      def eref_target(node)
+        href = "##{node['bibitemid']}"
+        url = node.at(ns("//bibitem[@id = '#{node['bibitemid']}']/"\
+                         "uri[@type = 'citation']"))
+        return href unless url
 
-      href = suffix_url(url.text)
-      anchor = node&.at(ns(".//locality[@type = 'anchor']"))&.text&.strip
-      anchor and href += "##{anchor}"
-      href
-    end
+        href = suffix_url(url.text)
+        anchor = node&.at(ns(".//locality[@type = 'anchor']"))&.text&.strip
+        anchor and href += "##{anchor}"
+        href
+      end
 
-    def eref_parse(node, out)
-      href = eref_target(node)
-      if node["type"] == "footnote"
-        out.sup do |s|
-          s.a(**{ "href": href }) { |l| no_locality_parse(node, l) }
+      def eref_parse(node, out)
+        href = eref_target(node)
+        if node["type"] == "footnote"
+          out.sup do |s|
+            s.a(**{ href: href }) { |l| no_locality_parse(node, l) }
+          end
+        else
+          out.a(**{ href: href }) { |l| no_locality_parse(node, l) }
         end
-      else
-        out.a(**{ "href": href }) { |l| no_locality_parse(node, l) }
       end
-    end
 
-    def origin_parse(node, out)
-      if t = node.at(ns("./termref"))
-        termrefelem_parse(t, out)
-      else
-        eref_parse(node, out)
+      def origin_parse(node, out)
+        if t = node.at(ns("./termref"))
+          termrefelem_parse(t, out)
+        else
+          eref_parse(node, out)
+        end
       end
-    end
 
-    def termrefelem_parse(node, out)
-      if node.text.strip.empty?
-        out << "Termbase #{node['base']}, term ID #{node['target']}"
-      else
-        node.children.each { |n| parse(n, out) }
+      def termrefelem_parse(node, out)
+        if node.text.strip.empty?
+          out << "Termbase #{node['base']}, term ID #{node['target']}"
+        else
+          node.children.each { |n| parse(n, out) }
+        end
       end
-    end
 
-    def stem_parse(node, out)
-      ooml = case node["type"]
-             when "AsciiMath"
-               "#{@openmathdelim}#{HTMLEntities.new.encode(node.text)}"\
+      def stem_parse(node, out)
+        ooml = case node["type"]
+               when "AsciiMath"
+                 "#{@openmathdelim}#{HTMLEntities.new.encode(node.text)}"\
                  "#{@closemathdelim}"
-             when "MathML" then node.first_element_child.to_s
-             else HTMLEntities.new.encode(node.text)
-             end
-      out.span **{ class: "stem" } do |span|
-        span.parent.add_child ooml
+               when "MathML" then node.first_element_child.to_s
+               else HTMLEntities.new.encode(node.text)
+               end
+        out.span **{ class: "stem" } do |span|
+          span.parent.add_child ooml
+        end
       end
-    end
 
-    def image_title_parse(out, caption)
-      unless caption.nil?
-        out.p **{ class: "FigureTitle", style: "text-align:center;" } do |p|
-          p.b { |b| b << caption.to_s }
+      def image_title_parse(out, caption)
+        unless caption.nil?
+          out.p **{ class: "FigureTitle", style: "text-align:center;" } do |p|
+            p.b { |b| b << caption.to_s }
+          end
         end
       end
-    end
 
-    def image_parse(node, out, caption)
-      attrs = { src: node["src"],
-                height: node["height"] || "auto",
-                width: node["width"] || "auto",
-                title: node["title"],
-                alt: node["alt"] }
-      out.img **attr_code(attrs)
-      image_title_parse(out, caption)
-    end
+      def image_parse(node, out, caption)
+        attrs = { src: node["src"],
+                  height: node["height"] || "auto",
+                  width: node["width"] || "auto",
+                  title: node["title"],
+                  alt: node["alt"] }
+        out.img **attr_code(attrs)
+        image_title_parse(out, caption)
+      end
 
-    def smallcap_parse(node, xml)
-      xml.span **{ style: "font-variant:small-caps;" } do |s|
-        node.children.each { |n| parse(n, s) }
+      def smallcap_parse(node, xml)
+        xml.span **{ style: "font-variant:small-caps;" } do |s|
+          node.children.each { |n| parse(n, s) }
+        end
       end
-    end
 
-    def text_parse(node, out)
-      return if node.nil? || node.text.nil?
+      def text_parse(node, out)
+        return if node.nil? || node.text.nil?
 
-      text = node.to_s
-      if in_sourcecode
-        text = text.gsub("\n", "<br/>").gsub("<br/> ", "<br/>&nbsp;")
-          .gsub(/ (?= )/, "&nbsp;")
+        text = node.to_s
+        if in_sourcecode
+          text = text.gsub("\n", "<br/>").gsub("<br/> ", "<br/>&nbsp;")
+            .gsub(/ (?= )/, "&nbsp;")
+        end
+        out << text
       end
-      out << text
-    end
 
-    def add_parse(node, out)
-      out.span **{ class: "addition" } do |e|
-        node.children.each { |n| parse(n, e) }
+      def add_parse(node, out)
+        out.span **{ class: "addition" } do |e|
+          node.children.each { |n| parse(n, e) }
+        end
       end
-    end
 
-    def del_parse(node, out)
-      out.span **{ class: "deletion" } do |e|
-        node.children.each { |n| parse(n, e) }
+      def del_parse(node, out)
+        out.span **{ class: "deletion" } do |e|
+          node.children.each { |n| parse(n, e) }
+        end
       end
-    end
 
-    def error_parse(node, out)
-      text = node.to_xml.gsub(/</, "&lt;").gsub(/>/, "&gt;")
-      out.para do |p|
-        p.b(**{ role: "strong" }) { |e| e << text }
+      def error_parse(node, out)
+        text = node.to_xml.gsub(/</, "&lt;").gsub(/>/, "&gt;")
+        out.para do |p|
+          p.b(**{ role: "strong" }) { |e| e << text }
+        end
       end
     end
   end