Fix RuboCop Style/SelectByKind and Style/PredicateWithKind offenses

Add default_font and default_size options to Document.create, rendered
as w:docDefaults in styles.xml. Defaults to Arial 12pt. Adjust heading
sizes for better visual hierarchy.

Styling based on uutilsynet guidance for accessible documents:
https://www.uutilsynet.no/veiledning/rettleiar-universelt-utforma-word-og-pdf-dokument/1636

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"

lib/notare/document.rb

@@ -4,16 +4,21 @@ module Notare
   class Document
     include Builder
 
-    attr_reader :nodes, :styles, :table_styles, :hyperlinks
+    DEFAULT_FONT = "Arial"
+    DEFAULT_SIZE = 12
 
-    def self.create(path, &block)
-      doc = new
+    attr_reader :nodes, :styles, :table_styles, :hyperlinks, :default_font, :default_size
+
+    def self.create(path, default_font: DEFAULT_FONT, default_size: DEFAULT_SIZE, &block)
+      doc = new(default_font: default_font, default_size: default_size)
       block.call(doc)
       doc.save(path)
       doc
     end
 
-    def initialize
+    def initialize(default_font: DEFAULT_FONT, default_size: DEFAULT_SIZE)
+      @default_font = default_font
+      @default_size = default_size
       @nodes = []
       @format_stack = []
       @current_target = nil
@@ -51,7 +56,7 @@ module Notare
     end
 
     def lists
-      @nodes.select { |n| n.is_a?(Nodes::List) }
+      @nodes.grep(Nodes::List)
     end
 
     def uses_lists?
@@ -101,12 +106,12 @@ module Notare
 
     def register_built_in_styles
       # Headings (spacing_before ensures they're rendered as paragraph styles)
-      define_style :heading1, size: 24, bold: true, spacing_before: 240, spacing_after: 120
-      define_style :heading2, size: 18, bold: true, spacing_before: 200, spacing_after: 100
+      define_style :heading1, size: 20, bold: true, spacing_before: 240, spacing_after: 120
+      define_style :heading2, size: 16, bold: true, spacing_before: 200, spacing_after: 100
       define_style :heading3, size: 14, bold: true, spacing_before: 160, spacing_after: 80
       define_style :heading4, size: 12, bold: true, spacing_before: 120, spacing_after: 60
-      define_style :heading5, size: 11, bold: true, italic: true, spacing_before: 100, spacing_after: 40
-      define_style :heading6, size: 10, bold: true, italic: true, spacing_before: 80, spacing_after: 40
+      define_style :heading5, size: 12, bold: true, italic: true, spacing_before: 100, spacing_after: 40
+      define_style :heading6, size: 12, italic: true, spacing_before: 80, spacing_after: 40
 
       # Other built-in styles
       define_style :title, size: 26, bold: true, align: :center

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/package.rb

@@ -59,7 +59,12 @@ module Notare
     end
 
     def styles_xml
-      Xml::StylesXml.new(@document.styles, @document.table_styles).to_xml
+      Xml::StylesXml.new(
+        @document.styles,
+        @document.table_styles,
+        default_font: @document.default_font,
+        default_size: @document.default_size
+      ).to_xml
     end
 
     def numbering_xml

lib/notare/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Notare
-  VERSION = "0.0.4"
+  VERSION = "0.0.7"
 end

lib/notare/xml/styles_xml.rb

@@ -18,9 +18,11 @@ module Notare
         right: "right"
       }.freeze
 
-      def initialize(styles, table_styles = {})
+      def initialize(styles, table_styles = {}, default_font: nil, default_size: nil)
         @styles = styles
         @table_styles = table_styles
+        @default_font = default_font
+        @default_size = default_size
       end
 
       def to_xml
@@ -28,6 +30,8 @@ module Notare
           xml.styles("xmlns:w" => NAMESPACE) do
             xml.parent.namespace = xml.parent.namespace_definitions.find { |ns| ns.prefix == "w" }
 
+            render_doc_defaults(xml) if @default_font || @default_size
+
             @styles.each_value do |style|
               render_style(xml, style)
             end
@@ -44,6 +48,28 @@ module Notare
 
       private
 
+      def render_doc_defaults(xml)
+        xml["w"].docDefaults do
+          xml["w"].rPrDefault do
+            xml["w"].rPr do
+              if @default_font
+                xml["w"].rFonts(
+                  "w:ascii" => @default_font,
+                  "w:hAnsi" => @default_font,
+                  "w:eastAsia" => @default_font,
+                  "w:cs" => @default_font
+                )
+              end
+              if @default_size
+                half_points = (@default_size * 2).to_i
+                xml["w"].sz("w:val" => half_points.to_s)
+                xml["w"].szCs("w:val" => half_points.to_s)
+              end
+            end
+          end
+        end
+      end
+
       def render_style(xml, style)
         style_type = style.paragraph_properties? ? "paragraph" : "character"
 

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

test/document_test.rb

@@ -69,6 +69,6 @@ class DocumentTest < Minitest::Test
     doc.table { doc.tr { doc.td "Cell" } }
 
     assert_equal 2, doc.lists.count
-    assert(doc.lists.all? { |l| l.is_a?(Notare::Nodes::List) })
+    assert(doc.lists.all?(Notare::Nodes::List))
   end
 end

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

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