[PATCH 7/7] implement public-inbox-purge tool

[Eric Wong <e@80x24.org>]

Expose the ->purge functionality of V2Writable for rewriting
git history to permanently purge messages from history.  This
may be necessary for legal reasons.

Usage:

	# requires ~/.public-inbox/config
	public-inbox-purge --all </path/to/message-to-purge

	# good for testing with unconfigured inboxes:
	public-inbox-purge $INBOX_DIR </path/to/message-to-purge
---
 MANIFEST                  |   2 +
 script/public-inbox-purge | 111 ++++++++++++++++++++++++++++++++++++++
 t/purge.t                 |  97 +++++++++++++++++++++++++++++++++
 3 files changed, 210 insertions(+)
 create mode 100755 script/public-inbox-purge
 create mode 100644 t/purge.t

diff --git a/MANIFEST b/MANIFEST
index 5ac85c3..886ae6b 100644
--- a/MANIFEST
+++ b/MANIFEST
@@ -128,6 +128,7 @@ script/public-inbox-init
 script/public-inbox-learn
 script/public-inbox-mda
 script/public-inbox-nntpd
+script/public-inbox-purge
 script/public-inbox-watch
 script/public-inbox.cgi
 scripts/dc-dlvr
@@ -198,6 +199,7 @@ t/psgi_multipart_not.t
 t/psgi_search.t
 t/psgi_text.t
 t/psgi_v2.t
+t/purge.t
 t/qspawn.t
 t/reply.t
 t/search-thr-index.t
diff --git a/script/public-inbox-purge b/script/public-inbox-purge
new file mode 100755
index 0000000..688dd95
--- /dev/null
+++ b/script/public-inbox-purge
@@ -0,0 +1,111 @@
+#!/usr/bin/perl -w
+# Copyright (C) 2019 all contributors <meta@public-inbox.org>
+# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
+#
+# Used for purging messages entirely from a public-inbox.  Currently
+# supports v2 inboxes only, for now.
+use strict;
+use warnings;
+use Getopt::Long qw(:config gnu_getopt no_ignore_case auto_abbrev);
+use PublicInbox::Config;
+use PublicInbox::MIME;
+use PublicInbox::Admin qw(resolve_repo_dir);
+use PublicInbox::Filter::Base;
+*REJECT = *PublicInbox::Filter::Base::REJECT;
+
+my $usage = "$0 [--all] [INBOX_DIRS] </path/to/message";
+
+eval { require PublicInbox::V2Writable } or die
+	"DBI, DBD::SQLite and Search::Xapian required for purge\n";
+my $config = eval { PublicInbox::Config->new };
+my $cfgfile = PublicInbox::Config::default_file();
+my ($all, $force);
+my $verbose = 1;
+my %opts = (
+	'all' => \$all,
+	'force|f' => \$force,
+	'verbose|v!' => \$verbose,
+);
+GetOptions(%opts) or die "bad command-line args\n", $usage, "\n";
+
+# TODO: clean this up and share code with -index via ::Admin
+my %dir2ibx; # ( path => Inbox object )
+my @inboxes;
+$config and $config->each_inbox(sub {
+	my ($ibx) = @_;
+	push @inboxes, $ibx if $all && $ibx->{version} != 1;
+	$dir2ibx{$ibx->{mainrepo}} = $ibx;
+});
+
+if ($all) {
+	$config or die "--all specified, but $cfgfile not readable\n";
+	@ARGV and die "--all specified, but directories specified\n";
+} else {
+	my @err;
+	my @dirs = scalar(@ARGV) ? @ARGV : ('.');
+	my $u = 0;
+
+	foreach my $dir (@dirs) {
+		my $v;
+		my $dir = resolve_repo_dir($dir, \$v);
+		if ($v == 1) {
+			push @err, $dir;
+			next;
+		}
+		my $ibx = $dir2ibx{$dir} ||= do {
+			warn "$dir not configured in $cfgfile\n";
+			$u++;
+			my $name = "unconfigured-$u";
+			PublicInbox::Inbox->new({
+				version => 2,
+				name => $name,
+				-primary_address => "$name\@example.com",
+				mainrepo => $dir,
+			});
+		};
+		push @inboxes, $ibx;
+	}
+
+	if (@err) {
+		die "v1 inboxes currently not supported by -purge\n\t",
+		    join("\n\t", @err), "\n";
+	}
+}
+
+my $data = do { local $/; scalar <STDIN> };
+$data =~ s/\A[\r\n]*From [^\r\n]*\r?\n//s;
+my $n_purged = 0;
+
+foreach my $ibx (@inboxes) {
+	my $mime = PublicInbox::MIME->new($data);
+	my $v2w = PublicInbox::V2Writable->new($ibx, 0);
+
+	my $commits = $v2w->purge($mime) || [];
+
+	if (my $scrub = $ibx->filter($v2w)) {
+		my $scrubbed = $scrub->scrub($mime, 1);
+
+		if ($scrubbed && $scrubbed != REJECT()) {
+			my $scrub_commits = $v2w->purge($scrubbed);
+			push @$commits, @$scrub_commits if $scrub_commits;
+		}
+	}
+
+	$v2w->done;
+
+	if ($verbose) { # should we consider this machine-parseable?
+		print "$ibx->{mainrepo}:";
+		if (scalar @$commits) {
+			print join("\n\t", '', @$commits), "\n";
+		} else {
+			print " NONE\n";
+		}
+	}
+	$n_purged += scalar @$commits;
+}
+
+# behave like "rm -f"
+exit(0) if ($force || $n_purged);
+
+warn "Not found\n" if $verbose;
+exit(1);
diff --git a/t/purge.t b/t/purge.t
new file mode 100644
index 0000000..9406005
--- /dev/null
+++ b/t/purge.t
@@ -0,0 +1,97 @@
+# Copyright (C) 2019 all contributors <meta@public-inbox.org>
+# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
+use strict;
+use warnings;
+use Test::More;
+use File::Temp qw/tempdir/;
+require './t/common.perl';
+require_git(2.6);
+my @mods = qw(IPC::Run DBI DBD::SQLite Search::Xapian);
+foreach my $mod (@mods) {
+	eval "require $mod";
+	plan skip_all => "missing $_ for t/purge.t" if $@;
+};
+use Cwd qw(abs_path);
+my $purge = abs_path('blib/script/public-inbox-purge');
+my $tmpdir = tempdir('pi-purge-XXXXXX', TMPDIR => 1, CLEANUP => 1);
+use_ok 'PublicInbox::V2Writable';
+my $mainrepo = "$tmpdir/v2";
+my $ibx = PublicInbox::Inbox->new({
+	mainrepo => $mainrepo,
+	name => 'test-v2purge',
+	version => 2,
+	-primary_address => 'test@example.com',
+	indexlevel => 'basic',
+});
+
+my $raw = <<'EOF';
+From: a@example.com
+To: test@example.com
+Subject: this is a subject
+Message-ID: <a-mid@b>
+Date: Fri, 02 Oct 1993 00:00:00 +0000
+
+Hello World
+
+EOF
+
+local $ENV{NPROC} = '1';
+my $cfgfile = "$tmpdir/config";
+local $ENV{PI_CONFIG} = $cfgfile;
+open my $cfg_fh, '>', $cfgfile or die "open: $!";
+
+my $v2w = PublicInbox::V2Writable->new($ibx, 1);
+my $mime = PublicInbox::MIME->new($raw);
+ok($v2w->add($mime), 'add message to be purged');
+$v2w->done;
+
+# failing cases, first:
+my $in = "$raw\nMOAR\n";
+my ($out, $err) = ('', '');
+ok(IPC::Run::run([$purge, '-f', $mainrepo], \$in, \$out, \$err),
+	'purge -f OK');
+
+$out = $err = '';
+ok(!IPC::Run::run([$purge, $mainrepo], \$in, \$out, \$err),
+	'mismatch fails without -f');
+is($? >> 8, 1, 'missed purge exits with 1');
+
+# a successful case:
+ok(IPC::Run::run([$purge, $mainrepo], \$raw, \$out, \$err), 'match OK');
+like($out, qr/^\t[a-f0-9]{40,}/m, 'removed commit noted');
+
+# add (old) vger filter to config file
+print $cfg_fh <<EOF or die "print $!";
+[publicinbox "test-v2purge"]
+	mainrepo = $mainrepo
+	address = test\@example.com
+	indexlevel = basic
+	filter = PublicInbox::Filter::Vger
+EOF
+close $cfg_fh or die "close: $!";
+
+ok($v2w->add($mime), 'add vger-signatured message to be purged');
+$v2w->done;
+
+my $pre_scrub = $raw . <<'EOF';
+
+--
+To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
+the body of a message to majordomo@vger.kernel.org
+More majordomo info at  http://vger.kernel.org/majordomo-info.html
+Please read the FAQ at  http://www.tux.org/lkml/
+EOF
+
+$out = $err = '';
+ok(chdir('/'), "chdir / OK for --all test");
+ok(IPC::Run::run([$purge, '--all'], \$pre_scrub, \$out, \$err),
+	'scrub purge OK');
+like($out, qr/^\t[a-f0-9]{40,}/m, 'removed commit noted');
+# diag "out: $out"; diag "err: $err";
+
+$out = $err = '';
+ok(!IPC::Run::run([$purge, '--all' ], \$pre_scrub, \$out, \$err),
+	'scrub purge not idempotent without -f');
+# diag "out: $out"; diag "err: $err";
+
+done_testing();
-- 
EW