lei q: improve --limit behavior and progress

[public-inbox.git] / lib / PublicInbox / LeiQuery.pm

diff --git a/lib/PublicInbox/LeiQuery.pm b/lib/PublicInbox/LeiQuery.pm
index 4099b26c85ce87e4b0005f98008987d2e518d72b..cb5ac8fb84a72a06907075c7a65c2a7d94c3aec6 100644 (file)
--- a/lib/PublicInbox/LeiQuery.pm
+++ b/lib/PublicInbox/LeiQuery.pm
@@ -1,11 +1,11 @@
 # Copyright (C) 2021 all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 
-# handles lei <q|ls-query|rm-query|mv-query> commands
+# handles "lei q" command and provides internals for
+# several other sub-commands (up, lcat, ...)
 package PublicInbox::LeiQuery;
 use strict;
 use v5.10.1;
-use POSIX ();
 
 sub prep_ext { # externals_each callback
        my ($lxs, $exclude, $loc) = @_;
@@ -23,26 +23,30 @@ sub _start_query { # used by "lei q" and "lei up"
        }
        my $lxs = $self->{lxs};
        $xj ||= $lxs->concurrency($opt); # allow: "--jobs ,$WRITER_ONLY"
-       my $nproc = $lxs->detect_nproc // 1; # don't memoize, schedtool(1) exists
+       my $nproc = $lxs->detect_nproc || 1; # don't memoize, schedtool(1) exists
        $xj = $nproc if $xj > $nproc;
        $lxs->{-wq_nr_workers} = $xj;
        if (defined($mj) && $mj !~ /\A[1-9][0-9]*\z/) {
                return $self->fail("`$mj' writer jobs must be >= 1");
        }
        my $l2m = $self->{l2m};
-       if ($l2m && ($opt->{'import-remote'} //= 1) |
-                               # we use \1 (a ref) to distinguish between
-                               # user-supplied and default value
-                               (($opt->{'import-before'} //= \1) ? 1 : 0)) {
+       # we use \1 (a ref) to distinguish between default vs. user-supplied
+       if ($l2m && grep { $opt->{$_} //= \1 } (qw(mail-sync import-remote
+                                                       import-before))) {
                $self->_lei_store(1)->write_prepare($self);
        }
        $l2m and $l2m->{-wq_nr_workers} = $mj // do {
-               $mj = POSIX::lround($nproc * 3 / 4); # keep some CPU for git
-               $mj <= 0 ? 1 : $mj;
+               $mj = int($nproc * 0.75 + 0.5); # keep some CPU for git
        };
 
        # descending docid order is cheapest, MUA controls sorting order
        $self->{mset_opt}->{relevance} //= -2 if $l2m || $opt->{threads};
+
+       my $tot = $self->{mset_opt}->{total} //= $self->{opt}->{limit} // 10000;
+       $self->{mset_opt}->{limit} = $tot > 10000 ? 10000 : $tot;
+       $self->{mset_opt}->{offset} //= 0;
+       $self->{mset_opt}->{threads} //= $opt->{threads};
+
        if ($self->{net}) {
                require PublicInbox::LeiAuth;
                $self->{auth} = PublicInbox::LeiAuth->new
@@ -54,9 +58,7 @@ sub qstr_add { # PublicInbox::InputPipe::consume callback for --stdin
        my ($self) = @_; # $_[1] = $rbuf
        if (defined($_[1])) {
                $_[1] eq '' and return eval {
-                       if (my $dfd = $self->{3}) {
-                               chdir($dfd) or return $self->fail("fchdir: $!");
-                       }
+                       $self->fchdir or return;
                        $self->{mset_opt}->{q_raw} = $self->{mset_opt}->{qstr};
                        $self->{lse}->query_approxidate($self->{lse}->git,
                                                $self->{mset_opt}->{qstr});
@@ -77,7 +79,7 @@ sub lxs_prepare {
        my @only = @{$opt->{only} // []};
        # --local is enabled by default unless --only is used
        # we'll allow "--only $LOCATION --local"
-       my $sto = $self->_lei_store(1); # FIXME: should not create
+       my $sto = $self->_lei_store(1);
        $self->{lse} = $sto->search;
        if ($opt->{'local'} //= scalar(@only) ? 0 : 1) {
                $lxs->prepare_external($self->{lse});
@@ -120,11 +122,10 @@ sub lei_q {
        my ($self, @argv) = @_;
        PublicInbox::Config->json; # preload before forking
        my $lxs = lxs_prepare($self) or return;
-       $self->ale->refresh_externals($lxs);
+       $self->ale->refresh_externals($lxs, $self);
        my $opt = $self->{opt};
-       my %mset_opt = map { $_ => $opt->{$_} } qw(threads limit offset);
+       my %mset_opt;
        $mset_opt{asc} = $opt->{'reverse'} ? 1 : 0;
-       $mset_opt{limit} //= 10000;
        if (defined(my $sort = $opt->{'sort'})) {
                if ($sort eq 'relevance') {
                        $mset_opt{relevance} = 1;
@@ -135,6 +136,8 @@ sub lei_q {
                } else {
                        die "unrecognized --sort=$sort\n";
                }
+               $opt->{save} and return
+                       $self->fail('--save and --sort are incompatible');
        }
        $self->{mset_opt} = \%mset_opt;
 
@@ -192,7 +195,7 @@ sub _complete_q {
 # analogues in git(1)? that would reduce likelyhood of conflicts with
 # our other CLI options
 # Note: some names are renamed to avoid potential conflicts,
-# see %lei2mail in lib/PublicInbox/LeiCurl.pm
+# see %lei2curl in lib/PublicInbox/LeiCurl.pm
 sub curl_opt { qw(
        curl-config=s@
        abstract-unix-socket=s anyauth basic cacert=s capath=s