Compute a digest of each report file, and nuke reports that have the same

digest as a file already added to the index.  This a workaround for the
analyzer analyzing the same file more than once, which can happen when building
multiple targets.

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@49903 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/utils/scan-build b/utils/scan-build
index f6d894b2f239d415c6759a8bda27d86390a5674a..441f63f1c1bee1b9c368670a987c34c249e6773b 100755 (executable)
--- a/utils/scan-build
+++ b/utils/scan-build
@@ -115,16 +115,47 @@ sub SetHtmlEnv {
   $ENV{'CCC_ANALYZER_HTML'} = $Dir;
 }
 
+##----------------------------------------------------------------------------##
+# ComputeDigest - Compute a digest of the specified file.
+##----------------------------------------------------------------------------##
+
+sub ComputeDigest {
+  my $FName = shift;
+  die "Cannot read $FName" if (! -r $FName);  
+  my $Result = `sha1sum -b $FName`;
+  my @Output = split /\s+/,$Result;
+  die "Bad output from sha1sum" if (scalar(@Output) != 2);
+  return $Output[0];
+}
+
 ##----------------------------------------------------------------------------##
 # ScanFile - Scan a report file for various identifying attributes.
 ##----------------------------------------------------------------------------##
 
+# Sometimes a source file is scanned more than once, and thus produces
+# multiple error reports.  We use a cache to solve this problem.
+
+my %AlreadyScanned;
+
 sub ScanFile {
   
   my $Index = shift;
   my $Dir = shift;
   my $FName = shift;
   
+  # Compute a digest for the report file.  Determine if we have already
+  # scanned a file that looks just like it.
+  
+  my $digest = ComputeDigest("$Dir/$FName");
+
+  if (defined($AlreadyScanned{$digest})) {
+    # Redundant file.  Remove it.
+    `rm -f $Dir/$FName`;
+    return;
+  }
+  
+  $AlreadyScanned{$digest} = 1;
+  
   open(IN, "$Dir/$FName") or die "$Prog: Cannot open '$Dir/$FName'\n";
 
   my $BugDesc = "";