SI-9038 fix scaladoc syntax highlightning to leave unicode alone

Syntax highlightning in code blocks used to manipulate the raw bytes of
a String, converting them to chars when needed, which breaks Unicode
surrogate pairs.

Using a char array instead of a byte array will leave them alone.

1 files changed, 22 insertions, 0 deletions

diff --git a/test/junit/scala/tools/nsc/doc/html/HtmlDocletTest.scala b/test/junit/scala/tools/nsc/doc/html/HtmlDocletTest.scala
new file mode 100644
index 0000000000..13a955b55d
--- /dev/null
+++ b/test/junit/scala/tools/nsc/doc/html/HtmlDocletTest.scala
@@ -0,0 +1,22 @@
+package scala.tools.nsc.doc.html
+
+import org.junit.Test
+import org.junit.Assert._
+import org.junit.runner.RunWith
+import org.junit.runners.JUnit4
+
+import scala.tools.testing.AssertUtil._
+
+@RunWith(classOf[JUnit4])
+class HtmlDocletTest {
+  @Test
+  def testSyntaxHighlightningUnicode() {
+    val in = "unicode: …"
+
+    val out = SyntaxHigh(in).toString
+
+    // SI-9038, this failed with
+    // "unicode: …" != "unicode: ￢ﾀﾦ"
+    assertEquals(in, out)
+  }
+}