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::Spawn qw(run_die);
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?
# move this to PublicInbox::Config if other things use it:
my %cquote = ("\n" => '\\n', "\t" => '\\t', "\b" => '\\b');
qw(external local remote import-remote import-before threads)
}
-sub lss_dir_for ($$) {
- my ($lei, $dstref) = @_;
+sub lss_dir_for ($$;$) {
+ my ($lei, $dstref, $on_fs) = @_;
my @n;
if ($$dstref =~ m,\Aimaps?://,i) { # already canonicalized
require PublicInbox::URIimap;
my $uri = PublicInbox::URIimap->new($$dstref)->canonical;
$$dstref = $$uri;
@n = ($uri->mailbox);
- } else { # basename
+ } 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 = ($$dstref =~ m{([^/]+)/*\z});
+ @n = ($$dstref =~ m{([^/]+)/*\z}); # basename
}
push @n, sha256_hex($$dstref);
- $lei->share_path . '/saved-searches/' . join('-', @n);
+ my $lss_dir = $lei->share_path . '/saved-searches/';
+ my $d = $lss_dir . join('-', @n);
+
+ # fall-back to looking up by st_ino + st_dev in case we're in
+ # a symlinked or bind-mounted path
+ if ($on_fs && !-d $d && -e $$dstref) {
+ my @cur = stat(_);
+ my $want = pack('dd', @cur[1,0]); # st_ino + st_dev
+ my ($c, $o, @st);
+ for my $g ("$n[0]-*", '*') {
+ my @maybe = glob("$lss_dir$g/lei.saved-search");
+ for my $f (@maybe) {
+ $c = PublicInbox::Config->git_config_dump($f);
+ $o = $c->{'lei.q.output'} // next;
+ $o =~ s!$LOCAL_PFX!! or next;
+ @st = stat($o) or next;
+ next if pack('dd', @st[1,0]) ne $want;
+ $f =~ m!\A(.+?)/[^/]+\z! and return $1;
+ }
+ }
+ }
+ $d;
}
sub list {
my ($lei, $pfx) = @_;
- my $lss_dir = $lei->share_path.'/saved-searches/';
+ my $lss_dir = $lei->share_path.'/saved-searches';
return () unless -d $lss_dir;
# TODO: persist the cache? Use another format?
my $f = $lei->cache_dir."/saved-tmp.$$.".time.'.config';
unlink($f);
my $out = $cfg->get_all('lei.q.output') or return ();
map {;
- s!\A(?:maildir|mh|mbox.+|mmdf):!!i;
+ s!$LOCAL_PFX!!;
$_;
} @$out
}
+sub translate_dedupe ($$$) {
+ my ($self, $lei, $dd) = @_;
+ $dd //= '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");
+}
+
sub up { # updating existing saved search via "lei up"
my ($cls, $lei, $dst) = @_;
my $f;
File::Path::make_path($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;
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';
print $fh <<EOM;
; to refresh with new results, run: lei up $sq_dst
[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) {
sub is_dup {
my ($self, $eml, $smsg) = @_;
my $oidx = $self->{oidx} // die 'BUG: no {oidx}';
- my $blob = $smsg ? $smsg->{blob} : undef;
- return 1 if $blob && $oidx->blob_exists($blob);
- my $lk = $self->lock_for_scope_fast;
+ 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, '.');
}
$oidx->commit_lazy;
- 1;
+ if ($self->{-dedupe_oid}) {
+ exists $xoids->{$blob} ? 1 : undef;
+ } else {
+ 1;
+ }
} else {
# n.b. above xoids_for fills out eml->{-lei_fake_mid} if needed
unless ($smsg) {
$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;
$oidx->commit_lazy;
}
sub output2lssdir {
my ($self, $lei, $dir_ref, $fn_ref) = @_;
my $dst = $$dir_ref; # imap://$MAILBOX, /path/to/maildir, /path/to/mbox
- my $dir = lss_dir_for($lei, \$dst);
+ 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);
undef;
}
+sub edit_begin {
+ my ($self, $lei) = @_;
+ if (ref($self->{-cfg}->{'lei.q.output'})) {
+ delete $self->{-cfg}->{'lei.q.output'}; # invalid
+ $lei->err(<<EOM);
+$self->{-f} has multiple values of lei.q.output
+please remove redundant ones
+EOM
+ }
+ $lei->{-lss_for_edit} = $self;
+}
+
+sub edit_done {
+ my ($self, $lei) = @_;
+ my $cfg = PublicInbox::Config->git_config_dump($self->{'-f'});
+ my $new_out = $cfg->{'lei.q.output'} // '';
+ return $lei->fail(<<EOM) if ref $new_out;
+$self->{-f} has multiple values of lei.q.output
+please edit again
+EOM
+ return $lei->fail(<<EOM) if $new_out eq '';
+$self->{-f} needs lei.q.output
+please edit again
+EOM
+ my $old_out = $self->{-cfg}->{'lei.q.output'} // '';
+ return if $old_out eq $new_out;
+ my $old_path = $old_out;
+ my $new_path = $new_out;
+ s!$LOCAL_PFX!! for ($old_path, $new_path);
+ my $dir_old = lss_dir_for($lei, \$old_path, 1);
+ my $dir_new = lss_dir_for($lei, \$new_path);
+ return if $dir_new eq $dir_old; # no change, likely
+ return $lei->fail(<<EOM) if -e $dir_new;
+lei.q.output changed from `$old_out' to `$new_out'
+However, $dir_new exists
+EOM
+ # start the conversion asynchronously
+ my $old_sq = PublicInbox::Config::squote_maybe($old_out);
+ my $new_sq = PublicInbox::Config::squote_maybe($new_out);
+ $lei->puts("lei.q.output changed from $old_sq to $new_sq");
+ $lei->qerr("# lei convert $old_sq -o $new_sq");
+ my $v = !$lei->{opt}->{quiet};
+ $lei->{opt} = { output => $new_out, verbose => $v };
+ require PublicInbox::LeiConvert;
+ PublicInbox::LeiConvert::lei_convert($lei, $old_out);
+
+ $lei->fail(<<EOM) if -e $dir_old && !rename($dir_old, $dir_new);
+E: rename($dir_old, $dir_new) error: $!
+EOM
+}
+
no warnings 'once';
*nntp_url = \&cloneurl;
*base_url = \&PublicInbox::Inbox::base_url;