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/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

lib/notare/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Notare
-  VERSION = "0.0.5"
+  VERSION = "0.0.6"
 end

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