Fix use-after-free lexing unterminated raw strings (PR preprocessor/78811)

gcc/ChangeLog:
	PR preprocessor/78680
	PR preprocessor/78811
	* input.c (struct selftest::lexer_test): Add field
	m_implicitly_expect_EOF.
	(selftest::lexer_error_sink): New class.
	(selftest::lexer_error_sink::s_singleton): New global.
	(selftest::lexer_test::lexer_test): Initialize new field
	"m_implicitly_expect_EOF".
	(selftest::lexer_test::~lexer_test): Conditionalize the
	check for the EOF token on the new field.
	(selftest::test_lexer_string_locations_raw_string_unterminated):
	New function.
	(selftest::input_c_tests): Call the new test.

libcpp/ChangeLog:
	PR preprocessor/78680
	PR preprocessor/78811
	* lex.c (_cpp_lex_direct): Only determine the end-location of
	the token and build a range for non-reserved start locations.
	Do not do it for EOF tokens.

From-SVN: r243721

1 files changed, 21 insertions, 19 deletions

diff --git a/libcpp/lex.c b/libcpp/lex.c
index ae458926b75..9b1bdf8ba30 100644
--- a/libcpp/lex.c
+++ b/libcpp/lex.c
@@ -3089,25 +3089,27 @@ _cpp_lex_direct (cpp_reader *pfile)
       break;
     }
 
-  /* Ensure that any line notes are processed, so that we have the
-     correct physical line/column for the end-point of the token even
-     when a logical line is split via one or more backslashes.  */
-  if (buffer->cur >= buffer->notes[buffer->cur_note].pos
-      && !pfile->overlaid_buffer)
-    _cpp_process_line_notes (pfile, false);
-
-  source_range tok_range;
-  tok_range.m_start = result->src_loc;
-  if (result->src_loc >= RESERVED_LOCATION_COUNT)
-    tok_range.m_finish
-      = linemap_position_for_column (pfile->line_table,
-				     CPP_BUF_COLUMN (buffer, buffer->cur));
-  else
-    tok_range.m_finish = tok_range.m_start;
-
-  result->src_loc = COMBINE_LOCATION_DATA (pfile->line_table,
-					   result->src_loc,
-					   tok_range, NULL);
+  /* Potentially convert the location of the token to a range.  */
+  if (result->src_loc >= RESERVED_LOCATION_COUNT
+      && result->type != CPP_EOF)
+    {
+      /* Ensure that any line notes are processed, so that we have the
+	 correct physical line/column for the end-point of the token even
+	 when a logical line is split via one or more backslashes.  */
+      if (buffer->cur >= buffer->notes[buffer->cur_note].pos
+	  && !pfile->overlaid_buffer)
+	_cpp_process_line_notes (pfile, false);
+
+      source_range tok_range;
+      tok_range.m_start = result->src_loc;
+      tok_range.m_finish
+	= linemap_position_for_column (pfile->line_table,
+				       CPP_BUF_COLUMN (buffer, buffer->cur));
+
+      result->src_loc = COMBINE_LOCATION_DATA (pfile->line_table,
+					       result->src_loc,
+					       tok_range, NULL);
+    }
 
   return result;
 }