-# Copyright (C) 2020 all contributors <meta@public-inbox.org>
+# Copyright (C) 2020-2021 all contributors <meta@public-inbox.org>
# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
# Writes PublicInbox::Eml objects atomically to a mbox variant or Maildir
package PublicInbox::LeiToMail;
use strict;
use v5.10.1;
+use parent qw(PublicInbox::IPC);
use PublicInbox::Eml;
use PublicInbox::Lock;
use PublicInbox::ProcessPipe;
use PublicInbox::LeiDedupe;
use Symbol qw(gensym);
use IO::Handle; # ->autoflush
-use Fcntl qw(SEEK_SET);
+use Fcntl qw(SEEK_SET SEEK_END O_CREAT O_EXCL O_WRONLY);
+use Errno qw(EEXIST ESPIPE ENOENT);
+use PublicInbox::Git;
my %kw2char = ( # Maildir characters
draft => 'D',
$buf;
}
-sub write_in_full ($$$) {
- my ($fh, $buf, $atomic) = @_;
- if ($atomic) {
- defined(my $w = syswrite($fh, $$buf)) or die "write: $!";
- $w == length($$buf) or die "short write: $w != ".length($$buf);
- } else {
- print $fh $$buf or die "print: $!";
- }
+sub atomic_append { # for on-disk destinations (O_APPEND, or O_EXCL)
+ my ($fh, $buf) = @_;
+ defined(my $w = syswrite($fh, $$buf)) or die "write: $!";
+ $w == length($$buf) or die "short write: $w != ".length($$buf);
+}
+
+sub _print_full {
+ my ($fh, $buf) = @_;
+ print $fh $$buf or die "print: $!";
}
sub eml2mboxrd ($;$) {
$buf;
}
-sub mkmaildir ($) {
- my ($maildir) = @_;
- for (qw(new tmp cur)) {
- my $d = "$maildir/$_";
- next if -d $d;
- require File::Path;
- if (!File::Path::mkpath($d) && !-d $d) {
- die "failed to mkpath($d): $!\n";
- }
- }
-}
-
sub git_to_mail { # git->cat_async callback
my ($bref, $oid, $type, $size, $arg) = @_;
if ($type ne 'blob') {
# { foo => '' } means "--foo" is passed to the command-line,
# otherwise { foo => '--bar' } passes "--bar"
our %zsfx2cmd = (
- gz => [ qw(GZIP pigz gzip), {
- rsyncable => '', threads => '-p' } ],
+ gz => [ qw(GZIP pigz gzip), { rsyncable => '', threads => '-p' } ],
bz2 => [ 'bzip2', {} ],
xz => [ 'xz', { threads => '-T' } ],
# XXX does anybody care for these? I prefer zstd on entire FSes,
\@cmd;
}
-sub compress_dst {
- my ($out, $zsfx, $lei) = @_;
+sub _post_augment_mbox { # open a compressor process
+ my ($self, $lei) = @_;
+ my $zsfx = $self->{zsfx} or return;
my $cmd = zsfx2cmd($zsfx, undef, $lei);
pipe(my ($r, $w)) or die "pipe: $!";
- my $rdr = { 0 => $r, 1 => $out, 2 => $lei->{2} };
+ my $rdr = { 0 => $r, 1 => $lei->{1}, 2 => $lei->{2} };
my $pid = spawn($cmd, $lei->{env}, $rdr);
$lei->{"pid.$pid"} = $cmd;
my $pp = gensym;
tie *$pp, 'PublicInbox::ProcessPipe', $pid, $w, \&reap_compress, $lei;
- my $pipe_lk = ($lei->{opt}->{jobs} // 0) > 1 ?
- PublicInbox::Lock->new_tmp($zsfx) : undef;
- ($pp, $pipe_lk);
+ $lei->{1} = $pp;
+ die 'BUG: unexpected {ovv}->{lock_path}' if $lei->{ovv}->{lock_path};
+ $lei->{ovv}->ovv_out_lk_init if ($lei->{opt}->{jobs} // 2) > 1;
}
sub decompress_src ($$$) {
my ($in, $zsfx, $lei) = @_;
my $cmd = zsfx2cmd($zsfx, 1, $lei);
- my $rdr = { 0 => $in, 2 => $lei->{2} };
- popen_rd($cmd, $lei->{env}, $rdr);
+ popen_rd($cmd, $lei->{env}, { 0 => $in, 2 => $lei->{2} });
}
sub dup_src ($) {
my ($in) = @_;
- open my $dup, '+>>&', $in or die "dup: $!";
+ # fileno needed because wq_set_recv_modes only used ">&=" for {1}
+ # and Perl blindly trusts that to reject the '+' (readability flag)
+ open my $dup, '+>>&=', fileno($in) or die "dup: $!";
$dup;
}
sub _augment { # MboxReader eml_cb
my ($eml, $lei) = @_;
# ignore return value, just populate the skv
- $lei->{dedupe_cb}->is_dup($eml);
+ $lei->{dedupe}->is_dup($eml);
}
-sub _mbox_write_cb ($$$$) {
- my ($cls, $mbox, $dst, $lei) = @_;
- my $m = "eml2$mbox";
- my $eml2mbox = $cls->can($m) or die "$cls->$m missing";
- my ($out, $pipe_lk);
- open $out, '+>>', $dst or die "open $dst: $!";
- # Perl does SEEK_END even with O_APPEND :<
- seek($out, 0, SEEK_SET) or die "seek $dst: $!";
- my $jobs = $lei->{opt}->{jobs} // 0;
- my $atomic = $jobs > 1;
- my $dedupe = $lei->{dedupe} = PublicInbox::LeiDedupe->new($lei);
- state $zsfx_allow = join('|', keys %zsfx2cmd);
- my ($zsfx) = ($dst =~ /\.($zsfx_allow)\z/);
- if ($lei->{opt}->{augment}) {
- if (-s $out && $dedupe->prepare_dedupe) {
- my $rd = $zsfx ? decompress_src($out, $zsfx, $lei) :
- dup_src($out);
- PublicInbox::MboxReader->$mbox($rd, \&_augment, $lei);
- }
- $dedupe->pause_dedupe if $jobs; # are we forking?
- } else {
- truncate($out, 0) or die "truncate $dst: $!";
- $dedupe->prepare_dedupe if !$jobs;
- }
- ($out, $pipe_lk) = compress_dst($out, $zsfx, $lei) if $zsfx;
- sub {
+sub _mbox_write_cb ($$) {
+ my ($self, $lei) = @_;
+ my $ovv = $lei->{ovv};
+ my $m = 'eml2'.$ovv->{fmt};
+ my $eml2mbox = $self->can($m) or die "$self->$m missing";
+ my $out = $lei->{1} // die "no stdout ($m, $ovv->{dst})"; # redirected earlier
+ $out->autoflush(1);
+ my $write = $ovv->{lock_path} ? \&_print_full : \&atomic_append;
+ my $dedupe = $lei->{dedupe};
+ $dedupe->prepare_dedupe;
+ sub { # for git_to_mail
my ($buf, $oid, $kw) = @_;
my $eml = PublicInbox::Eml->new($buf);
- if (!$lei->{dedupe}->is_dup($eml, $oid)) {
+ if (!$dedupe->is_dup($eml, $oid)) {
$buf = $eml2mbox->($eml, $kw);
- my $lock = $pipe_lk->lock_for_scope if $pipe_lk;
- write_in_full($out, $buf, $atomic);
+ my $lk = $ovv->lock_for_scope;
+ $write->($out, $buf);
}
}
}
+sub _maildir_each_file ($$;@) {
+ my ($dir, $cb, @arg) = @_;
+ for my $d (qw(new/ cur/)) {
+ my $pfx = $dir.$d;
+ opendir my $dh, $pfx or next;
+ while (defined(my $fn = readdir($dh))) {
+ $cb->($pfx.$fn, @arg) if $fn =~ /:2,[A-Za-z]*\z/;
+ }
+ }
+}
+
+sub _augment_file { # _maildir_each_file cb
+ my ($f, $lei) = @_;
+ my $eml = PublicInbox::InboxWritable::eml_from_path($f) or return;
+ _augment($eml, $lei);
+}
+
+# _maildir_each_file callback, \&CORE::unlink doesn't work with it
+sub _unlink { unlink($_[0]) }
+
+sub _buf2maildir {
+ my ($dst, $buf, $oid, $kw) = @_;
+ my $sfx = join('', sort(map { $kw2char{$_} // () } @$kw));
+ my $rand = ''; # chosen by die roll :P
+ my ($tmp, $fh, $final);
+ do {
+ $tmp = $dst.'tmp/'.$rand."oid=$oid";
+ } while (!sysopen($fh, $tmp, O_CREAT|O_EXCL|O_WRONLY) &&
+ $! == EEXIST && ($rand = int(rand 0x7fffffff).','));
+ if (print $fh $$buf and close($fh)) {
+ $dst .= $sfx eq '' ? 'new/' : 'cur/';
+ $rand = '';
+ do {
+ $final = $dst.$rand."oid=$oid:2,$sfx";
+ } while (!link($tmp, $final) && $! == EEXIST &&
+ ($rand = int(rand 0x7fffffff).','));
+ unlink($tmp) or warn "W: failed to unlink $tmp: $!\n";
+ } else {
+ my $err = $!;
+ unlink($tmp);
+ die "Error writing $oid to $dst: $err";
+ }
+}
+
+sub _maildir_write_cb ($$) {
+ my ($self, $lei) = @_;
+ my $dedupe = $lei->{dedupe};
+ $dedupe->prepare_dedupe;
+ my $dst = $lei->{ovv}->{dst};
+ sub { # for git_to_mail
+ my ($buf, $oid, $kw) = @_;
+ return _buf2maildir($dst, $buf, $oid, $kw) if !$dedupe;
+ my $eml = PublicInbox::Eml->new($$buf); # copy buf
+ return if $dedupe->is_dup($eml, $oid);
+ undef $eml;
+ _buf2maildir($dst, $buf, $oid, $kw);
+ }
+}
+
sub write_cb { # returns a callback for git_to_mail
- my ($cls, $dst, $lei) = @_;
- require PublicInbox::LeiDedupe;
- if ($dst =~ s!\A(mbox(?:rd|cl|cl2|o))?:!!) {
- _mbox_write_cb($cls, $1, $dst, $lei);
+ my ($self, $lei) = @_;
+ # _mbox_write_cb or _maildir_write_cb
+ my $m = "_$self->{base_type}_write_cb";
+ $self->$m($lei);
+}
+
+sub new {
+ my ($cls, $lei) = @_;
+ my $fmt = $lei->{ovv}->{fmt};
+ my $dst = $lei->{ovv}->{dst};
+ my $self = bless {}, $cls;
+ if ($fmt eq 'maildir') {
+ $self->{base_type} = 'maildir';
+ $lei->{ovv}->{dst} = $dst .= '/' if substr($dst, -1) ne '/';
+ } elsif (substr($fmt, 0, 4) eq 'mbox') {
+ $self->can("eml2$fmt") or die "bad mbox --format=$fmt\n";
+ $self->{base_type} = 'mbox';
+ } else {
+ die "bad mail --format=$fmt\n";
+ }
+ $lei->{dedupe} = PublicInbox::LeiDedupe->new($lei);
+ $self;
+}
+
+sub _pre_augment_maildir {} # noop
+
+sub _do_augment_maildir {
+ my ($self, $lei) = @_;
+ my $dst = $lei->{ovv}->{dst};
+ if ($lei->{opt}->{augment}) {
+ my $dedupe = $lei->{dedupe};
+ if ($dedupe && $dedupe->prepare_dedupe) {
+ require PublicInbox::InboxWritable; # eml_from_path
+ _maildir_each_file($dst, \&_augment_file, $lei);
+ $dedupe->pause_dedupe;
+ }
+ } else { # clobber existing Maildir
+ _maildir_each_file($dst, \&_unlink);
+ }
+}
+
+sub _post_augment_maildir {
+ my ($self, $lei) = @_;
+ my $dst = $lei->{ovv}->{dst};
+ for my $x (qw(tmp new cur)) {
+ my $d = $dst.$x;
+ next if -d $d;
+ require File::Path;
+ File::Path::mkpath($d) or die "mkpath($d): $!";
+ -d $d or die "$d is not a directory";
+ }
+}
+
+sub _pre_augment_mbox {
+ my ($self, $lei) = @_;
+ my $dst = $lei->{ovv}->{dst};
+ if ($dst ne '/dev/stdout') {
+ my $mode = -p $dst ? '>' : '+>>';
+ if (-f _ && !$lei->{opt}->{augment} and !unlink($dst)) {
+ $! == ENOENT or die "unlink($dst): $!";
+ }
+ open my $out, $mode, $dst or die "open($dst): $!";
+ $lei->{1} = $out;
+ }
+ # Perl does SEEK_END even with O_APPEND :<
+ $self->{seekable} = seek($lei->{1}, 0, SEEK_SET);
+ if (!$self->{seekable} && $! != ESPIPE && $dst ne '/dev/stdout') {
+ die "seek($dst): $!\n";
+ }
+ state $zsfx_allow = join('|', keys %zsfx2cmd);
+ ($self->{zsfx}) = ($dst =~ /\.($zsfx_allow)\z/);
+}
+
+sub _do_augment_mbox {
+ my ($self, $lei) = @_;
+ return if !$lei->{opt}->{augment};
+ my $dedupe = $lei->{dedupe};
+ my $dst = $lei->{ovv}->{dst};
+ die "cannot augment $dst, not seekable\n" if !$self->{seekable};
+ my $out = $lei->{1};
+ if (-s $out && $dedupe && $dedupe->prepare_dedupe) {
+ my $zsfx = $self->{zsfx};
+ my $rd = $zsfx ? decompress_src($out, $zsfx, $lei) :
+ dup_src($out);
+ my $fmt = $lei->{ovv}->{fmt};
+ require PublicInbox::MboxReader;
+ PublicInbox::MboxReader->$fmt($rd, \&_augment, $lei);
+ }
+ # maybe some systems don't honor O_APPEND, Perl does this:
+ seek($out, 0, SEEK_END) or die "seek $dst: $!";
+ $dedupe->pause_dedupe if $dedupe;
+}
+
+sub pre_augment { # fast (1 disk seek), runs in main daemon
+ my ($self, $lei) = @_;
+ # _pre_augment_maildir, _pre_augment_mbox
+ my $m = "_pre_augment_$self->{base_type}";
+ $self->$m($lei);
+}
+
+sub do_augment { # slow, runs in wq worker
+ my ($self, $lei) = @_;
+ # _do_augment_maildir, _do_augment_mbox
+ my $m = "_do_augment_$self->{base_type}";
+ $self->$m($lei);
+}
+
+sub post_augment { # fast (spawn compressor or mkdir), runs in main daemon
+ my ($self, $lei) = @_;
+ # _post_augment_maildir, _post_augment_mbox
+ my $m = "_post_augment_$self->{base_type}";
+ $self->$m($lei);
+}
+
+sub lock_free {
+ $_[0]->{base_type} =~ /\A(?:maildir|mh|imap|jmap)\z/ ? 1 : 0;
+}
+
+sub write_mail { # via ->wq_do
+ my ($self, $git_dir, $oid, $lei, $kw) = @_;
+ my $wcb = $self->{wcb} //= do { # first message
+ my %sig = $lei->atfork_child_wq($self);
+ @SIG{keys %sig} = values %sig; # not local
+ $lei->{dedupe}->prepare_dedupe;
+ $self->write_cb($lei);
+ };
+ my $git = $self->{"$$\0$git_dir"} //= PublicInbox::Git->new($git_dir);
+ $git->cat_async($oid, \&git_to_mail, [ $wcb, $kw ]);
+}
+
+sub ipc_atfork_prepare {
+ my ($self) = @_;
+ # (qry_status_wr, stdout|mbox, stderr, 3: sock, 4: each_smsg_done_wr)
+ $self->wq_set_recv_modes(qw[+<&= >&= >&= +<&= >&=]);
+ $self->SUPER::ipc_atfork_prepare; # PublicInbox::IPC
+}
+
+sub DESTROY {
+ my ($self) = @_;
+ for my $pid_git (grep(/\A$$\0/, keys %$self)) {
+ $self->{$pid_git}->async_wait_all;
}
- # TODO: Maildir, MH, IMAP, JMAP ...
}
1;