isodoc 3.5.2 → 3.6.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 85c86c0d97a88786700d65fdfedf86b6bc6c838f64e9278149e14686a0c8d96c
-  data.tar.gz: 7673f0d5b22d03588611ddbc60336d8cf516d71abb60c75faf24aa541fbf18e0
+  metadata.gz: a7090dc22f60e48ff426569497b98e6269308ad72b4a7198fbe08ee42a579944
+  data.tar.gz: b5843c03c85e957088107f0a6b30351f67c46117b2bc461c6a95739471077eb3
 SHA512:
-  metadata.gz: 2b5193c40be8084d8ba261719bd1ab184227611feaacdac805ad93349a01c2173a8502439a4a206fbaf805cb57015f23ef5915de9433ab866d2c8ca1489d3a9f
-  data.tar.gz: 83838850dd22316238d0a9c1125fd70f957dea4a361cb55f9697c4580c5c7cad43b1040740111ef710f690854fe180eb057153888e192c912cdfc9dd361b6ebd
+  metadata.gz: d0dac37b3d8c895bd2879f877231604b1ed71a350efc3c45bcc514dab06e3360b8d4c5df044412d90a82984639d02413cb9db15b1e3168e42a28d8a48300f4ab
+  data.tar.gz: 3f83a6ad5fe77b8fd81d644f8edc56a0dd5a9d24c19202a561ece45c7c3d1d2109a6da4e427a45c3a6d22bb36836d248662765775e605f83a84e2e93e4ed47f6

data/Gemfile

@@ -4,6 +4,21 @@ Encoding.default_internal = Encoding::UTF_8
 source "https://rubygems.org"
 git_source(:github) { |repo| "https://github.com/#{repo}" }
 
-gemspec
+gem "benchmark"
+gem "canon"
+gem "debug"
+gem "equivalent-xml", "~> 0.6"
+gem "guard", "~> 2.14"
+gem "guard-rspec", "~> 4.7"
+gem "rake"
+gem "rspec", "~> 3.6"
+gem "rubocop", "~> 1"
+gem "rubocop-performance"
+gem "sassc-embedded", "~> 1"
+gem "simplecov", "~> 0.15"
+gem "timecop", "~> 0.9"
 
 eval_gemfile("Gemfile.devel") rescue nil
+
+gemspec
+

data/isodoc.gemspec

@@ -30,32 +30,18 @@ Gem::Specification.new do |spec|
 
   spec.add_dependency "base64"
   spec.add_dependency "bigdecimal"
-  spec.add_dependency "html2doc", "~> 1.10.0"
+  spec.add_dependency "html2doc", "~> 1.11.0"
   # spec.add_dependency "isodoc-i18n", "~> 1.1.0" # already in relaton-render and mn-requirements
   # spec.add_dependency "relaton-cli"
   # spec.add_dependency "metanorma-utils", "~> 1.5.0" # already in isodoc-i18n
   spec.add_dependency "mn2pdf", ">= 2.13"
   spec.add_dependency "mn-requirements", "~> 0.5.0"
-  spec.add_dependency "rake", "~> 13.0"
-  spec.add_dependency "relaton-render", "~> 1.1.0"
+  spec.add_dependency "relaton-render", "~> 1.2.0"
   spec.add_dependency "roman-numerals"
   spec.add_dependency "rouge", "~> 4.0"
   spec.add_dependency "thread_safe"
   spec.add_dependency "twitter_cldr", ">= 6.6.0"
   spec.add_dependency "uuidtools"
 
-  spec.add_development_dependency "benchmark"
-  spec.add_development_dependency "bigdecimal"
-  spec.add_development_dependency "canon", "= 0.2.3"
-  spec.add_development_dependency "debug"
-  spec.add_development_dependency "equivalent-xml", "~> 0.6"
-  spec.add_development_dependency "guard", "~> 2.14"
-  spec.add_development_dependency "guard-rspec", "~> 4.7"
-  spec.add_development_dependency "rspec", "~> 3.6"
-  spec.add_development_dependency "rubocop", "~> 1"
-  spec.add_development_dependency "rubocop-performance"
-  spec.add_development_dependency "sassc-embedded", "~> 1"
-  spec.add_development_dependency "simplecov", "~> 0.15"
-  spec.add_development_dependency "timecop", "~> 0.9"
   # spec.metadata["rubygems_mfa_required"] = "true"
 end

data/lib/isodoc/function/cleanup.rb

@@ -60,17 +60,17 @@ module IsoDoc
       def merge_fnref_into_fn_text(elem)
         fn = elem.at('.//span[@class="TableFootnoteRef"]/..') or return
         n = fn.next_element
-        n&.children&.first&.add_previous_sibling(fn.remove)
+        n or return
+        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|
+        docxml.xpath("//tfoot[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 # this is redundant
           end
         end
         table_footnote_cleanup_propagate(docxml)
@@ -83,55 +83,8 @@ module IsoDoc
         end
       end
 
-      def remove_bottom_border(cell)
-        # [^;]* (not +): the preceding property name is the unambiguous
-        # delimiter, so zero-or-more is equivalent and avoids polynomial
-        # backtracking on the value portion.
-        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>")
-          tfoot = table.at(".//tfoot")
-        else
-          tfoot.xpath(".//td | .//th").each { |td| remove_bottom_border(td) }
-        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)
-        end
-        table["class"].nil? or # = plain table
-          s = "style='border-top:0pt;border-bottom:#{IsoDoc::Function::Table::SW} 1.5pt;'"
-        tfoot.add_child("<tr><td colspan='#{cols}' #{s}/></tr>")
-        tfoot.xpath(".//td").last
-      end
-
-      TABLENOTE_CSS = "div[@class = 'Note' or @class = 'BlockSource' " \
-                      "or @class = 'TableFootnote' or @class = 'figdl' or @class = 'key']"
-        .freeze
-
-      def table_note_cleanup(docxml)
-        docxml.xpath("//table[dl or #{TABLENOTE_CSS}]").each do |t|
-          tfoot = table_get_or_make_tfoot(t)
-          insert_here = new_fullcolspan_row(t, tfoot)
-          t.xpath("dl | p[@class = 'ListTitle'] | #{TABLENOTE_CSS}")
-            .each do |d|
-            d.parent = insert_here
-          end
-        end
-      end
-
       def table_cleanup(docxml)
         table_footnote_cleanup(docxml)
-        table_note_cleanup(docxml)
         docxml
       end
 
@@ -141,9 +94,10 @@ module IsoDoc
       # characters. Quoted alternatives listed first so `/` inside
       # attribute values (e.g. URLs in href="...") is consumed as part
       # of the quoted string, not rejected by [^>/].
+      # Includes Word HTML tags
       def empty_tags(html)
         void_elements = %w[area base br col embed hr img input link meta
-                           source track wbr]
+                           source track wbr wrapblock]
         html.gsub(%r{<([\w:]+)((?>"[^"]*"|'[^']*'|[^>/])*)\s*/>}) do
           if void_elements.include?($1)
             $&

data/lib/isodoc/function/table.rb

@@ -89,12 +89,26 @@ module IsoDoc
         @in_table = false
       end
 
+      def table_parse_tail_elems
+        ["./key", "./fmt-source", "./note",
+         "./fmt-footnote-container/fmt-fn-body"]
+      end
+
       def table_parse_tail(node, out)
-        (dl = node.at(ns("./key"))) && parse(dl, out)
-        node.xpath(ns("./fmt-source")).each { |n| parse(n, out) }
-        node.xpath(ns("./note")).each { |n| parse(n, out) }
-        node.xpath(ns("./fmt-footnote-container/fmt-fn-body"))
-          .each { |n| parse(n, out) }
+        table_parse_tail?(node) or return
+        tfoot = table_get_or_make_tfoot(out.parent)
+        ins = new_fullcolspan_row(out.parent, tfoot)
+        b = Nokogiri::XML::Builder.with(ins)
+        table_parse_tail_elems.each do |k|
+          node.xpath(ns(k)).each { |n| parse(n, b) }
+        end
+      end
+
+      def table_parse_tail?(node)
+        table_parse_tail_elems.each do |k|
+          !node.xpath(ns(k)).empty? and return true
+        end
+        false
       end
 
       def table_parse_core(node, out)
@@ -139,16 +153,47 @@ module IsoDoc
       end
 
       def tr_parse(node, out, ord, totalrows, header)
-        bordered = table_bordered?(node)
         out.tr(**attr_code(style: node["style"])) do |r|
           node.elements.each do |td|
-            attrs = make_tr_attr(td, ord, totalrows - 1, header, bordered)
+            attrs = make_tr_attr(td, ord, totalrows - 1, header,
+                                 table_bordered?(node))
             r.send td.name, **attr_code(attrs) do |entry|
               td.children.each { |n| parse(n, entry) }
             end
           end
         end
       end
+
+      def remove_bottom_border(cell)
+        # [^;]* (not +): the preceding property name is the unambiguous
+        # delimiter, so zero-or-more is equivalent and avoids polynomial
+        # backtracking on the value portion.
+        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>")
+          tfoot = table.at(".//tfoot")
+        else
+          tfoot.xpath(".//td | .//th").each { |td| remove_bottom_border(td) }
+        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)
+        end
+        table["class"].nil? or # = plain table
+          s = "style='border-top:0pt;border-bottom:#{SW} 1.5pt;'"
+        tfoot.add_child("<tr><td colspan='#{cols}' #{s}/></tr>")
+        tfoot.xpath(".//td").last
+      end
     end
   end
 end

data/lib/isodoc/metadata.rb

@@ -116,7 +116,7 @@ module IsoDoc
       return "" unless draft
 
       draftinfo = " (#{@labels['draft_label']} <esc>#{draft}</esc>"
-      draftinfo += ", #{revdate}" if revdate
+      draftinfo += ", #{revdate}" if revdate && revdate != draft
       draftinfo += ")"
       l10n(draftinfo, @lang, @script)
     end
@@ -126,8 +126,8 @@ module IsoDoc
       set(:edition_display,
           isoxml.at(ns("//bibdata/edition#{currlang}"))&.text)
       set(:docyear, isoxml.at(ns("//bibdata/copyright/from"))&.text)
-      set(:draft, isoxml.at(ns("//bibdata/version/draft"))&.text)
-      revdate = isoxml.at(ns("//bibdata/version/revision-date"))&.text
+      set(:draft, isoxml.at(ns("//bibdata/version"))&.text)
+      revdate = isoxml.at(ns("//bibdata/date[@type='updated']/on"))&.text
       set(:revdate, revdate)
       set(:revdate_monthyear, monthyr(revdate))
       set(:draftinfo,

data/lib/isodoc/metadata_date.rb

@@ -42,7 +42,7 @@ module IsoDoc
 
     def bibdate(isoxml, _out)
       isoxml.xpath(ns("//bibdata/date")).each do |d|
-        set("#{d['type'].tr('-', '_')}date".to_sym, Common::date_range(d))
+        set(:"#{d['type'].tr('-', '_')}date", Common::date_range(d))
       end
     end
   end

data/lib/isodoc/spec_helpers/canon_html_input_guard.rb

@@ -0,0 +1,93 @@
+# frozen_string_literal: true
+
+require "canon"
+
+# Guard against leading "<?xml ?>" processing instructions in HTML
+# input strings passed to Canon's be_html_equivalent_to /
+# be_html4_equivalent_to / be_html5_equivalent_to matchers.
+#
+# WHY: Nokogiri::HTML5.fragment parses a leading "<?xml ?>" as a bogus
+# Nokogiri::XML::Comment at index 0 of the fragment.  In Canon's
+# verbose mode (used by the matchers) comments are intentionally not
+# filtered, so the bogus comment shifts fragment child indices and
+# causes Canon's diff report to blame elements at the tail of the
+# document for an offence at the head — an "uninterpretable report"
+# remote from the actual cause.  Canon's maintainer has chosen not to
+# normalise this at the input boundary (closed PR lutaml/canon#124);
+# this guard is the local defence.
+#
+# WHEN: required for the side effect.  Requiring this file installs a
+# Module#prepend on Canon::RSpecMatchers::SerializationMatcher's
+# matches? method that raises IsoDoc::SpecHelpers::CanonGuardError if
+# either side of an HTML-format comparison begins with an XML PI.
+#
+# REUSE: downstream gems that build on isodoc's spec idioms (metanorma
+# family, mn2pdf, etc.) can opt in by adding a single line to their
+# own spec_helper:
+#
+#   require "isodoc/spec_helpers/canon_html_input_guard"
+#
+# No further setup is needed — the module installs on require.
+
+module IsoDoc
+  module SpecHelpers
+    class CanonGuardError < StandardError; end
+
+    # Prepended onto Canon::RSpecMatchers::SerializationMatcher to
+    # intercept matches? before Canon's own implementation runs.
+    module CanonHtmlInputGuard
+      ILLEGAL_HTML_PREFIX = /\A\s*<\?xml\b/i.freeze
+
+      def matches?(target)
+        if html_format? &&
+            (illegal_prefix?(@expected) || illegal_prefix?(target))
+          side = illegal_prefix?(@expected) ? "expected" : "received"
+          raise CanonGuardError, build_message(side)
+        end
+        super
+      end
+
+      private
+
+      def html_format?
+        %i[html html4 html5].include?(@format)
+      end
+
+      def illegal_prefix?(value)
+        value.is_a?(String) && value.match?(ILLEGAL_HTML_PREFIX)
+      end
+
+      def matcher_label
+        case @format
+        when :html4 then "be_html4_equivalent_to"
+        when :html5 then "be_html5_equivalent_to"
+        else "be_html_equivalent_to"
+        end
+      end
+
+      def build_message(side)
+        <<~MSG
+          #{matcher_label}: the #{side} side begins with an XML
+          processing instruction (<?xml ?>).
+
+          Nokogiri::HTML5.fragment parses this as a bogus comment node,
+          which shifts fragment child indices and causes Canon's diff
+          report to blame elements remote from the actual offending
+          node.
+
+          Strip the PI before comparing — e.g. use
+          Nokogiri::HTML(...).to_xhtml in place of
+          Nokogiri::XML(...).to_xml, or sub it away explicitly.
+
+          This guard is enforced by
+          isodoc/spec_helpers/canon_html_input_guard because Canon
+          does not surface this condition (see closed PR
+          lutaml/canon#124).
+        MSG
+      end
+    end
+  end
+end
+
+Canon::RSpecMatchers::SerializationMatcher
+  .prepend(IsoDoc::SpecHelpers::CanonHtmlInputGuard)

data/lib/isodoc/version.rb

@@ -1,3 +1,3 @@
 module IsoDoc
-  VERSION = "3.5.2".freeze
+  VERSION = "3.6.0".freeze
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: isodoc
 version: !ruby/object:Gem::Version
-  version: 3.5.2
+  version: 3.6.0
 platform: ruby
 authors:
 - Ribose Inc.
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2026-04-27 00:00:00.000000000 Z
+date: 2026-05-11 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: base64
@@ -44,14 +44,14 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 1.10.0
+        version: 1.11.0
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 1.10.0
+        version: 1.11.0
 - !ruby/object:Gem::Dependency
   name: mn2pdf
   requirement: !ruby/object:Gem::Requirement
@@ -80,34 +80,20 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: 0.5.0
-- !ruby/object:Gem::Dependency
-  name: rake
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '13.0'
-  type: :runtime
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '13.0'
 - !ruby/object:Gem::Dependency
   name: relaton-render
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 1.1.0
+        version: 1.2.0
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 1.1.0
+        version: 1.2.0
 - !ruby/object:Gem::Dependency
   name: roman-numerals
   requirement: !ruby/object:Gem::Requirement
@@ -178,188 +164,6 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
-- !ruby/object:Gem::Dependency
-  name: benchmark
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-- !ruby/object:Gem::Dependency
-  name: bigdecimal
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-- !ruby/object:Gem::Dependency
-  name: canon
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - '='
-      - !ruby/object:Gem::Version
-        version: 0.2.3
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - '='
-      - !ruby/object:Gem::Version
-        version: 0.2.3
-- !ruby/object:Gem::Dependency
-  name: debug
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-- !ruby/object:Gem::Dependency
-  name: equivalent-xml
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '0.6'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '0.6'
-- !ruby/object:Gem::Dependency
-  name: guard
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '2.14'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '2.14'
-- !ruby/object:Gem::Dependency
-  name: guard-rspec
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '4.7'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '4.7'
-- !ruby/object:Gem::Dependency
-  name: rspec
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '3.6'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '3.6'
-- !ruby/object:Gem::Dependency
-  name: rubocop
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '1'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '1'
-- !ruby/object:Gem::Dependency
-  name: rubocop-performance
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-- !ruby/object:Gem::Dependency
-  name: sassc-embedded
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '1'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '1'
-- !ruby/object:Gem::Dependency
-  name: simplecov
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '0.15'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '0.15'
-- !ruby/object:Gem::Dependency
-  name: timecop
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '0.9'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '0.9'
 description: |
   isodoc converts documents in the IsoDoc document model into
   Microsoft Word and HTML.
@@ -482,6 +286,7 @@ files:
 - lib/isodoc/presentation_function/xrefs.rb
 - lib/isodoc/presentation_xml_convert.rb
 - lib/isodoc/sassc_importer.rb
+- lib/isodoc/spec_helpers/canon_html_input_guard.rb
 - lib/isodoc/version.rb
 - lib/isodoc/word_convert.rb
 - lib/isodoc/word_function.rb