build: Allow symbol search tool to skip directories

At the end of "make install", a tool is run to search for common
symbols in the built artifacts, to work around issues on MacOS.
This tool requires an exclude list for symbols that must be
in the common section (such as in executables instead of libraries
and because Fortran).

This commit adds the ability to exclude certain directories from
the search, such as directories that are 3rd party packages or
only contain tests/executables, which will not run into problems
on MacOS.

To simplify that change, the file search in find_common_syms was
also rewritten to use the Perl-standard File::Find package instead
of calling the find executable.  Theoretically, this should be
mildly faster, but is also significantly easier to modify.

Signed-off-by: Brian Barrett <bbarrett@amazon.com>

LICENSE

@@ -53,7 +53,7 @@ Copyright (c) 2014-2015 Hewlett-Packard Development Company, LP.  All
                         rights reserved.
 Copyright (c) 2013-2017 Research Organization for Information Science (RIST).
                         All rights reserved.
-Copyright (c) 2017-2018 Amazon.com, Inc. or its affiliates.  All Rights
+Copyright (c) 2017-2020 Amazon.com, Inc. or its affiliates.  All Rights
                         reserved.
 Copyright (c) 2018      DataDirect Networks. All rights reserved.
 Copyright (c) 2018-2019 Triad National Security, LLC. All rights reserved.

Makefile.am

@@ -12,7 +12,7 @@
 # Copyright (c) 2006-2016 Cisco Systems, Inc.  All rights reserved.
 # Copyright (c) 2012-2015 Los Alamos National Security, Inc.  All rights reserved.
 # Copyright (c) 2014-2019 Intel, Inc.  All rights reserved.
-# Copyright (c) 2017-2018 Amazon.com, Inc. or its affiliates.
+# Copyright (c) 2017-2020 Amazon.com, Inc. or its affiliates.
 #                         All Rights reserved.
 # Copyright (c) 2020      IBM Corporation.  All rights reserved.
 # $COPYRIGHT$
@@ -50,7 +50,7 @@ install-exec-hook:
 	        --brief \
 	        --top_builddir=$(top_builddir) \
 	        --top_srcdir=$(top_srcdir) \
-	        --objext=$(OBJEXT); \
+	        --objext=$(OBJEXT) ; \
 	fi
 
 ACLOCAL_AMFLAGS = -I config

config/find_common_syms

@@ -1,5 +1,7 @@
 #!/usr/bin/env perl
 # Copyright (c) 2006-2016 Cisco Systems, Inc.  All rights reserved.
+# Copyright (c) 2020      Amazon.com, Inc. or its affiliates.
+#                         All Rights reserved.
 # $COPYRIGHT$
 #
 # Additional copyrights may follow
@@ -16,6 +18,8 @@ use warnings;
 
 use Getopt::Long;
 use File::Basename qw(basename);
+use File::Find;
+use Data::Dumper;
 
 sub is_allowlisted;
 
@@ -27,10 +31,10 @@ my @sym_allowlist = ();
 sub usage {
     print STDERR <<EOT;
 Usage: $0 --top_builddir=BUILDDIR --top_srcdir=SRCDIR [--objext=OBJEXT] [--brief] [--full-path]
-
+[--skipdir=DIR]
 Searches for all ".OBJEXT" files in BUILDDIR and checks for the existence of
 common symbols.  Common symbols are problematic for some platforms, including
-OS X.
+OS X.  Skipdir can be specified multiple times.
 
 OBJEXT defaults to 'o' if not specified.
 EOT
@@ -43,6 +47,9 @@ my $objext = 'o';
 my $top_builddir = '';
 my $top_srcdir = '';
 my $print_full_obj_path = 0;
+my $n = 0;
+my @skipdirs = ();
+
 GetOptions(
     "all!" => \$all,
     "brief!" => \$brief,
@@ -50,6 +57,7 @@ GetOptions(
     "objext=s" => \$objext,
     "top_builddir=s" => \$top_builddir,
     "top_srcdir=s" => \$top_srcdir,
+    "skipdir=s" => \@skipdirs
 ) || usage();
 
 if (!$top_builddir or !$top_srcdir) {
@@ -69,23 +77,33 @@ if (0 != system("command -v nm >/dev/null 2>&1")) {
 # subdirectories.  That way a allowlisted symbol in one component doesn't
 # "shadow" a symbol that should not be allowlisted in another component.  If we
 # find this is actually a problem in practice then we can write a v2 update.
-my @wl_files = `find '${top_srcdir}' -name 'common_sym_allowlist.txt'`;
-foreach my $wl_file (@wl_files) {
-    chomp $wl_file;
-    my @lines = `cat $wl_file`;
-    foreach my $line (@lines) {
-        chomp $line;
+sub allowlist_find {
+    if (!/^common_sym_allowlist.txt\z/) { return; }
+
+    open(my $fh, "<", $_) or die "Can't open $_: $!";
+    while (my $line = <$fh>) {
+	chomp $line;
         next if ($line =~ /^\s*#/); # skip comments
         next if ($line =~ /^\s*$/); # skip blank lines
         push @sym_allowlist, $line;
     }
+    close($fh);
 }
+File::Find::find({wanted => \&allowlist_find}, $top_srcdir);
 
-my $n = 0;
-open(FIND, '-|', "find ${top_builddir} -name '*.${objext}'");
-OBJECT: while (my $obj_line = <FIND>) {
-    my $obj = $obj_line;
-    chomp $obj;
+sub object_find {
+    my $obj = $_;
+
+    # skip specified directories.  This needs to be before the objext
+    # search below, or the prune will be missed and we'll recursive
+    # into the directory anyway.
+    if (grep { $_ eq $obj} @skipdirs) {
+	$File::Find::prune = 1;
+	return;
+    }
+
+    # skip any files not of form *.$objext
+    if (!/^.*\.$objext\z/) { return; }
 
     # This pattern may not be 100% robust for all implementations of nm.  If
     # that turns out to be the case, we can try switching to "nm -P", which is
@@ -100,23 +118,23 @@ OBJECT: while (my $obj_line = <FIND>) {
         if ($n == 0) {
             print STDERR "WARNING!  Common symbols found:\n";
         }
+
+	$n++;
+
         if ($brief and $n == $MAX_BRIEF) {
             print STDERR "[...]\n";
             print STDERR "skipping remaining symbols. To see all symbols, run:\n";
             print STDERR "  " . join(" ", ($0, grep {!/--brief/} @orig_argv)) . "\n";
-            last OBJECT;
-        }
-        if ($print_full_obj_path) {
-            print STDERR "$obj: $sym_line";
         } else {
-            my $obj_basename = basename($obj);
-            printf STDERR "%25s: %s", $obj_basename, $sym_line;
-        }
-        ++$n;
+	    if ($print_full_obj_path) {
+		print STDERR $File::Find::name . ": " . $sym_line;
+	    } else {
+		printf STDERR "%25s: %s", $obj, $sym_line;
+	    }
+	}
     }
-    close(NM);
 }
-close(FIND);
+File::Find::find({wanted => \&object_find}, $top_builddir);
 
 if ($n > 0) {
     exit 1;