index|extindex: support --dangerous flag

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

diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm
index e5c872d52fd3fd477f42301f7407acbd8d0061fb..85fae4adf8b7f3f81c014776af5cbcd9fe29ef6d 100644 (file)
--- a/lib/PublicInbox/SearchIdx.pm
+++ b/lib/PublicInbox/SearchIdx.pm
@@ -1,4 +1,4 @@
-# Copyright (C) 2015-2021 all contributors <meta@public-inbox.org>
+# Copyright (C) all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 # based on notmuch, but with no concept of folders, files
 #
@@ -20,7 +20,7 @@ use Carp qw(croak carp);
 use POSIX qw(strftime);
 use Time::Local qw(timegm);
 use PublicInbox::OverIdx;
-use PublicInbox::Spawn qw(spawn nodatacow_dir);
+use PublicInbox::Spawn qw(spawn);
 use PublicInbox::Git qw(git_unquote);
 use PublicInbox::MsgTime qw(msg_timestamp msg_datestamp);
 use PublicInbox::Address;
@@ -30,6 +30,7 @@ our @EXPORT_OK = qw(log2stack is_ancestor check_size prepare_stack
 my $X = \%PublicInbox::Search::X;
 our ($DB_CREATE_OR_OPEN, $DB_OPEN);
 our $DB_NO_SYNC = 0;
+our $DB_DANGEROUS = 0;
 our $BATCH_BYTES = $ENV{XAPIAN_FLUSH_THRESHOLD} ? 0x7fffffff :
        # assume a typical 64-bit system has 8x more RAM than a
        # typical 32-bit system:
@@ -115,7 +116,10 @@ sub load_xapian_writable () {
        my $ver = (eval($xap.'::major_version()') << 16) |
                (eval($xap.'::minor_version()') << 8) |
                eval($xap.'::revision()');
-       $DB_NO_SYNC = 0x4 if $ver >= 0x10400;
+       if ($ver >= 0x10400) {
+               $DB_NO_SYNC = 0x4;
+               $DB_DANGEROUS = 0x10;
+       }
        # Xapian v1.2.21..v1.2.24 were missing close-on-exec on OFD locks
        $X->{CLOEXEC_UNSET} = 1 if $ver >= 0x010215 && $ver <= 0x010218;
        1;
@@ -139,8 +143,12 @@ sub idx_acquire {
                if (!-d $dir && (!$is_shard ||
                                ($is_shard && need_xapian($self)))) {
                        File::Path::mkpath($dir);
-                       nodatacow_dir($dir);
+                       require PublicInbox::Syscall;
+                       PublicInbox::Syscall::nodatacow_dir($dir);
                        $self->{-set_has_threadid_once} = 1;
+                       if (($self->{ibx} // $self->{eidx})->{-dangerous}) {
+                               $flag |= $DB_DANGEROUS;
+                       }
                }
        }
        return unless defined $flag;
@@ -259,6 +267,7 @@ sub index_diff ($$$) {
                } elsif (m!^diff --git "?[^/]+/.+ "?[^/]+/.+\z!) {
                        # wait until "---" and "+++" to capture filenames
                        $in_diff = 1;
+                       push @xnq, $_;
                # traditional diff:
                } elsif (m/^diff -(.+) (\S+) (\S+)$/) {
                        my ($opt, $fa, $fb) = ($1, $2, $3);
@@ -451,10 +460,9 @@ sub add_xapian ($$$$) {
 sub _msgmap_init ($) {
        my ($self) = @_;
        die "BUG: _msgmap_init is only for v1\n" if $self->{ibx}->version != 1;
-       $self->{mm} //= eval {
+       $self->{mm} //= do {
                require PublicInbox::Msgmap;
-               my $rw = $self->{ibx}->{-no_fsync} ? 2 : 1;
-               PublicInbox::Msgmap->new($self->{ibx}->{inboxdir}, $rw);
+               PublicInbox::Msgmap->new_file($self->{ibx}, 1);
        };
 }
 
@@ -518,6 +526,12 @@ sub add_eidx_info {
        $self->{xdb}->replace_document($docid, $doc);
 }
 
+sub get_terms {
+       my ($self, $pfx, $docid) = @_;
+       begin_txn_lazy($self);
+       xap_terms($pfx, $self->{xdb}, $docid);
+}
+
 sub remove_eidx_info {
        my ($self, $docid, $eidx_key, $eml) = @_;
        begin_txn_lazy($self);
@@ -637,14 +651,24 @@ sub update_vmd {
 
 sub xdb_remove {
        my ($self, @docids) = @_;
-       $self->begin_txn_lazy;
-       my $xdb = $self->{xdb} or return;
+       begin_txn_lazy($self);
+       my $xdb = $self->{xdb} // die 'BUG: missing {xdb}';
        for my $docid (@docids) {
                eval { $xdb->delete_document($docid) };
                warn "E: #$docid not in in Xapian? $@\n" if $@;
        }
 }
 
+sub xdb_remove_quiet {
+       my ($self, $docid) = @_;
+       begin_txn_lazy($self);
+       my $xdb = $self->{xdb} // die 'BUG: missing {xdb}';
+       eval { $xdb->delete_document($docid) };
+       ++$self->{-quiet_rm} unless $@;
+}
+
+sub nr_quiet_rm { delete($_[0]->{-quiet_rm}) // 0 }
+
 sub index_git_blob_id {
        my ($doc, $pfx, $objid) = @_;
 
@@ -784,6 +808,7 @@ sub v1_checkpoint ($$;$) {
        ${$sync->{max}} = $self->{batch_bytes};
 
        $self->{mm}->{dbh}->commit;
+       eval { $self->{mm}->{dbh}->do('PRAGMA optimize') };
        my $xdb = $self->{xdb};
        if ($newest && $xdb) {
                my $cur = $xdb->get_metadata('last_commit');
@@ -879,20 +904,20 @@ sub log2stack ($$$) {
                push @cmd, "--$k=$v";
        }
        my $fh = $git->popen(@cmd, $range);
-       my ($at, $ct, $stk, $cmt);
-       while (<$fh>) {
+       my ($at, $ct, $stk, $cmt, $l);
+       while (defined($l = <$fh>)) {
                return if $sync->{quit};
-               if (/\A([0-9]+)-([0-9]+)-($OID)$/o) {
+               if ($l =~ /\A([0-9]+)-([0-9]+)-($OID)$/o) {
                        ($at, $ct, $cmt) = ($1 + 0, $2 + 0, $3);
                        $stk //= PublicInbox::IdxStack->new($cmt);
-               } elsif (/$del/) {
+               } elsif ($l =~ /$del/) {
                        my $oid = $1;
                        if ($D) { # reindex case
                                $D->{pack('H*', $oid)}++;
                        } else { # non-reindex case:
                                $stk->push_rec('d', $at, $ct, $oid, $cmt);
                        }
-               } elsif (/$add/) {
+               } elsif ($l =~ /$add/) {
                        my $oid = $1;
                        if ($D) {
                                my $oid_bin = pack('H*', $oid);
@@ -1098,25 +1123,4 @@ sub eidx_shard_new {
        $self;
 }
 
-# ensure there's no stale Xapian docs by treating $over as canonical
-sub over_check {
-       my ($self, $over) = @_;
-       begin_txn_lazy($self);
-       my $sth = $over->dbh->prepare(<<'');
-SELECT COUNT(*) FROM over WHERE num = ?
-
-       my $xdb = $self->{xdb};
-       my $cur = $xdb->postlist_begin('');
-       my $end = $xdb->postlist_end('');
-       my $xdir = $self->xdir;
-       for (; $cur != $end; $cur++) {
-               my $docid = $cur->get_docid;
-               $sth->execute($docid);
-               my $x = $sth->fetchrow_array;
-               next if $x > 0;
-               warn "I: removing $xdir #$docid, not in `over'\n";
-               $xdb->delete_document($docid);
-       }
-}
-
 1;