package PublicInbox::LeiOverview;
use strict;
use v5.10.1;
+use parent qw(PublicInbox::Lock);
use POSIX qw(strftime);
+use Fcntl qw(F_GETFL O_APPEND);
use File::Spec;
+use File::Temp ();
use PublicInbox::MID qw($MID_EXTRACT);
use PublicInbox::Address qw(pairs);
use PublicInbox::Config;
use PublicInbox::Search qw(get_pct);
+use PublicInbox::LeiDedupe;
+use PublicInbox::LeiToMail;
# cf. https://en.wikipedia.org/wiki/JSON_streaming
my $JSONL = 'ldjson|ndjson|jsonl'; # 3 names for the same thing
sub _iso8601 ($) { strftime('%Y-%m-%dT%H:%M:%SZ', gmtime($_[0])) }
+# we open this in the parent process before ->wq_do handoff
+sub ovv_out_lk_init ($) {
+ my ($self) = @_;
+ $self->{tmp_lk_id} = "$self.$$";
+ my $tmp = File::Temp->new("lei-ovv.dst.$$.lock-XXXXXX",
+ TMPDIR => 1, UNLINK => 0);
+ $self->{lock_path} = $tmp->filename;
+}
+
+sub ovv_out_lk_cancel ($) {
+ my ($self) = @_;
+ ($self->{tmp_lk_id}//'') eq "$self.$$" and
+ unlink(delete($self->{lock_path}));
+}
+
sub new {
my ($class, $lei) = @_;
my $opt = $lei->{opt};
- my $out = $opt->{output} // '-';
- $out = '/dev/stdout' if $out eq '-';
+ my $dst = $opt->{output} // '-';
+ $dst = '/dev/stdout' if $dst eq '-';
my $fmt = $opt->{'format'};
$fmt = lc($fmt) if defined $fmt;
- if ($out =~ s/\A([a-z]+)://is) { # e.g. Maildir:/home/user/Mail/
+ if ($dst =~ s/\A([a-z0-9]+)://is) { # e.g. Maildir:/home/user/Mail/
my $ofmt = lc $1;
$fmt //= $ofmt;
return $lei->fail(<<"") if $fmt ne $ofmt;
--format=$fmt and --output=$ofmt conflict
}
- $fmt //= 'json' if $out eq '/dev/stdout';
- $fmt //= 'maildir'; # TODO
+ $fmt //= 'json' if $dst eq '/dev/stdout';
+ $fmt //= 'maildir';
- if (index($out, '://') < 0) { # not a URL, so assume path
- $out = File::Spec->canonpath($out);
+ if (index($dst, '://') < 0) { # not a URL, so assume path
+ $dst = File::Spec->canonpath($dst);
} # else URL
- my $self = bless { fmt => $fmt, out => $out }, $class;
+ my $self = bless { fmt => $fmt, dst => $dst }, $class;
+ $lei->{ovv} = $self;
my $json;
if ($fmt =~ /\A($JSONL|(?:concat)?json)\z/) {
$json = $self->{json} = ref(PublicInbox::Config->json);
}
my ($isatty, $seekable);
- if ($out eq '/dev/stdout') {
+ if ($dst eq '/dev/stdout') {
$isatty = -t $lei->{1};
$lei->start_pager if $isatty;
$opt->{pretty} //= $isatty;
- } elsif ($json) {
- return $lei->fail('JSON formats only output to stdout');
+ if (!$isatty && -f _) {
+ my $fl = fcntl($lei->{1}, F_GETFL, 0) //
+ return $lei->fail("fcntl(stdout): $!");
+ ovv_out_lk_init($self) unless ($fl & O_APPEND);
+ } else {
+ ovv_out_lk_init($self);
+ }
}
+ if (!$json) {
+ # default to the cheapest sort since MUA usually resorts
+ $lei->{opt}->{'sort'} //= 'docid' if $dst ne '/dev/stdout';
+ $lei->{l2m} = PublicInbox::LeiToMail->new($lei);
+ }
+ $lei->{dedupe} //= PublicInbox::LeiDedupe->new($lei);
$self;
}
sub ovv_atexit_child {
my ($self, $lei) = @_;
+ if (my $l2m = delete $lei->{l2m}) {
+ # gracefully stop lei2mail processes after all
+ # ->write_mail work is complete
+ delete $l2m->{-wq_s1};
+ if (my $rd = delete $l2m->{each_smsg_done}) {
+ read($rd, my $buf, 1); # wait for EOF
+ }
+ }
+ # order matters, git->{-tmp}->DESTROY must not fire until
+ # {each_smsg_done} hits EOF above
+ if (my $git = delete $self->{git}) {
+ $git->async_wait_all;
+ }
if (my $bref = delete $lei->{ovv_buf}) {
- print { $lei->{1} } $$bref;
+ my $out = $lei->{1} or return;
+ my $lk = $self->lock_for_scope;
+ print $out $$bref;
}
}
qq{ "$k": }.$v;
}
-sub ovv_each_smsg_cb {
- my ($self, $lei) = @_;
- $lei->{ovv_buf} = \(my $buf = '');
- my $json = $self->{json}->new;
- if ($json) {
+sub ovv_each_smsg_cb { # runs in wq worker usually
+ my ($self, $lei, $ibxish) = @_;
+ my $json;
+ $lei->{1}->autoflush(1);
+ if (my $pkg = $self->{json}) {
+ $json = $pkg->new;
$json->utf8->canonical;
$json->ascii(1) if $lei->{opt}->{ascii};
}
- if ($self->{fmt} =~ /\A(concat)?json\z/ && $lei->{opt}->{pretty}) {
+ my $l2m = $lei->{l2m};
+ if ($l2m && $l2m->{-wq_s1}) {
+ my ($lei_ipc, @io) = $lei->atfork_parent_wq($l2m);
+ # n.b. $io[0] = qry_status_wr, $io[1] = mbox|stdout,
+ # $io[4] becomes a notification pipe that triggers EOF
+ # in this wq worker when all outstanding ->write_mail
+ # calls are complete
+ die "BUG: \$io[4] $io[4] unexpected" if $io[4];
+ pipe($l2m->{each_smsg_done}, $io[4]) or die "pipe: $!";
+ fcntl($io[4], 1031, 4096) if $^O eq 'linux';
+ delete @$lei_ipc{qw(l2m opt mset_opt cmd)};
+ my $git = $ibxish->git; # (LeiXSearch|Inbox|ExtSearch)->git
+ $self->{git} = $git;
+ my $git_dir = $git->{git_dir};
+ sub {
+ my ($smsg, $mitem) = @_;
+ my $kw = []; # TODO get from mitem
+ $l2m->wq_do('write_mail', \@io, $git_dir,
+ $smsg->{blob}, $lei_ipc, $kw)
+ }
+ } elsif ($l2m) {
+ my $wcb = $l2m->write_cb($lei);
+ my $git = $ibxish->git; # (LeiXSearch|Inbox|ExtSearch)->git
+ $self->{git} = $git; # for ovv_atexit_child
+ my $g2m = $l2m->can('git_to_mail');
+ sub {
+ my ($smsg, $mitem) = @_;
+ my $kw = []; # TODO get from mitem
+ $git->cat_async($smsg->{blob}, $g2m, [ $wcb, $kw ]);
+ };
+ } elsif ($self->{fmt} =~ /\A(concat)?json\z/ && $lei->{opt}->{pretty}) {
my $EOR = ($1//'') eq 'concat' ? "\n}" : "\n},";
+ $lei->{ovv_buf} = \(my $buf = '');
sub { # DIY prettiness :P
my ($smsg, $mitem) = @_;
$smsg = _unbless_smsg($smsg, $mitem);
} sort keys %$smsg);
$buf .= $EOR;
if (length($buf) > 65536) {
+ my $lk = $self->lock_for_scope;
print { $lei->{1} } $buf;
$buf = '';
}
}
} elsif ($json) {
my $ORS = $self->{fmt} eq 'json' ? ",\n" : "\n"; # JSONL
+ $lei->{ovv_buf} = \(my $buf = '');
sub {
my ($smsg, $mitem) = @_;
delete @$smsg{qw(tid num)};
$buf .= $json->encode(_unbless_smsg(@_)) . $ORS;
if (length($buf) > 65536) {
+ my $lk = $self->lock_for_scope;
print { $lei->{1} } $buf;
$buf = '';
}
} # else { ...
}
+no warnings 'once';
+*DESTROY = \&ovv_out_lk_cancel;
+
1;