use POSIX qw(strftime);
use PublicInbox::OverIdx;
use PublicInbox::Spawn qw(spawn);
-require PublicInbox::Git;
+use PublicInbox::Git qw(git_unquote);
use Compress::Zlib qw(compress);
use constant {
- BATCH_BYTES => 1_000_000,
+ BATCH_BYTES => defined($ENV{XAPIAN_FLUSH_THRESHOLD}) ?
+ 0x7fffffff : 1_000_000,
DEBUG => !!$ENV{DEBUG},
};
-my %GIT_ESC = (
- a => "\a",
- b => "\b",
- f => "\f",
- n => "\n",
- r => "\r",
- t => "\t",
- v => "\013",
-);
-
-sub git_unquote ($) {
- my ($s) = @_;
- return $s unless ($s =~ /\A"(.*)"\z/);
- $s = $1;
- $s =~ s/\\([abfnrtv])/$GIT_ESC{$1}/g;
- $s =~ s/\\([0-7]{1,3})/chr(oct($1))/ge;
- $s;
-}
+my $xapianlevels = qr/\A(?:full|medium)\z/;
sub new {
my ($class, $ibx, $creat, $part) = @_;
+ my $levels = qr/\A(?:full|medium|basic)\z/;
my $mainrepo = $ibx; # for "public-inbox-index" w/o entry in config
my $git_dir = $mainrepo;
my ($altid, $git);
PublicInbox::AltId->new($ibx, $_);
} @$altid ];
}
+ if ($ibx->{indexlevel}) {
+ if ($ibx->{indexlevel} =~ $levels) {
+ $indexlevel = $ibx->{indexlevel};
+ } else {
+ die("Invalid indexlevel $ibx->{indexlevel}\n");
+ }
+ }
} else { # v1
$ibx = { mainrepo => $git_dir, version => 1 };
}
@$lines = ();
}
+sub add_xapian ($$$$$) {
+ my ($self, $mime, $num, $oid, $mids, $mid0) = @_;
+ my $smsg = PublicInbox::SearchMsg->new($mime);
+ my $doc = Search::Xapian::Document->new;
+ my $subj = $smsg->subject;
+ add_val($doc, PublicInbox::Search::TS(), $smsg->ts);
+ my @ds = gmtime($smsg->ds);
+ my $yyyymmdd = strftime('%Y%m%d', @ds);
+ add_val($doc, PublicInbox::Search::YYYYMMDD(), $yyyymmdd);
+ my $dt = strftime('%Y%m%d%H%M%S', @ds);
+ add_val($doc, PublicInbox::Search::DT(), $dt);
+
+ my $tg = $self->term_generator;
+
+ $tg->set_document($doc);
+ $self->index_text($subj, 1, 'S') if $subj;
+ $self->index_users($smsg);
+
+ msg_iter($mime, sub {
+ my ($part, $depth, @idx) = @{$_[0]};
+ my $ct = $part->content_type || 'text/plain';
+ my $fn = $part->filename;
+ if (defined $fn && $fn ne '') {
+ $self->index_text($fn, 1, 'XFN');
+ }
+
+ my ($s, undef) = msg_part_text($part, $ct);
+ defined $s or return;
+
+ my (@orig, @quot);
+ my @lines = split(/\n/, $s);
+ while (defined(my $l = shift @lines)) {
+ if ($l =~ /^>/) {
+ $self->index_body(\@orig, $doc) if @orig;
+ push @quot, $l;
+ } else {
+ $self->index_body(\@quot, 0) if @quot;
+ push @orig, $l;
+ }
+ }
+ $self->index_body(\@quot, 0) if @quot;
+ $self->index_body(\@orig, $doc) if @orig;
+ });
+
+ foreach my $mid (@$mids) {
+ $self->index_text($mid, 1, 'XM');
+
+ # because too many Message-IDs are prefixed with
+ # "Pine.LNX."...
+ if ($mid =~ /\w{12,}/) {
+ my @long = ($mid =~ /(\w{3,}+)/g);
+ $self->index_text(join(' ', @long), 1, 'XM');
+ }
+ }
+ $smsg->{to} = $smsg->{cc} = '';
+ PublicInbox::OverIdx::parse_references($smsg, $mid0, $mids);
+ my $data = $smsg->to_doc_data($oid, $mid0);
+ $doc->set_data($data);
+ if (my $altid = $self->{-altid}) {
+ foreach my $alt (@$altid) {
+ my $pfx = $alt->{xprefix};
+ foreach my $mid (@$mids) {
+ my $id = $alt->mid2alt($mid);
+ next unless defined $id;
+ $doc->add_boolean_term($pfx . $id);
+ }
+ }
+ }
+ $doc->add_boolean_term('Q' . $_) foreach @$mids;
+ $self->{xdb}->replace_document($num, $doc);
+}
+
sub add_message {
# mime = Email::MIME object
my ($self, $mime, $bytes, $num, $oid, $mid0) = @_;
- my $doc_id;
my $mids = mids($mime->header_obj);
$mid0 = $mids->[0] unless defined $mid0; # v1 compatibility
unless (defined $num) { # v1
$num = index_mm($self, $mime);
}
eval {
- my $smsg = PublicInbox::SearchMsg->new($mime);
- my $doc = $smsg->{doc};
- my $subj = $smsg->subject;
- add_val($doc, PublicInbox::Search::TS(), $smsg->ts);
- my @ds = gmtime($smsg->ds);
- my $yyyymmdd = strftime('%Y%m%d', @ds);
- add_val($doc, PublicInbox::Search::YYYYMMDD(), $yyyymmdd);
- my $dt = strftime('%Y%m%d%H%M%S', @ds);
- add_val($doc, PublicInbox::Search::DT(), $dt);
-
- my $tg = $self->term_generator;
-
- $tg->set_document($doc);
- $self->index_text($subj, 1, 'S') if $subj;
- $self->index_users($smsg);
-
- msg_iter($mime, sub {
- my ($part, $depth, @idx) = @{$_[0]};
- my $ct = $part->content_type || 'text/plain';
- my $fn = $part->filename;
- if (defined $fn && $fn ne '') {
- $self->index_text($fn, 1, 'XFN');
- }
-
- return if $ct =~ m!\btext/x?html\b!i;
-
- my $s = eval { $part->body_str };
- if ($@) {
- if ($ct =~ m!\btext/plain\b!i) {
- # Try to assume UTF-8 because Alpine
- # seems to do wacky things and set
- # charset=X-UNKNOWN
- $part->charset_set('UTF-8');
- $s = eval { $part->body_str };
- $s = $part->body if $@;
- }
- }
- defined $s or return;
-
- my (@orig, @quot);
- my $body = $part->body;
- my @lines = split(/\n/, $body);
- while (defined(my $l = shift @lines)) {
- if ($l =~ /^>/) {
- $self->index_body(\@orig, $doc) if @orig;
- push @quot, $l;
- } else {
- $self->index_body(\@quot, 0) if @quot;
- push @orig, $l;
- }
- }
- $self->index_body(\@quot, 0) if @quot;
- $self->index_body(\@orig, $doc) if @orig;
- });
-
- foreach my $mid (@$mids) {
- $self->index_text($mid, 1, 'XM');
-
- # because too many Message-IDs are prefixed with
- # "Pine.LNX."...
- if ($mid =~ /\w{12,}/) {
- my @long = ($mid =~ /(\w{3,}+)/g);
- $self->index_text(join(' ', @long), 1, 'XM');
- }
+ if ($self->{indexlevel} =~ $xapianlevels) {
+ $self->add_xapian($mime, $num, $oid, $mids, $mid0)
}
- $smsg->{to} = $smsg->{cc} = '';
- PublicInbox::OverIdx::parse_references($smsg, $mid0, $mids);
- my $data = $smsg->to_doc_data($oid, $mid0);
- $doc->set_data($data);
- if (my $altid = $self->{-altid}) {
- foreach my $alt (@$altid) {
- my $pfx = $alt->{xprefix};
- foreach my $mid (@$mids) {
- my $id = $alt->mid2alt($mid);
- next unless defined $id;
- $doc->add_boolean_term($pfx . $id);
- }
- }
- }
-
if (my $over = $self->{over}) {
$over->add_overview($mime, $bytes, $num, $oid, $mid0);
}
- $doc->add_boolean_term('Q' . $_) foreach @$mids;
- $self->{xdb}->replace_document($doc_id = $num, $doc);
};
if ($@) {
warn "failed to index message <".join('> <',@$mids).">: $@\n";
return undef;
}
- $doc_id;
+ $num;
}
# returns begin and end PostingIterator
($db->postlist_begin($termval), $db->postlist_end($termval));
}
+# v1 only
sub batch_do {
my ($self, $termval, $cb) = @_;
my $batch_size = 1000; # don't let @ids grow too large to avoid OOM
}
}
+# v1 only, where $mid is unique
sub remove_message {
my ($self, $mid) = @_;
my $db = $self->{xdb};
- my $called;
$mid = mid_clean($mid);
- my $over = $self->{over};
+ if (my $over = $self->{over}) {
+ my $nr = eval { $over->remove_oid(undef, $mid) };
+ if ($@) {
+ warn "failed to remove <$mid> from overview: $@\n";
+ } elsif ($nr == 0) {
+ warn "<$mid> missing for removal from overview\n";
+ }
+ }
+ return if $self->{indexlevel} !~ $xapianlevels;
+ my $nr = 0;
eval {
batch_do($self, 'Q' . $mid, sub {
my ($ids) = @_;
$db->delete_document($_) for @$ids;
- $over->delete_articles($ids) if $over;
- $called = 1;
+ $nr = scalar @$ids;
});
};
if ($@) {
- warn "failed to remove message <$mid>: $@\n";
- } elsif (!$called) {
- warn "cannot remove non-existent <$mid>\n";
+ warn "failed to remove <$mid> from Xapian: $@\n";
+ } elsif ($nr == 0) {
+ warn "<$mid> missing for removal from Xapian\n";
}
}
for (; $head != $tail; $head->inc) {
my $docid = $head->get_docid;
my $doc = $db->get_document($docid);
- my $smsg = PublicInbox::SearchMsg->wrap($doc, $mid);
- $smsg->load_expand;
+ my $smsg = PublicInbox::SearchMsg->wrap($mid);
+ $smsg->load_expand($doc);
if ($smsg->{blob} eq $oid) {
push(@delete, $docid);
}
my $blob = $1;
if (delete $D{$blob}) {
if (defined $self->{regen_down}) {
- $self->{regen_down}--;
+ my $num = $self->{regen_down}--;
+ $self->{mm}->num_highwater($num);
}
next;
}
my $git = $self->{git};
if (index($range, '..') < 0) {
- my $regen_max = 0;
- # can't use 'rev-list --count' if we use --diff-filter
- my $fh = $git->popen(qw(log --pretty=tformat:%h
- --no-notes --no-color --no-renames
- --diff-filter=AM), $range);
- ++$regen_max while <$fh>;
- my (undef, $max) = $self->{mm}->minmax;
-
- if ($max && $max == $regen_max) {
+ # don't show annoying git errrors to users who run -index
+ # on empty inboxes
+ $git->qx(qw(rev-parse -q --verify), "$range^0");
+ if ($?) {
+ open my $fh, '<', '/dev/null' or
+ die "failed to open /dev/null: $!\n";
+ return $fh;
+ }
+ }
+
+ # Count the new files so they can be added newest to oldest
+ # and still have numbers increasing from oldest to newest
+ my $fcount = 0;
+ # can't use 'rev-list --count' if we use --diff-filter
+ my $fh = $git->popen(qw(log --pretty=tformat:%h
+ --no-notes --no-color --no-renames
+ --diff-filter=AM), $range);
+ ++$fcount while <$fh>;
+ my $high = $self->{mm}->num_highwater;
+
+ if (index($range, '..') < 0) {
+ if ($high && $high == $fcount) {
# fix up old bugs in full indexes which caused messages to
# not appear in Msgmap
- $self->{regen_up} = $max;
+ $self->{regen_up} = $high;
} else {
# normal regen is for for fresh data
- $self->{regen_down} = $regen_max;
+ $self->{regen_down} = $fcount;
}
+ } else {
+ # Give oldest messages the smallest numbers
+ $self->{regen_down} = $high + $fcount;
}
$git->popen(qw/log --no-notes --no-color --no-renames
--raw -r --no-abbrev/, $range);
}
+# --is-ancestor requires git 1.8.0+
sub is_ancestor ($$$) {
my ($git, $cur, $tip) = @_;
return 0 unless $git->check($cur);
($n eq '' || $n > 0);
}
+# The last git commit we indexed with Xapian or SQLite (msgmap)
+# This needs to account for cases where Xapian or SQLite is
+# out-of-date with respect to the other.
+sub _last_x_commit {
+ my ($self, $mm) = @_;
+ my $lm = $mm->last_commit || '';
+ my $lx = '';
+ if ($self->{indexlevel} =~ $xapianlevels) {
+ $lx = $self->{xdb}->get_metadata('last_commit') || '';
+ } else {
+ $lx = $lm;
+ }
+ # Use last_commit from msgmap if it is older or unset
+ if (!$lm || ($lx && $lx && is_ancestor($self->{git}, $lm, $lx))) {
+ $lx = $lm;
+ }
+ $lx;
+}
+
# indexes all unindexed messages (v1 only)
sub _index_sync {
my ($self, $opts) = @_;
my $tip = $opts->{ref} || 'HEAD';
- my $reindex = $opts->{reindex};
- my ($mkey, $last_commit, $lx, $xlog);
+ my ($last_commit, $lx, $xlog);
my $git = $self->{git};
$git->batch_prepare;
my $mm = _msgmap_init($self);
do {
$xlog = undef;
- $mkey = 'last_commit';
- $last_commit = $xdb->get_metadata('last_commit');
- $lx = $last_commit;
- if ($reindex) {
- $lx = '';
- $mkey = undef if $last_commit ne '';
- }
-
- # use last_commit from msgmap if it is older or unset
- my $lm = $mm->last_commit || '';
- if (!$lm || ($lm && $lx && is_ancestor($git, $lm, $lx))) {
- $lx = $lm;
- }
+ $last_commit = _last_x_commit($self, $mm);
+ $lx = $opts->{reindex} ? '' : $last_commit;
$self->{over}->rollback_lazy;
$self->{over}->disconnect;
$xlog = _git_log($self, $range);
$xdb = $self->begin_txn_lazy;
- } while ($xdb->get_metadata('last_commit') ne $last_commit);
+ } while (_last_x_commit($self, $mm) ne $last_commit);
my $dbh = $mm->{dbh} if $mm;
my $cb = sub {
}
$dbh->commit;
}
- if ($mkey && $newest) {
- my $cur = $xdb->get_metadata($mkey);
+ if ($newest && $self->{indexlevel} =~ $xapianlevels) {
+ my $cur = $xdb->get_metadata('last_commit');
if (need_update($self, $cur, $newest)) {
- $xdb->set_metadata($mkey, $newest);
+ $xdb->set_metadata('last_commit', $newest);
}
}
$self->commit_txn_lazy;