8269150: UnicodeReader not translating \u005c\\u005d to \\]

Reviewed-by: jjg, jlahoda, darcy

src/jdk.compiler/share/classes/com/sun/tools/javac/parser/UnicodeReader.java

@@ -85,6 +85,11 @@ public class UnicodeReader {
      */
     private boolean wasBackslash;
 
+    /**
+     * true if the last character was derived from an unicode escape sequence.
+     */
+    private boolean wasUnicodeEscape;
+
     /**
      * Log for error reporting.
      */
@@ -105,6 +110,7 @@ public class UnicodeReader {
         this.character = '\0';
         this.codepoint = 0;
         this.wasBackslash = false;
+        this.wasUnicodeEscape = false;
         this.log = sf.log;
 
         nextCodePoint();
@@ -161,17 +167,22 @@ public class UnicodeReader {
         // Fetch next character.
         nextCodeUnit();
 
-        // If second backslash is detected.
+        if (character == '\\' && (!wasBackslash || wasUnicodeEscape)) {
-        if (wasBackslash) {
+            // Is a backslash and may be an unicode escape.
-            // Treat like a normal character (not part of unicode escape.)
-            wasBackslash = false;
-        } else if (character == '\\') {
-            // May be an unicode escape.
             switch (unicodeEscape()) {
-                case BACKSLASH -> wasBackslash = true;
+                case BACKSLASH -> {
-                case VALID_ESCAPE -> wasBackslash = false;
+                    wasUnicodeEscape = false;
+                    wasBackslash = !wasBackslash;
+                }
+                case VALID_ESCAPE -> {
+                    wasUnicodeEscape = true;
+                    wasBackslash = character == '\\' && !wasBackslash;
+                }
                 case BROKEN_ESCAPE -> nextUnicodeInputCharacter(); //skip broken unicode escapes
             }
+        } else {
+            wasBackslash = false;
+            wasUnicodeEscape = false;
         }
 
         // Codepoint and character match if not surrogate.
@@ -297,6 +308,7 @@ public class UnicodeReader {
         position = pos;
         width = 0;
         wasBackslash = false;
+        wasUnicodeEscape = false;
         nextCodePoint();
     }
 

test/langtools/tools/javac/UnicodeBackslash/UnicodeBackslash.java

@@ -0,0 +1,72 @@
+/*
+ * Copyright (c) 2021, Oracle and/or its affiliates. All rights reserved.
+ * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
+ *
+ * This code is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 only, as
+ * published by the Free Software Foundation.
+ *
+ * This code is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
+ * version 2 for more details (a copy is included in the LICENSE file that
+ * accompanied this code).
+ *
+ * You should have received a copy of the GNU General Public License version
+ * 2 along with this work; if not, write to the Free Software Foundation,
+ * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
+ * or visit www.oracle.com if you need additional information or have any
+ * questions.
+ */
+
+/*
+ * @test
+ * @bug 8269150
+ * @summary Unicode \ u 0 0 5 C not treated as an escaping backslash
+ * @run main UnicodeBackslash
+ */
+
+public class UnicodeBackslash {
+    static boolean failed = false;
+
+    public static void main(String... args) {
+        //   id     source                       expected
+        test("1.1", "\\]",                       "\\]");
+        test("1.2", "\u005C\]",                  "\\]");
+        test("1.3", "\\u005C]",                  "\\u005C]");
+        test("1.4", "\u005C\u005C]",             "\\]");
+
+        test("2.1", "\\\\]",                     "\\\\]");
+        test("2.2", "\u005C\\\]",                "\\\\]");
+        test("2.3", "\\u005C\\]",                "\\u005C\\]");
+        test("2.4", "\\\u005C\]",                "\\\\]");
+        test("2.5", "\\\\u005C]",                "\\\\u005C]");
+
+        test("3.1", "\u005C\u005C\\]",           "\\\\]");
+        test("3.2", "\u005C\\u005C\]",           "\\\\]");
+        test("3.3", "\u005C\\\u005C]",           "\\\\u005C]");
+        test("3.4", "\\u005C\u005C\]",           "\\u005C\\]");
+        test("3.5", "\\u005C\\u005C]",           "\\u005C\\u005C]");
+        test("3.6", "\\\u005C\u005C]",           "\\\\]");
+
+        test("4.1", "\u005C\u005C\u005C\]",      "\\\\]");
+        test("4.2", "\u005C\\u005C\u005C]",      "\\\\]");
+        test("4.3", "\u005C\u005C\\u005C]",      "\\\\u005C]");
+        test("4.4", "\\u005C\u005C\u005C]",      "\\u005C\\]");
+
+        test("5.1", "\u005C\u005C\u005C\u005C]", "\\\\]");
+
+        if (failed) {
+            throw new RuntimeException("Unicode escapes not handled correctly");
+        }
+    }
+
+    static void test(String id, String source, String expected) {
+        if (!source.equals(expected)) {
+            System.err.println(id + ": expected: " +  expected + ", found: " + source);
+            failed = true;
+        }
+    }
+}