re PR preprocessor/53690 ([C++11] \u0000 and \U00000000 are wrongly encoded as U+0001.)

/libcpp
2015-07-02  Paolo Carlini  <paolo.carlini@oracle.com>

	PR c++/53690
	* charset.c (_cpp_valid_ucn): Add cppchar_t * parameter and change
	return type to bool.  Fix encoding of \u0000 and \U00000000 in C++.
	(convert_ucn): Adjust call.
	* lex.c (forms_identifier_p): Likewise.
	* internal.h (_cpp_valid_ucn): Adjust declaration.

/gcc/testsuite
2015-07-02  Paolo Carlini  <paolo.carlini@oracle.com>

	PR c++/53690
	* g++.dg/cpp/pr53690.C: New.

From-SVN: r225353

6 files changed, 43 insertions, 20 deletions

diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index 8d7005f..530f8fc 100644
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,8 @@
+2015-07-02  Paolo Carlini  <paolo.carlini@oracle.com>
+
+	PR c++/53690
+	* g++.dg/cpp/pr53690.C: New.
+
 2015-07-02  Bill Schmidt  <wschmidt@linux.vnet.ibm.com>
 
 	* gcc.target/powerpc/vec-cmp.c: New test.
diff --git a/gcc/testsuite/g++.dg/cpp/pr53690.C b/gcc/testsuite/g++.dg/cpp/pr53690.C
new file mode 100644
index 0000000..ea91359
--- /dev/null
+++ b/gcc/testsuite/g++.dg/cpp/pr53690.C
@@ -0,0 +1,7 @@
+// PR c++/53690
+// { dg-do compile { target c++11 } }
+
+int array1[U'\U00000000' == 0 ? 1 : -1];
+int array2[U'\u0000' == 0 ? 1 : -1];
+int array3[u'\U00000000' == 0 ? 1 : -1];
+int array4[u'\u0000' == 0 ? 1 : -1];
diff --git a/libcpp/ChangeLog b/libcpp/ChangeLog
index 4e29802..ab259c5 100644
--- a/libcpp/ChangeLog
+++ b/libcpp/ChangeLog
@@ -1,3 +1,12 @@
+2015-07-02  Paolo Carlini  <paolo.carlini@oracle.com>
+
+	PR c++/53690
+	* charset.c (_cpp_valid_ucn): Add cppchar_t * parameter and change
+	return type to bool.  Fix encoding of \u0000 and \U00000000 in C++.
+	(convert_ucn): Adjust call.
+	* lex.c (forms_identifier_p): Likewise.
+	* internal.h (_cpp_valid_ucn): Adjust declaration.
+
 2015-06-30  Edward Smith-Rowland  <3dw4rd@verizon.net>
 
 	Implement N4197 - Adding u8 character literals
@@ -5,7 +14,7 @@
 	(struct cpp_options): Add utf8_char_literals.
 	* init.c (struct lang_flags): Add utf8_char_literals;
 	(struct lang_flags lang_defaults): Add column for utf8_char_literals.
-	* macro.c (stringify_arg()): Treat CPP_UTF8CHAR token; 
+	* macro.c (stringify_arg()): Treat CPP_UTF8CHAR token;
 	* expr.c (cpp_userdef_char_remove_type(), cpp_userdef_char_add_type()):
 	Treat CPP_UTF8CHAR_USERDEF, CPP_UTF8CHAR tokens;
 	(cpp_userdef_char_p()): Treat CPP_UTF8CHAR_USERDEF token;
diff --git a/libcpp/charset.c b/libcpp/charset.c
index 8e92bc6..5a1c929 100644
--- a/libcpp/charset.c
+++ b/libcpp/charset.c
@@ -972,21 +972,20 @@ ucn_valid_in_identifier (cpp_reader *pfile, cppchar_t c,
    or 0060 (`), nor one in the range D800 through DFFF inclusive.
 
    *PSTR must be preceded by "\u" or "\U"; it is assumed that the
-   buffer end is delimited by a non-hex digit.  Returns zero if the
-   UCN has not been consumed.
+   buffer end is delimited by a non-hex digit.  Returns false if the
+   UCN has not been consumed, true otherwise.
 
-   Otherwise the nonzero value of the UCN, whether valid or invalid,
-   is returned.  Diagnostics are emitted for invalid values.  PSTR
-   is updated to point one beyond the UCN, or to the syntactically
-   invalid character.
+   The value of the UCN, whether valid or invalid, is returned in *CP.
+   Diagnostics are emitted for invalid values.  PSTR is updated to point
+   one beyond the UCN, or to the syntactically invalid character.
 
    IDENTIFIER_POS is 0 when not in an identifier, 1 for the start of
    an identifier, or 2 otherwise.  */
 
-cppchar_t
+bool
 _cpp_valid_ucn (cpp_reader *pfile, const uchar **pstr,
 		const uchar *limit, int identifier_pos,
-		struct normalize_state *nst)
+		struct normalize_state *nst, cppchar_t *cp)
 {
   cppchar_t result, c;
   unsigned int length;
@@ -1030,8 +1029,11 @@ _cpp_valid_ucn (cpp_reader *pfile, const uchar **pstr,
      multiple tokens in identifiers, so we can't give a helpful
      error message in that case.  */
   if (length && identifier_pos)
-    return 0;
-  
+    {
+      *cp = 0;
+      return false;
+    }
+
   *pstr = str;
   if (length)
     {
@@ -1079,10 +1081,8 @@ _cpp_valid_ucn (cpp_reader *pfile, const uchar **pstr,
 		   (int) (str - base), base);
     }
 
-  if (result == 0)
-    result = 1;
-
-  return result;
+  *cp = result;
+  return true;
 }
 
 /* Convert an UCN, pointed to by FROM, to UTF-8 encoding, then translate
@@ -1100,7 +1100,7 @@ convert_ucn (cpp_reader *pfile, const uchar *from, const uchar *limit,
   struct normalize_state nst = INITIAL_NORMALIZE_STATE;
 
   from++;  /* Skip u/U.  */
-  ucn = _cpp_valid_ucn (pfile, &from, limit, 0, &nst);
+  _cpp_valid_ucn (pfile, &from, limit, 0, &nst, &ucn);
 
   rval = one_cppchar_to_utf8 (ucn, &bufp, &bytesleft);
   if (rval)
diff --git a/libcpp/internal.h b/libcpp/internal.h
index 95cf9c2..abd464f 100644
--- a/libcpp/internal.h
+++ b/libcpp/internal.h
@@ -744,9 +744,10 @@ struct normalize_state
 #define NORMALIZE_STATE_UPDATE_IDNUM(st, c)	\
   ((st)->previous = (c), (st)->prev_class = 0)
 
-extern cppchar_t _cpp_valid_ucn (cpp_reader *, const unsigned char **,
-				 const unsigned char *, int,
-				 struct normalize_state *state);
+extern bool _cpp_valid_ucn (cpp_reader *, const unsigned char **,
+			    const unsigned char *, int,
+			    struct normalize_state *state,
+			    cppchar_t *);
 extern void _cpp_destroy_iconv (cpp_reader *);
 extern unsigned char *_cpp_convert_input (cpp_reader *, const char *,
 					  unsigned char *, size_t, size_t,
diff --git a/libcpp/lex.c b/libcpp/lex.c
index 8f2bdc8..0aa1090 100644
--- a/libcpp/lex.c
+++ b/libcpp/lex.c
@@ -1244,9 +1244,10 @@ forms_identifier_p (cpp_reader *pfile, int first,
       && *buffer->cur == '\\'
       && (buffer->cur[1] == 'u' || buffer->cur[1] == 'U'))
     {
+      cppchar_t s;
       buffer->cur += 2;
       if (_cpp_valid_ucn (pfile, &buffer->cur, buffer->rlimit, 1 + !first,
-			  state))
+			  state, &s))
 	return true;
       buffer->cur -= 2;
     }