RubyGems - isodoc - Versions diffs - 1.2.8 → 1.4.2 - Mend

isodoc 1.2.8 → 1.4.2

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (47) hide show

checksums.yaml +4 -4
data/.github/workflows/rake.yml +15 -1
data/isodoc.gemspec +1 -1
data/lib/isodoc-yaml/i18n-en.yaml +55 -0
data/lib/isodoc-yaml/i18n-fr.yaml +56 -0
data/lib/isodoc/base_style/blocks.scss +2 -2
data/lib/isodoc/base_style/typography.scss +1 -1
data/lib/isodoc/convert.rb +13 -85
data/lib/isodoc/css.rb +95 -0
data/lib/isodoc/function/inline_simple.rb +10 -1
data/lib/isodoc/function/lists.rb +2 -1
data/lib/isodoc/function/references.rb +7 -12
data/lib/isodoc/function/section.rb +1 -1
data/lib/isodoc/function/table.rb +10 -0
data/lib/isodoc/function/to_word_html.rb +4 -2
data/lib/isodoc/function/utils.rb +2 -2
data/lib/isodoc/gem_tasks.rb +4 -0
data/lib/isodoc/html_function/html.rb +7 -0
data/lib/isodoc/html_function/mathvariant_to_plain.rb +82 -0
data/lib/isodoc/html_function/postprocess.rb +43 -22
data/lib/isodoc/metadata_contributor.rb +4 -3
data/lib/isodoc/presentation_function/bibdata.rb +3 -3
data/lib/isodoc/presentation_function/inline.rb +5 -3
data/lib/isodoc/presentation_function/section.rb +9 -0
data/lib/isodoc/presentation_xml_convert.rb +2 -0
data/lib/isodoc/version.rb +1 -1
data/lib/isodoc/word_convert.rb +0 -20
data/lib/isodoc/word_function/inline.rb +2 -2
data/lib/isodoc/word_function/postprocess.rb +38 -80
data/lib/isodoc/word_function/postprocess_cover.rb +55 -0
data/lib/isodoc/word_function/table.rb +10 -0
data/lib/isodoc/xref.rb +1 -0
data/lib/isodoc/xref/xref_counter.rb +63 -20
data/lib/isodoc/xref/xref_gen.rb +20 -2
data/lib/isodoc/xref/xref_sect_gen.rb +34 -27
data/spec/assets/html.scss +14 -0
data/spec/isodoc/blocks_spec.rb +26 -73
data/spec/isodoc/cleanup_spec.rb +0 -1
data/spec/isodoc/inline_spec.rb +14 -14
data/spec/isodoc/lists_spec.rb +1 -1
data/spec/isodoc/metadata_spec.rb +3 -1
data/spec/isodoc/postproc_spec.rb +473 -11
data/spec/isodoc/presentation_xml_spec.rb +2 -2
data/spec/isodoc/ref_spec.rb +323 -5
data/spec/isodoc/table_spec.rb +28 -0
data/spec/isodoc/xref_spec.rb +472 -19
metadata +6 -4

data/lib/isodoc/presentation_function/inline.rb CHANGED

@@ -164,14 +164,16 @@ module IsoDoc
     def localize_maths(f, locale)
       f.xpath(".//m:mn", MATHML).each do |x|
         num = /\./.match(x.text) ? x.text.to_f : x.text.to_i
-        x.children = localized_number(num, locale)
+        precision = /\./.match(x.text) ? x.text.sub(/^.*\./, "").size : 0
+        x.children = localized_number(num, locale, precision)
       end
     end
     # By itself twiiter cldr does not support fraction part digits grouping
     # and custom delimeter, will decorate fraction part manually
-    def localized_number(num, locale)
-      localized = num.localize(locale).to_s
+    def localized_number(num, locale, precision)
+      localized = precision == 0 ? num.localize(locale).to_s :
+        num.localize(locale).to_decimal.to_s(:precision => 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])

data/lib/isodoc/presentation_function/section.rb CHANGED

@@ -42,5 +42,14 @@ module IsoDoc
       lbl = @xrefs.get[f["id"]][:label] or return
       prefix_name(f, "", "#{lbl}#{clausedelim}", "name")
     end
+    def references(docxml)
+    end
+    def index(docxml)
+      docxml.xpath(ns("//index | //index-xref")).each do |f|
+        f.remove
+      end
+    end
   end
 end

data/lib/isodoc/presentation_xml_convert.rb CHANGED

@@ -30,6 +30,8 @@ module IsoDoc
       clause docxml
       annex docxml
       term docxml
+      references docxml
+      index docxml
     end
     def block(docxml)

data/lib/isodoc/version.rb CHANGED

@@ -1,3 +1,3 @@
 module IsoDoc
-  VERSION = "1.2.8".freeze
+  VERSION = "1.4.2".freeze
 end

data/lib/isodoc/word_convert.rb CHANGED

@@ -4,26 +4,6 @@ require_relative "word_function/body.rb"
 require_relative "word_function/postprocess.rb"
 module IsoDoc
-=begin
-  module WordConvertModule
-    # http://tech.tulentsev.com/2012/02/ruby-how-to-override-class-method-with-a-module/
-    # https://www.ruby-forum.com/topic/148303
-    #
-    # The following is ugly indeed, but the only way I can split module override methods
-    # across files
-    def self.included base
-      base.class_eval do
-        eval File.open(File.join(File.dirname(__FILE__),"wordconvertmodule.rb")).read
-        eval File.open(File.join(File.dirname(__FILE__),"comments.rb")).read
-        eval File.open(File.join(File.dirname(__FILE__),"footnotes.rb")).read
-        eval File.open(File.join(File.dirname(__FILE__),"postprocess.rb")).read
-      end
-    end
-  end
-=end
   class WordConvert < ::IsoDoc::Convert
     include WordFunction::Comments
     include WordFunction::Footnotes

data/lib/isodoc/word_function/inline.rb CHANGED

@@ -24,7 +24,7 @@ module IsoDoc::WordFunction
     def imgsrc(node)
       ret = svg_to_emf(node) and return ret
-      return node["src"] unless %r{^data:image/}.match node["src"]
+      return node["src"] unless %r{^data:}.match node["src"]
       save_dataimage(node["src"])
     end
@@ -45,7 +45,7 @@ module IsoDoc::WordFunction
     def svg_to_emf(node)
       return unless node["mimetype"] == "image/svg+xml"
       uri = node["src"]
-      %r{^data:image/}.match(uri) and uri = save_dataimage(uri)
+      %r{^data:}.match(uri) and uri = save_dataimage(uri)
       ret = svg_to_emf_filename(uri)
       File.exists?(ret) and return ret
       exe = inkscape_installed? or return nil

data/lib/isodoc/word_function/postprocess.rb CHANGED

@@ -5,11 +5,9 @@ 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">
+    <!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: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>
@@ -18,15 +16,13 @@ xmlns:m="http://schemas.microsoft.com/office/2004/12/omml">
     def to_word_xhtml_fragment(xml)
       doc = ::Nokogiri::XML.parse(WORD_NOKOHEAD)
-      fragment = ::Nokogiri::XML::DocumentFragment.new(doc, xml, doc.root)
-      fragment
+      ::Nokogiri::XML::DocumentFragment.new(doc, xml, doc.root)
     end
     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
@@ -56,8 +52,7 @@ 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
@@ -65,6 +60,7 @@ xmlns:m="http://schemas.microsoft.com/office/2004/12/omml">
       word_annex_cleanup(docxml)
       word_preface(docxml)
       word_nested_tables(docxml)
+      word_colgroup(docxml)
       word_table_align(docxml)
       word_table_separator(docxml)
       word_admonition_images(docxml)
@@ -78,28 +74,44 @@ xmlns:m="http://schemas.microsoft.com/office/2004/12/omml">
       docxml
     end
-    def word_nested_tables(docxml)
-      docxml.xpath("//table").each do |t|
-        t.xpath(".//table").reverse.each do |tt|
-          t.next = tt.remove
+    def word_colgroup(docxml)
+      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 do |tr, r|
+          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
+            end
+            for y2 in r..(r + rs - 1)
+              for x2 in x..(x + cs - 1)
+                cells2d[y2][x2] = 1
+              end
+            end
+            width = (x..(x+cs-1)).each_with_object({width: 0}) { |z, m| m[:width] += w[z] }
+            td["width"] = "#{width[:width]}%"
+            x += cs
+          end
         end
       end
     end
-    def authority_cleanup1(docxml, klass)
-      dest = docxml.at("//div[@id = 'boilerplate-#{klass}-destination']")
-      auth = docxml.at("//div[@id = 'boilerplate-#{klass}' or @class = 'boilerplate-#{klass}']")
-      auth&.xpath(".//h1[not(text())] | .//h2[not(text())]")&.each { |h| h.remove }
-      auth&.xpath(".//h1 | .//h2")&.each do |h|
-        h.name = "p"
-        h["class"] = "TitlePageSubhead"
+    # assume percentages
+    def colgroup_widths(t)
+      t.xpath("./colgroup/col").each_with_object([]) do |c, m|
+        m << c["width"].sub(/%$/, "").to_f
       end
-      dest and auth and dest.replace(auth.remove)
     end
-    def authority_cleanup(docxml)
-      %w(copyright license legal feedback).each do |t|
-        authority_cleanup1(docxml, t)
+    def word_nested_tables(docxml)
+      docxml.xpath("//table").each do |t|
+        t.xpath(".//table").reverse.each do |tt|
+          t.next = tt.remove
+        end
       end
     end
@@ -144,19 +156,6 @@ xmlns:m="http://schemas.microsoft.com/office/2004/12/omml">
       end
     end
-=begin
-    EMPTY_PARA = "<p style='margin-top:0cm;margin-right:0cm;"\
-      "margin-bottom:0cm;margin-left:0.0pt;margin-bottom:.0001pt;"\
-      "line-height:1.0pt;mso-line-height-rule:exactly'>"\
-      "<span lang=EN-GB style='display:none;mso-hide:all'>&nbsp;</span></p>"
-    def table_after_table(docxml)
-     docxml.xpath("//table[following-sibling::*[1]/self::table]").each do |t|
-        t.add_next_sibling(EMPTY_PARA)
-      end
-    end
-=end
     def word_table_separator(docxml)
       docxml.xpath("//p[@class = 'TableTitle']").each do |t|
         next unless t.children.empty?
@@ -180,46 +179,6 @@ xmlns:m="http://schemas.microsoft.com/office/2004/12/omml">
       end
     end
-    def generate_header(filename, _dir)
-      return nil unless @header
-      template = IsoDoc::Common.liquid(File.read(@header, encoding: "UTF-8"))
-      meta = @meta.get.merge(@labels || {}).merge(@meta.labels || {})
-      meta[:filename] = filename
-      params = meta.map { |k, v| [k.to_s, v] }.to_h
-      Tempfile.open(%w(header html), :encoding => "utf-8") do |f|
-        f.write(template.render(params))
-        f
-      end
-    end
-    def word_section_breaks(docxml)
-      @landscapestyle = ""
-      word_section_breaks1(docxml, "WordSection2")
-      word_section_breaks1(docxml, "WordSection3")
-      word_remove_pb_before_annex(docxml)
-      docxml.xpath("//br[@orientation]").each { |br| br.delete("orientation") }
-    end
-    def word_section_breaks1(docxml, sect)
-      docxml.xpath("//div[@class = '#{sect}']//br[@orientation]").reverse.
-        each_with_index do |br, i|
-        @landscapestyle += "\ndiv.#{sect}_#{i} {page:#{sect}"\
-          "#{br["orientation"] == "landscape" ? "L" : "P"};}\n"
-        split_at_section_break(docxml, sect, br, i)
-      end
-    end
-    def split_at_section_break(docxml, sect, br, i)
-      move = br.parent.xpath("following::node()") &
-        br.document.xpath("//div[@class = '#{sect}']//*")
-      ins = docxml.at("//div[@class = '#{sect}']").
-        after("<div class='#{sect}_#{i}'/>").next_element
-      move.each do |m|
-        next if m.at("./ancestor::div[@class = '#{sect}_#{i}']")
-        ins << m.remove
-      end
-    end
     # applies for <div class="WordSectionN_M"><p><pagebreak/></p>...
     def word_remove_pb_before_annex(docxml)
       docxml.xpath("//div[p/br]").each do |d|
@@ -237,8 +196,7 @@ xmlns:m="http://schemas.microsoft.com/office/2004/12/omml">
       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

data/lib/isodoc/word_function/postprocess_cover.rb CHANGED

@@ -75,5 +75,60 @@ module IsoDoc::WordFunction
       toc.sub(/(<p class="MsoToc1">)/,
               %{\\1#{word_toc_preface(level)}}) +  WORD_TOC_SUFFIX1
     end
+    def authority_cleanup1(docxml, klass)
+      dest = docxml.at("//div[@id = 'boilerplate-#{klass}-destination']")
+      auth = docxml.at("//div[@id = 'boilerplate-#{klass}' or @class = 'boilerplate-#{klass}']")
+      auth&.xpath(".//h1[not(text())] | .//h2[not(text())]")&.each { |h| h.remove }
+      auth&.xpath(".//h1 | .//h2")&.each do |h|
+        h.name = "p"
+        h["class"] = "TitlePageSubhead"
+      end
+      dest and auth and dest.replace(auth.remove)
+    end
+    def authority_cleanup(docxml)
+      %w(copyright license legal feedback).each do |t|
+        authority_cleanup1(docxml, t)
+      end
+    end
+    def generate_header(filename, _dir)
+      return nil unless @header
+      template = IsoDoc::Common.liquid(File.read(@header, encoding: "UTF-8"))
+      meta = @meta.get.merge(@labels || {}).merge(@meta.labels || {})
+      meta[:filename] = filename
+      params = meta.map { |k, v| [k.to_s, v] }.to_h
+      Tempfile.open(%w(header html), :encoding => "utf-8") do |f|
+        f.write(template.render(params))
+        f
+      end
+    end
+    def word_section_breaks(docxml)
+      @landscapestyle = ""
+      word_section_breaks1(docxml, "WordSection2")
+      word_section_breaks1(docxml, "WordSection3")
+      word_remove_pb_before_annex(docxml)
+      docxml.xpath("//br[@orientation]").each { |br| br.delete("orientation") }
+    end
+    def word_section_breaks1(docxml, sect)
+      docxml.xpath("//div[@class = '#{sect}']//br[@orientation]").reverse.
+        each_with_index do |br, i|
+        @landscapestyle += "\ndiv.#{sect}_#{i} {page:#{sect}#{br["orientation"] == "landscape" ? "L" : "P"};}\n"
+        split_at_section_break(docxml, sect, br, i)
+      end
+    end
+    def split_at_section_break(docxml, sect, br, i)
+      move = br.parent.xpath("following::node()") &
+        br.document.xpath("//div[@class = '#{sect}']//*")
+      ins = docxml.at("//div[@class = '#{sect}']").after("<div class='#{sect}_#{i}'/>").next_element
+      move.each do |m|
+        next if m.at("./ancestor::div[@class = '#{sect}_#{i}']")
+        ins << m.remove
+      end
+    end
   end
 end

data/lib/isodoc/word_function/table.rb CHANGED

@@ -43,11 +43,21 @@ module IsoDoc::WordFunction
       }))
     end
+    def colgroup(node, t)
+      colgroup = node.at(ns("./colgroup")) or return
+      t.colgroup do |cg|
+        colgroup.xpath(ns("./col")).each do |c|
+          cg.col **{ width: c["width"] }
+        end
+      end
+    end
     def table_parse(node, out)
       @in_table = true
       table_title_parse(node, out)
       out.div **{ align: "center", class: "table_container" } do |div|
         div.table **table_attrs(node) do |t|
+          colgroup(node, t)
           thead_parse(node, t)
           tbody_parse(node, t)
           tfoot_parse(node, t)

data/lib/isodoc/xref.rb CHANGED

@@ -49,6 +49,7 @@ module IsoDoc
       note_anchor_names(docxml.xpath(ns(SECTIONS_XPATH)))
       example_anchor_names(docxml.xpath(ns(SECTIONS_XPATH)))
       list_anchor_names(docxml.xpath(ns(SECTIONS_XPATH)))
+      bookmark_anchor_names(docxml.xpath(ns(SECTIONS_XPATH)))
     end
     def ns(xpath)

data/lib/isodoc/xref/xref_counter.rb CHANGED

@@ -2,41 +2,56 @@ require "roman-numerals"
 module IsoDoc::XrefGen
   class Counter
-    def initialize
-      @num = 0
+    def initialize(num = 0, opts = {numerals: :arabic})
+      @num = num
       @letter = ""
       @subseq = ""
       @letter_override = nil
       @number_override = nil
+      @style = opts[:numerals]
       @base = ""
+      if num.is_a? String
+        if /^\d+$/.match(num)
+          @num = num.to_i
+        else
+          @num = nil
+          @base = num[0..-2]
+          @letter = num[-1]
+        end
+      end
     end
     def new_subseq_increment(node)
       @subseq = node["subsequence"]
-      @num += 1
+      @num += 1 unless @num.nil?
       @letter = node["subsequence"] ? "a" : ""
       @base = ""
       if node["number"]
-        /^(?<b>.*?)(?<n>\d*)(?<a>[a-z]*)$/ =~ node["number"]
+        /^(?<b>.*?)(?<n>\d*)(?<a>[a-zA-Z]*)$/ =~ node["number"]
         if !n.empty? || !a.empty?
           @letter_override = @letter = a unless a.empty?
           @number_override = @num = n.to_i unless n.empty?
           @base = b
         else
           @letter_override = node["number"]
-          @letter = @letter_override if /^[a-z]$/.match(@letter_override)
+          @letter = @letter_override if /^[a-zA-Z]$/.match(@letter_override)
         end
       end
     end
     def sequence_increment(node)
       if node["number"]
-        @base = ""
-        @number_override = node["number"]
+        @base = @letter_override = @number_override = ""
         /^(?<b>.*?)(?<n>\d+)$/ =~ node["number"]
-        unless n.nil? || n.empty?
+        if blank?(n)
+          @num = nil
+          @base = node["number"][0..-2]
+          @letter = @letter_override = node["number"][-1]
+        else
+          @number_override = node["number"]
           @num = n.to_i
           @base = b
+          @letter = ""
         end
       else
         @num += 1
@@ -47,9 +62,20 @@ module IsoDoc::XrefGen
       if node["number"]
         @base = ""
         @letter_override = node["number"]
-        /^(?<b>.*?)(?<n>\d*)(?<a>[a-z]+)$/ =~ node["number"]
-        unless a.empty?
-          @letter = a
+        /^(?<b>.*?)(?<n>\d*)(?<a>[a-zA-Z])$/ =~ node["number"]
+        if blank?(a)
+          if /^\d+$/.match(node["number"])
+            @letter_override = @letter = ""
+            @number_override = @num = node["number"].to_i
+          else
+            /^(?<b>.*)(?<a>[a-zA-Z])$/ =~ node["number"]
+            unless blank?(a)
+              @letter = @letter_override = a
+              @base = b
+            end
+          end
+        else
+          @letter_override = @letter = a
           @base = b
           @number_override = @num = n.to_i unless n.empty?
         end
@@ -58,11 +84,15 @@ module IsoDoc::XrefGen
       end
     end
+    def blank?(x)
+      x.nil? || x.empty?
+    end
     def increment(node)
       return self if node["unnumbered"]
       @letter_override = nil
       @number_override = nil
-      if node["subsequence"] != @subseq
+      if node["subsequence"] != @subseq && !(blank?(node["subsequence"]) && blank?(@subseq))
         new_subseq_increment(node)
       elsif @letter.empty?
         sequence_increment(node)
@@ -73,16 +103,29 @@ module IsoDoc::XrefGen
     end
     def print
-      "#{@base}#{@number_override || @num}#{@letter_override || @letter}"
+      num = @number_override || @num
+      num_out = @style == :roman && !num.nil? ? RomanNumerals.to_roman(num) : num
+      "#{@base}#{num_out}#{@letter_override || @letter}"
     end
-    def listlabel(depth)
-      return @num.to_s if [2, 7].include? depth
-      return (96 + @num).chr.to_s if [1, 6].include? depth
-      return (64 + @num).chr.to_s if [4, 9].include? depth
-      return RomanNumerals.to_roman(@num).downcase if [3, 8].include? depth
-      return RomanNumerals.to_roman(@num).upcase if [5, 10].include? depth
-      return @num.to_s
+    def ol_type(list, depth)
+      return list["type"].to_sym if list["type"]
+      return :arabic if [2, 7].include? depth
+      return :alphabet if [1, 6].include? depth
+      return :alphabet_upper if [4, 9].include? depth
+      return :roman if [3, 8].include? depth
+      return :roman_upper if [5, 10].include? depth
+      return :arabic
+    end
+    def listlabel(list, depth)
+      case ol_type(list, depth)
+      when :arabic then @num.to_s
+      when :alphabet then (96 + @num).chr.to_s
+      when :alphabet_upper then (64 + @num).chr.to_s
+      when :roman then RomanNumerals.to_roman(@num).downcase
+      when :roman_upper then RomanNumerals.to_roman(@num).upcase
+      end
     end
   end
 end