From b9dfc77ee846ea2cee5637654bb733573f1bba14 Mon Sep 17 00:00:00 2001
From: youdie006 <xncb135@korea.ac.kr>
Date: Wed, 9 Sep 2026 09:51:24 +0900
Subject: [PATCH] Don't mutate the text node while pretty printing

Pretty#write_text called gsub! and squeeze! on the string returned by
Text#to_s, and Text#to_s returns the node's own string: @string when @raw,
otherwise the memoized @normalized. So pretty printing rewrote the document
it was printing.

    d = REXML::Document.new("<a><b>hello   world</b></a>")
    d.write(out, 2)
    d.to_s  # => "<a><b>hello world</b></a>"

Use the non-destructive gsub and squeeze. The other four node.to_s call
sites in the formatters only read the value.
---
 lib/rexml/formatters/pretty.rb |  5 ++---
 test/formatter/test_pretty.rb  | 34 ++++++++++++++++++++++++++++++++++
 2 files changed, 36 insertions(+), 3 deletions(-)
 create mode 100644 test/formatter/test_pretty.rb

diff --git a/lib/rexml/formatters/pretty.rb b/lib/rexml/formatters/pretty.rb
index a838d835..ff0e1022 100644
--- a/lib/rexml/formatters/pretty.rb
+++ b/lib/rexml/formatters/pretty.rb
@@ -86,9 +86,8 @@ def write_element(node, output)
       end
 
       def write_text( node, output )
-        s = node.to_s()
-        s.gsub!(/\s/,' ')
-        s.squeeze!(" ")
+        # Not gsub!/squeeze!: Text#to_s returns the node's own string.
+        s = node.to_s().gsub(/\s/, ' ').squeeze(" ")
         s = wrap(s, @width - @level)
         s = indent_text(s, @level, " ", true)
         output << (' '*@level + s)
diff --git a/test/formatter/test_pretty.rb b/test/formatter/test_pretty.rb
new file mode 100644
index 00000000..a3e97d54
--- /dev/null
+++ b/test/formatter/test_pretty.rb
@@ -0,0 +1,34 @@
+module REXMLTests
+  class PrettyFormatterTest < Test::Unit::TestCase
+    def format(node, indentation=2)
+      formatter = REXML::Formatters::Pretty.new(indentation)
+      output = +""
+      formatter.write(node, output)
+      output
+    end
+
+    class TextTest < self
+      def test_source_document_is_not_modified
+        document = REXML::Document.new("<a><b>hello   world</b></a>")
+        format(document)
+        assert_equal("<a><b>hello   world</b></a>", document.to_s)
+      end
+
+      def test_raw_text_value_is_not_modified
+        text = REXML::Text.new("hello   world", true, nil, true)
+        format(text)
+        assert_equal("hello   world", text.value)
+      end
+
+      def test_whitespace_is_replaced_with_space
+        document = REXML::Document.new("<a><b>x\ty</b></a>")
+        assert_equal("<a>\n  <b>\n    x y\n  </b>\n</a>", format(document))
+      end
+
+      def test_consecutive_spaces_are_squeezed
+        document = REXML::Document.new("<a><b>x   y</b></a>")
+        assert_equal("<a>\n  <b>\n    x y\n  </b>\n</a>", format(document))
+      end
+    end
+  end
+end