lex.c (lex_string): Return a CPP_LESS token for missing '>' in a header name.

libcpp:
	* lex.c (lex_string): Return a CPP_LESS token for missing '>' in a
	header name.
	(_cpp_lex_direct): Handle this.

gcc/testsuite:
	* gcc.dg/cpp/include4.c: New test.

From-SVN: r144361

diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index 160b9f69b69df3f5a2b5a71fe96bb925c3b541f2..1d2db2ea3f07af29f6e8b987bc871d163fc21307 100644 (file)
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,7 @@
+2009-02-21  Joseph Myers  <joseph@codesourcery.com>
+
+       * gcc.dg/cpp/include4.c: New test.
+
 2008-02-21  Uros Bizjak  <ubizjak@gmail.com>
 
        PR target/39256

diff --git a/gcc/testsuite/gcc.dg/cpp/include4.c b/gcc/testsuite/gcc.dg/cpp/include4.c
new file mode 100644 (file)
index 0000000..d5e7fee
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/cpp/include4.c
@@ -0,0 +1,14 @@
+/* Preprocessing tokens are always formed according to a greedy algorithm,
+   so "#include <stddef.h" must be interpreted as a sequence of tokens,
+   of which the "h" then gets macro expanded.  Likewise the other
+   examples.  */
+
+#define h h>
+#include <stddef.h
+#undef h
+
+#define foo stddef.h>
+#include <foo
+
+#include <foo /*
+> */

diff --git a/libcpp/ChangeLog b/libcpp/ChangeLog
index f84aab398337b6b49236d3ac09cb5c85bb382f3f..d86092b677c076959adc00f5e437d3ad6a0f02df 100644 (file)
--- a/libcpp/ChangeLog
+++ b/libcpp/ChangeLog
@@ -1,3 +1,9 @@
+2009-02-21  Joseph Myers  <joseph@codesourcery.com>
+
+       * lex.c (lex_string): Return a CPP_LESS token for missing '>' in a
+       header name.
+       (_cpp_lex_direct): Handle this.
+
 2009-02-15  Richard Guenther  <rguenther@suse.de>
 
        Revert last change.

diff --git a/libcpp/lex.c b/libcpp/lex.c
index 96d1a99e283e1edb25db144c88253af3cf1d4550..452e8eafce59bd4ae182d3851631648d865bb6b5 100644 (file)
--- a/libcpp/lex.c
+++ b/libcpp/lex.c
@@ -613,7 +613,9 @@ create_literal (cpp_reader *pfile, cpp_token *token, const uchar *base,
 /* Lexes a string, character constant, or angle-bracketed header file
    name.  The stored string contains the spelling, including opening
    quote and leading any leading 'L', 'u' or 'U'.  It returns the type
-   of the literal, or CPP_OTHER if it was not properly terminated.
+   of the literal, or CPP_OTHER if it was not properly terminated, or
+   CPP_LESS for an unterminated header name which must be relexed as
+   normal tokens.
 
    The spelling is NUL-terminated, but it is not guaranteed that this
    is the first NUL since embedded NULs are preserved.  */
@@ -652,6 +654,14 @@ lex_string (cpp_reader *pfile, cpp_token *token, const uchar *base)
       else if (c == '\n')
        {
          cur--;
+         /* Unmatched quotes always yield undefined behavior, but
+            greedy lexing means that what appears to be an unterminated
+            header name may actually be a legitimate sequence of tokens.  */
+         if (terminator == '>')
+           {
+             token->type = CPP_LESS;
+             return;
+           }
          type = CPP_OTHER;
          break;
        }
@@ -1181,7 +1191,8 @@ _cpp_lex_direct (cpp_reader *pfile)
       if (pfile->state.angled_headers)
        {
          lex_string (pfile, result, buffer->cur - 1);
-         break;
+         if (result->type != CPP_LESS)
+           break;
        }
 
       result->type = CPP_LESS;