use strict;
use v5.10.1;
use parent qw(PublicInbox::Lock);
+use PublicInbox::Git;
use PublicInbox::OverIdx;
use PublicInbox::LeiSearch;
use PublicInbox::Config;
use PublicInbox::ContentHash qw(git_sha);
use PublicInbox::MID qw(mids_for_index);
use Digest::SHA qw(sha256_hex);
-my $LOCAL_PFX = qr!\A(?:maildir|mh|mbox.+|mmdf):!i; # TODO: put in LeiToMail?
+our $LOCAL_PFX = qr!\A(?:maildir|mh|mbox.+|mmdf|v2):!i; # TODO: put in LeiToMail?
# move this to PublicInbox::Config if other things use it:
my %cquote = ("\n" => '\\n', "\t" => '\\t', "\b" => '\\b');
sub cquote_val ($) { # cf. git-config(1)
my ($val) = @_;
$val =~ s/([\n\t\b])/$cquote{$1}/g;
+ $val =~ s/\"/\\\"/g;
$val;
}
qw(external local remote import-remote import-before threads)
}
+sub SINGLE_FIELDS () { qw(limit dedupe output) }
+
sub lss_dir_for ($$;$) {
my ($lei, $dstref, $on_fs) = @_;
- my @n;
+ my $pfx;
if ($$dstref =~ m,\Aimaps?://,i) { # already canonicalized
require PublicInbox::URIimap;
my $uri = PublicInbox::URIimap->new($$dstref)->canonical;
$$dstref = $$uri;
- @n = ($uri->mailbox);
+ $pfx = $uri->mailbox;
} else {
# can't use Cwd::abs_path since dirname($$dstref) may not exist
$$dstref = $lei->rel2abs($$dstref);
- # Maildirs have trailing '/' internally
- $$dstref .= '/' if -d $$dstref;
$$dstref =~ tr!/!/!s;
- @n = ($$dstref =~ m{([^/]+)/*\z}); # basename
+ $pfx = $$dstref;
}
- push @n, sha256_hex($$dstref);
+ ($pfx) = ($pfx =~ m{([^/]+)/*\z}); # basename
my $lss_dir = $lei->share_path . '/saved-searches/';
- my $d = $lss_dir . join('-', @n);
+ my $d = "$lss_dir$pfx-".sha256_hex($$dstref);
# fall-back to looking up by st_ino + st_dev in case we're in
# a symlinked or bind-mounted path
my @cur = stat(_);
my $want = pack('dd', @cur[1,0]); # st_ino + st_dev
my ($c, $o, @st);
- for my $g ("$n[0]-*", '*') {
+ for my $g ("$pfx-*", '*') {
my @maybe = glob("$lss_dir$g/lei.saved-search");
for my $f (@maybe) {
- $c = PublicInbox::Config->git_config_dump($f);
+ $c = $lei->cfg_dump($f) // next;
$o = $c->{'lei.q.output'} // next;
$o =~ s!$LOCAL_PFX!! or next;
@st = stat($o) or next;
print $fh "\tpath = ", cquote_val($p), "\n";
}
close $fh or die "close $f: $!";
- my $cfg = PublicInbox::Config->git_config_dump($f);
+ my $cfg = $lei->cfg_dump($f);
unlink($f);
- my $out = $cfg->get_all('lei.q.output') or return ();
+ my $out = $cfg ? $cfg->get_all('lei.q.output') : [];
map {;
s!$LOCAL_PFX!!;
$_;
} @$out
}
-sub translate_dedupe ($$$) {
- my ($self, $lei, $dd) = @_;
- $dd //= 'content';
+sub translate_dedupe ($$) {
+ my ($self, $lei) = @_;
+ my $dd = $lei->{opt}->{dedupe} // 'content';
return 1 if $dd eq 'content'; # the default
return $self->{"-dedupe_$dd"} = 1 if ($dd eq 'oid' || $dd eq 'mid');
- $lei->fail("--dedupe=$dd unsupported with --save");
+ die("--dedupe=$dd requires --no-save\n");
}
sub up { # updating existing saved search via "lei up"
my $self = bless { ale => $lei->ale }, $cls;
my $dir = $dst;
output2lssdir($self, $lei, \$dir, \$f) or
- return $lei->fail("--save was not used with $dst cwd=".
- $lei->rel2abs('.'));
- $self->{-cfg} = PublicInbox::Config->git_config_dump($f);
+ return die("--no-save was used with $dst cwd=".
+ $lei->rel2abs('.')."\n");
+ $self->{-cfg} = $lei->cfg_dump($f) // return $lei->child_error;
$self->{-ovf} = "$dir/over.sqlite3";
$self->{'-f'} = $f;
$self->{lock_path} = "$self->{-f}.flock";
sub new { # new saved search "lei q --save"
my ($cls, $lei) = @_;
my $self = bless { ale => $lei->ale }, $cls;
+ require File::Path;
my $dst = $lei->{ovv}->{dst};
+
+ # canonicalize away relative paths into the config
+ if ($lei->{ovv}->{fmt} eq 'maildir' &&
+ $dst =~ m!(?:/*|\A)\.\.(?:/*|\z)! && !-d $dst) {
+ File::Path::make_path($dst);
+ $lei->{ovv}->{dst} = $dst = $lei->abs_path($dst);
+ }
my $dir = lss_dir_for($lei, \$dst);
- require File::Path;
File::Path::make_path($dir); # raises on error
$self->{-cfg} = {};
my $f = $self->{'-f'} = "$dir/lei.saved-search";
- my $dd = $lei->{opt}->{dedupe};
- translate_dedupe($self, $lei, $dd) or return;
+ translate_dedupe($self, $lei) or return;
open my $fh, '>', $f or return $lei->fail("open $f: $!");
my $sq_dst = PublicInbox::Config::squote_maybe($dst);
my $q = $lei->{mset_opt}->{q_raw} // die 'BUG: {q_raw} missing';
$q = "\tq = ".cquote_val($q);
}
$dst = "$lei->{ovv}->{fmt}:$dst" if $dst !~ m!\Aimaps?://!i;
+ $lei->{opt}->{output} = $dst;
print $fh <<EOM;
; to refresh with new results, run: lei up $sq_dst
+; `maxuid' and `lastresult' lines are maintained by "lei up" for optimization
[lei]
- $q
+$q
[lei "q"]
- output = $dst
EOM
- print $fh "\tdedupe = $dd\n" if $dd;
for my $k (ARRAY_FIELDS) {
my $ary = $lei->{opt}->{$k} // next;
for my $x (@$ary) {
my $val = $lei->{opt}->{$k} // next;
print $fh "\t$k = ".($val ? 1 : 0)."\n";
}
+ for my $k (SINGLE_FIELDS) {
+ my $val = $lei->{opt}->{$k} // next;
+ print $fh "\t$k = $val\n";
+ }
+ $lei->{opt}->{stdin} and print $fh <<EOM;
+[lei "internal"]
+ rawstr = 1 # stdin was used initially
+EOM
close($fh) or return $lei->fail("close $f: $!");
$self->{lock_path} = "$self->{-f}.flock";
$self->{-ovf} = "$dir/over.sqlite3";
sub is_dup {
my ($self, $eml, $smsg) = @_;
my $oidx = $self->{oidx} // die 'BUG: no {oidx}';
- my $blob = $smsg ? $smsg->{blob} : undef;
- my $lk = $self->lock_for_scope_fast;
- return 1 if $blob && $oidx->blob_exists($blob);
+ my $lk;
if ($self->{-dedupe_mid}) {
+ $lk //= $self->lock_for_scope_fast;
for my $mid (@{mids_for_index($eml)}) {
my ($id, $prv);
return 1 if $oidx->next_by_mid($mid, \$id, \$prv);
}
}
+ my $blob = $smsg ? $smsg->{blob} : git_sha(1, $eml)->hexdigest;
+ $lk //= $self->lock_for_scope_fast;
+ return 1 if $oidx->blob_exists($blob);
if (my $xoids = PublicInbox::LeiSearch::xoids_for($self, $eml, 1)) {
for my $docid (values %$xoids) {
$oidx->add_xref3($docid, -1, $blob, '.');
}
$oidx->commit_lazy;
if ($self->{-dedupe_oid}) {
- $smsg->{blob} //= git_sha(1, $eml)->hexdigest;
- exists $xoids->{$smsg->{blob}} ? 1 : undef;
+ exists $xoids->{$blob} ? 1 : undef;
} else {
1;
}
$smsg->{bytes} = 0;
$smsg->populate($eml);
}
+ $smsg->{blob} //= $blob;
$oidx->begin_lazy;
$smsg->{num} = $oidx->adj_counter('eidx_docid', '+');
- $smsg->{blob} //= git_sha(1, $eml)->hexdigest;
$oidx->add_overview($eml, $smsg);
- $oidx->add_xref3($smsg->{num}, -1, $smsg->{blob}, '.');
+ $oidx->add_xref3($smsg->{num}, -1, $blob, '.');
$oidx->commit_lazy;
undef;
}
sub over { $_[0]->{oidx} } # for xoids_for
-sub git { $_[0]->{ale}->git }
+# don't use ale->git directly since is_dup is called inside
+# ale->git->cat_async callbacks
+sub git { $_[0]->{git} //= PublicInbox::Git->new($_[0]->{ale}->git->{git_dir}) }
sub pause_dedupe {
my ($self) = @_;
- $self->{ale}->git->cleanup;
+ git($self)->cleanup;
my $lockfh = delete $self->{lockfh}; # from lock_for_scope_fast;
my $oidx = delete($self->{oidx}) // return;
$oidx->commit_lazy;
}
+sub reset_dedupe {
+ my ($self) = @_;
+ prepare_dedupe($self);
+ my $lk = $self->lock_for_scope_fast;
+ for my $t (qw(xref3 over id2num)) {
+ $self->{oidx}->{dbh}->do("DELETE FROM $t");
+ }
+ pause_dedupe($self);
+}
+
sub mm { undef }
sub altid_map { {} }
my $dir = lss_dir_for($lei, \$dst, 1);
my $f = "$dir/lei.saved-search";
if (-f $f && -r _) {
- $self->{-cfg} = PublicInbox::Config->git_config_dump($f);
+ $self->{-cfg} = $lei->cfg_dump($f) // return;
$$dir_ref = $dir;
$$fn_ref = $f;
return 1;
undef;
}
+# cf. LeiDedupe->has_entries
+sub has_entries {
+ my $oidx = $_[0]->{oidx} // die 'BUG: no {oidx}';
+ my @n = $oidx->{dbh}->selectrow_array('SELECT num FROM over LIMIT 1');
+ scalar(@n) ? 1 : undef;
+}
+
no warnings 'once';
*nntp_url = \&cloneurl;
*base_url = \&PublicInbox::Inbox::base_url;