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?
+my $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');
} 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
}
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";
print $fh <<EOM;
; to refresh with new results, run: lei up $sq_dst
[lei]
- $q
+$q
[lei "q"]
output = $dst
EOM
sub is_dup {
my ($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 { {} }
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 $dir_old; # no change, likely
+
+ ($old_out =~ m!\Av2:!i || $new_out =~ m!\Av2:!) and
+ return $lei->fail(<<EOM);
+conversions from/to v2 inboxes not supported at this time
+EOM
+
+ 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
+}
+
+# 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;