preprocessor: -Wbidi-chars and UCNs [PR104030]

diff --git a/gcc/c-family/c.opt b/gcc/c-family/c.opt
index db65c14a7a5..f829656fc36 100644
--- a/gcc/c-family/c.opt
+++ b/gcc/c-family/c.opt
@@ -380,7 +380,7 @@  C ObjC C++ ObjC++ Warning Alias(Wbidi-chars=,any,none)
 
 Wbidi-chars=
 C ObjC C++ ObjC++ RejectNegative Joined Warning CPP(cpp_warn_bidirectional) CppReason(CPP_W_BIDIRECTIONAL) Var(warn_bidirectional) Init(bidirectional_unpaired) Enum(cpp_bidirectional_level)
--Wbidi-chars=[none|unpaired|any] Warn about UTF-8 bidirectional control characters.
+-Wbidi-chars=[none|unpaired|any|unpaired,ucn|any,ucn] Warn about UTF-8 bidirectional control characters.
 
 ; Required for these enum values.
 SourceInclude
@@ -398,6 +398,18 @@  Enum(cpp_bidirectional_level) String(unpaired) Value(bidirectional_unpaired)
 EnumValue
 Enum(cpp_bidirectional_level) String(any) Value(bidirectional_any)
 
+EnumValue
+Enum(cpp_bidirectional_level) String(any,ucn) Value(bidirectional_any_ucn)
+
+EnumValue
+Enum(cpp_bidirectional_level) String(ucn,any) Value(bidirectional_any_ucn)
+
+EnumValue
+Enum(cpp_bidirectional_level) String(unpaired,ucn) Value(bidirectional_unpaired_ucn)
+
+EnumValue
+Enum(cpp_bidirectional_level) String(ucn,unpaired) Value(bidirectional_unpaired_ucn)
+
 Wbool-compare
 C ObjC C++ ObjC++ Var(warn_bool_compare) Warning LangEnabledBy(C ObjC C++ ObjC++,Wall)
 Warn about boolean expression compared with an integer value different from true/false.
diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
index 67693d6c5cf..5498d908f18 100644
--- a/gcc/doc/invoke.texi
+++ b/gcc/doc/invoke.texi
@@ -328,7 +328,7 @@  Objective-C and Objective-C++ Dialects}.
 -Warray-bounds  -Warray-bounds=@var{n}  -Warray-compare @gol
 -Wno-attributes  -Wattribute-alias=@var{n} -Wno-attribute-alias @gol
 -Wno-attribute-warning  @gol
--Wbidi-chars=@r{[}none@r{|}unpaired@r{|}any@r{]} @gol
+-Wbidi-chars=@r{[}none@r{|}unpaired@r{|}any@r{|}unpaired,ucn@r{|}any,ucn@r{]} @gol
 -Wbool-compare  -Wbool-operation @gol
 -Wno-builtin-declaration-mismatch @gol
 -Wno-builtin-macro-redefined  -Wc90-c99-compat  -Wc99-c11-compat @gol
@@ -7802,7 +7802,7 @@  Attributes considered include @code{alloc_align}, @code{alloc_size},
 This is the default.  You can disable these warnings with either
 @option{-Wno-attribute-alias} or @option{-Wattribute-alias=0}.
 
-@item -Wbidi-chars=@r{[}none@r{|}unpaired@r{|}any@r{]}
+@item -Wbidi-chars=@r{[}none@r{|}unpaired@r{|}any@r{|}unpaired,ucn@r{|}any,ucn@r{]}
 @opindex Wbidi-chars=
 @opindex Wbidi-chars
 @opindex Wno-bidi-chars
@@ -7819,6 +7819,10 @@  bidi contexts.  @option{-Wbidi-chars=none} turns the warning off.
 @option{-Wbidi-chars=any} warns about any use of bidirectional control
 characters.
 
+By default, this warning does not warn about UCNs.  It is, however, possible
+to turn on such checking by using @option{-Wbidi-chars=unpaired,ucn} or
+@option{-Wbidi-chars=any,ucn}.
+
 @item -Wbool-compare
 @opindex Wno-bool-compare
 @opindex Wbool-compare
diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-10.c b/gcc/testsuite/c-c++-common/Wbidi-chars-10.c
index 3f851b69e65..cdcdce2be08 100644
--- a/gcc/testsuite/c-c++-common/Wbidi-chars-10.c
+++ b/gcc/testsuite/c-c++-common/Wbidi-chars-10.c
@@ -1,6 +1,6 @@ 
 /* PR preprocessor/103026 */
 /* { dg-do compile } */
-/* { dg-options "-Wbidi-chars=unpaired" } */
+/* { dg-options "-Wbidi-chars=unpaired,ucn" } */
 /* More nesting testing.  */
 
 /* RLE‫ LRI⁦ PDF‬ PDI⁩*/
diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-11.c b/gcc/testsuite/c-c++-common/Wbidi-chars-11.c
index 270ce2368a9..ea83029d6b9 100644
--- a/gcc/testsuite/c-c++-common/Wbidi-chars-11.c
+++ b/gcc/testsuite/c-c++-common/Wbidi-chars-11.c
@@ -1,6 +1,6 @@ 
 /* PR preprocessor/103026 */
 /* { dg-do compile } */
-/* { dg-options "-Wbidi-chars=unpaired" } */
+/* { dg-options "-Wbidi-chars=unpaired,ucn" } */
 /* Test that we warn when mixing UCN and UTF-8.  */
 
 int LRE_‪_PDF_\u202c;
diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-14.c b/gcc/testsuite/c-c++-common/Wbidi-chars-14.c
index ba5f75d9553..cb6b05efac1 100644
--- a/gcc/testsuite/c-c++-common/Wbidi-chars-14.c
+++ b/gcc/testsuite/c-c++-common/Wbidi-chars-14.c
@@ -1,6 +1,6 @@ 
 /* PR preprocessor/103026 */
 /* { dg-do compile } */
-/* { dg-options "-Wbidi-chars=unpaired" } */
+/* { dg-options "-Wbidi-chars=unpaired,ucn" } */
 /* Test PDI handling, which also pops any subsequent LREs, RLEs, LROs,
    or RLOs.  */
 
diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-16.c b/gcc/testsuite/c-c++-common/Wbidi-chars-16.c
index baa0159861c..eaf0ec9a777 100644
--- a/gcc/testsuite/c-c++-common/Wbidi-chars-16.c
+++ b/gcc/testsuite/c-c++-common/Wbidi-chars-16.c
@@ -1,6 +1,6 @@ 
 /* PR preprocessor/103026 */
 /* { dg-do compile } */
-/* { dg-options "-Wbidi-chars=any" } */
+/* { dg-options "-Wbidi-chars=any,ucn" } */
 /* Test LTR/RTL chars.  */
 
 /* LTR<‎> */
diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-17.c b/gcc/testsuite/c-c++-common/Wbidi-chars-17.c
index 07cb4321f96..341922146a7 100644
--- a/gcc/testsuite/c-c++-common/Wbidi-chars-17.c
+++ b/gcc/testsuite/c-c++-common/Wbidi-chars-17.c
@@ -1,6 +1,6 @@ 
 /* PR preprocessor/103026 */
 /* { dg-do compile } */
-/* { dg-options "-Wbidi-chars=unpaired" } */
+/* { dg-options "-Wbidi-chars=unpaired,ucn" } */
 /* Test LTR/RTL chars.  */
 
 /* LTR<‎> */
diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-18.c b/gcc/testsuite/c-c++-common/Wbidi-chars-18.c
new file mode 100644
index 00000000000..ae586d5e08c
--- /dev/null
+++ b/gcc/testsuite/c-c++-common/Wbidi-chars-18.c
@@ -0,0 +1,11 @@ 
+/* PR preprocessor/104030 */
+/* { dg-do compile } */
+/* By default, don't warn about UCNs.  */
+
+const char *
+fn ()
+{
+  const char *aText = "\u202D" "abc";
+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
+  return aText;
+}
diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-19.c b/gcc/testsuite/c-c++-common/Wbidi-chars-19.c
new file mode 100644
index 00000000000..9985c3be7a5
--- /dev/null
+++ b/gcc/testsuite/c-c++-common/Wbidi-chars-19.c
@@ -0,0 +1,11 @@ 
+/* PR preprocessor/104030 */
+/* { dg-do compile } */
+/* { dg-options "-Wbidi-chars=unpaired,ucn" } */
+
+const char *
+fn ()
+{
+  const char *aText = "\u202D" "abc";
+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
+  return aText;
+}
diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-20.c b/gcc/testsuite/c-c++-common/Wbidi-chars-20.c
new file mode 100644
index 00000000000..859f3d53779
--- /dev/null
+++ b/gcc/testsuite/c-c++-common/Wbidi-chars-20.c
@@ -0,0 +1,11 @@ 
+/* PR preprocessor/104030 */
+/* { dg-do compile } */
+/* { dg-options "-Wbidi-chars=any" } */
+
+const char *
+fn ()
+{
+  const char *aText = "\u202D" "abc";
+/* { dg-bogus "U\\+202D" "" { target *-*-* } .-1 } */
+  return aText;
+}
diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-21.c b/gcc/testsuite/c-c++-common/Wbidi-chars-21.c
new file mode 100644
index 00000000000..2720b8a883e
--- /dev/null
+++ b/gcc/testsuite/c-c++-common/Wbidi-chars-21.c
@@ -0,0 +1,11 @@ 
+/* PR preprocessor/104030 */
+/* { dg-do compile } */
+/* { dg-options "-Wbidi-chars=ucn,any" } */
+
+const char *
+fn ()
+{
+  const char *aText = "\u202D" "abc";
+/* { dg-warning "U\\+202D" "" { target *-*-* } .-1 } */
+  return aText;
+}
diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-4.c b/gcc/testsuite/c-c++-common/Wbidi-chars-4.c
index 639e5c62e88..d2f0739dae0 100644
--- a/gcc/testsuite/c-c++-common/Wbidi-chars-4.c
+++ b/gcc/testsuite/c-c++-common/Wbidi-chars-4.c
@@ -1,6 +1,6 @@ 
 /* PR preprocessor/103026 */
 /* { dg-do compile } */
-/* { dg-options "-Wbidi-chars=any -Wno-multichar -Wno-overflow" } */
+/* { dg-options "-Wbidi-chars=any,ucn -Wno-multichar -Wno-overflow" } */
 /* Test all bidi chars in various contexts (identifiers, comments,
    string literals, character constants), both UCN and UTF-8.  The bidi
    chars here are properly terminated, except for the character constants.  */
diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-5.c b/gcc/testsuite/c-c++-common/Wbidi-chars-5.c
index 68cb053144b..ad49498fe23 100644
--- a/gcc/testsuite/c-c++-common/Wbidi-chars-5.c
+++ b/gcc/testsuite/c-c++-common/Wbidi-chars-5.c
@@ -1,6 +1,6 @@ 
 /* PR preprocessor/103026 */
 /* { dg-do compile } */
-/* { dg-options "-Wbidi-chars=unpaired -Wno-multichar -Wno-overflow" } */
+/* { dg-options "-Wbidi-chars=unpaired,ucn -Wno-multichar -Wno-overflow" } */
 /* Test all bidi chars in various contexts (identifiers, comments,
    string literals, character constants), both UCN and UTF-8.  The bidi
    chars here are properly terminated, except for the character constants.  */
diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-6.c b/gcc/testsuite/c-c++-common/Wbidi-chars-6.c
index 0ce6fff2dee..8c1c1b2a270 100644
--- a/gcc/testsuite/c-c++-common/Wbidi-chars-6.c
+++ b/gcc/testsuite/c-c++-common/Wbidi-chars-6.c
@@ -1,6 +1,6 @@ 
 /* PR preprocessor/103026 */
 /* { dg-do compile } */
-/* { dg-options "-Wbidi-chars=unpaired" } */
+/* { dg-options "-Wbidi-chars=ucn,unpaired" } */
 /* Test nesting of bidi chars in various contexts.  */
 
 /* Terminated by the wrong char:  */
diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-7.c b/gcc/testsuite/c-c++-common/Wbidi-chars-7.c
index d012d420ec0..3270952a09a 100644
--- a/gcc/testsuite/c-c++-common/Wbidi-chars-7.c
+++ b/gcc/testsuite/c-c++-common/Wbidi-chars-7.c
@@ -1,6 +1,6 @@ 
 /* PR preprocessor/103026 */
 /* { dg-do compile } */
-/* { dg-options "-Wbidi-chars=any" } */
+/* { dg-options "-Wbidi-chars=any,ucn" } */
 /* Test we ignore UCNs in comments.  */
 
 // a b c \u202a 1 2 3
diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-8.c b/gcc/testsuite/c-c++-common/Wbidi-chars-8.c
index 4f54c5092ec..3983168c9f1 100644
--- a/gcc/testsuite/c-c++-common/Wbidi-chars-8.c
+++ b/gcc/testsuite/c-c++-common/Wbidi-chars-8.c
@@ -1,6 +1,6 @@ 
 /* PR preprocessor/103026 */
 /* { dg-do compile } */
-/* { dg-options "-Wbidi-chars=any" } */
+/* { dg-options "-Wbidi-chars=any,ucn" } */
 /* Test \u vs \U.  */
 
 int a_\u202A;
diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-9.c b/gcc/testsuite/c-c++-common/Wbidi-chars-9.c
index e2af1b1ca97..0ddb0d93108 100644
--- a/gcc/testsuite/c-c++-common/Wbidi-chars-9.c
+++ b/gcc/testsuite/c-c++-common/Wbidi-chars-9.c
@@ -1,6 +1,6 @@ 
 /* PR preprocessor/103026 */
 /* { dg-do compile } */
-/* { dg-options "-Wbidi-chars=unpaired" } */
+/* { dg-options "-Wbidi-chars=unpaired,ucn" } */
 /* Test that we properly separate bidi contexts (comment/identifier/character
    constant/string literal).  */
 
diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-ranges.c b/gcc/testsuite/c-c++-common/Wbidi-chars-ranges.c
index 298750a2a64..0c71f306dbc 100644
--- a/gcc/testsuite/c-c++-common/Wbidi-chars-ranges.c
+++ b/gcc/testsuite/c-c++-common/Wbidi-chars-ranges.c
@@ -1,6 +1,6 @@ 
 /* PR preprocessor/103026 */
 /* { dg-do compile } */
-/* { dg-options "-Wbidi-chars=unpaired -fdiagnostics-show-caret" } */
+/* { dg-options "-Wbidi-chars=unpaired,ucn -fdiagnostics-show-caret" } */
 /* Verify that we escape and underline pertinent bidirectional
    control characters when quoting the source.  */
 
diff --git a/libcpp/include/cpplib.h b/libcpp/include/cpplib.h
index 940c79f98c1..9661b7151b1 100644
--- a/libcpp/include/cpplib.h
+++ b/libcpp/include/cpplib.h
@@ -327,7 +327,10 @@  enum cpp_bidirectional_level {
   /* Only detect unpaired uses of bidirectional control characters.  */
   bidirectional_unpaired,
   /* Detect any use of bidirectional control characters.  */
-  bidirectional_any
+  bidirectional_any,
+  /* Like above, but also warn about UCNs.  */
+  bidirectional_unpaired_ucn,
+  bidirectional_any_ucn
 };
 
 /* This structure is nested inside struct cpp_reader, and
diff --git a/libcpp/lex.cc b/libcpp/lex.cc
index 4d736576cc1..348ec553b7a 100644
--- a/libcpp/lex.cc
+++ b/libcpp/lex.cc
@@ -1560,8 +1560,11 @@  class unpaired_bidi_rich_location : public rich_location
 static void
 maybe_warn_bidi_on_close (cpp_reader *pfile, const uchar *p)
 {
-  if (CPP_OPTION (pfile, cpp_warn_bidirectional) == bidirectional_unpaired
-      && bidi::vec.count () > 0)
+  const auto warn_bidi = CPP_OPTION (pfile, cpp_warn_bidirectional);
+  if (bidi::vec.count () > 0
+      && (warn_bidi == bidirectional_unpaired_ucn
+	  || (warn_bidi == bidirectional_unpaired
+	      && !bidi::current_ctx_ucn_p ())))
     {
       const location_t loc
 	= linemap_position_for_column (pfile->line_table,
@@ -1605,10 +1608,10 @@  maybe_warn_bidi_on_char (cpp_reader *pfile, bidi::kind kind,
       /* It seems excessive to warn about a PDI/PDF that is closing
 	 an opened context because we've already warned about the
 	 opening character.  Except warn when we have a UCN x UTF-8
-	 mismatch.  */
+	 mismatch, if UCN checking is enabled.  */
       if (kind == bidi::current_ctx ())
 	{
-	  if (warn_bidi == bidirectional_unpaired
+	  if (warn_bidi == bidirectional_unpaired_ucn
 	      && bidi::current_ctx_ucn_p () != ucn_p)
 	    {
 	      rich_loc.add_range (bidi::current_ctx_loc ());
@@ -1617,7 +1620,8 @@  maybe_warn_bidi_on_char (cpp_reader *pfile, bidi::kind kind,
 			      "a context by \"%s\"", bidi::to_str (kind));
 	    }
 	}
-      else if (warn_bidi == bidirectional_any)
+      else if (warn_bidi == bidirectional_any_ucn
+	       || (warn_bidi == bidirectional_any && !ucn_p))
 	{
 	  if (kind == bidi::kind::PDF || kind == bidi::kind::PDI)
 	    cpp_warning_at (pfile, CPP_W_BIDIRECTIONAL, &rich_loc,