Fix issues in adoc to HTML formatting found by Copilot review

Signed-off-by: James Ball <jameball@qti.qualcomm.com>

Author: james-ball-qualcomm

tests/norm-rule/expected/test-norm-rules.adoc

@@ -12,13 +12,14 @@
 | [Zicsr, ABC] | Rule Instances
 | inside inline a| link:test.html#norm:inline[norm:inline]
 
-.2+| no_tag
-| Normative rule *without* tag/tags | Rule's 'summary' property
+.3+| no_tag
+| Normative rule *without* tag/tags and *nested **bold** cases*. | Rule's 'summary' property
 | This normative rule has no references to the standard. This should only be used in extraordinary circumstances.
 It does include a link to <<table1>> (another normative rule).
 Has basic adoc formatting such as *bold*, ita__lics__, `monospace`, 2^superscript^, ~subscript~, [.underline]#underline#,
 and &le; (Unicode text for less-than-equals-to) and &#8800; (Unicode decimal value for not-equal-to).
  | Rule's 'note' property
+| Let's try a nested *_bold italics_* case or all 3 *_`bold italic monospace`_* too. | Rule's 'description' property
 
 .1+| inline-with-hash
 | includes a hash # symbol. a| link:test.html#norm:inline-with-hash[norm:inline-with-hash]

tests/norm-rule/expected/test-norm-rules.html

@@ -130,14 +130,18 @@ <h3>my-chapter_name</h3>
               <td><a href="test.html#norm:inline">norm:inline</a></td>
             </tr>
             <tr>
-              <td rowspan=2 id="no_tag">no_tag</td>
-              <td>Normative rule <b>without</b> tag/tags</td>
+              <td rowspan=3 id="no_tag">no_tag</td>
+              <td>Normative rule <b>without</b> tag/tags and <b>nested <b>bold</b> cases</b>.</td>
               <td>Rule's "summary" property</td>
             </tr>
             <tr>
               <td>This normative rule has no references to the standard. This should only be used in extraordinary circumstances.<br>It does include a link to <a href="#table1">table1</a> (another normative rule).<br>Has basic adoc formatting such as <b>bold</b>, ita<i>lics</i>, <code>monospace</code>, 2<sup>superscript</sup>, <sub>subscript</sub>, <span class="underline">underline</span>,<br>and &#8804; (Unicode text for less-than-equals-to) and &#8800; (Unicode decimal value for not-equal-to).<br></td>
               <td>Rule's "note" property</td>
             </tr>
+            <tr>
+              <td>Let's try a nested <b>_bold italics_</b> case or all 3 <b>_`bold italic monospace`_</b> too.</td>
+              <td>Rule's "description" property</td>
+            </tr>
             <tr>
               <td rowspan=1 id="inline-with-hash">inline-with-hash</td>
               <td>includes a hash # symbol.</td>

tests/norm-rule/expected/test-norm-rules.json

@@ -23,8 +23,9 @@
       "name": "no_tag",
       "def_filename": "tests/norm-rule/test.yaml",
       "chapter_name": "my-chapter_name",
-      "summary": "Normative rule *without* tag/tags",
+      "summary": "Normative rule *without* tag/tags and *nested **bold** cases*.",
       "note": "This normative rule has no references to the standard. This should only be used in extraordinary circumstances.\nIt does include a link to <<table1>> (another normative rule).\nHas basic adoc formatting such as *bold*, ita__lics__, `monospace`, 2^superscript^, ~subscript~, [.underline]#underline#,\nand &le; (Unicode text for less-than-equals-to) and &#8800; (Unicode decimal value for not-equal-to).\n",
+      "description": "Let's try a nested *_bold italics_* case or all 3 *_`bold italic monospace`_* too.",
       "tags": []
     },
     {

tests/norm-rule/expected/test-norm-rules.xlsx

@@ -14,7 +14,8 @@ normative_rule_definitions:
     instances: [Zicsr, ABC]
     tag: "norm:inline"
   - name: no_tag
-    summary: Normative rule *without* tag/tags
+    summary: Normative rule *without* tag/tags and *nested **bold** cases*.
+    description: Let's try a nested *_bold italics_* case or all 3 *_`bold italic monospace`_* too.
     note: |
       This normative rule has no references to the standard. This should only be used in extraordinary circumstances.
       It does include a link to <<table1>> (another normative rule).

tests/norm-rule/test.yaml

@@ -568,16 +568,16 @@ module Adoc2HTML
 
   # Apply constrained formatting pair transformation
   # Single delimiter, bounded by whitespace/punctuation
-  # Matches: *text*, _text_, ^text^, ~text~
   # Example: "That is *strong* stuff!" or "This is *strong*!"
   #
   # @param text [String] The text to transform
-  # @param delimiter [String] The formatting delimiter (e.g., '*', '_', '^', '~')
+  # @param delimiter [String] The formatting delimiter (e.g., '*', '_', '`')
+  # @param recursive [Boolean] Whether to recursively process nested formatting
   # @yield [content] Block that transforms the captured content
   # @yieldparam content [String] The text between the delimiters
   # @yieldreturn [String] The transformed content
   # @return [String] The text with formatting applied
-  def constrained_format_pattern(text, delimiter, &block)
+  def constrained_format_pattern(text, delimiter, recursive: false, &block)
     escaped_delimiter = Regexp.escape(delimiter)
     # (?:^|\s) - start of line or space before
     # \K - keep assertion (excludes preceding pattern from match)
@@ -586,32 +586,41 @@ def constrained_format_pattern(text, delimiter, &block)
     # #{escaped_delimiter} - single closing mark
     # (?=[,;".?!\s]|$) - followed by punctuation, space, or end of line
     pattern = /(?:^|\s)\K#{escaped_delimiter}(\S(?:(?!\s).*?(?<!\s))?)#{escaped_delimiter}(?=[,;".?!\s]|$)/
-    text.gsub(pattern) { block.call($1) }
+    text.gsub(pattern) do
+      content = $1
+      # Recursively process nested formatting if enabled
+      content = convert_nested(content) if recursive
+      block.call(content)
+    end
   end
 
   # Apply unconstrained formatting pair transformation
   # Double delimiter, can be used anywhere
-  # Matches: **text**, __text__, ^^text^^, ~~text~~
   # Example: "Sara**h**" or "**man**ual"
   #
   # @param text [String] The text to transform
-  # @param delimiter [String] The formatting delimiter (e.g., '*', '_', '^', '~')
+  # @param delimiter [String] The formatting delimiter (e.g., '*', '_', '`')
+  # @param recursive [Boolean] Whether to recursively process nested formatting
   # @yield [content] Block that transforms the captured content
   # @yieldparam content [String] The text between the delimiters
   # @yieldreturn [String] The transformed content
   # @return [String] The text with formatting applied
-  def unconstrained_format_pattern(text, delimiter, &block)
+  def unconstrained_format_pattern(text, delimiter, recursive: false, &block)
     escaped_delimiter = Regexp.escape(delimiter)
     # #{escaped_delimiter}{2} - double opening mark
     # (.+?) - any text (non-greedy)
     # #{escaped_delimiter}{2} - double closing mark
     pattern = /#{escaped_delimiter}{2}(.+?)#{escaped_delimiter}{2}/
-    text.gsub(pattern) { block.call($1) }
+    text.gsub(pattern) do
+      content = $1
+      # Recursively process nested formatting if enabled
+      content = convert_nested(content) if recursive
+      block.call(content)
+    end
   end
 
   # Apply superscript/subscript formatting transformation
   # Single delimiter, can be used anywhere, but text must be continuous (no spaces)
-  # Matches: ^text^, ~text~ where text contains no spaces
   # Example: "2^32^" or "X~i~"
   #
   # @param text [String] The text to transform
@@ -625,26 +634,43 @@ def continuous_format_pattern(text, delimiter, &block)
     # #{escaped_delimiter} - single opening mark
     # (\S+?) - continuous non-space text (no spaces allowed)
     # #{escaped_delimiter} - single closing mark
+    # Note: Superscript/subscript don't support nesting in AsciiDoc
     pattern = /#{escaped_delimiter}(\S+?)#{escaped_delimiter}/
     text.gsub(pattern) { block.call($1) }
   end
 
-  # Convert bold notation: *foo* -> <b>foo</b>
-  def convert_bold(text)
-    text = constrained_format_pattern(text, "*") { |content| "<b>#{content}</b>" }
-    text = unconstrained_format_pattern(text, "*") { |content| "<b>#{content}</b>" }
+  # Convert nested formatting within already-captured content
+  # This processes innermost formatting first to support nesting
+  # For example: *_foo_* becomes <b><i>foo</i></b>
+  def convert_nested(text)
+    result = text.dup
+    # Process unconstrained first (double delimiters)
+    result = unconstrained_format_pattern(result, "*", recursive: true) { |content| "<b>#{content}</b>" }
+    result = unconstrained_format_pattern(result, "_", recursive: true) { |content| "<i>#{content}</i>" }
+    result = unconstrained_format_pattern(result, "`", recursive: true) { |content| "<code>#{content}</code>" }
+    # Then process constrained (single delimiters)
+    result = constrained_format_pattern(result, "*", recursive: true) { |content| "<b>#{content}</b>" }
+    result = constrained_format_pattern(result, "_", recursive: true) { |content| "<i>#{content}</i>" }
+    result = constrained_format_pattern(result, "`", recursive: true) { |content| "<code>#{content}</code>" }
+    result
   end
 
-  # Convert italics notation: _bar_ -> <i>bar</i>
-  def convert_italics(text)
-    text = constrained_format_pattern(text, "_") { |content| "<i>#{content}</i>" }
-    text = unconstrained_format_pattern(text, "_") { |content| "<i>#{content}</i>" }
+  # Convert unconstrained bold, italics, monospaces notation.
+  # For example, **foo**bar -> <b>foo</b>bar
+  # Supports nesting when recursive: true
+  def convert_unconstrained(text)
+    text = unconstrained_format_pattern(text, "*", recursive: true) { |content| "<b>#{content}</b>" }
+    text = unconstrained_format_pattern(text, "_", recursive: true) { |content| "<i>#{content}</i>" }
+    text = unconstrained_format_pattern(text, "`", recursive: true) { |content| "<code>#{content}</code>" }
   end
 
-  # Convert monospace notation: `zort` -> <code>zort</code>
-  def convert_monospace(text)
-    text = constrained_format_pattern(text, "`") { |content| "<code>#{content}</code>" }
-    text = unconstrained_format_pattern(text, "`") { |content| "<code>#{content}</code>" }
+  # Convert constrained bold, italics, monospaces notation.
+  # For example, *foo* -> <b>foo</b>
+  # Supports nesting when recursive: true
+  def convert_constrained(text)
+    text = constrained_format_pattern(text, "*", recursive: true) { |content| "<b>#{content}</b>" }
+    text = constrained_format_pattern(text, "_", recursive: true) { |content| "<i>#{content}</i>" }
+    text = constrained_format_pattern(text, "`", recursive: true) { |content| "<code>#{content}</code>" }
   end
 
   # Convert superscript notation: 2^32^ -> 2<sup>32</sup>
@@ -729,9 +755,8 @@ def convert_unicode_names(text)
   # Apply all format conversions (keeping numeric entities).
   def convert(text)
     result = text.dup
-    result = convert_bold(result)
-    result = convert_italics(result)
-    result = convert_monospace(result)
+    result = convert_unconstrained(result)
+    result = convert_constrained(result)
     result = convert_superscript(result)
     result = convert_subscript(result)
     result = convert_underline(result)