From f8517093da973f5bd7eeb0045fbed7bb32d15d92 Mon Sep 17 00:00:00 2001
From: Dan Allen <dan.j.allen@gmail.com>
Date: Thu, 22 Jun 2023 23:54:31 -0600
Subject: [PATCH] backport fix for #2430 remove null character enclosed by XML
 tag when sanitizing text

---
 CHANGELOG.adoc                   | 1 +
 lib/asciidoctor/pdf/sanitizer.rb | 4 ++--
 spec/outline_spec.rb             | 8 ++++++--
 3 files changed, 9 insertions(+), 4 deletions(-)

diff --git a/CHANGELOG.adoc b/CHANGELOG.adoc
index fe9d8be2e..0571ac6b4 100644
--- a/CHANGELOG.adoc
+++ b/CHANGELOG.adoc
@@ -9,6 +9,7 @@ For a detailed view of what has changed, refer to the {url-repo}/commits/main[co
 
 Bug Fixes::
 
+* remove null character enclosed in XML tag when santizing text; fixes invisible text in outline when heading contains index term (#2430)
 * alias `File.exists?` to `File.exist?` when loading RGhost optimizer to patch incompatibility when using Ruby 3.2
 
 Build / Infrastructure::
diff --git a/lib/asciidoctor/pdf/sanitizer.rb b/lib/asciidoctor/pdf/sanitizer.rb
index 8c009ca95..e55744143 100644
--- a/lib/asciidoctor/pdf/sanitizer.rb
+++ b/lib/asciidoctor/pdf/sanitizer.rb
@@ -19,11 +19,11 @@ module Sanitizer
         'nbsp' => ' ',
         'quot' => '"',
       }).default = '?'
-      SanitizeXMLRx = /<[^>]+>/
+      SanitizeXMLRx = /<[^>]+>\0?/
       CharRefRx = /&(?:amp;)?(?:([a-z][a-z]+\d{0,2})|#(?:(\d\d\d{0,4})|x(\h\h\h{0,3})));/
       UnescapedAmpersandRx = /&(?!(?:[a-z][a-z]+\d{0,2}|#(?:\d\d\d{0,4}|x\h\h\h{0,3}));)/
 
-      # Strip leading, trailing and repeating whitespace, remove XML tags and
+      # Strip leading, trailing and repeating whitespace, remove XML tags along with an enclosed null character, and
       # resolve all entities in the specified string.
       #
       # FIXME: move to a module so we can mix it in elsewhere
diff --git a/spec/outline_spec.rb b/spec/outline_spec.rb
index 34363ba59..79f9056c1 100644
--- a/spec/outline_spec.rb
+++ b/spec/outline_spec.rb
@@ -749,14 +749,18 @@
       pdf = to_pdf <<~'EOS'
       = _Document_ *Title*
       :doctype: book
+      :sectnums:
 
       == _First_ *Chapter*
+
+      == ((Wetland Birds))
       EOS
 
       outline = extract_outline pdf
-      (expect outline).to have_size 2
+      (expect outline).to have_size 3
       (expect outline[0][:title]).to eql 'Document Title'
-      (expect outline[1][:title]).to eql 'First Chapter'
+      (expect outline[1][:title]).to eql 'Chapter 1. First Chapter'
+      (expect outline[2][:title]).to eql 'Chapter 2. Wetland Birds'
     end
 
     it 'should decode character references in entries' do