-# Copyright (C) 2015, all contributors <meta@public-inbox.org>
+# Copyright (C) 2015 all contributors <meta@public-inbox.org>
# License: AGPLv3 or later (https://www.gnu.org/licenses/agpl-3.0.txt)
# based on notmuch, but with no concept of folders, files or flags
package PublicInbox::SearchIdx;
$self;
}
+sub add_val {
+ my ($doc, $col, $num) = @_;
+ $num = Search::Xapian::sortable_serialise($num);
+ $doc->add_value($col, $num);
+}
+
sub add_message {
- my ($self, $mime) = @_; # mime = Email::MIME object
+ my ($self, $mime, $bytes, $num) = @_; # mime = Email::MIME object
my $db = $self->{xdb};
my $doc_id;
$doc->add_term(xpfx('path') . mid_compress($path));
}
- my $ts = Search::Xapian::sortable_serialise($smsg->ts);
- $doc->add_value(PublicInbox::Search::TS, $ts);
+ add_val($doc, &PublicInbox::Search::TS, $smsg->ts);
+
+ defined($num) and
+ add_val($doc, &PublicInbox::Search::NUM, $num);
+
+ defined($bytes) and
+ add_val($doc, &PublicInbox::Search::BYTES, $bytes);
+
+ add_val($doc, &PublicInbox::Search::LINES,
+ $mime->body_raw =~ tr!\n!\n!);
my $tg = $self->term_generator;
$tg->index_text($subj) if $subj;
$tg->increase_termpos;
- $tg->index_text($smsg->from->format);
+ $tg->index_text($smsg->from);
$tg->increase_termpos;
$mime->walk_parts(sub {
$self->{term_generator} = $tg;
}
-sub next_doc_id { $_[0]->{xdb}->get_lastdocid + 1 }
-
# increments last_thread_id counter
# returns a 64-bit integer represented as a hex string
sub next_thread_id {
}
}
if (@refs) {
- $smsg->{references_sorted} = '<'.join('><', @refs).'>';
+ $smsg->{references} = '<'.join('> <', @refs).'>';
# first ref *should* be the thread root,
# but we can never trust clients to do the right thing
}
sub index_blob {
- my ($self, $git, $blob) = @_;
- my $mime = do_cat_mail($git, $blob) or return;
- eval { $self->add_message($mime) };
- warn "W: index_blob $blob: $@\n" if $@;
+ my ($self, $git, $mime, $bytes, $num) = @_;
+ $self->add_message($mime, $bytes, $num);
}
sub unindex_blob {
- my ($self, $git, $blob) = @_;
- my $mime = do_cat_mail($git, $blob) or return;
- my $mid = $mime->header('Message-ID');
- eval { $self->remove_message($mid) } if defined $mid;
- warn "W: unindex_blob $blob: $@\n" if $@;
+ my ($self, $git, $mime) = @_;
+ my $mid = mid_clean($mime->header('Message-ID'));
+ $self->remove_message($mid) if defined $mid;
+}
+
+sub index_mm {
+ my ($self, $git, $mime) = @_;
+ $self->{mm}->mid_insert(mid_clean($mime->header('Message-ID')));
+}
+
+sub unindex_mm {
+ my ($self, $git, $mime) = @_;
+ $self->{mm}->mid_delete(mid_clean($mime->header('Message-ID')));
+}
+
+sub index_mm2 {
+ my ($self, $git, $mime, $bytes) = @_;
+ my $num = $self->{mm}->num_for(mid_clean($mime->header('Message-ID')));
+ index_blob($self, $git, $mime, $bytes, $num);
+}
+
+sub unindex_mm2 {
+ my ($self, $git, $mime) = @_;
+ $self->{mm}->mid_delete(mid_clean($mime->header('Message-ID')));
+ unindex_blob($self, $git, $mime);
+}
+
+sub index_both {
+ my ($self, $git, $mime, $bytes) = @_;
+ my $num = index_mm($self, $git, $mime);
+ index_blob($self, $git, $mime, $bytes, $num);
+}
+
+sub unindex_both {
+ my ($self, $git, $mime) = @_;
+ unindex_blob($self, $git, $mime);
+ unindex_mm($self, $git, $mime);
}
sub do_cat_mail {
- my ($git, $blob) = @_;
+ my ($git, $blob, $sizeref) = @_;
my $mime = eval {
- my $str = $git->cat_file($blob);
+ my $str = $git->cat_file($blob, $sizeref);
Email::MIME->new($str);
};
$@ ? undef : $mime;
$self->with_umask(sub { $self->_index_sync($head) });
}
-# indexes all unindexed messages
-sub _index_sync {
- my ($self, $head) = @_;
- require PublicInbox::GitCatFile;
- my $db = $self->{xdb};
+sub rlog {
+ my ($self, $range, $add_cb, $del_cb) = @_;
my $hex = '[a-f0-9]';
my $h40 = $hex .'{40}';
my $addmsg = qr!^:000000 100644 \S+ ($h40) A\t${hex}{2}/${hex}{38}$!;
my $delmsg = qr!^:100644 000000 ($h40) \S+ D\t${hex}{2}/${hex}{38}$!;
+ my $git_dir = $self->{git_dir};
+ require PublicInbox::GitCatFile;
+ my $git = PublicInbox::GitCatFile->new($git_dir);
+ my @cmd = ('git', "--git-dir=$git_dir", "log",
+ qw/--reverse --no-notes --no-color --raw -r --no-abbrev/,
+ $range);
+ my $latest;
+ my $bytes;
+ my $pid = open(my $log, '-|', @cmd) or
+ die('open` '.join(' ', @cmd) . " pipe failed: $!\n");
+ while (my $line = <$log>) {
+ if ($line =~ /$addmsg/o) {
+ my $mime = do_cat_mail($git, $1, \$bytes) or next;
+ $add_cb->($self, $git, $mime, $bytes);
+ } elsif ($line =~ /$delmsg/o) {
+ my $mime = do_cat_mail($git, $1) or next;
+ $del_cb->($self, $git, $mime);
+ } elsif ($line =~ /^commit ($h40)/o) {
+ $latest = $1;
+ }
+ }
+ close $log;
+ $latest;
+}
+
+# indexes all unindexed messages
+sub _index_sync {
+ my ($self, $head) = @_;
+ my $db = $self->{xdb};
$head ||= 'HEAD';
+ my $mm = $self->{mm} = eval {
+ require PublicInbox::Msgmap;
+ PublicInbox::Msgmap->new($self->{git_dir}, 1);
+ };
$db->begin_transaction;
- eval {
- my $git = PublicInbox::GitCatFile->new($self->{git_dir});
-
- my $latest = $db->get_metadata('last_commit');
- my $range = $latest eq '' ? $head : "$latest..$head";
- $latest = undef;
-
- # get indexed messages
- my @cmd = ('git', "--git-dir=$self->{git_dir}", "log",
- qw/--reverse --no-notes --no-color --raw -r
- --no-abbrev/, $range);
- my $pid = open(my $log, '-|', @cmd) or
- die('open` '.join(' ', @cmd) . " pipe failed: $!\n");
-
- while (my $line = <$log>) {
- if ($line =~ /$addmsg/o) {
- $self->index_blob($git, $1);
- } elsif ($line =~ /$delmsg/o) {
- $self->unindex_blob($git, $1);
- } elsif ($line =~ /^commit ($h40)/o) {
- $latest = $1;
+ my $lx = $db->get_metadata('last_commit');
+ my $range = $lx eq '' ? $head : "$lx..$head";
+ if ($mm) {
+ $mm->{dbh}->begin_work;
+ my $lm = $mm->last_commit || '';
+ if ($lm eq $lx) {
+ # Common case is the indexes are synced,
+ # we only need to run git-log once:
+ $lx = $self->rlog($range, *index_both, *unindex_both);
+ $mm->{dbh}->commit;
+ if (defined $lx) {
+ $db->set_metadata('last_commit', $lx);
+ $mm->last_commit($lx);
}
+ } else {
+ # dumb case, msgmap and xapian are out-of-sync
+ # do not care for performance:
+ my $r = $lm eq '' ? $head : "$lm..$head";
+ $lm = $self->rlog($r, *index_mm, *unindex_mm);
+ $mm->{dbh}->commit;
+ $mm->last_commit($lm) if defined $lm;
+
+ $lx = $self->rlog($range, *index_mm2, *unindex_mm2);
+ $db->set_metadata('last_commit', $lx) if defined $lx;
}
- close $log;
- $db->set_metadata('last_commit', $latest) if defined $latest;
- };
+ } else {
+ # user didn't install DBD::SQLite and DBI
+ $lx = $self->rlog($range, *index_blob, *unindex_blob);
+ $db->set_metadata('last_commit', $lx) if defined $lx;
+ }
if ($@) {
- warn "indexing failed: $@\n";
$db->cancel_transaction;
+ $mm->{dbh}->rollback if $mm;
} else {
$db->commit_transaction;
}