Patchwork Add an intermediate coverage format for gcov

login
register
mail settings
Submitter Sharad Singhai
Date Oct. 5, 2011, 7:47 a.m.
Message ID <20111005074800.03AD4A0183@nabu.mtv.corp.google.com>
Download mbox | patch
Permalink /patch/117755/
State New
Headers show

Comments

Sharad Singhai - Oct. 5, 2011, 7:47 a.m.
Sorry about the badly formatted mail. Here is another version with a
Mike Stump - Oct. 5, 2011, 4:58 p.m.
On Oct 5, 2011, at 12:47 AM, Sharad Singhai wrote:
> This patch adds an intermediate coverage format (enabled via 'gcov
> -i'). This is a compact format as it does not require source files.

I don't like any of the tags, I think if you showed them to 100 people that had used gcov before, very few of them would be able to figure out the meaning without reading the manual.  Why make it completely cryptic?  A binary encoded compress format is smaller and just as readable.

SF, sounds like single float to me, I'd propose file.
FN, sounds like filename, I'd propose line.
FNDA, can't even guess at what it means, I'd propose fcount.
BA, I'd propose branch, for 0, notexe, for 1, nottaken, for 2 taken.
DA, I'd propose lcount

I'd propose fcount be listed as fname,ecount, to match the ordering of lcount.  Also, implicit in the name, is the ordering f, then count, l, then count.

I think if you showed the above to 100 people that had used gcov before, I think we'd be up past 90% of the people able to figure it out, without reading the doc.

Patch

different mailer. -Sharad
----

This patch was earlier submitted to google/main, but I propose it
for the trunk as well.

This patch adds an intermediate coverage format (enabled via 'gcov
-i'). This is a compact format as it does not require source files.

The new option ('gcov -i') outputs .gcov files in an intermediate text
format that can be postprocessed by lcov or other applications. It
will output a single *.gcov file per *.gcda file. No source code is
required.

The format of the intermediate .gcov file is plain text with one entry
per line

    SF:source_file_name
    FN:line_number,function_name
    FNDA:execution_count,function_name
    BA:line_num,branch_coverage_type
    DA:line number,execution_count

    Where the branch_coverage_type is
       0 (Branch not executed)
       1 (Branch executed, but not taken)
       2 (Branch executed and taken)

There can be multiple SF entries in an intermediate gcov file. All
entries following SF pertain to that source file until the next SF
entry.

A concrete example looks like this:

  SF:array.c
  FN:4,sum
  FNDA:0,sum
  FN:13,main
  FNDA:1,main
  DA:4,2
  BA:8,2
  DA:7,1

I have bootstrapped and tested this patch on x86_64-linux. No new test
failures were observed. 

Okay for trunk?

Thanks,
Sharad


2011-10-04   Sharad Singhai  <singhai@google.com>

	* doc/gcov.texi: Document gcov intermediate format.
	* gcov.c (print_usage): Handle new option.
	(process_args): Handle new option.
	(get_gcov_file_intermediate_name): New function.
	(output_intermediate_file): New function.
	(generate_results): Handle new option.
	* testsuite/lib/gcov.exp: Handle intermediate format.
	* testsuite/g++.dg/gcov/gcov-8.C: New testcase.

Index: doc/gcov.texi
===================================================================
--- doc/gcov.texi	(revision 179475)
+++ doc/gcov.texi	(working copy)
@@ -130,6 +130,7 @@  gcov [@option{-v}|@option{--version}] [@
      [@option{-f}|@option{--function-summaries}]
      [@option{-o}|@option{--object-directory} @var{directory|file}] @var{sourcefiles}
      [@option{-u}|@option{--unconditional-branches}]
+     [@option{-i}|@option{--intermediate-format}]
      [@option{-d}|@option{--display-progress}]
 @c man end
 @c man begin SEEALSO
@@ -216,6 +217,32 @@  Unconditional branches are normally not 
 @itemx --display-progress
 Display the progress on the standard output.
 
+@item -i
+@itemx --intermediate-format
+Output gcov file in an intermediate text format that can be used by
+@command{lcov} or other applications. It will output a single *.gcov file per
+*.gcda file. No source code is required.
+
+The format of the intermediate @file{.gcov} file is plain text with
+one entry per line
+
+@smallexample
+SF:@var{source_file_name}
+FN:@var{line_number},@var{function_name}
+FNDA:@var{execution_count},@var{function_name}
+BA:@var{line_num},@var{branch_coverage_type}
+DA:@var{line number},@var{execution_count}
+
+Where the @var{branch_coverage_type} is
+   0 (Branch not executed)
+   1 (Branch executed, but not taken)
+   2 (Branch executed and taken)
+
+There can be multiple SF entries in an intermediate gcov file. All
+entries following SF pertain to that source file until the next SF
+entry.
+@end smallexample
+
 @end table
 
 @command{gcov} should be run with the current directory the same as that
Index: gcov.c
===================================================================
--- gcov.c	(revision 179475)
+++ gcov.c	(working copy)
@@ -39,6 +39,7 @@  along with Gcov; see the file COPYING3. 
 #include "intl.h"
 #include "diagnostic.h"
 #include "version.h"
+#include "demangle.h"
 
 #include <getopt.h>
 
@@ -311,6 +312,9 @@  static int flag_gcov_file = 1;
 
 static int flag_display_progress = 0;
 
+/* Output *.gcov file in intermediate format used by 'lcov'.  */
+static int flag_intermediate_format = 0;
+
 /* For included files, make the gcov output file name include the name
    of the input source file.  For example, if x.h is included in a.c,
    then the output file name is a.c##x.h.gcov instead of x.h.gcov.  */
@@ -436,6 +440,11 @@  print_usage (int error_p)
   fnotice (file, "  -o, --object-directory DIR|FILE Search for object files in DIR or called FILE\n");
   fnotice (file, "  -p, --preserve-paths            Preserve all pathname components\n");
   fnotice (file, "  -u, --unconditional-branches    Show unconditional branch counts too\n");
+  fnotice (file, "  -i, --intermediate-format       Output .gcov file in an intermediate text\n\
+                                    format that can be used by 'lcov' or other\n\
+                                    applications.  It will output a single\n\
+                                    .gcov file per .gcda file.  No source file\n\
+                                    is required.\n");
   fnotice (file, "  -d, --display-progress          Display progress information\n");
   fnotice (file, "\nFor bug reporting instructions, please see:\n%s.\n",
 	   bug_report_url);
@@ -472,6 +481,7 @@  static const struct option options[] =
   { "object-file",          required_argument, NULL, 'o' },
   { "unconditional-branches", no_argument,     NULL, 'u' },
   { "display-progress",     no_argument,       NULL, 'd' },
+  { "intermediate-format",  no_argument,       NULL, 'i' },
   { 0, 0, 0, 0 }
 };
 
@@ -482,7 +492,8 @@  process_args (int argc, char **argv)
 {
   int opt;
 
-  while ((opt = getopt_long (argc, argv, "abcdfhlno:puv", options, NULL)) != -1)
+  while ((opt = getopt_long (argc, argv, "abcdfhilno:puv", options, NULL)) !=
+         -1)
     {
       switch (opt)
 	{
@@ -516,6 +527,10 @@  process_args (int argc, char **argv)
 	case 'u':
 	  flag_unconditional = 1;
 	  break;
+	case 'i':
+          flag_intermediate_format = 1;
+          flag_gcov_file = 1;
+          break;
         case 'd':
           flag_display_progress = 1;
           break;
@@ -531,6 +546,107 @@  process_args (int argc, char **argv)
   return optind;
 }
 
+/* Get the name of the gcov file.  The return value must be free'd.
+
+   It appends the '.gcov' extension to the *basename* of the file.
+   The resulting file name will be in PWD.
+
+   e.g.,
+   input: foo.da,       output: foo.da.gcov
+   input: a/b/foo.cc,   output: foo.cc.gcov  */
+
+static char *
+get_gcov_file_intermediate_name (const char *file_name)
+{
+  const char *gcov = ".gcov";
+  char *result;
+  const char *cptr;
+
+  /* Find the 'basename'.  */
+  cptr = lbasename (file_name);
+
+  result = XNEWVEC(char, strlen (cptr) + strlen (gcov) + 1);
+  sprintf (result, "%s%s", cptr, gcov);
+
+  return result;
+}
+
+/* Output the result in intermediate format used by 'lcov'.
+
+The intermediate format contains a single file named 'foo.cc.gcov',
+with no source code included.
+
+SF:/home/.../foo.h
+DA:10,1
+DA:30,0
+DA:35,1
+SF:/home/.../bar.h
+DA:12,0
+DA:33,0
+DA:55,1
+SF:/home/.../foo.cc
+FN:30,<function_name>
+FNDA:2,<function_name>
+DA:42,0
+DA:53,1
+BA:55,1
+BA:55,2
+DA:95,1
+...
+
+The default format contains 3 separate files: 'foo.h.gcov', 'foo.cc.gcov',
+'bar.h.gcov', each with source code included.  */
+
+static void
+output_intermediate_file (FILE *gcov_file, source_t *src)
+{
+  unsigned line_num;    /* current line number.  */
+  const line_t *line;   /* current line info ptr.  */
+  function_t *fn;       /* current function info ptr. */
+
+  fprintf (gcov_file, "SF:%s\n", src->name);    /* source file name */
+
+  /* NOTE: 'gcov' sometimes output 2 extra lines (including 1 EOF
+     line) in the end. Likely related:
+     http://gcc.gnu.org/bugzilla/show_bug.cgi?id=15369
+  */
+
+  for (fn = src->functions; fn; fn = fn->line_next)
+    {
+      char *demangled_name;
+      demangled_name = cplus_demangle (fn->name, DMGL_PARAMS);
+      /* FN:<line_number>,<function_name> */
+      fprintf (gcov_file, "FN:%d,%s\n", fn->line,
+               demangled_name ? demangled_name : fn->name);
+      /* FNDA:<execution_count>,<function_name> */
+      fprintf (gcov_file, "FNDA:%s,%s\n",
+               format_gcov (fn->blocks[0].count, 0, -1),
+               demangled_name ? demangled_name : fn->name);
+    }
+
+  for (line_num = 1, line = &src->lines[line_num];
+       line_num < src->num_lines;
+       line_num++, line++)
+    {
+      arc_t *arc;
+      if (line->exists)
+        fprintf (gcov_file, "DA:%u,%d\n", line_num,
+                 line->count != 0 ? 1 : 0);
+      if (flag_branches)
+        for (arc = line->u.branches; arc; arc = arc->line_next)
+          {
+            /* BA:<line_num>,<branch_coverage_type>
+                  branch_coverage_type: 0 (Branch not executed)
+                                      : 1 (Branch executed, but not taken)
+                                      : 2 (Branch executed and taken)
+            */
+            if (!arc->is_unconditional && !arc->is_call_non_return)
+              fprintf(gcov_file, "BA:%d,%d\n", line_num,
+                      arc->src->count ? (arc->count > 0) + 1 : 0);
+          }
+    }
+}
+
 /* Process a single source file.  */
 
 static void
@@ -570,6 +686,8 @@  generate_results (const char *file_name)
 {
   source_t *src;
   function_t *fn;
+  FILE *gcov_file_intermediate = NULL;
+  char *gcov_file_intermediate_name = NULL;
 
   for (src = sources; src; src = src->next)
     src->lines = XCNEWVEC (line_t, src->num_lines);
@@ -587,31 +705,55 @@  generate_results (const char *file_name)
 	}
     }
 
+  if (flag_gcov_file && flag_intermediate_format)
+    {
+      /* Open the intermediate file.  */
+      gcov_file_intermediate_name =
+        get_gcov_file_intermediate_name (file_name);
+      gcov_file_intermediate = fopen (gcov_file_intermediate_name, "w");
+    }
   for (src = sources; src; src = src->next)
     {
       accumulate_line_counts (src);
       function_summary (&src->coverage, "File");
       if (flag_gcov_file)
 	{
-	  char *gcov_file_name = make_gcov_file_name (file_name, src->name);
-	  FILE *gcov_file = fopen (gcov_file_name, "w");
-
-	  if (gcov_file)
-	    {
-	      fnotice (stdout, "%s:creating '%s'\n",
-		       src->name, gcov_file_name);
-	      output_lines (gcov_file, src);
-	      if (ferror (gcov_file))
-		    fnotice (stderr, "%s:error writing output file '%s'\n",
-			     src->name, gcov_file_name);
-	      fclose (gcov_file);
-	    }
-	  else
-	    fnotice (stderr, "%s:could not open output file '%s'\n",
-		     src->name, gcov_file_name);
-	  free (gcov_file_name);
-	}
-      fnotice (stdout, "\n");
+         if (flag_intermediate_format)
+           /* Now output in the intermediate format without requiring
+              source files.  This outputs a section to a *single* file.  */
+           output_intermediate_file (gcov_file_intermediate, src);
+         else
+           {
+             /* Now output the version with source files.
+                This outputs a separate *.gcov file for each source file
+                involved.  */
+             char *gcov_file_name = make_gcov_file_name (file_name, src->name);
+             FILE *gcov_file = fopen (gcov_file_name, "w");
+
+             if (gcov_file)
+               {
+                 fnotice (stdout, "%s:creating '%s'\n",
+                          src->name, gcov_file_name);
+                 output_lines (gcov_file, src);
+                 if (ferror (gcov_file))
+                   fnotice (stderr, "%s:error writing output file '%s'\n",
+                            src->name, gcov_file_name);
+                 fclose (gcov_file);
+               }
+             else
+               fnotice (stderr, "%s:could not open output file '%s'\n",
+                        src->name, gcov_file_name);
+             free (gcov_file_name);
+           }
+         fnotice (stdout, "\n");
+        }
+    }
+
+  if (flag_gcov_file && flag_intermediate_format)
+    {
+      /* Now we've finished writing the intermediate file.  */
+      fclose (gcov_file_intermediate);
+      XDELETEVEC (gcov_file_intermediate_name);
     }
 }
 
Index: testsuite/lib/gcov.exp
===================================================================
--- testsuite/lib/gcov.exp	(revision 179475)
+++ testsuite/lib/gcov.exp	(working copy)
@@ -60,6 +60,59 @@  proc verify-lines { testcase file } {
 }
 
 #
+# verify-intermediate -- check that intermediate file has certain lines
+#
+# TESTCASE is the name of the test.
+# FILE is the name of the gcov output file.
+#
+# Checks are very loose, they are based on being certain tags present
+# in the output. They do not check for exact expected execution
+# counts. For that the regular gcov format should be checked.
+#
+proc verify-intermediate { testcase file } {
+    set failed 0
+    set sf 0
+    set fn 0
+    set fnda 0
+    set da 0
+    set fd [open $file r]
+    while { [gets $fd line] >= 0 } {
+	if [regexp "^SF:" $line] {
+	    incr sf
+	}
+	if [regexp "^FN:(\[0-9\]+)," $line] {
+	    incr fn
+	}
+	if [regexp "^FNDA:(\[0-9\]+)," $line] {
+	    incr fnda
+	}
+	if [regexp "^DA:(\[0-9\]+),(\[0-9\]+)" $line] {
+	    incr da
+	}
+    }
+
+    # We should see at least one tag of each type
+    if {$sf == 0} {
+	fail "expected SF: not found"
+	incr failed
+    }
+    if {$fn == 0} {
+	fail "expected FN: not found"
+	incr failed
+    }
+    if {$fnda == 0} {
+	fail "expected FNDA: not found"
+	incr failed
+    }
+    if {$da == 0} {
+	fail "expected DA: not found"
+	incr failed
+    }
+    return $failed
+}
+
+
+#
 # verify-branches -- check that branch percentages are as expected
 #
 # TESTCASE is the name of the test.
@@ -234,6 +287,8 @@  proc run-gcov { args } {
 
     set gcov_verify_calls 0
     set gcov_verify_branches 0
+    set gcov_verify_lines 1
+    set gcov_verify_intermediate 0
     set gcov_execute_xfail ""
     set gcov_verify_xfail ""
 
@@ -242,6 +297,11 @@  proc run-gcov { args } {
 	  set gcov_verify_calls 1
 	} elseif { $a == "branches" } {
 	  set gcov_verify_branches 1
+	} elseif { $a == "intermediate" } {
+	  set gcov_verify_intermediate 1
+	  set gcov_verify_calls 0
+	  set gcov_verify_branches 0
+	  set gcov_verify_lines 0
 	}
     }
 
@@ -274,8 +334,12 @@  proc run-gcov { args } {
 	eval setup_xfail [split $gcov_verify_xfail]
     }
 
-    # Check that line execution counts are as expected.
-    set lfailed [verify-lines $testcase $testcase.gcov]
+    if { $gcov_verify_lines } {
+	# Check that line execution counts are as expected.
+	set lfailed [verify-lines $testcase $testcase.gcov]
+    } else {
+	set lfailed 0
+    }
 
     # If requested via the .x file, check that branch and call information
     # is correct.
@@ -289,12 +353,18 @@  proc run-gcov { args } {
     } else {
 	set cfailed 0
     }
+    if { $gcov_verify_intermediate } {
+	# Check that intermediate format has the expected format
+	set ifailed [verify-intermediate $testcase $testcase.gcov]
+    } else {
+	set ifailed 0
+    }
 
     # Report whether the gcov test passed or failed.  If there were
     # multiple failures then the message is a summary.
-    set tfailed [expr $lfailed + $bfailed + $cfailed]
+    set tfailed [expr $lfailed + $bfailed + $cfailed + $ifailed]
     if { $tfailed > 0 } {
-	fail "$subdir/$testcase gcov: $lfailed failures in line counts, $bfailed in branch percentages, $cfailed in return percentages"
+	fail "$subdir/$testcase gcov: $lfailed failures in line counts, $bfailed in branch percentages, $cfailed in return percentages, $ifailed in intermediate format"
     } else {
 	pass "$subdir/$testcase gcov"
 	clean-gcov $testcase
Index: testsuite/g++.dg/gcov/gcov-8.C
===================================================================
--- testsuite/g++.dg/gcov/gcov-8.C	(revision 0)
+++ testsuite/g++.dg/gcov/gcov-8.C	(revision 0)
@@ -0,0 +1,32 @@ 
+/* Verify that intermediate coverage format can be generated for simple code. */
+
+/* { dg-options "-fprofile-arcs -ftest-coverage" } */
+/* { dg-do run { target native } } */
+
+class C {
+public:
+  C()
+  {
+    i = 0;                              /* count(1) */
+  }
+  ~C() {}
+  void seti (int j)
+  {
+    i = j;                              /* count(1) */
+  }
+private:
+  int i;
+};
+
+void foo()
+{
+  C c;                                  /* count(2) */
+  c.seti (1);                           /* count(1) */
+}
+
+int main()
+{
+  foo();                                /* count(1) */
+}
+
+/* { dg-final { run-gcov intermediate { -i gcov-8.C } } } */