-# 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 IO::Handle; # ->autoflush
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',
);
sub _mbox_hdr_buf ($$$) {
- my ($eml, $type, $kw) = @_;
+ my ($eml, $type, $smsg) = @_;
$eml->header_set($_) for (qw(Lines Bytes Content-Length));
- my %hdr; # set Status, X-Status
- for my $k (@$kw) {
+
+ # Messages are always 'O' (non-\Recent in IMAP), it saves
+ # MUAs the trouble of rewriting the mbox if no other
+ # changes are made
+ my %hdr = (Status => [ 'O' ]); # set Status, X-Status
+ for my $k (@{$smsg->{kw} // []}) {
if (my $ent = $kw2status{$k}) {
push @{$hdr{$ent->[0]}}, $ent->[1];
} else { # X-Label?
# fixup old bug from import (pre-a0c07cba0e5d8b6a)
$$buf =~ s/\A[\r\n]*From [^\r\n]*\r?\n//s;
+ my $ident = $smsg->{blob} // 'lei';
+ if (defined(my $pct = $smsg->{pct})) { $ident .= "=$pct" }
substr($$buf, 0, 0, # prepend From line
- "From lei\@$type Thu Jan 1 00:00:00 1970$eml->{crlf}");
+ "From $ident\@$type Thu Jan 1 00:00:00 1970$eml->{crlf}");
$buf;
}
}
sub eml2mboxrd ($;$) {
- my ($eml, $kw) = @_;
- my $buf = _mbox_hdr_buf($eml, 'mboxrd', $kw);
+ my ($eml, $smsg) = @_;
+ my $buf = _mbox_hdr_buf($eml, 'mboxrd', $smsg);
if (my $bdy = delete $eml->{bdy}) {
$$bdy =~ s/^(>*From )/>$1/gm;
$$buf .= $eml->{crlf};
}
sub eml2mboxo {
- my ($eml, $kw) = @_;
- my $buf = _mbox_hdr_buf($eml, 'mboxo', $kw);
+ my ($eml, $smsg) = @_;
+ my $buf = _mbox_hdr_buf($eml, 'mboxo', $smsg);
if (my $bdy = delete $eml->{bdy}) {
$$bdy =~ s/^From />From /gm;
$$buf .= $eml->{crlf};
$buf;
}
+sub _mboxcl_common ($$$) {
+ my ($buf, $bdy, $crlf) = @_;
+ # add Lines: so mutt won't have to add it on MUA close
+ my $lines = $$bdy =~ tr!\n!\n!;
+ $$buf .= 'Content-Length: '.length($$bdy).$crlf.
+ 'Lines: '.$lines.$crlf.$crlf;
+ substr($$bdy, 0, 0, $$buf); # prepend header
+ $_[0] = $bdy;
+}
+
# mboxcl still escapes "From " lines
sub eml2mboxcl {
- my ($eml, $kw) = @_;
- my $buf = _mbox_hdr_buf($eml, 'mboxcl', $kw);
+ my ($eml, $smsg) = @_;
+ my $buf = _mbox_hdr_buf($eml, 'mboxcl', $smsg);
my $crlf = $eml->{crlf};
if (my $bdy = delete $eml->{bdy}) {
$$bdy =~ s/^From />From /gm;
- $$buf .= 'Content-Length: '.length($$bdy).$crlf.$crlf;
- substr($$bdy, 0, 0, $$buf); # prepend header
- $buf = $bdy;
+ _mboxcl_common($buf, $bdy, $crlf);
}
$$buf .= $crlf;
$buf;
# mboxcl2 has no "From " escaping
sub eml2mboxcl2 {
- my ($eml, $kw) = @_;
- my $buf = _mbox_hdr_buf($eml, 'mboxcl2', $kw);
+ my ($eml, $smsg) = @_;
+ my $buf = _mbox_hdr_buf($eml, 'mboxcl2', $smsg);
my $crlf = $eml->{crlf};
if (my $bdy = delete $eml->{bdy}) {
- $$buf .= 'Content-Length: '.length($$bdy).$crlf.$crlf;
- substr($$bdy, 0, 0, $$buf); # prepend header
- $buf = $bdy;
+ _mboxcl_common($buf, $bdy, $crlf);
}
$$buf .= $crlf;
$buf;
warn "unexpected type=$type for $oid\n";
}
}
- if ($size > 0) {
- my ($write_cb, $kw) = @$arg;
- $write_cb->($bref, $oid, $kw);
+ my ($write_cb, $smsg) = @$arg;
+ if ($smsg->{blob} ne $oid) {
+ die "BUG: expected=$smsg->{blob} got=$oid";
}
+ $write_cb->($bref, $smsg) if $size > 0;
}
sub reap_compress { # dwaitpid callback
# { foo => '' } means "--foo" is passed to the command-line,
# otherwise { foo => '--bar' } passes "--bar"
our %zsfx2cmd = (
- gz => [ qw(GZIP pigz gzip), {
- rsyncable => '', threads => '-p' } ],
+ gz => [ qw(GZIP pigz gzip), { rsyncable => '', threads => '-p' } ],
bz2 => [ 'bzip2', {} ],
xz => [ 'xz', { threads => '-T' } ],
# XXX does anybody care for these? I prefer zstd on entire FSes,
\@cmd;
}
-sub compress_dst {
- my ($out, $zsfx, $lei) = @_;
+sub _post_augment_mbox { # open a compressor process
+ my ($self, $lei, $zpipe) = @_;
+ 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 => $lei->{2} };
+ my ($r, $w) = splice(@$zpipe, 0, 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);
+ my $dup = bless { "pid.$pid" => $cmd }, ref($lei);
+ $dup->{$_} = $lei->{$_} for qw(2 sock);
+ tie *$pp, 'PublicInbox::ProcessPipe', $pid, $w, \&reap_compress, $dup;
+ $lei->{1} = $pp;
+ die 'BUG: unexpected {ovv}->{lock_path}' if $lei->{ovv}->{lock_path};
+ $lei->{ovv}->ovv_out_lk_init;
}
sub decompress_src ($$$) {
my ($in, $zsfx, $lei) = @_;
my $cmd = zsfx2cmd($zsfx, 1, $lei);
- my $rdr = { 0 => $in, 2 => $lei->{2} };
- popen_rd($cmd, $lei->{env}, $rdr);
+ popen_rd($cmd, $lei->{env}, { 0 => $in, 2 => $lei->{2} });
}
sub dup_src ($) {
my ($in) = @_;
- open my $dup, '+>>&', $in or die "dup: $!";
+ # fileno needed because wq_set_recv_modes only used ">&=" for {1}
+ # and Perl blindly trusts that to reject the '+' (readability flag)
+ open my $dup, '+>>&=', fileno($in) or die "dup: $!";
$dup;
}
$lei->{dedupe}->is_dup($eml);
}
-sub _mbox_write_cb ($$$$) {
- my ($cls, $mbox, $dst, $lei) = @_;
- my $m = "eml2$mbox";
- my $eml2mbox = $cls->can($m) or die "$cls->$m missing";
- my ($out, $pipe_lk, $seekable);
- # XXX should we support /dev/stdout.gz ?
- if ($dst eq '/dev/stdout') {
- $out = $lei->{1};
- } else { # TODO: mbox locking (but mairix doesn't...)
- if (!$lei->{opt}->{augment} && -f $dst and !unlink($dst)) {
- die "unlink $dst: $!" if $! != ENOENT;
- }
- open $out, '+>>', $dst or die "open $dst: $!";
- # Perl does SEEK_END even with O_APPEND :<
- $seekable = seek($out, 0, SEEK_SET);
- die "seek $dst: $!\n" if !$seekable && $! != ESPIPE;
- }
- my $jobs = $lei->{opt}->{jobs} // 0;
- state $zsfx_allow = join('|', keys %zsfx2cmd);
- my ($zsfx) = ($dst =~ /\.($zsfx_allow)\z/);
- my $write = $jobs > 1 && !$zsfx ? \&atomic_append : \&_print_full;
- my $dedupe = $lei->{dedupe} = PublicInbox::LeiDedupe->new($lei);
- if ($lei->{opt}->{augment}) {
- die "cannot augment $dst, not seekable\n" if !$seekable;
- if (-s $out && $dedupe->prepare_dedupe) {
- my $rd = $zsfx ? decompress_src($out, $zsfx, $lei) :
- dup_src($out);
- PublicInbox::MboxReader->$mbox($rd, \&_augment, $lei);
- }
- # maybe some systems don't honor O_APPEND, Perl does this:
- seek($out, 0, SEEK_END) or die "seek $dst: $!";
- $dedupe->pause_dedupe if $jobs; # are we forking?
- }
- $dedupe->prepare_dedupe if !$jobs;
- ($out, $pipe_lk) = compress_dst($out, $zsfx, $lei) if $zsfx;
+sub _mbox_write_cb ($$) {
+ 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, $kw) = @_;
+ my ($buf, $smsg) = @_;
+ return unless $out;
my $eml = PublicInbox::Eml->new($buf);
- if (!$dedupe->is_dup($eml, $oid)) {
- $buf = $eml2mbox->($eml, $kw);
- my $lock = $pipe_lk->lock_for_scope if $pipe_lk;
- $write->($out, $buf);
+ if (!$dedupe->is_dup($eml, $smsg->{blob})) {
+ $buf = $eml2mbox->($eml, $smsg);
+ my $lk = $ovv->lock_for_scope;
+ eval { $write->($out, $buf) };
+ if ($@) {
+ die $@ if ref($@) ne 'PublicInbox::SIGPIPE';
+ undef $out
+ }
}
}
}
sub _unlink { unlink($_[0]) }
sub _buf2maildir {
- my ($dst, $buf, $oid, $kw) = @_;
+ my ($dst, $buf, $smsg) = @_;
+ my $kw = $smsg->{kw} // [];
my $sfx = join('', sort(map { $kw2char{$_} // () } @$kw));
my $rand = ''; # chosen by die roll :P
my ($tmp, $fh, $final);
+ my $common = $smsg->{blob};
+ if (defined(my $pct = $smsg->{pct})) { $common .= "=$pct" }
do {
- $tmp = $dst.'tmp/'.$rand."oid=$oid";
+ $tmp = $dst.'tmp/'.$rand.$common;
} while (!sysopen($fh, $tmp, O_CREAT|O_EXCL|O_WRONLY) &&
$! == EEXIST && ($rand = int(rand 0x7fffffff).','));
if (print $fh $$buf and close($fh)) {
- $dst .= $sfx eq '' ? 'new/' : 'cur/';
+ # ignore new/ and write only to cur/, otherwise MUAs
+ # with R/W access to the Maildir will end up doing
+ # a mass rename which can take a while with thousands
+ # of messages.
+ $dst .= 'cur/';
$rand = '';
do {
- $final = $dst.$rand."oid=$oid:2,$sfx";
+ $final = $dst.$rand.$common.':2,'.$sfx;
} while (!link($tmp, $final) && $! == EEXIST &&
($rand = int(rand 0x7fffffff).','));
unlink($tmp) or warn "W: failed to unlink $tmp: $!\n";
} else {
my $err = $!;
unlink($tmp);
- die "Error writing $oid to $dst: $err";
+ die "Error writing $smsg->{blob} to $dst: $err";
}
}
-
sub _maildir_write_cb ($$) {
- my ($dst, $lei) = @_;
- $dst .= '/' unless substr($dst, -1) eq '/';
- my $dedupe = $lei->{dedupe} = PublicInbox::LeiDedupe->new($lei, $dst);
- my $jobs = $lei->{opt}->{jobs} // 0;
+ my ($self, $lei) = @_;
+ my $dedupe = $lei->{dedupe};
+ $dedupe->prepare_dedupe;
+ my $dst = $lei->{ovv}->{dst};
+ sub { # for git_to_mail
+ my ($buf, $smsg) = @_;
+ return _buf2maildir($dst, $buf, $smsg) if !$dedupe;
+ my $eml = PublicInbox::Eml->new($$buf); # copy buf
+ return if $dedupe->is_dup($eml, $smsg->{blob});
+ undef $eml;
+ _buf2maildir($dst, $buf, $smsg);
+ }
+}
+
+sub write_cb { # returns a callback for git_to_mail
+ 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';
+ -e $dst && !-d _ and die
+ "$dst exists and is not a directory\n";
+ $lei->{ovv}->{dst} = $dst .= '/' if substr($dst, -1) ne '/';
+ } elsif (substr($fmt, 0, 4) eq 'mbox') {
+ (-d $dst || (-e _ && !-w _)) and die
+ "$dst exists and is not a writable file\n";
+ $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 if $jobs; # are we forking?
+ $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;
- if (!File::Path::mkpath($d) && !-d $d) {
- die "failed to mkpath($d): $!\n";
+ File::Path::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;
}
- $dedupe->prepare_dedupe if $dedupe && !$jobs;
- 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);
+ # 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/) or return;
+ pipe(my ($r, $w)) or die "pipe: $!";
+ [ $r, $w ];
}
-sub write_cb { # returns a callback for git_to_mail
- my ($cls, $dst, $lei) = @_;
- require PublicInbox::LeiDedupe;
- if ($dst =~ s!\A(mbox(?:rd|cl|cl2|o))?:!!) {
- _mbox_write_cb($cls, $1, $dst, $lei);
- } elsif ($dst =~ s!\A[Mm]aildir:!!) { # typically capitalized
- _maildir_write_cb($dst, $lei);
+sub _do_augment_mbox {
+ my ($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, @args) = @_;
+ # _post_augment_maildir, _post_augment_mbox
+ my $m = "_post_augment_$self->{base_type}";
+ $self->$m($lei, @args);
+}
+
+sub write_mail { # via ->wq_do
+ my ($self, $git_dir, $smsg, $lei) = @_;
+ my $not_done = delete $self->{4}; # write end of {each_smsg_done}
+ 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->{"$$\0$git_dir"} //= PublicInbox::Git->new($git_dir);
+ $git->cat_async($smsg->{blob}, \&git_to_mail, [$wcb, $smsg, $not_done]);
+}
+
+sub ipc_atfork_prepare {
+ my ($self) = @_;
+ # (qry_status_wr, stdout|mbox, stderr, 3: sock, 4: each_smsg_done_wr)
+ $self->wq_set_recv_modes(qw[+<&= >&= >&= +<&= >&=]);
+ $self->SUPER::ipc_atfork_prepare; # PublicInbox::IPC
+}
+
+sub DESTROY {
+ my ($self) = @_;
+ for my $pid_git (grep(/\A$$\0/, keys %$self)) {
+ $self->{$pid_git}->async_wait_all;
}
- # TODO: Maildir, MH, IMAP, JMAP ...
+ $self->SUPER::DESTROY; # PublicInbox::IPC
}
1;