From 64c8679044dd91ae33cf6c1e52b6d211358cdf1c Mon Sep 17 00:00:00 2001
From: mathias234 <mathiasda98@gmail.com>
Date: Thu, 22 Jan 2026 09:10:33 +0100
Subject: [PATCH] Sanitize invalid XML characters in text content

Strip invalid XML 1.0 control characters (0x00-0x08, 0x0B-0x0C, 0x0E-0x1F)
from text to prevent corrupted docx files that fail to open in LibreOffice.

Fixes SAXParseException 'PCData Invalid Char value' errors.
---
 lib/notare.rb               |  1 +
 lib/notare/nodes/run.rb     |  2 +-
 lib/notare/version.rb       |  2 +-
 lib/notare/xml_sanitizer.rb | 15 ++++++++
 test/paragraph_test.rb      | 17 +++++++++
 test/xml_sanitizer_test.rb  | 73 +++++++++++++++++++++++++++++++++++++
 6 files changed, 108 insertions(+), 2 deletions(-)
 create mode 100644 lib/notare/xml_sanitizer.rb
 create mode 100644 test/xml_sanitizer_test.rb

diff --git a/lib/notare.rb b/lib/notare.rb
index 99f6bfe..5702ea3 100644
--- a/lib/notare.rb
+++ b/lib/notare.rb
@@ -3,6 +3,7 @@
 require "nokogiri"
 
 require_relative "notare/version"
+require_relative "notare/xml_sanitizer"
 require_relative "notare/nodes/base"
 require_relative "notare/nodes/break"
 require_relative "notare/nodes/hyperlink"
diff --git a/lib/notare/nodes/run.rb b/lib/notare/nodes/run.rb
index 5cc9e6e..ef142ee 100644
--- a/lib/notare/nodes/run.rb
+++ b/lib/notare/nodes/run.rb
@@ -8,7 +8,7 @@ module Notare
       def initialize(text, bold: false, italic: false, underline: false,
                      strike: false, highlight: nil, color: nil, style: nil)
         super()
-        @text = text
+        @text = XmlSanitizer.sanitize(text)
         @bold = bold
         @italic = italic
         @underline = underline
diff --git a/lib/notare/version.rb b/lib/notare/version.rb
index fb0d1c8..d5c8336 100644
--- a/lib/notare/version.rb
+++ b/lib/notare/version.rb
@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Notare
-  VERSION = "0.0.5"
+  VERSION = "0.0.6"
 end
diff --git a/lib/notare/xml_sanitizer.rb b/lib/notare/xml_sanitizer.rb
new file mode 100644
index 0000000..d3867f0
--- /dev/null
+++ b/lib/notare/xml_sanitizer.rb
@@ -0,0 +1,15 @@
+# frozen_string_literal: true
+
+module Notare
+  module XmlSanitizer
+    # Invalid XML 1.0 characters: 0x00, 0x01-0x08, 0x0B-0x0C, 0x0E-0x1F
+    # Valid whitespace preserved: 0x09 (tab), 0x0A (LF), 0x0D (CR)
+    INVALID_XML_CHARS = /[\x00-\x08\x0B\x0C\x0E-\x1F]/
+
+    def self.sanitize(text)
+      return text unless text.is_a?(String)
+
+      text.gsub(INVALID_XML_CHARS, "")
+    end
+  end
+end
diff --git a/test/paragraph_test.rb b/test/paragraph_test.rb
index 5615df2..a265249 100644
--- a/test/paragraph_test.rb
+++ b/test/paragraph_test.rb
@@ -111,4 +111,21 @@ class ParagraphTest < Minitest::Test
     # Newlines should be preserved in the text
     assert_includes xml, "Line 1\nLine 2\nLine 3"
   end
+
+  def test_invalid_xml_characters_are_stripped
+    xml = create_doc_and_read_xml do |doc|
+      doc.p "infrastruktur\x02bidrag"
+      doc.p "hello\x00world"
+      doc.p "test\x01\x03\x04value"
+    end
+
+    # Invalid characters should be stripped
+    assert_includes xml, "infrastrukturbidrag"
+    assert_includes xml, "helloworld"
+    assert_includes xml, "testvalue"
+
+    # Verify the XML is valid by parsing it (will raise if invalid)
+    doc = Nokogiri::XML(xml, &:strict)
+    assert doc.errors.empty?, "XML should be valid: #{doc.errors}"
+  end
 end
diff --git a/test/xml_sanitizer_test.rb b/test/xml_sanitizer_test.rb
new file mode 100644
index 0000000..20865d5
--- /dev/null
+++ b/test/xml_sanitizer_test.rb
@@ -0,0 +1,73 @@
+# frozen_string_literal: true
+
+require "test_helper"
+
+class XmlSanitizerTest < Minitest::Test
+  def test_removes_null_character
+    assert_equal "hello", Notare::XmlSanitizer.sanitize("hel\x00lo")
+  end
+
+  def test_removes_control_characters_0x01_to_0x08
+    input = "a\x01b\x02c\x03d\x04e\x05f\x06g\x07h\x08i"
+    assert_equal "abcdefghi", Notare::XmlSanitizer.sanitize(input)
+  end
+
+  def test_removes_control_characters_0x0b_and_0x0c
+    input = "hello\x0Bworld\x0Ctest"
+    assert_equal "helloworldtest", Notare::XmlSanitizer.sanitize(input)
+  end
+
+  def test_removes_control_characters_0x0e_to_0x1f
+    input = "a\x0Eb\x0Fc\x10d\x11e\x1Ff"
+    assert_equal "abcdef", Notare::XmlSanitizer.sanitize(input)
+  end
+
+  def test_preserves_tab_character
+    input = "hello\tworld"
+    assert_equal "hello\tworld", Notare::XmlSanitizer.sanitize(input)
+  end
+
+  def test_preserves_newline_character
+    input = "hello\nworld"
+    assert_equal "hello\nworld", Notare::XmlSanitizer.sanitize(input)
+  end
+
+  def test_preserves_carriage_return_character
+    input = "hello\rworld"
+    assert_equal "hello\rworld", Notare::XmlSanitizer.sanitize(input)
+  end
+
+  def test_preserves_crlf
+    input = "hello\r\nworld"
+    assert_equal "hello\r\nworld", Notare::XmlSanitizer.sanitize(input)
+  end
+
+  def test_returns_nil_unchanged
+    assert_nil Notare::XmlSanitizer.sanitize(nil)
+  end
+
+  def test_returns_non_string_unchanged
+    assert_equal 123, Notare::XmlSanitizer.sanitize(123)
+    assert_equal :symbol, Notare::XmlSanitizer.sanitize(:symbol)
+  end
+
+  def test_preserves_unicode_characters
+    input = "café naïve 日本語 🎉"
+    assert_equal "café naïve 日本語 🎉", Notare::XmlSanitizer.sanitize(input)
+  end
+
+  def test_preserves_regular_text
+    input = "Hello, World! This is normal text."
+    assert_equal input, Notare::XmlSanitizer.sanitize(input)
+  end
+
+  def test_handles_empty_string
+    assert_equal "", Notare::XmlSanitizer.sanitize("")
+  end
+
+  def test_real_world_case_stx_character
+    # The actual case from the failed.docx: 0x02 (STX) character
+    input = "infrastruktur\x02bidrag"
+    assert_equal "infrastrukturbidrag", Notare::XmlSanitizer.sanitize(input)
+  end
+end