-# Copyright (C) 2016-2019 all contributors <meta@public-inbox.org>
+# Copyright (C) 2016-2020 all contributors <meta@public-inbox.org>
# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
#
# git fast-import-based ssoma-mda MDA replacement
use strict;
use warnings;
use base qw(PublicInbox::Lock);
-use PublicInbox::Spawn qw(spawn);
-use PublicInbox::MID qw(mids mid_mime mid2path);
+use PublicInbox::Spawn qw(spawn popen_rd);
+use PublicInbox::MID qw(mids mid2path);
use PublicInbox::Address;
use PublicInbox::MsgTime qw(msg_timestamp msg_datestamp);
use PublicInbox::ContentId qw(content_digest);
return ($self->{in}, $self->{out}) if $self->{pid};
- my ($in_r, $in_w, $out_r, $out_w);
- pipe($in_r, $in_w) or die "pipe failed: $!";
+ my ($out_r, $out_w);
pipe($out_r, $out_w) or die "pipe failed: $!";
my $git = $self->{git};
my $git_dir = $git->{git_dir};
my @cmd = ('git', "--git-dir=$git_dir", qw(fast-import
--quiet --done --date-format=raw));
- my $rdr = { 0 => fileno($out_r), 1 => fileno($in_w) };
- my $pid = spawn(\@cmd, undef, $rdr);
- die "spawn fast-import failed: $!" unless defined $pid;
+ my ($in_r, $pid) = popen_rd(\@cmd, undef, { 0 => $out_r });
$out_w->autoflush(1);
$self->{in} = $in_r;
$self->{out} = $out_w;
my $env = { GIT_INDEX_FILE => $index };
run_die([@cmd, qw(read-tree -m -v -i), $self->{ref}], $env);
}
- run_die([@cmd, 'update-server-info'], undef);
- ($self->{path_type} eq '2/38') and eval {
+ run_die([@cmd, 'update-server-info']);
+ my $ibx = $self->{-inbox};
+ ($ibx && $self->{path_type} eq '2/38') and eval {
require PublicInbox::SearchIdx;
- my $ibx = $self->{-inbox} || $git_dir;
my $s = PublicInbox::SearchIdx->new($ibx);
$s->index_sync({ ref => $self->{ref} });
};
- eval { run_die([@cmd, qw(gc --auto)], undef) } if $do_gc;
+ eval { run_die([@cmd, qw(gc --auto)]) } if $do_gc;
}
sub barrier {
"$ts $zone";
}
-sub extract_cmt_info ($) {
- my ($mime) = @_;
+sub extract_cmt_info ($;$) {
+ my ($mime, $smsg) = @_;
my $sender = '';
my $from = $mime->header('From');
}
}
if (defined $email) {
+ # Email::Address::XS may leave quoted '<' in addresses,
+ # which git-fast-import doesn't like
+ $email =~ tr/<>//d;
+
# quiet down wide character warnings with utf8::encode
utf8::encode($email);
} else {
utf8::encode($subject);
my $at = git_timestamp(my @at = msg_datestamp($hdr));
my $ct = git_timestamp(my @ct = msg_timestamp($hdr));
+ if ($smsg) {
+ $smsg->{ds} = $at[0];
+ $smsg->{ts} = $ct[0];
+ }
($name, $email, $at, $ct, $subject);
}
my $hdr = $mime->header_obj;
my $mids = mids($hdr);
- if (!scalar(@$mids)) { # spam often has no Message-Id
+ if (!scalar(@$mids)) { # spam often has no Message-ID
my $mid0 = digest2mid(content_digest($mime), $hdr);
append_mid($hdr, $mid0);
return $mid0;
# returns undef on duplicate
# returns the :MARK of the most recent commit
sub add {
- my ($self, $mime, $check_cb) = @_; # mime = Email::MIME
+ my ($self, $mime, $check_cb, $smsg) = @_; # mime = Email::MIME
- my ($name, $email, $at, $ct, $subject) = extract_cmt_info($mime);
+ my ($name, $email, $at, $ct, $subject) = extract_cmt_info($mime, $smsg);
my $path_type = $self->{path_type};
my $path;
if ($path_type eq '2/38') {
}
my $blob = $self->{mark}++;
- my $str = $mime->as_string;
- my $n = length($str);
+ my $raw_email = $mime->{-public_inbox_raw} // $mime->as_string;
+ my $n = length($raw_email);
$self->{bytes_added} += $n;
print $w "blob\nmark :$blob\ndata ", $n, "\n" or wfail;
- print $w $str, "\n" or wfail;
+ print $w $raw_email, "\n" or wfail;
# v2: we need this for Xapian
- if ($self->{want_object_info}) {
- my $oid = $self->get_mark(":$blob");
- $self->{last_object} = [ $oid, $n, \$str ];
+ if ($smsg) {
+ $smsg->{blob} = $self->get_mark(":$blob");
+ $smsg->{bytes} = $n;
+ $smsg->{-raw_email} = \$raw_email;
}
my $ref = $self->{ref};
my $commit = $self->{mark}++;
sub run_die ($;$$) {
my ($cmd, $env, $rdr) = @_;
my $pid = spawn($cmd, $env, $rdr);
- defined $pid or die "spawning ".join(' ', @$cmd)." failed: $!";
waitpid($pid, 0) == $pid or die join(' ', @$cmd) .' did not finish';
$? == 0 or die join(' ', @$cmd) . " failed: $?\n";
}
+my @INIT_FILES = ('HEAD' => "ref: refs/heads/master\n",
+ 'description' => <<EOD,
+Unnamed repository; edit this file 'description' to name the repository.
+EOD
+ 'config' => <<EOC);
+[core]
+ repositoryFormatVersion = 0
+ filemode = true
+ bare = true
+[repack]
+ writeBitmaps = true
+EOC
+
sub init_bare {
- my ($dir) = @_;
- my @cmd = (qw(git init --bare -q), $dir);
- run_die(\@cmd);
- # set a reasonable default:
- @cmd = (qw/git config/, "--file=$dir/config",
- 'repack.writeBitmaps', 'true');
- run_die(\@cmd);
+ my ($dir) = @_; # or self
+ $dir = $dir->{git}->{git_dir} if ref($dir);
+ require File::Path;
+ File::Path::mkpath([ map { "$dir/$_" } qw(objects/info refs/heads) ]);
+ for (my $i = 0; $i < @INIT_FILES; $i++) {
+ my $f = $dir.'/'.$INIT_FILES[$i++];
+ next if -f $f;
+ open my $fh, '>', $f or die "open $f: $!";
+ print $fh $INIT_FILES[$i] or die "print $f: $!";
+ close $fh or die "close $f: $!";
+ }
}
sub done {
"$dt.$b64" . '@z';
}
-sub clean_purge_buffer {
- my ($oids, $buf) = @_;
- my $cmt_msg = 'purged '.join(' ',@$oids)."\n";
+sub rewrite_commit ($$$$) {
+ my ($self, $oids, $buf, $mime) = @_;
+ my ($name, $email, $at, $ct, $subject);
+ if ($mime) {
+ ($name, $email, $at, $ct, $subject) = extract_cmt_info($mime);
+ } else {
+ $name = $email = '';
+ $subject = 'purged '.join(' ', @$oids);
+ }
@$oids = ();
-
+ $subject .= "\n";
foreach my $i (0..$#$buf) {
my $l = $buf->[$i];
if ($l =~ /^author .* ([0-9]+ [\+-]?[0-9]+)$/) {
- $buf->[$i] = "author <> $1\n";
+ $at //= $1;
+ $buf->[$i] = "author $name <$email> $at\n";
+ } elsif ($l =~ /^committer .* ([0-9]+ [\+-]?[0-9]+)$/) {
+ $ct //= $1;
+ $buf->[$i] = "committer $self->{ident} $ct\n";
} elsif ($l =~ /^data ([0-9]+)/) {
- $buf->[$i++] = "data " . length($cmt_msg) . "\n";
- $buf->[$i] = $cmt_msg;
+ $buf->[$i++] = "data " . length($subject) . "\n";
+ $buf->[$i] = $subject;
last;
}
}
}
-sub purge_oids {
- my ($self, $purge) = @_;
- my $tmp = "refs/heads/purge-".((keys %$purge)[0]);
+# returns the new commit OID if a replacement was done
+# returns undef if nothing was done
+sub replace_oids {
+ my ($self, $mime, $replace_map) = @_; # oid => raw string
+ my $tmp = "refs/heads/replace-".((keys %$replace_map)[0]);
my $old = $self->{'ref'};
my $git = $self->{git};
my @export = (qw(fast-export --no-data --use-done-feature), $old);
my $rd = $git->popen(@export);
my ($r, $w) = $self->gfi_start;
my @buf;
- my $npurge = 0;
+ my $nreplace = 0;
my @oids;
my ($done, $mark);
my $tree = $self->{-tree};
} elsif (/^M 100644 ([a-f0-9]+) (\w+)/) {
my ($oid, $path) = ($1, $2);
$tree->{$path} = 1;
- if ($purge->{$oid}) {
+ my $sref = $replace_map->{$oid};
+ if (defined $sref) {
push @oids, $oid;
- my $cmd = "M 100644 inline $path\ndata 0\n\n";
- push @buf, $cmd;
+ my $n = length($$sref);
+ push @buf, "M 100644 inline $path\ndata $n\n";
+ push @buf, $$sref; # hope CoW works...
+ push @buf, "\n";
} else {
push @buf, $_;
}
push @buf, $_ if $tree->{$path};
} elsif ($_ eq "\n") {
if (@oids) {
- my $out = join('', @buf);
- $out =~ s/^/# /sgm;
- warn "purge rewriting\n", $out, "\n";
- clean_purge_buffer(\@oids, \@buf);
- $npurge++;
+ if (!$mime) {
+ my $out = join('', @buf);
+ $out =~ s/^/# /sgm;
+ warn "purge rewriting\n", $out, "\n";
+ }
+ rewrite_commit($self, \@oids, \@buf, $mime);
+ $nreplace++;
}
$w->print(@buf, "\n") or wfail;
@buf = ();
$w->print(@buf) or wfail;
}
die 'done\n not seen from fast-export' unless $done;
- chomp(my $cmt = $self->get_mark(":$mark")) if $npurge;
+ chomp(my $cmt = $self->get_mark(":$mark")) if $nreplace;
$self->{nchg} = 0; # prevent _update_git_info until update-ref:
$self->done;
my @git = ('git', "--git-dir=$git->{git_dir}");
- run_die([@git, qw(update-ref), $old, $tmp]) if $npurge;
+ run_die([@git, qw(update-ref), $old, $tmp]) if $nreplace;
run_die([@git, qw(update-ref -d), $tmp]);
- return if $npurge == 0;
+ return if $nreplace == 0;
+
+ run_die([@git, qw(-c gc.reflogExpire=now gc --prune=all --quiet)]);
- run_die([@git, qw(-c gc.reflogExpire=now gc --prune=all)]);
+ # check that old OIDs are gone
my $err = 0;
- foreach my $oid (keys %$purge) {
+ foreach my $oid (keys %$replace_map) {
my @info = $git->check($oid);
if (@info) {
- warn "$oid not purged\n";
+ warn "$oid not replaced\n";
$err++;
}
}
_update_git_info($self, 0);
- die "Failed to purge $err object(s)\n" if $err;
+ die "Failed to replace $err object(s)\n" if $err;
$cmt;
}
version 1.0
-=head1 SYNOPSYS
+=head1 SYNOPSIS
use Email::MIME;
use PublicInbox::Git;