Ensure IO.copy_stream buffer is an independent string

jeremyevans · jeremyevans · commit f423f6e10c0c · 2025-02-18T17:18:16.000-08:00
Otherwise, changes to the buffer by the destination write method
could result in data changing for supposedly independent strings.

Fixes [Bug #21131]
diff --git a/io.c b/io.c
@@ -13139,6 +13139,7 @@ copy_stream_fallback_body(VALUE arg)
     while (1) {
         long numwrote;
         long l;
+        rb_str_make_independent(buf);
         if (stp->copy_length < (rb_off_t)0) {
             l = buflen;
         }
diff --git a/test/ruby/test_io.rb b/test/ruby/test_io.rb
@@ -1141,6 +1141,34 @@ def test_copy_stream_pathname_to_pathname
     }
   end
 
+  def test_copy_stream_dup_buffer
+    bug21131 = '[ruby-core:120961] [Bug #21131]'
+    mkcdtmpdir do
+      dst_class = Class.new do
+        def initialize(&block)
+          @block = block
+        end
+
+        def write(data)
+          @block.call(data.dup)
+          data.bytesize
+        end
+      end
+
+      rng = Random.new(42)
+      body = Tempfile.new("ruby-bug", binmode: true)
+      body.write(rng.bytes(16_385))
+      body.rewind
+
+      payload = []
+      IO.copy_stream(body, dst_class.new{payload << it})
+      body.rewind
+      assert_equal(body.read, payload.join, bug21131)
+    ensure
+      body&.close
+    end
+  end
+
   def test_copy_stream_write_in_binmode
     bug8767 = '[ruby-core:56518] [Bug #8767]'
     mkcdtmpdir {

Original file line number	Diff line number	Diff line change
`@@ -13139,6 +13139,7 @@ copy_stream_fallback_body(VALUE arg)`
`13139`	`13139`	`while (1) {`
`13140`	`13140`	`long numwrote;`
`13141`	`13141`	`long l;`
	`13142`	`+ rb_str_make_independent(buf);`
`13142`	`13143`	`if (stp->copy_length < (rb_off_t)0) {`
`13143`	`13144`	`l = buflen;`
`13144`	`13145`	`}`