# Copyright (C) 2021 all contributors
# License: AGPL-3.0+
# per-mitem/smsg iterators for search results
# "ovv" => "Overview viewer"
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);
# 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.$$";
my $tmp = File::Temp->new("lei-ovv.out.$$.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 $fmt = $opt->{'format'};
$fmt = lc($fmt) if defined $fmt;
if ($out =~ s/\A([a-z]+)://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
if (index($out, '://') < 0) { # not a URL, so assume path
$out = File::Spec->canonpath($out);
} # else URL
my $self = bless { fmt => $fmt, out => $out }, $class;
my $json;
if ($fmt =~ /\A($JSONL|(?:concat)?json)\z/) {
$json = $self->{json} = ref(PublicInbox::Config->json);
}
my ($isatty, $seekable);
if ($out eq '/dev/stdout') {
$isatty = -t $lei->{1};
$lei->start_pager if $isatty;
$opt->{pretty} //= $isatty;
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);
}
} elsif ($json) {
return $lei->fail('JSON formats only output to stdout');
} else {
return $lei->fail("TODO: $out -f $fmt");
}
$self;
}
# called once by parent
sub ovv_begin {
my ($self, $lei) = @_;
if ($self->{fmt} eq 'json') {
print { $lei->{1} } '[';
} # TODO HTML/Atom/...
}
# called once by parent (via PublicInbox::EOFpipe)
sub ovv_end {
my ($self, $lei) = @_;
if ($self->{fmt} eq 'json') {
# JSON doesn't allow trailing commas, and preventing
# trailing commas is a PITA when parallelizing outputs
print { $lei->{1} } "null]\n";
} elsif ($self->{fmt} eq 'concatjson') {
print { $lei->{1} } "\n";
}
}
sub ovv_atfork_child {
my ($self) = @_;
# reopen dedupe here
}
# prepares an smsg for JSON
sub _unbless_smsg {
my ($smsg, $mitem) = @_;
delete @$smsg{qw(lines bytes num tid)};
$smsg->{rt} = _iso8601(delete $smsg->{ts}); # JMAP receivedAt
$smsg->{dt} = _iso8601(delete $smsg->{ds}); # JMAP UTCDate
$smsg->{relevance} = get_pct($mitem) if $mitem;
if (my $r = delete $smsg->{references}) {
$smsg->{refs} = [
map { "<$_>" } ($r =~ m/$MID_EXTRACT/go) ];
}
if (my $m = delete($smsg->{mid})) {
$smsg->{'m'} = "<$m>";
}
for my $f (qw(from to cc)) {
my $v = delete $smsg->{$f} or next;
$smsg->{substr($f, 0, 1)} = pairs($v);
}
$smsg->{'s'} = delete $smsg->{subject};
# can we be bothered to parse From/To/Cc into arrays?
scalar { %$smsg }; # unbless
}
sub ovv_atexit_child {
my ($self, $lei) = @_;
if (my $bref = delete $lei->{ovv_buf}) {
my $lk = $self->lock_for_scope;
print { $lei->{1} } $$bref;
}
}
# JSON module ->pretty output wastes too much vertical white space,
# this (IMHO) provides better use of screen real-estate while not
# being excessively compact:
sub _json_pretty {
my ($json, $k, $v) = @_;
if (ref $v eq 'ARRAY') {
if (@$v) {
my $sep = ",\n" . (' ' x (length($k) + 7));
if (ref($v->[0])) { # f/t/c
$v = '[' . join($sep, map {
my $pair = $json->encode($_);
$pair =~ s/(null|"),"/$1, "/g;
$pair;
} @$v) . ']';
} else { # references
$v = '[' . join($sep, map {
substr($json->encode([$_]), 1, -1);
} @$v) . ']';
}
} else {
$v = '[]';
}
}
qq{ "$k": }.$v;
}
sub ovv_each_smsg_cb {
my ($self, $lei) = @_;
$lei->{ovv_buf} = \(my $buf = '');
delete(@$self{qw(lock_path tmp_lk_id)}) unless $lei->{-parallel};
my $json = $self->{json}->new;
$lei->{1}->autoflush(1);
if ($json) {
$json->utf8->canonical;
$json->ascii(1) if $lei->{opt}->{ascii};
}
if ($self->{fmt} =~ /\A(concat)?json\z/ && $lei->{opt}->{pretty}) {
my $EOR = ($1//'') eq 'concat' ? "\n}" : "\n},";
sub { # DIY prettiness :P
my ($smsg, $mitem) = @_;
$smsg = _unbless_smsg($smsg, $mitem);
$buf .= "{\n";
$buf .= join(",\n", map {
my $v = $smsg->{$_};
if (ref($v)) {
_json_pretty($json, $_, $v);
} else {
$v = $json->encode([$v]);
qq{ "$_": }.substr($v, 1, -1);
}
} sort keys %$smsg);
$buf .= $EOR;
if (length($buf) > 65536) {
my $lk = $self->lock_for_scope;
print { $lei->{1} } $buf;
$buf = '';
}
}
} elsif ($json) {
my $ORS = $self->{fmt} eq 'json' ? ",\n" : "\n"; # JSONL
sub {
my ($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;
$buf = '';
}
}
} elsif ($self->{fmt} eq 'oid') {
sub {
my ($smsg, $mitem) = @_;
}
} # else { ...
}
no warnings 'once';
*DESTROY = \&ovv_out_lk_cancel;
1;