use base qw(PublicInbox::Search PublicInbox::Lock);
use PublicInbox::MIME;
use PublicInbox::InboxWritable;
-use PublicInbox::MID qw/mid_clean id_compress mid_mime mids references/;
+use PublicInbox::MID qw/mid_clean id_compress mid_mime mids/;
use PublicInbox::MsgIter;
use Carp qw(croak);
use POSIX qw(strftime);
+use PublicInbox::OverIdx;
+use PublicInbox::Spawn qw(spawn);
require PublicInbox::Git;
+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 $xapianlevels = qr/\A(?:full|medium)\z/;
+
my %GIT_ESC = (
a => "\a",
b => "\b",
sub new {
my ($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);
my $version = 1;
+ my $indexlevel = 'full';
if (ref $ibx) {
$mainrepo = $ibx->{mainrepo};
$altid = $ibx->{altid};
PublicInbox::AltId->new($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 };
}
git => $ibx->git,
-altid => $altid,
version => $version,
+ indexlevel => $indexlevel,
}, $class;
$ibx->umask_prepare;
if ($version == 1) {
$self->{lock_path} = "$mainrepo/ssoma.lock";
+ my $dir = $self->xdir;
+ $self->{over} = PublicInbox::OverIdx->new("$dir/over.sqlite3");
} elsif ($version == 2) {
defined $part or die "partition is required for v2\n";
- # partition is a number or "all"
+ # partition is a number
$self->{partition} = $part;
$self->{lock_path} = undef;
- $self->{msgmap_path} = "$mainrepo/msgmap.sqlite3";
} else {
die "unsupported inbox version=$version\n";
}
$doc->add_value($col, $num);
}
-sub add_values {
- my ($doc, $ts, $ds, $num) = @_;
- add_val($doc, PublicInbox::Search::TS, $ts);
- my $yyyymmdd = strftime('%Y%m%d', gmtime($ds));
- add_val($doc, PublicInbox::Search::YYYYMMDD, $yyyymmdd);
- defined($num) and add_val($doc, PublicInbox::Search::NUM, $num);
+sub index_text ($$$$)
+{
+ my ($self, $field, $n, $text) = @_;
+ my $tg = $self->term_generator;
+
+ if ($self->{indexlevel} eq 'full') {
+ $tg->index_text($field, $n, $text);
+ $tg->increase_termpos;
+ } else {
+ $tg->index_text_without_positions($field, $n, $text);
+ }
}
sub index_users ($$) {
- my ($tg, $smsg) = @_;
+ my ($self, $smsg) = @_;
my $from = $smsg->from;
my $to = $smsg->to;
my $cc = $smsg->cc;
- $tg->index_text($from, 1, 'A'); # A - author
- $tg->increase_termpos;
- $tg->index_text($to, 1, 'XTO') if $to ne '';
- $tg->increase_termpos;
- $tg->index_text($cc, 1, 'XCC') if $cc ne '';
- $tg->increase_termpos;
+ $self->index_text($from, 1, 'A'); # A - author
+ $self->index_text($to, 1, 'XTO') if $to ne '';
+ $self->index_text($cc, 1, 'XCC') if $cc ne '';
}
sub index_diff_inc ($$$$) {
- my ($tg, $text, $pfx, $xnq) = @_;
+ my ($self, $text, $pfx, $xnq) = @_;
if (@$xnq) {
- $tg->index_text(join("\n", @$xnq), 1, 'XNQ');
- $tg->increase_termpos;
+ $self->index_text(join("\n", @$xnq), 1, 'XNQ');
@$xnq = ();
}
- $tg->index_text($text, 1, $pfx);
- $tg->increase_termpos;
+ $self->index_text($text, 1, $pfx);
}
sub index_old_diff_fn {
- my ($tg, $seen, $fa, $fb, $xnq) = @_;
+ my ($self, $seen, $fa, $fb, $xnq) = @_;
# no renames or space support for traditional diffs,
# find the number of leading common paths to strip:
$fb = join('/', @fb);
if ($fa eq $fb) {
unless ($seen->{$fa}++) {
- index_diff_inc($tg, $fa, 'XDFN', $xnq);
+ $self->index_diff_inc($fa, 'XDFN', $xnq);
}
return 1;
}
}
sub index_diff ($$$) {
- my ($tg, $lines, $doc) = @_;
+ my ($self, $lines, $doc) = @_;
my %seen;
my $in_diff;
my @xnq;
my $xnq = \@xnq;
foreach (@$lines) {
if ($in_diff && s/^ //) { # diff context
- index_diff_inc($tg, $_, 'XDFCTX', $xnq);
+ $self->index_diff_inc($_, 'XDFCTX', $xnq);
} elsif (/^-- $/) { # email signature begins
$in_diff = undef;
} elsif (m!^diff --git ("?a/.+) ("?b/.+)\z!) {
my ($fa, $fb) = ($1, $2);
my $fn = (split('/', git_unquote($fa), 2))[1];
- $seen{$fn}++ or index_diff_inc($tg, $fn, 'XDFN', $xnq);
+ $seen{$fn}++ or $self->index_diff_inc($fn, 'XDFN', $xnq);
$fn = (split('/', git_unquote($fb), 2))[1];
- $seen{$fn}++ or index_diff_inc($tg, $fn, 'XDFN', $xnq);
+ $seen{$fn}++ or $self->index_diff_inc($fn, 'XDFN', $xnq);
$in_diff = 1;
# traditional diff:
} elsif (m/^diff -(.+) (\S+) (\S+)$/) {
push @xnq, $_;
# only support unified:
next unless $opt =~ /[uU]/;
- $in_diff = index_old_diff_fn($tg, \%seen, $fa, $fb,
+ $in_diff = $self->index_old_diff_fn(\%seen, $fa, $fb,
$xnq);
} elsif (m!^--- ("?a/.+)!) {
my $fn = (split('/', git_unquote($1), 2))[1];
- $seen{$fn}++ or index_diff_inc($tg, $fn, 'XDFN', $xnq);
+ $seen{$fn}++ or $self->index_diff_inc($fn, 'XDFN', $xnq);
$in_diff = 1;
} elsif (m!^\+\+\+ ("?b/.+)!) {
my $fn = (split('/', git_unquote($1), 2))[1];
- $seen{$fn}++ or index_diff_inc($tg, $fn, 'XDFN', $xnq);
+ $seen{$fn}++ or $self->index_diff_inc($fn, 'XDFN', $xnq);
$in_diff = 1;
} elsif (/^--- (\S+)/) {
$in_diff = $1;
push @xnq, $_;
} elsif (defined $in_diff && /^\+\+\+ (\S+)/) {
- $in_diff = index_old_diff_fn($tg, \%seen, $in_diff, $1,
+ $in_diff = $self->index_old_diff_fn(\%seen, $in_diff, $1,
$xnq);
} elsif ($in_diff && s/^\+//) { # diff added
- index_diff_inc($tg, $_, 'XDFB', $xnq);
+ $self->index_diff_inc($_, 'XDFB', $xnq);
} elsif ($in_diff && s/^-//) { # diff removed
- index_diff_inc($tg, $_, 'XDFA', $xnq);
+ $self->index_diff_inc($_, 'XDFA', $xnq);
} elsif (m!^index ([a-f0-9]+)\.\.([a-f0-9]+)!) {
my ($ba, $bb) = ($1, $2);
index_git_blob_id($doc, 'XDFPRE', $ba);
# traditional diff w/o -p
} elsif (/^@@ (?:\S+) (?:\S+) @@\s*(\S+.*)$/) {
# hunk header context
- index_diff_inc($tg, $1, 'XDFHH', $xnq);
+ $self->index_diff_inc($1, 'XDFHH', $xnq);
# ignore the following lines:
} elsif (/^(?:dis)similarity index/ ||
/^(?:old|new) mode/ ||
}
}
- $tg->index_text(join("\n", @xnq), 1, 'XNQ');
- $tg->increase_termpos;
+ $self->index_text(join("\n", @xnq), 1, 'XNQ');
}
sub index_body ($$$) {
- my ($tg, $lines, $doc) = @_;
+ my ($self, $lines, $doc) = @_;
my $txt = join("\n", @$lines);
if ($doc) {
# does it look like a diff?
if ($txt =~ /^(?:diff|---|\+\+\+) /ms) {
$txt = undef;
- index_diff($tg, $lines, $doc);
+ $self->index_diff($lines, $doc);
} else {
- $tg->index_text($txt, 1, 'XNQ');
+ $self->index_text($txt, 1, 'XNQ');
}
} else {
- $tg->index_text($txt, 0, 'XQUOT');
+ $self->index_text($txt, 0, 'XQUOT');
}
- $tg->increase_termpos;
@$lines = ();
}
-sub add_message {
- # mime = Email::MIME object
- my ($self, $mime, $bytes, $num, $oid, $mid0) = @_;
- my $doc_id;
- my $mids = mids($mime->header_obj);
- my $skel = $self->{skeleton};
-
- eval {
- my $smsg = PublicInbox::SearchMsg->new($mime);
- my $doc = $smsg->{doc};
- my $subj = $smsg->subject;
- my $xpath;
- if ($subj ne '') {
- $xpath = $self->subject_path($subj);
- $xpath = id_compress($xpath);
+sub add_xapian ($$$$$) {
+ 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 $lines = $mime->body_raw =~ tr!\n!\n!;
- $smsg->{lines} = $mime->body_raw =~ tr!\n!\n!;
- defined $bytes or $bytes = length($mime->as_string);
- $smsg->{bytes} = $bytes;
- add_values($doc, $smsg->ts, $smsg->ds, $num);
-
- my $tg = $self->term_generator;
-
- $tg->set_document($doc);
- $tg->index_text($subj, 1, 'S') if $subj;
- $tg->increase_termpos;
-
- index_users($tg, $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 '') {
- $tg->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;
+ });
- 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 =~ /^>/) {
- index_body($tg, \@orig, $doc) if @orig;
- push @quot, $l;
- } else {
- index_body($tg, \@quot, 0) if @quot;
- push @orig, $l;
- }
- }
- index_body($tg, \@quot, 0) if @quot;
- index_body($tg, \@orig, $doc) if @orig;
- });
+ foreach my $mid (@$mids) {
+ $self->index_text($mid, 1, 'XM');
- # populates smsg->references for smsg->to_doc_data
- my $refs = parse_references($smsg);
- $mid0 = $mids->[0] unless defined $mid0; # v1 compatibility
- my $data = $smsg->to_doc_data($oid, $mid0);
- foreach my $mid (@$mids) {
- $tg->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');
}
- $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);
- }
+ }
+ $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);
+}
- $self->delete_article($num) if defined $num; # for reindexing
- if ($skel) {
- my @vals = ($smsg->ts, $num, $mids, $xpath, $data);
- $skel->index_skeleton(\@vals);
- $doc->add_boolean_term('Q' . $_) foreach @$mids;
- $doc->add_boolean_term('XNUM' . $num) if defined $num;
- $doc_id = $self->{xdb}->add_document($doc);
- } else {
- $doc_id = link_and_save($self, $doc, $mids, $refs,
- $num, $xpath);
+sub add_message {
+ # mime = Email::MIME object
+ my ($self, $mime, $bytes, $num, $oid, $mid0) = @_;
+ my $mids = mids($mime->header_obj);
+ $mid0 = $mids->[0] unless defined $mid0; # v1 compatibility
+ unless (defined $num) { # v1
+ $self->_msgmap_init;
+ $num = index_mm($self, $mime);
+ }
+ eval {
+ if ($self->{indexlevel} =~ $xapianlevels) {
+ $self->add_xapian($mime, $num, $oid, $mids, $mid0)
+ }
+ if (my $over = $self->{over}) {
+ $over->add_overview($mime, $bytes, $num, $oid, $mid0);
}
};
warn "failed to index message <".join('> <',@$mids).">: $@\n";
return undef;
}
- $doc_id;
+ $num;
}
# returns begin and end PostingIterator
my $db = $self->{xdb};
my $called;
$mid = mid_clean($mid);
+ my $over = $self->{over};
eval {
batch_do($self, 'Q' . $mid, sub {
my ($ids) = @_;
$db->delete_document($_) for @$ids;
+ $over->delete_articles($ids) if $over;
$called = 1;
});
};
}
}
-sub delete_article {
- my ($self, $num) = @_;
- my $ndel = 0;
- batch_do($self, 'XNUM' . $num, sub {
- my ($ids) = @_;
- $ndel += scalar @$ids;
- $self->{xdb}->delete_document($_) for @$ids;
- });
-}
-
# MID is a hint in V2
sub remove_by_oid {
my ($self, $oid, $mid) = @_;
my $db = $self->{xdb};
+ $self->{over}->remove_oid($oid, $mid) if $self->{over};
+
# XXX careful, we cannot use batch_do here since we conditionally
# delete documents based on other factors, so we cannot call
# find_doc_ids twice.
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;
- push(@delete, $docid) if $smsg->{blob} eq $oid;
+ my $smsg = PublicInbox::SearchMsg->wrap($mid);
+ $smsg->load_expand($doc);
+ if ($smsg->{blob} eq $oid) {
+ push(@delete, $docid);
+ }
}
$db->delete_document($_) foreach @delete;
scalar(@delete);
$self->{term_generator} = $tg;
}
-# increments last_thread_id counter
-# returns a 64-bit integer represented as a decimal string
-sub next_thread_id {
- my ($self) = @_;
- my $db = $self->{xdb};
- my $last_thread_id = int($db->get_metadata('last_thread_id') || 0);
-
- $db->set_metadata('last_thread_id', ++$last_thread_id);
-
- $last_thread_id;
-}
-
-sub parse_references ($) {
- my ($smsg) = @_;
- my $mime = $smsg->{mime};
- my $hdr = $mime->header_obj;
- my $refs = references($hdr);
- return $refs if scalar(@$refs) == 0;
-
- # prevent circular references via References here:
- my %mids = map { $_ => 1 } @{mids($hdr)};
- my @keep;
- foreach my $ref (@$refs) {
- if (length($ref) > PublicInbox::MID::MAX_MID_SIZE) {
- warn "References: <$ref> too long, ignoring\n";
- next;
- }
- next if $mids{$ref};
- push @keep, $ref;
- }
- $smsg->{references} = '<'.join('> <', @keep).'>' if @keep;
- \@keep;
-}
-
-sub link_doc {
- my ($self, $doc, $refs, $old_tid) = @_;
- my $tid;
-
- if (@$refs) {
- # first ref *should* be the thread root,
- # but we can never trust clients to do the right thing
- my $ref = shift @$refs;
- $tid = resolve_mid_to_tid($self, $ref);
- merge_threads($self, $tid, $old_tid) if defined $old_tid;
-
- # the rest of the refs should point to this tid:
- foreach $ref (@$refs) {
- my $ptid = resolve_mid_to_tid($self, $ref);
- merge_threads($self, $tid, $ptid);
- }
- } else {
- $tid = defined $old_tid ? $old_tid : $self->next_thread_id;
- }
- $doc->add_boolean_term('G' . $tid);
- $tid;
-}
-
-sub link_and_save {
- my ($self, $doc, $mids, $refs, $num, $xpath) = @_;
- my $db = $self->{xdb};
- my $old_tid;
- my $doc_id;
- $doc->add_boolean_term('XNUM' . $num) if defined $num;
- $doc->add_boolean_term('XPATH' . $xpath) if defined $xpath;
- $doc->add_boolean_term('Q' . $_) foreach @$mids;
-
- $self->{skel} and die "Should not have read-only skel here\n";;
- foreach my $mid (@$mids) {
- my $vivified = 0;
- $self->each_smsg_by_mid($mid, sub {
- my ($cur) = @_;
- my $type = $cur->type;
- my $cur_tid = $cur->thread_id;
- $old_tid = $cur_tid unless defined $old_tid;
- if ($type eq 'mail') {
- # do not break existing mail messages,
- # just merge the threads
- merge_threads($self, $old_tid, $cur_tid);
- return 1;
- }
- if ($type ne 'ghost') {
- die "<$mid> has a bad type: $type\n";
- }
- my $tid = link_doc($self, $doc, $refs, $old_tid);
- $old_tid = $tid unless defined $old_tid;
- $doc_id = $cur->{doc_id};
- $self->{xdb}->replace_document($doc_id, $doc);
- ++$vivified;
- 1;
- });
- $vivified > 1 and warn
- "BUG: vivified multiple ($vivified) ghosts for $mid\n";
- }
- # not really important, but we return any vivified ghost docid, here:
- return $doc_id if defined $doc_id;
- link_doc($self, $doc, $refs, $old_tid);
- $self->{xdb}->add_document($doc);
-}
-
sub index_git_blob_id {
my ($doc, $pfx, $objid) = @_;
my ($self, $mime) = @_;
my $mid = mid_clean(mid_mime($mime));
my $mm = $self->{mm};
- my $num = $mm->mid_insert($mid);
- return $num if defined $num;
+ my $num;
+
+ if (defined $self->{regen_down}) {
+ $num = $mm->num_for($mid) and return $num;
+
+ while (($num = $self->{regen_down}--) > 0) {
+ if ($mm->mid_set($num, $mid) != 0) {
+ return $num;
+ }
+ }
+ } elsif (defined $self->{regen_up}) {
+ $num = $mm->num_for($mid) and return $num;
+
+ # this is to fixup old bugs due to add-remove-add
+ while (($num = ++$self->{regen_up})) {
+ if ($mm->mid_set($num, $mid) != 0) {
+ return $num;
+ }
+ }
+ }
+
+ $num = $mm->mid_insert($mid) and return $num;
# fallback to num_for since filters like RubyLang set the number
$mm->num_for($mid);
$self->{mm}->mid_delete(mid_clean(mid_mime($mime)));
}
-sub index_mm2 {
- my ($self, $mime, $bytes, $blob) = @_;
- my $num = $self->{mm}->num_for(mid_clean(mid_mime($mime)));
- add_message($self, $mime, $bytes, $num, $blob);
-}
-
-sub unindex_mm2 {
- my ($self, $mime) = @_;
- $self->{mm}->mid_delete(mid_clean(mid_mime($mime)));
- unindex_blob($self, $mime);
-}
-
sub index_both {
my ($self, $mime, $bytes, $blob) = @_;
my $num = index_mm($self, $mime);
$$max -= $bytes;
if ($$max <= 0) {
$$max = BATCH_BYTES;
- $batch_cb->($latest, 1);
+ $batch_cb->($latest);
}
}
# only for v1
-sub rlog {
+sub read_log {
my ($self, $log, $add_cb, $del_cb, $batch_cb) = @_;
my $hex = '[a-f0-9]';
my $h40 = $hex .'{40}';
my $bytes;
my $max = BATCH_BYTES;
local $/ = "\n";
+ my %D;
my $line;
+ my $newest;
while (defined($line = <$log>)) {
if ($line =~ /$addmsg/o) {
my $blob = $1;
+ if (delete $D{$blob}) {
+ if (defined $self->{regen_down}) {
+ my $num = $self->{regen_down}--;
+ $self->{mm}->num_highwater($num);
+ }
+ next;
+ }
my $mime = do_cat_mail($git, $blob, \$bytes) or next;
batch_adjust(\$max, $bytes, $batch_cb, $latest);
$add_cb->($self, $mime, $bytes, $blob);
} elsif ($line =~ /$delmsg/o) {
my $blob = $1;
- my $mime = do_cat_mail($git, $blob, \$bytes) or next;
- batch_adjust(\$max, $bytes, $batch_cb, $latest);
- $del_cb->($self, $mime);
+ $D{$blob} = 1;
} elsif ($line =~ /^commit ($h40)/o) {
$latest = $1;
+ $newest ||= $latest;
}
}
- $batch_cb->($latest, 0);
+ # get the leftovers
+ foreach my $blob (keys %D) {
+ my $mime = do_cat_mail($git, $blob, \$bytes) or next;
+ $del_cb->($self, $mime);
+ }
+ $batch_cb->($latest, $newest);
}
sub _msgmap_init {
my ($self) = @_;
+ die "BUG: _msgmap_init is only for v1\n" if $self->{version} != 1;
$self->{mm} ||= eval {
require PublicInbox::Msgmap;
- my $msgmap_path = $self->{msgmap_path};
- if (defined $msgmap_path) { # v2
- PublicInbox::Msgmap->new_file($msgmap_path, 1);
- } else {
- PublicInbox::Msgmap->new($self->{mainrepo}, 1);
- }
+ PublicInbox::Msgmap->new($self->{mainrepo}, 1);
};
}
sub _git_log {
my ($self, $range) = @_;
- $self->{git}->popen(qw/log --reverse --no-notes --no-color
+ my $git = $self->{git};
+
+ if (index($range, '..') < 0) {
+ # 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} = $high;
+ } else {
+ # normal regen is for for fresh data
+ $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);
}
-# indexes all unindexed messages
+# --is-ancestor requires git 1.8.0+
+sub is_ancestor ($$$) {
+ my ($git, $cur, $tip) = @_;
+ return 0 unless $git->check($cur);
+ my $cmd = [ 'git', "--git-dir=$git->{git_dir}",
+ qw(merge-base --is-ancestor), $cur, $tip ];
+ my $pid = spawn($cmd);
+ defined $pid or die "spawning ".join(' ', @$cmd)." failed: $!";
+ waitpid($pid, 0) == $pid or die join(' ', @$cmd) .' did not finish';
+ $? == 0;
+}
+
+sub need_update ($$$) {
+ my ($self, $cur, $new) = @_;
+ my $git = $self->{git};
+ return 1 if $cur && !is_ancestor($git, $cur, $new);
+ my $range = $cur eq '' ? $new : "$cur..$new";
+ chomp(my $n = $git->qx(qw(rev-list --count), $range));
+ ($n eq '' || $n > 0);
+}
+
+# indexes all unindexed messages (v1 only)
sub _index_sync {
my ($self, $opts) = @_;
my $tip = $opts->{ref} || 'HEAD';
my $reindex = $opts->{reindex};
my ($mkey, $last_commit, $lx, $xlog);
- $self->{git}->batch_prepare;
- my $xdb = _xdb_acquire($self);
- $xdb->begin_transaction;
+ my $git = $self->{git};
+ $git->batch_prepare;
+
+ my $xdb = $self->begin_txn_lazy;
+ my $mm = _msgmap_init($self);
do {
$xlog = undef;
$mkey = 'last_commit';
$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;
+ }
+
+ $self->{over}->rollback_lazy;
+ $self->{over}->disconnect;
+ $git->cleanup;
+ delete $self->{txn};
$xdb->cancel_transaction;
$xdb = _xdb_release($self);
- # ensure we leak no FDs to "git log"
+ # ensure we leak no FDs to "git log" with Xapian <= 1.2
my $range = $lx eq '' ? $tip : "$lx..$tip";
$xlog = _git_log($self, $range);
- $xdb = _xdb_acquire($self);
- $xdb->begin_transaction;
+ $xdb = $self->begin_txn_lazy;
} while ($xdb->get_metadata('last_commit') ne $last_commit);
- my $mm = _msgmap_init($self);
my $dbh = $mm->{dbh} if $mm;
- my $mm_only;
my $cb = sub {
- my ($commit, $more) = @_;
+ my ($commit, $newest) = @_;
if ($dbh) {
- $mm->last_commit($commit) if $commit;
+ if ($newest) {
+ my $cur = $mm->last_commit || '';
+ if (need_update($self, $cur, $newest)) {
+ $mm->last_commit($newest);
+ }
+ }
$dbh->commit;
}
- if (!$mm_only) {
- $xdb->set_metadata($mkey, $commit) if $mkey && $commit;
- $xdb->commit_transaction;
- $xdb = _xdb_release($self);
+ if ($mkey && $newest && $self->{indexlevel} =~ $xapianlevels) {
+ my $cur = $xdb->get_metadata($mkey);
+ if (need_update($self, $cur, $newest)) {
+ $xdb->set_metadata($mkey, $newest);
+ }
}
+ $self->commit_txn_lazy;
+ $git->cleanup;
+ $xdb = _xdb_release($self);
# let another process do some work... <
- if ($more) {
- if (!$mm_only) {
- $xdb = _xdb_acquire($self);
- $xdb->begin_transaction;
- }
+ if (!$newest) {
+ $xdb = $self->begin_txn_lazy;
$dbh->begin_work if $dbh;
}
};
- if ($mm) {
- $dbh->begin_work;
- my $lm = $mm->last_commit || '';
- if ($lm eq $lx) {
- # Common case is the indexes are synced,
- # we only need to run git-log once:
- rlog($self, $xlog, *index_both, *unindex_both, $cb);
- } else {
- # Uncommon case, msgmap and xapian are out-of-sync
- # do not care for performance (but git is fast :>)
- # This happens if we have to reindex Xapian since
- # msgmap is a frozen format and our Xapian format
- # is evolving.
- my $r = $lm eq '' ? $tip : "$lm..$tip";
-
- # first, ensure msgmap is up-to-date:
- my $mkey_prev = $mkey;
- $mkey = undef; # ignore xapian, for now
- my $mlog = _git_log($self, $r);
- $mm_only = 1;
- rlog($self, $mlog, *index_mm, *unindex_mm, $cb);
- $mm_only = $mlog = undef;
-
- # now deal with Xapian
- $mkey = $mkey_prev;
- $dbh = undef;
- rlog($self, $xlog, *index_mm2, *unindex_mm2, $cb);
- }
- } else {
- # user didn't install DBD::SQLite and DBI
- rlog($self, $xlog, *add_message, *unindex_blob, $cb);
- }
-}
-
-# this will create a ghost as necessary
-sub resolve_mid_to_tid {
- my ($self, $mid) = @_;
- my $tid;
- $self->each_smsg_by_mid($mid, sub {
- my ($smsg) = @_;
- my $cur_tid = $smsg->thread_id;
- if (defined $tid) {
- merge_threads($self, $tid, $cur_tid);
- } else {
- $tid = $smsg->thread_id;
- }
- 1;
- });
- return $tid if defined $tid;
-
- $self->create_ghost($mid)->thread_id;
-}
-
-sub create_ghost {
- my ($self, $mid) = @_;
-
- my $tid = $self->next_thread_id;
- my $doc = Search::Xapian::Document->new;
- $doc->add_boolean_term('Q' . $mid);
- $doc->add_boolean_term('G' . $tid);
- $doc->add_boolean_term('T' . 'ghost');
-
- my $smsg = PublicInbox::SearchMsg->wrap($doc, $mid);
- $self->{xdb}->add_document($doc);
-
- $smsg;
-}
-
-sub merge_threads {
- my ($self, $winner_tid, $loser_tid) = @_;
- return if $winner_tid == $loser_tid;
- my $db = $self->{xdb};
- batch_do($self, 'G' . $loser_tid, sub {
- my ($ids) = @_;
- foreach my $docid (@$ids) {
- my $doc = $db->get_document($docid);
- $doc->remove_term('G' . $loser_tid);
- $doc->add_boolean_term('G' . $winner_tid);
- $db->replace_document($docid, $doc);
- }
- });
+ $dbh->begin_work;
+ read_log($self, $xlog, *index_both, *unindex_both, $cb);
}
sub DESTROY {
$_[0]->{lockfh} = undef;
}
-# remote_* subs are only used by SearchIdxPart and SearchIdxSkeleton
+# remote_* subs are only used by SearchIdxPart
sub remote_commit {
my ($self) = @_;
if (my $w = $self->{w}) {
print $w "commit\n" or die "failed to write commit: $!";
} else {
$self->commit_txn_lazy;
- if (my $skel = $self->{skeleton}) {
- $skel->commit_txn_lazy;
- }
}
}
sub remote_remove {
my ($self, $oid, $mid) = @_;
if (my $w = $self->{w}) {
- # triggers remove_by_oid in partition or skeleton
+ # triggers remove_by_oid in a partition
print $w "D $oid $mid\n" or die "failed to write remove $!";
} else {
$self->begin_txn_lazy;
sub begin_txn_lazy {
my ($self) = @_;
return if $self->{txn};
- my $xdb = $self->{xdb} || $self->_xdb_acquire;
- $xdb->begin_transaction;
- $self->{txn} = 1;
+
+ $self->{-inbox}->with_umask(sub {
+ my $xdb = $self->{xdb} || $self->_xdb_acquire;
+ $self->{over}->begin_lazy if $self->{over};
+ $xdb->begin_transaction;
+ $self->{txn} = 1;
+ $xdb;
+ });
}
sub commit_txn_lazy {
my ($self) = @_;
delete $self->{txn} or return;
- $self->{xdb}->commit_transaction;
+ $self->{-inbox}->with_umask(sub {
+ $self->{xdb}->commit_transaction;
+ $self->{over}->commit_lazy if $self->{over};
+ });
}
sub worker_done {