From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.2 (2018-09-13) on dcvr.yhbt.net X-Spam-Level: X-Spam-Status: No, score=-4.0 required=3.0 tests=ALL_TRUSTED,BAYES_00 shortcircuit=no autolearn=ham autolearn_force=no version=3.4.2 Received: from localhost (dcvr.yhbt.net [127.0.0.1]) by dcvr.yhbt.net (Postfix) with ESMTP id 9AD2C1FA12 for ; Thu, 31 Dec 2020 13:51:54 +0000 (UTC) From: Eric Wong To: meta@public-inbox.org Subject: [PATCH 02/36] lei_store: use per-machine refname as git HEAD Date: Thu, 31 Dec 2020 13:51:20 +0000 Message-Id: <20201231135154.6070-3-e@80x24.org> In-Reply-To: <20201231135154.6070-1-e@80x24.org> References: <20201231135154.6070-1-e@80x24.org> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit List-Id: It may be helpful to identify the source of messages and perhaps avoid conflicting history. On the other hand, this may be a terrible idea for users who move portable storage (e.g. USB sticks) across computers... --- lib/PublicInbox/Import.pm | 10 ++++++---- lib/PublicInbox/LeiStore.pm | 21 ++++++++++++++++++++- 2 files changed, 26 insertions(+), 5 deletions(-) diff --git a/lib/PublicInbox/Import.pm b/lib/PublicInbox/Import.pm index 7258e848..60cff9c2 100644 --- a/lib/PublicInbox/Import.pm +++ b/lib/PublicInbox/Import.pm @@ -463,16 +463,18 @@ EOD EOC sub init_bare { - my ($dir) = @_; # or self + my ($dir, $head) = @_; # or self $dir = $dir->{git}->{git_dir} if ref($dir); require File::Path; File::Path::mkpath([ map { "$dir/$_" } qw(objects/info refs/heads) ]); $INIT_FILES[1] //= 'ref: '.default_branch."\n"; - for (my $i = 0; $i < @INIT_FILES; $i++) { - my $f = $dir.'/'.$INIT_FILES[$i++]; + my @fn_contents = @INIT_FILES; + $fn_contents[1] = "ref: refs/heads/$head\n" if defined $head; + while (my ($fn, $contents) = splice(@fn_contents, 0, 2)) { + my $f = $dir.'/'.$fn; next if -f $f; open my $fh, '>', $f or die "open $f: $!"; - print $fh $INIT_FILES[$i] or die "print $f: $!"; + print $fh $contents or die "print $f: $!"; close $fh or die "close $f: $!"; } } diff --git a/lib/PublicInbox/LeiStore.pm b/lib/PublicInbox/LeiStore.pm index 553adbc8..a17c7bab 100644 --- a/lib/PublicInbox/LeiStore.pm +++ b/lib/PublicInbox/LeiStore.pm @@ -60,6 +60,24 @@ sub git_ident ($) { ('lei user', 'x@example.com') } +# We will support users combining storage across multiple machines +# somehow. Use per-machine refnames to make it easy-to-identify +# where a message came from +sub host_head () { + state $h = do { + my $x = PublicInbox::ExtSearchIdx::host_ident; + # Similar rules found in git.git/remote.c::valid_remote_nick + # and git.git/refs.c::check_refname_component + $x =~ s!(?:\.lock|/)+\z!!gs; # must not end with ".lock" or "/" + $x =~ tr/././s; # no dot-dot, collapse them + $x =~ s/@\{/\@-/gs; + $x =~ s/\A\./-/s; + # no "*", ":", "?", "[", "\", "^", "~", SP, TAB; "]" is OK + $x =~ tr^a-zA-Z0-9!"#$%&'()+,\-.;<=>@]_`{|}^-^c; + $x + }; +} + sub importer { my ($self) = @_; my $max; @@ -78,8 +96,8 @@ sub importer { while (1) { my $latest = "$pfx/$max.git"; my $old = -e $latest; + PublicInbox::Import::init_bare($latest, host_head); my $git = PublicInbox::Git->new($latest); - PublicInbox::Import::init_bare({ git => $git }); $git->qx(qw(config core.sharedRepository 0600)) if !$old; my $packed_bytes = $git->packed_bytes; my $unpacked_bytes = $packed_bytes / $self->packing_factor; @@ -92,6 +110,7 @@ sub importer { $im->{bytes_added} = int($packed_bytes / $self->packing_factor); $im->{lock_path} = undef; $im->{path_type} = 'v2'; + $im->{'ref'} = host_head; return $im; } }