re PR preprocessor/78680 (ICE in get_substring_ranges_for_loc, at input.c:1398)

Fix for PR preprocessor/78680

PR preprocessor/78680 identifies a crash when attempting to issue
a -Wformat warning, where the format string includes a string token
split across multiple physical source lines via backslash-continued
lines.

The issue is that libcpp is generating bogus range information for
such tokens.

For example, in:

void fn1() {
  __builtin_printf("\
     %ld.\n\
        2\n"); };

the range of the string token is printed as:

   __builtin_printf("\
                    ^~

whereas the range ought to be:

  __builtin_printf("\
                   ^~
     %ld.\n\
     ~~~~~~~
        2\n"); };
        ~~~~

The root cause is that the line notes expressing the update
of the buffer in lex.c aren't yet updated when the end-point of
the token is computed

3095	    tok_range.m_finish
3096	      = linemap_position_for_column (pfile->line_table,
3097					     CPP_BUF_COLUMN (buffer, buffer->cur));

so that the physical line is still regarded as that of the start
of the token, and, where CPP_BUF_COLUMN uses (BUF)->line_base,
line_base is still the location of the first physical line in the
and hence the column information is too large (as if it were the
offset in the *logical* line).

(the printed range is somewhat misleading; the actual buggy range
extends beyond the "\ in the line, but within diagnostic-show-locus.c
layout::print_annotation_line only prints up to the xbound set by
layout::print_source_line and so truncates most of the buggy range).

The fix is to ensure that line notes are handled before calculating
the end-point of the token range.

This leads to the range for the string token being correctly
computed, as:

  __builtin_printf("\
                   ^~
     %ld.\n\
     ~~~~~~~
        2\n"); };
        ~~~~

and this leads to get_substring_ranges_for_loc failing gracefully,
rather than crashing.

gcc/testsuite/ChangeLog:
	PR preprocessor/78680
	* gcc.dg/format/pr78680.c: New test case.
	* gcc.dg/plugin/diagnostic-test-expressions-1.c
	(test_multiline_token): New function.
	* gcc.dg/plugin/diagnostic-test-string-literals-1.c
	(test_backslash_continued_logical_lines): New function.

libcpp/ChangeLog:
	PR preprocessor/78680
	* lex.c (_cpp_lex_direct): Ensure line notes are processed before
	computing the end-point of the token.

From-SVN: r243567

6 files changed, 77 insertions, 0 deletions

diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index 982a203..f1f5184 100644
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,12 @@
+2016-12-12  David Malcolm  <dmalcolm@redhat.com>
+
+	PR preprocessor/78680
+	* gcc.dg/format/pr78680.c: New test case.
+	* gcc.dg/plugin/diagnostic-test-expressions-1.c
+	(test_multiline_token): New function.
+	* gcc.dg/plugin/diagnostic-test-string-literals-1.c
+	(test_backslash_continued_logical_lines): New function.
+
 2016-12-12  Nathan Sidwell  <nathan@acm.org>
 
 	PR c++/78252
diff --git a/gcc/testsuite/gcc.dg/format/pr78680.c b/gcc/testsuite/gcc.dg/format/pr78680.c
new file mode 100644
index 0000000..0c599f3
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/format/pr78680.c
@@ -0,0 +1,16 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -Wall -Wextra -fdiagnostics-show-caret" } */
+
+void fn1() {
+  __builtin_printf("\
+     %ld.\n\
+        2\n"); };
+/* { dg-warning "expects a matching" "" { target *-*-* } .-3 } */
+/* { dg-begin-multiline-output "" }
+   __builtin_printf("\
+                    ^~
+      %ld.\n\
+      ~~~~~~~        
+         2\n"); };
+         ~~~~        
+   { dg-end-multiline-output "" } */
diff --git a/gcc/testsuite/gcc.dg/plugin/diagnostic-test-expressions-1.c b/gcc/testsuite/gcc.dg/plugin/diagnostic-test-expressions-1.c
index 9372936..afbe0f7 100644
--- a/gcc/testsuite/gcc.dg/plugin/diagnostic-test-expressions-1.c
+++ b/gcc/testsuite/gcc.dg/plugin/diagnostic-test-expressions-1.c
@@ -689,3 +689,22 @@ void test_multiple_ordinary_maps (void)
         ~~                      
    { dg-end-multiline-output "" } */
 }
+
+/* Verify that we correctly handle a token that spans multiple
+   physical lines.  */
+
+const char *test_multiline_token (void)
+{
+  __emit_expression_range (0, "foo\
+bar\
+baz");
+/* { dg-warning "range" "" { target *-*-* } .-3 } */
+/* { dg-begin-multiline-output "" }
+   __emit_expression_range (0, "foo\
+                               ^~~~~
+ bar\
+ ~~~~                           
+ baz");
+ ~~~~                           
+   { dg-end-multiline-output "" } */
+}
diff --git a/gcc/testsuite/gcc.dg/plugin/diagnostic-test-string-literals-1.c b/gcc/testsuite/gcc.dg/plugin/diagnostic-test-string-literals-1.c
index 76a085e..03f042a 100644
--- a/gcc/testsuite/gcc.dg/plugin/diagnostic-test-string-literals-1.c
+++ b/gcc/testsuite/gcc.dg/plugin/diagnostic-test-string-literals-1.c
@@ -272,3 +272,23 @@ test_terminator_location (void)
                                            ^
    { dg-end-multiline-output "" } */
 }
+
+/* Verify that we fail gracefully when a string literal token is split
+   across multiple physical lines.  */
+
+void
+test_backslash_continued_logical_lines (void)
+{
+  __emit_string_literal_range ("\
+01234\
+56789", 6, 6, 7);
+  /* { dg-error "unable to read substring location: range endpoints are on different lines" "" { target *-*-* } .-3 } */
+  /* { dg-begin-multiline-output "" }
+   __emit_string_literal_range ("\
+                                ^~
+ 01234\
+ ~~~~~~                          
+ 56789", 6, 6, 7);
+ ~~~~~~                          
+   { dg-end-multiline-output "" } */
+}
diff --git a/libcpp/ChangeLog b/libcpp/ChangeLog
index 1a7e737..6368122 100644
--- a/libcpp/ChangeLog
+++ b/libcpp/ChangeLog
@@ -1,3 +1,9 @@
+2016-12-12  David Malcolm  <dmalcolm@redhat.com>
+
+	PR preprocessor/78680
+	* lex.c (_cpp_lex_direct): Ensure line notes are processed before
+	computing the end-point of the token.
+
 2016-11-23  Paolo Bonzini  <bonzini@gnu.org>
 
 	* include/cpplib.h (struct cpp_options): Add new member
diff --git a/libcpp/lex.c b/libcpp/lex.c
index cea8848..ae45892 100644
--- a/libcpp/lex.c
+++ b/libcpp/lex.c
@@ -3089,6 +3089,13 @@ _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)