charset.c (one_utf8_to_cppchar): Correct mask used for 5-byte UTF-8 sequences.

libcpp:
	* charset.c (one_utf8_to_cppchar): Correct mask used for 5-byte
	UTF-8 sequences.

gcc/testsuite:
	* gcc.dg/cpp/utf8-5byte-1.c: New test.

From-SVN: r147073

diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index da4f0e2fa7345939d8e042ba22834203b79e26df..bdb6f4419268f7c94115d6970660a5d98efe651d 100644 (file)
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,7 @@
+2009-05-03  Joseph Myers  <joseph@codesourcery.com>
+
+       * gcc.dg/cpp/utf8-5byte-1.c: New test.
+
 2009-05-02  Joseph Myers  <joseph@codesourcery.com>
 
        * gcc.dg/ucnid-6.c: Fix typo in dg-do directive.

diff --git a/gcc/testsuite/gcc.dg/cpp/utf8-5byte-1.c b/gcc/testsuite/gcc.dg/cpp/utf8-5byte-1.c
new file mode 100644 (file)
index 0000000..7f96a56
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/cpp/utf8-5byte-1.c
@@ -0,0 +1,17 @@
+/* Test for bug in conversions from 5-byte UTF-8 sequences in
+   cpplib.  */
+/* { dg-do run { target { 4byte_wchar_t } } } */
+/* { dg-options "-std=gnu99" } */
+
+extern void abort (void);
+extern void exit (int);
+
+__WCHAR_TYPE__ ws[] = L"û¿¿¿¿";
+
+int
+main (void)
+{
+  if (ws[0] != L'\U03FFFFFF' || ws[1] != 0)
+    abort ();
+  exit (0);
+}

diff --git a/libcpp/ChangeLog b/libcpp/ChangeLog
index 24f3f8debcf5bc4a32994fb9b543c49239eb4c2b..a541b69211cbaebea1f411aa95b29bb20959784d 100644 (file)
--- a/libcpp/ChangeLog
+++ b/libcpp/ChangeLog
@@ -1,3 +1,8 @@
+2009-05-03  Joseph Myers  <joseph@codesourcery.com>
+
+       * charset.c (one_utf8_to_cppchar): Correct mask used for 5-byte
+       UTF-8 sequences.
+
 2009-04-25  Joseph Myers  <joseph@codesourcery.com>
 
        PR preprocessor/39559

diff --git a/libcpp/charset.c b/libcpp/charset.c
index e743b1e277fcd412972bde2d70871697075ca028..f1da4265dddf11ea9684353798c57cfdb1c3ee2b 100644 (file)
--- a/libcpp/charset.c
+++ b/libcpp/charset.c
@@ -169,7 +169,7 @@ static inline int
 one_utf8_to_cppchar (const uchar **inbufp, size_t *inbytesleftp,
                     cppchar_t *cp)
 {
-  static const uchar masks[6] = { 0x7F, 0x1F, 0x0F, 0x07, 0x02, 0x01 };
+  static const uchar masks[6] = { 0x7F, 0x1F, 0x0F, 0x07, 0x03, 0x01 };
   static const uchar patns[6] = { 0x00, 0xC0, 0xE0, 0xF0, 0xF8, 0xFC };
 
   cppchar_t c;