From 33b9a9ea4cadcdf7fde87be65bcdf826755bcf31 Mon Sep 17 00:00:00 2001
From: "B. Watson" <yalhcru@gmail.com>
Date: Sun, 3 Jun 2018 23:14:35 -0400
Subject: sbosrcarch purge_mode fix, wip

---
 sbosrcarch | 38 ++++++++++++++++++++++++--------------
 1 file changed, 24 insertions(+), 14 deletions(-)

diff --git a/sbosrcarch b/sbosrcarch
index 944e5ba..bfa91b5 100755
--- a/sbosrcarch
+++ b/sbosrcarch
@@ -378,7 +378,8 @@ our($sbogiturl, $sbogitdir, $archivedir, $maxfilemegs, $wget,
     $wgetargs, $symlinks, $wgetrc_contents, $wgetrc, %user_agent_overrides,
     @trim_empty_dirs, $skipcount, $urlcount, $archivecount,
     $attemptcount, $failcount, $dlcount, $nowarchived, $coverage,
-    $purgebytes, $purgefiles, $trimcount, $trimbytes, %keep_filenames);
+    $purgebytes, $purgefiles, $trimcount, $trimbytes,
+    %keep_filenames, %keep_md5sums, $fake_purge);
 our ($curl, $curlopts);
 our (%whitehash, %blackhash, $use_bwlist);
 our @whitelist = ();
@@ -561,6 +562,7 @@ sub parse_info {
 		$ret{$_} = $m;
 	}
 
+	close $fh;
 	return \%ret;
 }
 
@@ -1198,16 +1200,16 @@ sub update_mode {
 }
 
 # purge_mode() does 3 passes.
-# 1. get all the filenames from all the info files, build a hash of filenames.
-# 2. walk the archive tree with File::Find and rm any file that's in a
-#    category/name dir, but not mentioned in the filename hash (also, rm its
-#    md5_dir() counterpart).
+# 1. get all the filenames from all the info files, build hashes of filenames
+#    and md5sums that we want to keep.
+# 2. walk the archive tree with File::Find and rm any file that's (a) in a
+#    category/name dir, but not mentioned in the filename hash, or (b) in a
+#    by-md5 dir, but whose md5sum is not mentioned in the md5sum hash.
 # 3. do a trim_post() pass to delete any empty dirs and/or dangling symlinks
 # If --rebuild is given, pass 3 instead deletes the by-md5 tree and
 # recreates it.
+# If --fake is given, the 3 passes are all done, but nothing is deleted.
 
-# FIXME: files from different URLs but with the same filename will not be
-# purged when they should, because the comparison is solely filename-based!
 sub purge_mode {
 	my $rebuild = 0;
 
@@ -1215,6 +1217,8 @@ sub purge_mode {
 	if($ARGV[0]) {
 		if($ARGV[0] =~ /^--?r(?:ebuild)?/) {
 			$rebuild = 1;
+		} elsif($ARGV[0] =~ /^--?f(?:ake)?/) {
+			$fake_purge = 1;
 		} else {
 			die "Unknown option: $ARGV[0]\n";
 		}
@@ -1225,7 +1229,7 @@ sub purge_mode {
 	$purgebytes = $purgefiles = 0;
 
 	# pass 1
-	%keep_filenames = (); # populated by the find():
+	%keep_filenames = %keep_md5sums = (); # populated by the find():
 	find({wanted => \&purge_pass_1_wanted, no_chdir => 1}, ".");
 
 #	for(keys %keep_filenames) {
@@ -1249,13 +1253,15 @@ sub purge_mode {
 	exit 0;
 }
 
-# helper for purge_mode, populates %keep_filenames
+# helper for purge_mode, populates %keep_filenames and %keep_md5sums
 sub purge_pass_1_wanted {
 	return unless /\.info$/;
 	my $dls = parse_info($_);
+	my ($cat, $name, undef) = split /\//, $_;
 	for(keys %$dls) {
-		$_ = url_to_filename($_);
+		my $path = "by-name/$cat/$name/" . url_to_filename($_);
 		$keep_filenames{$_}++;
+		# TODO: populate %keep_md5sums
 	}
 }
 
@@ -1271,10 +1277,13 @@ sub purge_pass_2_wanted {
 	$purgefiles++;
 
 	my $namepath = name_dir($cat, $name) . "$file";
-	my $md5path = md5_dir(md5sum_file($namepath)) . "$file";
-	print "purge $namepath $md5path\n";
-	unlink $namepath;
-	unlink $md5path;
+	#my $md5path = md5_dir(md5sum_file($namepath)) . "$file";
+
+	#print "purge $namepath $md5path\n";
+	print "purge $namepath\n";
+
+	unlink $namepath unless $fake_purge;
+	#unlink $md5path;
 }
 
 sub rebuild_wanted {
@@ -1307,6 +1316,7 @@ sub trim_wanted {
 
 # helper for trim_post
 sub trim_post_wanted {
+	return if $fake_purge;
 	unlink $_ if -l $_ && ! -e _;
 	return unless -d _;
 	push @trim_empty_dirs, $_ if !<*>;
-- 
cgit v1.2.3