use File::Temp 0.19 (); # 0.19 for ->newdir
use File::Spec ();
use PublicInbox::Search qw(xap_terms);
-use PublicInbox::Spawn qw(popen_rd);
+use PublicInbox::Spawn qw(popen_rd spawn which);
+use PublicInbox::MID qw(mids);
+use Fcntl qw(SEEK_SET F_SETFL O_APPEND O_RDWR);
sub new {
my ($class) = @_;
my $mo = { %{$lei->{mset_opt}} };
my $mset;
my $each_smsg = $lei->{ovv}->ovv_each_smsg_cb($lei, $ibxish);
- my $dedupe = $lei->{dedupe} // die 'BUG: {dedupe} missing';
- $dedupe->prepare_dedupe;
do {
$mset = $srch->mset($mo->{qstr}, $mo);
my $ids = $srch->mset_to_artnums($mset, $mo);
for my $n (@{$ctx->{xids}}) {
my $smsg = $over->get_art($n) or next;
wait_startq($startq) if $startq;
- next if $dedupe->is_smsg_dup($smsg);
my $mitem = delete $n2item{$smsg->{num}};
$each_smsg->($smsg, $mitem);
}
attach_external($self, $loc);
}
my $each_smsg = $lei->{ovv}->ovv_each_smsg_cb($lei, $self);
- my $dedupe = $lei->{dedupe} // die 'BUG: {dedupe} missing';
- $dedupe->prepare_dedupe;
do {
$mset = $self->mset($mo->{qstr}, $mo);
for my $mitem ($mset->items) {
my $smsg = smsg_for($self, $mitem) or next;
wait_startq($startq) if $startq;
- next if $dedupe->is_smsg_dup($smsg);
$each_smsg->($smsg, $mitem);
}
} while (_mset_more($mset, $mo));
my ($eml, $self, $lei, $each_smsg) = @_;
my $smsg = bless {}, 'PublicInbox::Smsg';
$smsg->populate($eml);
+ $smsg->parse_references($eml, mids($eml));
$smsg->{$_} //= '' for qw(from to cc ds subject references mid);
delete @$smsg{qw(From Subject -ds -ts)};
if (my $startq = delete($self->{5})) { wait_startq($startq) }
- return if !$lei->{l2m} && $lei->{dedupe}->is_smsg_dup($smsg);
$each_smsg->($smsg, undef, $eml);
}
+# PublicInbox::OnDestroy callback
+sub kill_reap {
+ my ($pid) = @_;
+ kill('KILL', $pid); # spawn() blocks other signals
+ waitpid($pid, 0);
+}
+
sub query_remote_mboxrd {
my ($self, $lei, $uris) = @_;
local $0 = "$0 query_remote_mboxrd";
my ($opt, $env) = @$lei{qw(opt env)};
my @qform = (q => $lei->{mset_opt}->{qstr}, x => 'm');
push(@qform, t => 1) if $opt->{thread};
- my $dedupe = $lei->{dedupe} // die 'BUG: {dedupe} missing';
- $dedupe->prepare_dedupe;
- my @cmd = (qw(curl -sSf -d), '');
+ my @cmd = ($self->{curl}, qw(-sSf -d), '');
my $verbose = $opt->{verbose};
- push @cmd, '-v' if $verbose;
+ my $reap;
+ my $cerr = File::Temp->new(TEMPLATE => 'curl.err-XXXX', TMPDIR => 1);
+ fcntl($cerr, F_SETFL, O_APPEND|O_RDWR) or warn "set O_APPEND: $!";
+ my $rdr = { 2 => $cerr };
+ my $coff = 0;
+ if ($verbose) {
+ # spawn a process to force line-buffering, otherwise curl
+ # will write 1 character at-a-time and parallel outputs
+ # mmmaaayyy llloookkk llliiikkkeee ttthhhiiisss
+ push @cmd, '-v';
+ my $o = { 1 => $lei->{2}, 2 => $lei->{2} };
+ my $pid = spawn(['tail', '-f', $cerr->filename], undef, $o);
+ $reap = PublicInbox::OnDestroy->new(\&kill_reap, $pid);
+ }
for my $o ($lei->curl_opt) {
$o =~ s/\|[a-z0-9]\b//i; # remove single char short option
if ($o =~ s/=[is]@\z//) {
}
$opt->{torsocks} = 'false' if $opt->{'no-torsocks'};
my $tor = $opt->{torsocks} //= 'auto';
+ my $each_smsg = $lei->{ovv}->ovv_each_smsg_cb($lei);
for my $uri (@$uris) {
$uri->query_form(@qform);
- my $each_smsg = $lei->{ovv}->ovv_each_smsg_cb($lei, $uri);
my $cmd = [ @cmd, $uri->as_string ];
if ($tor eq 'auto' && substr($uri->host, -6) eq '.onion' &&
(($env->{LD_PRELOAD}//'') !~ /torsocks/)) {
- unshift @$cmd, 'torsocks';
+ unshift @$cmd, which('torsocks');
} elsif (PublicInbox::Config::git_bool($tor)) {
- unshift @$cmd, 'torsocks';
+ unshift @$cmd, which('torsocks');
}
+
+ # continue anyways if torsocks is missing; a proxy may be
+ # specified via CLI, curlrc, environment variable, or even
+ # firewall rule
+ shift(@$cmd) if !$cmd->[0];
+
$lei->err("# @$cmd") if $verbose;
$? = 0;
- my $fh = popen_rd($cmd, $env, { 2 => $lei->{2} });
+ my $fh = popen_rd($cmd, $env, $rdr);
$fh = IO::Uncompress::Gunzip->new($fh);
eval {
PublicInbox::MboxReader->mboxrd($fh, \&each_eml, $self,
$lei, $each_smsg);
};
return $lei->fail("E: @$cmd: $@") if $@;
- if (($? >> 8) == 22) { # HTTP 404 from curl(1)
- $uri->query_form(q => $lei->{mset_opt}->{qstr});
- $lei->err('# no results from '.$uri->as_string);
- } elsif ($?) {
- $uri->query_form(q => $lei->{mset_opt}->{qstr});
- $lei->err('E: '.$uri->as_string);
- $lei->child_error($?);
- }
+ next unless $?;
+ seek($cerr, $coff, SEEK_SET) or warn "seek(curl stderr): $!\n";
+ my $e = do { local $/; <$cerr> } //
+ die "read(curl stderr): $!\n";
+ $coff += length($e);
+ next if (($? >> 8) == 22 && $e =~ /\b404\b/);
+ $lei->child_error($?);
+ $uri->query_form(q => $lei->{mset_opt}->{qstr});
+ # --verbose already showed the error via tail(1)
+ $lei->err("E: $uri \$?=$?\n", $verbose ? () : $e);
}
+ undef $each_smsg;
$lei->{ovv}->ovv_atexit_child($lei);
}
$self->SUPER::ipc_atfork_prepare; # PublicInbox::IPC
}
+sub add_uri {
+ my ($self, $uri) = @_;
+ if (my $curl = $self->{curl} //= which('curl') // 0) {
+ push @{$self->{remotes}}, $uri;
+ } else {
+ warn "curl missing, ignoring $uri\n";
+ }
+}
+
sub prepare_external {
my ($self, $loc, $boost) = @_; # n.b. already ordered by boost
if (ref $loc) { # already a URI, or PublicInbox::Inbox-like object
- return push(@{$self->{remotes}}, $loc) if $loc->can('scheme');
+ return add_uri($self, $loc) if $loc->can('scheme');
} elsif ($loc =~ m!\Ahttps?://!) {
require URI;
- return push(@{$self->{remotes}}, URI->new($loc));
+ return add_uri($self, URI->new($loc));
} elsif (-f "$loc/ei.lock") {
require PublicInbox::ExtSearch;
$loc = PublicInbox::ExtSearch->new($loc);