-# Copyright (C) 2015, all contributors <meta@public-inbox.org>
-# License: AGPLv3 or later (https://www.gnu.org/licenses/agpl-3.0.txt)
+# Copyright (C) 2015-2020 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 or flags
+#
+# Indexes mail with Xapian and our (SQLite-based) ::Msgmap for use
+# with the web and NNTP interfaces. This index maintains thread
+# relationships for use by PublicInbox::SearchThread.
+# This writes to the search index.
package PublicInbox::SearchIdx;
use strict;
use warnings;
-use base qw(PublicInbox::Search);
-use PublicInbox::MID qw/mid_clean mid_compress/;
-*xpfx = *PublicInbox::Search::xpfx;
-
+use base qw(PublicInbox::Search PublicInbox::Lock);
+use PublicInbox::MIME;
+use PublicInbox::InboxWritable;
+use PublicInbox::MID qw/mid_clean mid_mime mids_for_index/;
+use PublicInbox::MsgIter;
+use Carp qw(croak);
+use POSIX qw(strftime);
+use PublicInbox::OverIdx;
+use PublicInbox::Spawn qw(spawn);
+use PublicInbox::Git qw(git_unquote);
+use PublicInbox::MsgTime qw(msg_timestamp msg_datestamp);
+my $X = \%PublicInbox::Search::X;
+my ($DB_CREATE_OR_OPEN, $DB_OPEN);
use constant {
- PERM_UMASK => 0,
- OLD_PERM_GROUP => 1,
- OLD_PERM_EVERYBODY => 2,
- PERM_GROUP => 0660,
- PERM_EVERYBODY => 0664,
+ BATCH_BYTES => defined($ENV{XAPIAN_FLUSH_THRESHOLD}) ?
+ 0x7fffffff : 1_000_000,
+ DEBUG => !!$ENV{DEBUG},
};
+my $xapianlevels = qr/\A(?:full|medium)\z/;
+
sub new {
- my ($class, $git_dir, $writable) = @_;
- my $dir = $class->xdir($git_dir);
- require Search::Xapian::WritableDatabase;
- my $flag = Search::Xapian::DB_OPEN;
- my $self = bless { git_dir => $git_dir }, $class;
- my $perm = $self->_git_config_perm;
- my $umask = _umask_for($perm);
- $self->{umask} = $umask;
- $self->{xdb} = $self->with_umask(sub {
- if ($writable == 1) {
- require File::Path;
- File::Path::mkpath($dir);
- $flag = Search::Xapian::DB_CREATE_OR_OPEN;
+ my ($class, $ibx, $creat, $shard) = @_;
+ ref $ibx or die "BUG: expected PublicInbox::Inbox object: $ibx";
+ my $levels = qr/\A(?:full|medium|basic)\z/;
+ my $inboxdir = $ibx->{inboxdir};
+ my $version = $ibx->version;
+ my $indexlevel = 'full';
+ my $altid = $ibx->{altid};
+ if ($altid) {
+ require PublicInbox::AltId;
+ $altid = [ map { PublicInbox::AltId->new($ibx, $_); } @$altid ];
+ }
+ if ($ibx->{indexlevel}) {
+ if ($ibx->{indexlevel} =~ $levels) {
+ $indexlevel = $ibx->{indexlevel};
+ } else {
+ die("Invalid indexlevel $ibx->{indexlevel}\n");
}
- Search::Xapian::WritableDatabase->new($dir, $flag);
- });
+ }
+ $ibx = PublicInbox::InboxWritable->new($ibx);
+ my $self = bless {
+ inboxdir => $inboxdir,
+ -inbox => $ibx,
+ git => $ibx->git,
+ -altid => $altid,
+ ibx_ver => $version,
+ indexlevel => $indexlevel,
+ }, $class;
+ $self->{-set_indexlevel_once} = 1 if $indexlevel eq 'medium';
+ $ibx->umask_prepare;
+ if ($version == 1) {
+ $self->{lock_path} = "$inboxdir/ssoma.lock";
+ my $dir = $self->xdir;
+ $self->{over} = PublicInbox::OverIdx->new("$dir/over.sqlite3");
+ } elsif ($version == 2) {
+ defined $shard or die "shard is required for v2\n";
+ # shard is a number
+ $self->{shard} = $shard;
+ $self->{lock_path} = undef;
+ } else {
+ die "unsupported inbox version=$version\n";
+ }
+ $self->{creat} = ($creat || 0) == 1;
$self;
}
-sub add_message {
- my ($self, $mime) = @_; # mime = Email::MIME object
- my $db = $self->{xdb};
-
- my $doc_id;
- my $mid_orig = mid_clean($mime->header('Message-ID'));
- my $mid = mid_compress($mid_orig);
- my $was_ghost = 0;
- my $ct_msg = $mime->header('Content-Type') || 'text/plain';
+sub need_xapian ($) { $_[0]->{indexlevel} =~ $xapianlevels }
- eval {
- my $smsg = $self->lookup_message($mid);
- my $doc;
-
- if ($smsg) {
- $smsg->ensure_metadata;
- # convert a ghost to a regular message
- # it will also clobber any existing regular message
- $smsg->mime($mime);
- $doc = $smsg->{doc};
-
- my $type = xpfx('type');
- eval {
- $doc->remove_term($type . 'ghost');
- $was_ghost = 1;
- };
-
- # probably does not exist:
- eval { $doc->remove_term($type . 'mail') };
- $doc->add_term($type . 'mail');
- } else {
- $smsg = PublicInbox::SearchMsg->new($mime);
- $doc = $smsg->{doc};
- $doc->add_term(xpfx('mid') . $mid);
- }
+sub _xdb_release {
+ my ($self) = @_;
+ if (need_xapian($self)) {
+ my $xdb = delete $self->{xdb} or croak 'not acquired';
+ $xdb->close;
+ }
+ $self->lock_release if $self->{creat};
+ undef;
+}
- my $subj = $smsg->subject;
+sub load_xapian_writable () {
+ return 1 if $X->{WritableDatabase};
+ PublicInbox::Search::load_xapian() or return;
+ my $xap = $PublicInbox::Search::Xap;
+ for (qw(Document TermGenerator WritableDatabase)) {
+ $X->{$_} = $xap.'::'.$_;
+ }
+ eval 'require '.$X->{WritableDatabase} or die;
+ *sortable_serialise = $xap.'::sortable_serialise';
+ $DB_CREATE_OR_OPEN = eval($xap.'::DB_CREATE_OR_OPEN()');
+ $DB_OPEN = eval($xap.'::DB_OPEN()');
+ 1;
+}
- if (length $subj) {
- $doc->add_term(xpfx('subject') . $subj);
+sub _xdb_acquire {
+ my ($self) = @_;
+ my $flag;
+ my $dir = $self->xdir;
+ if (need_xapian($self)) {
+ croak 'already acquired' if $self->{xdb};
+ load_xapian_writable();
+ $flag = $self->{creat} ? $DB_CREATE_OR_OPEN : $DB_OPEN;
+ }
+ if ($self->{creat}) {
+ require File::Path;
+ $self->lock_acquire;
- my $path = $self->subject_path($subj);
- $doc->add_term(xpfx('path') . mid_compress($path));
+ # don't create empty Xapian directories if we don't need Xapian
+ my $is_shard = defined($self->{shard});
+ if (!$is_shard || ($is_shard && need_xapian($self))) {
+ File::Path::mkpath($dir);
}
+ }
+ return unless defined $flag;
+ my $xdb = eval { ($X->{WritableDatabase})->new($dir, $flag) };
+ if ($@) {
+ die "Failed opening $dir: ", $@;
+ }
+ $self->{xdb} = $xdb;
+}
- my $from = $smsg->from_name;
- my $date = $smsg->date;
- my $ts = Search::Xapian::sortable_serialise($smsg->ts);
- $doc->add_value(PublicInbox::Search::TS, $ts);
+sub add_val ($$$) {
+ my ($doc, $col, $num) = @_;
+ $num = sortable_serialise($num);
+ $doc->add_value($col, $num);
+}
- my $tg = $self->term_generator;
+sub term_generator ($) { # write-only
+ my ($self) = @_;
- $tg->set_document($doc);
- $tg->index_text($subj, 1, 'S') if $subj;
- $tg->increase_termpos;
- $tg->index_text($subj) if $subj;
- $tg->increase_termpos;
+ $self->{term_generator} //= do {
+ my $tg = $X->{TermGenerator}->new;
+ $tg->set_stemmer($self->stemmer);
+ $tg;
+ }
+}
+
+sub index_text ($$$$) {
+ my ($self, $text, $wdf_inc, $prefix) = @_;
+ my $tg = term_generator($self); # man Search::Xapian::TermGenerator
- $tg->index_text($smsg->from->format);
+ if ($self->{indexlevel} eq 'full') {
+ $tg->index_text($text, $wdf_inc, $prefix);
$tg->increase_termpos;
+ } else {
+ $tg->index_text_without_positions($text, $wdf_inc, $prefix);
+ }
+}
- $mime->walk_parts(sub {
- my ($part) = @_;
- return if $part->subparts; # walk_parts already recurses
- my $ct = $part->content_type || $ct_msg;
-
- # account for filter bugs...
- $ct =~ m!\btext/plain\b!i or return;
-
- my (@orig, @quot);
- my $body = $part->body;
- $part->body_set('');
- my @lines = split(/\n/, $body);
- while (defined(my $l = shift @lines)) {
- if ($l =~ /^\s*>/) {
- push @quot, $l;
- } else {
- push @orig, $l;
- }
- }
- if (@quot) {
- $tg->index_text(join("\n", @quot), 0);
- @quot = ();
- $tg->increase_termpos;
- }
- if (@orig) {
- $tg->index_text(join("\n", @orig));
- @orig = ();
- $tg->increase_termpos;
+sub index_users ($$) {
+ my ($self, $smsg) = @_;
+
+ my $from = $smsg->from;
+ my $to = $smsg->to;
+ my $cc = $smsg->cc;
+
+ index_text($self, $from, 1, 'A'); # A - author
+ index_text($self, $to, 1, 'XTO') if $to ne '';
+ index_text($self, $cc, 1, 'XCC') if $cc ne '';
+}
+
+sub index_diff_inc ($$$$) {
+ my ($self, $text, $pfx, $xnq) = @_;
+ if (@$xnq) {
+ index_text($self, join("\n", @$xnq), 1, 'XNQ');
+ @$xnq = ();
+ }
+ index_text($self, $text, 1, $pfx);
+}
+
+sub index_old_diff_fn {
+ my ($self, $seen, $fa, $fb, $xnq) = @_;
+
+ # no renames or space support for traditional diffs,
+ # find the number of leading common paths to strip:
+ my @fa = split('/', $fa);
+ my @fb = split('/', $fb);
+ while (scalar(@fa) && scalar(@fb)) {
+ $fa = join('/', @fa);
+ $fb = join('/', @fb);
+ if ($fa eq $fb) {
+ unless ($seen->{$fa}++) {
+ index_diff_inc($self, $fa, 'XDFN', $xnq);
}
- });
+ return 1;
+ }
+ shift @fa;
+ shift @fb;
+ }
+ 0;
+}
- if ($was_ghost) {
- $doc_id = $smsg->doc_id;
- $self->link_message($smsg, 0);
- $doc->set_data($smsg->to_doc_data);
- $db->replace_document($doc_id, $doc);
+sub index_diff ($$$) {
+ my ($self, $txt, $doc) = @_;
+ my %seen;
+ my $in_diff;
+ my @xnq;
+ my $xnq = \@xnq;
+ foreach (split(/\n/, $txt)) {
+ if ($in_diff && s/^ //) { # diff context
+ index_diff_inc($self, $_, 'XDFCTX', $xnq);
+ } elsif (/^-- $/) { # email signature begins
+ $in_diff = undef;
+ } elsif (m!^diff --git "?[^/]+/.+ "?[^/]+/.+\z!) {
+ # wait until "---" and "+++" to capture filenames
+ $in_diff = 1;
+ # traditional diff:
+ } elsif (m/^diff -(.+) (\S+) (\S+)$/) {
+ my ($opt, $fa, $fb) = ($1, $2, $3);
+ push @xnq, $_;
+ # only support unified:
+ next unless $opt =~ /[uU]/;
+ $in_diff = index_old_diff_fn($self, \%seen, $fa, $fb,
+ $xnq);
+ } elsif (m!^--- ("?[^/]+/.+)!) {
+ my $fn = $1;
+ $fn = (split('/', git_unquote($fn), 2))[1];
+ $seen{$fn}++ or index_diff_inc($self, $fn, 'XDFN', $xnq);
+ $in_diff = 1;
+ } elsif (m!^\+\+\+ ("?[^/]+/.+)!) {
+ my $fn = $1;
+ $fn = (split('/', git_unquote($fn), 2))[1];
+ $seen{$fn}++ or index_diff_inc($self, $fn, 'XDFN', $xnq);
+ $in_diff = 1;
+ } elsif (/^--- (\S+)/) {
+ $in_diff = $1;
+ push @xnq, $_;
+ } elsif (defined $in_diff && /^\+\+\+ (\S+)/) {
+ $in_diff = index_old_diff_fn($self, \%seen, $in_diff,
+ $1, $xnq);
+ } elsif ($in_diff && s/^\+//) { # diff added
+ index_diff_inc($self, $_, 'XDFB', $xnq);
+ } elsif ($in_diff && s/^-//) { # diff removed
+ index_diff_inc($self, $_, 'XDFA', $xnq);
+ } elsif (m!^index ([a-f0-9]+)\.\.([a-f0-9]+)!) {
+ my ($ba, $bb) = ($1, $2);
+ index_git_blob_id($doc, 'XDFPRE', $ba);
+ index_git_blob_id($doc, 'XDFPOST', $bb);
+ $in_diff = 1;
+ } elsif (/^@@ (?:\S+) (?:\S+) @@\s*$/) {
+ # traditional diff w/o -p
+ } elsif (/^@@ (?:\S+) (?:\S+) @@\s*(\S+.*)$/) {
+ # hunk header context
+ index_diff_inc($self, $1, 'XDFHH', $xnq);
+ # ignore the following lines:
+ } elsif (/^(?:dis)similarity index/ ||
+ /^(?:old|new) mode/ ||
+ /^(?:deleted|new) file mode/ ||
+ /^(?:copy|rename) (?:from|to) / ||
+ /^(?:dis)?similarity index / ||
+ /^\\ No newline at end of file/ ||
+ /^Binary files .* differ/) {
+ push @xnq, $_;
+ } elsif ($_ eq '') {
+ # possible to be in diff context, some mail may be
+ # stripped by MUA or even GNU diff(1). "git apply"
+ # treats a bare "\n" as diff context, too
} else {
- $self->link_message($smsg, 0);
- $doc->set_data($smsg->to_doc_data);
- $doc_id = $db->add_document($doc);
+ push @xnq, $_;
+ warn "non-diff line: $_\n" if DEBUG && $_ ne '';
+ $in_diff = undef;
}
- };
+ }
- if ($@) {
- warn "failed to index message <$mid_orig>: $@\n";
- return undef;
+ index_text($self, join("\n", @xnq), 1, 'XNQ');
+}
+
+sub index_body ($$$) {
+ my ($self, $txt, $doc) = @_;
+ if ($doc) {
+ # does it look like a diff?
+ if ($txt =~ /^(?:diff|---|\+\+\+) /ms) {
+ index_diff($self, $txt, $doc);
+ } else {
+ index_text($self, $txt, 1, 'XNQ');
+ }
+ } else {
+ index_text($self, $txt, 0, 'XQUOT');
}
- $doc_id;
}
-# returns deleted doc_id on success, undef on missing
-sub remove_message {
- my ($self, $mid_orig) = @_;
- my $db = $self->{xdb};
- my $doc_id;
- $mid_orig = mid_clean($mid_orig);
- my $mid = mid_compress($mid_orig);
+sub index_xapian { # msg_iter callback
+ my ($part, $depth, @idx) = @{$_[0]};
+ my ($self, $doc) = @{$_[1]};
+ my $ct = $part->content_type || 'text/plain';
+ my $fn = $part->filename;
+ if (defined $fn && $fn ne '') {
+ index_text($self, $fn, 1, 'XFN');
+ }
+
+ my ($s, undef) = msg_part_text($part, $ct);
+ defined $s or return;
+
+ # split off quoted and unquoted blocks:
+ my @sections = split(/((?:^>[^\n]*\n)+)/sm, $s);
+ $part = $s = undef;
+ index_body($self, $_, /\A>/ ? 0 : $doc) for @sections;
+}
+
+sub add_xapian ($$$$) {
+ my ($self, $mime, $smsg, $mids) = @_;
+ $smsg->{mime} = $mime; # XXX dangerous
+ my $hdr = $mime->header_obj;
+ my $doc = $X->{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 = term_generator($self);
+
+ $tg->set_document($doc);
+ index_text($self, $subj, 1, 'S') if $subj;
+ index_users($self, $smsg);
+
+ msg_iter($mime, \&index_xapian, [ $self, $doc ]);
+ foreach my $mid (@$mids) {
+ index_text($self, $mid, 1, 'XM');
+
+ # because too many Message-IDs are prefixed with
+ # "Pine.LNX."...
+ if ($mid =~ /\w{12,}/) {
+ my @long = ($mid =~ /(\w{3,}+)/g);
+ index_text($self, join(' ', @long), 1, 'XM');
+ }
+ }
+ $smsg->{to} = $smsg->{cc} = ''; # WWW doesn't need these, only NNTP
+ PublicInbox::OverIdx::parse_references($smsg, $hdr, $mids);
+ my $data = $smsg->to_doc_data;
+ $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($smsg->{num}, $doc);
+}
+
+sub _msgmap_init ($) {
+ my ($self) = @_;
+ die "BUG: _msgmap_init is only for v1\n" if $self->{ibx_ver} != 1;
+ $self->{mm} //= eval {
+ require PublicInbox::Msgmap;
+ PublicInbox::Msgmap->new($self->{inboxdir}, 1);
+ };
+}
+
+sub add_message {
+ # mime = Email::MIME object
+ my ($self, $mime, $smsg) = @_;
+ my $hdr = $mime->header_obj;
+ my $mids = mids_for_index($hdr);
+ $smsg //= bless { blob => '' }, 'PublicInbox::Smsg'; # test-only compat
+ $smsg->{mid} //= $mids->[0]; # v1 compatibility
+ $smsg->{num} //= do { # v1
+ _msgmap_init($self);
+ index_mm($self, $mime);
+ };
+
+ # v1 and tests only:
+ $smsg->{ds} //= msg_datestamp($hdr, $self->{autime});
+ $smsg->{ts} //= msg_timestamp($hdr, $self->{cotime});
eval {
- $doc_id = $self->find_unique_doc_id('mid', $mid);
- $db->delete_document($doc_id) if defined $doc_id;
+ # order matters, overview stores every possible piece of
+ # data in doc_data (deflated). Xapian only stores a subset
+ # of the fields which exist in over.sqlite3. We may stop
+ # storing doc_data in Xapian sometime after we get multi-inbox
+ # search working.
+ if (my $over = $self->{over}) { # v1 only
+ $over->add_overview($mime, $smsg);
+ }
+ if (need_xapian($self)) {
+ add_xapian($self, $mime, $smsg, $mids);
+ }
};
if ($@) {
- warn "failed to remove message <$mid_orig>: $@\n";
+ warn "failed to index message <".join('> <',@$mids).">: $@\n";
return undef;
}
- $doc_id;
+ $smsg->{num};
}
-sub term_generator { # write-only
- my ($self) = @_;
+# returns begin and end PostingIterator
+sub find_doc_ids {
+ my ($self, $termval) = @_;
+ my $db = $self->{xdb};
- my $tg = $self->{term_generator};
- return $tg if $tg;
+ ($db->postlist_begin($termval), $db->postlist_end($termval));
+}
- $tg = Search::Xapian::TermGenerator->new;
- $tg->set_stemmer($self->stemmer);
+# v1 only
+sub batch_do {
+ my ($self, $termval, $cb) = @_;
+ my $batch_size = 1000; # don't let @ids grow too large to avoid OOM
+ while (1) {
+ my ($head, $tail) = $self->find_doc_ids($termval);
+ return if $head == $tail;
+ my @ids;
+ for (; $head != $tail && @ids < $batch_size; $head++) {
+ push @ids, $head->get_docid;
+ }
+ $cb->(\@ids);
+ }
+}
- $self->{term_generator} = $tg;
+# v1 only, where $mid is unique
+sub remove_message {
+ my ($self, $mid) = @_;
+ $mid = mid_clean($mid);
+
+ 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 unless need_xapian($self);
+ my $db = $self->{xdb};
+ my $nr = 0;
+ eval {
+ batch_do($self, 'Q' . $mid, sub {
+ my ($ids) = @_;
+ $db->delete_document($_) for @$ids;
+ $nr += scalar @$ids;
+ });
+ };
+ if ($@) {
+ warn "failed to remove <$mid> from Xapian: $@\n";
+ } elsif ($nr == 0) {
+ warn "<$mid> missing for removal from Xapian\n";
+ }
}
-sub next_doc_id { $_[0]->{xdb}->get_lastdocid + 1 }
+# MID is a hint in V2
+sub remove_by_oid {
+ my ($self, $oid, $mid) = @_;
-# increments last_thread_id counter
-# returns a 64-bit integer represented as a hex string
-sub next_thread_id {
- my ($self) = @_;
+ $self->{over}->remove_oid($oid, $mid) if $self->{over};
+
+ return unless need_xapian($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);
+ # 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.
+ my ($head, $tail) = $self->find_doc_ids('Q' . $mid);
+ return if $head == $tail;
- $last_thread_id;
+ # there is only ONE element in @delete unless we
+ # have bugs in our v2writable deduplication check
+ my @delete;
+ for (; $head != $tail; $head++) {
+ my $docid = $head->get_docid;
+ my $doc = $db->get_document($docid);
+ my $smsg = PublicInbox::Smsg->wrap($mid);
+ $smsg->load_expand($doc);
+ if ($smsg->{blob} eq $oid) {
+ push(@delete, $docid);
+ }
+ }
+ $db->delete_document($_) foreach @delete;
+ scalar(@delete);
}
-sub link_message {
- my ($self, $smsg, $is_ghost) = @_;
+sub index_git_blob_id {
+ my ($doc, $pfx, $objid) = @_;
- if ($is_ghost) {
- $smsg->ensure_metadata;
- } else {
- $self->link_message_to_parents($smsg);
+ my $len = length($objid);
+ for (my $len = length($objid); $len >= 7; ) {
+ $doc->add_term($pfx.$objid);
+ $objid = substr($objid, 0, --$len);
}
}
-sub link_message_to_parents {
- my ($self, $smsg) = @_;
- my $doc = $smsg->{doc};
- my $mid = mid_compress($smsg->mid);
- my $mime = $smsg->mime;
- my $refs = $mime->header('References');
- my @refs = $refs ? ($refs =~ /<([^>]+)>/g) : ();
- my $irt = $mime->header('In-Reply-To');
- if ($irt) {
- $irt = mid_compress(mid_clean($irt));
-
- # maybe some crazies will try to make a circular reference:
- if ($irt eq $mid) {
- $irt = undef;
- } else {
- # last References should be $irt
- # we will de-dupe later
- push @refs, $irt;
- }
- }
-
- my $tid;
- if (@refs) {
- my @crefs = map { mid_compress($_) } @refs;
- my %uniq = ($mid => 1);
+sub unindex_blob {
+ my ($self, $mime) = @_;
+ my $mid = eval { mid_mime($mime) };
+ $self->remove_message($mid) if defined $mid;
+}
- # prevent circular references via References: here:
- @refs = ();
- foreach my $ref (@crefs) {
- next if $uniq{$ref};
- $uniq{$ref} = 1;
- push @refs, $ref;
- }
- }
- if (@refs) {
- $doc->add_term(xpfx('inreplyto') . $irt) if defined $irt;
- $smsg->{references_sorted} = '<'.join('><', @refs).'>';
+sub index_mm {
+ my ($self, $mime) = @_;
+ my $mid = mid_mime($mime);
+ my $mm = $self->{mm};
+ my $num;
- my $ref_pfx = xpfx('references');
+ if (defined $self->{regen_down}) {
+ $num = $mm->num_for($mid) and return $num;
- # first ref *should* be the thread root,
- # but we can never trust clients to do the right thing
- my $ref = shift @refs;
- $doc->add_term($ref_pfx . $ref);
- $tid = $self->_resolve_mid_to_tid($ref);
+ 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;
- # the rest of the refs should point to this tid:
- foreach $ref (@refs) {
- $doc->add_term($ref_pfx . $ref);
- my $ptid = $self->_resolve_mid_to_tid($ref);
- if ($tid ne $ptid) {
- $self->merge_threads($tid, $ptid);
+ # 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;
}
}
- } else {
- $tid = $self->next_thread_id;
}
- $doc->add_term(xpfx('thread') . $tid);
+
+ $num = $mm->mid_insert($mid) and return $num;
+
+ # fallback to num_for since filters like RubyLang set the number
+ $mm->num_for($mid);
}
-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 $@;
+sub unindex_mm {
+ my ($self, $mime) = @_;
+ $self->{mm}->mid_delete(mid_mime($mime));
}
-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 $@;
+sub index_both {
+ my ($self, $mime, $smsg) = @_;
+ my $num = index_mm($self, $mime);
+ $smsg->{num} = $num;
+ add_message($self, $mime, $smsg);
+}
+
+sub unindex_both {
+ my ($self, $mime) = @_;
+ unindex_blob($self, $mime);
+ unindex_mm($self, $mime);
}
sub do_cat_mail {
- my ($git, $blob) = @_;
+ my ($git, $blob, $sizeref) = @_;
my $mime = eval {
- my $str = $git->cat_file($blob);
- Email::MIME->new($str);
+ my $str = $git->cat_file($blob, $sizeref);
+ # fixup bugs from import:
+ $$str =~ s/\A[\r\n]*From [^\r\n]*\r?\n//s;
+ PublicInbox::MIME->new($str);
};
$@ ? undef : $mime;
}
+# called by public-inbox-index
sub index_sync {
- my ($self, $head) = @_;
- $self->with_umask(sub { $self->_index_sync($head) });
+ my ($self, $opts) = @_;
+ delete $self->{lock_path} if $opts->{-skip_lock};
+ $self->{-inbox}->with_umask(sub { $self->_index_sync($opts) })
}
-# indexes all unindexed messages
-sub _index_sync {
- my ($self, $head) = @_;
- require PublicInbox::GitCatFile;
- my $db = $self->{xdb};
+sub batch_adjust ($$$$$) {
+ my ($max, $bytes, $batch_cb, $latest, $nr) = @_;
+ $$max -= $bytes;
+ if ($$max <= 0) {
+ $$max = BATCH_BYTES;
+ $batch_cb->($nr, $latest);
+ }
+}
+
+# only for v1
+sub read_log {
+ my ($self, $log, $add_cb, $del_cb, $batch_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}$!;
- $head ||= 'HEAD';
-
- $db->begin_transaction;
- eval {
- my $git = PublicInbox::GitCatFile->new($self->{git_dir});
-
- my $latest = $db->get_metadata('last_commit');
- my $range = length $latest ? "$latest..$head" : $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 $git = $self->{git};
+ my $latest;
+ my $bytes;
+ my $max = BATCH_BYTES;
+ local $/ = "\n";
+ my %D;
+ my $line;
+ my $newest;
+ my $nr = 0;
+ while (defined($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;
+ my $smsg = bless {}, 'PublicInbox::Smsg';
+ batch_adjust(\$max, $bytes, $batch_cb, $latest, ++$nr);
+ $smsg->{blob} = $blob;
+ $smsg->{bytes} = $bytes;
+ $add_cb->($self, $mime, $smsg);
+ } elsif ($line =~ /$delmsg/o) {
+ my $blob = $1;
+ $D{$blob} = 1;
+ } elsif ($line =~ /^commit ($h40)/o) {
+ $latest = $1;
+ $newest ||= $latest;
+ } elsif ($line =~ /^author .*? ([0-9]+) [\-\+][0-9]+$/) {
+ $self->{autime} = $1;
+ } elsif ($line =~ /^committer .*? ([0-9]+) [\-\+][0-9]+$/) {
+ $self->{cotime} = $1;
+ }
+ }
+ close($log) or die "git log failed: \$?=$?";
+ # get the leftovers
+ foreach my $blob (keys %D) {
+ my $mime = do_cat_mail($git, $blob, \$bytes) or next;
+ $del_cb->($self, $mime);
+ }
+ $batch_cb->($nr, $latest, $newest);
+}
+
+sub _git_log {
+ my ($self, $opts, $range) = @_;
+ 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;
+ my $pr = $opts->{-progress};
+ $pr->("counting changes\n\t$range ... ") if $pr;
+ # 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>;
+ close $fh or die "git log failed: \$?=$?";
+ my $high = $self->{mm}->num_highwater;
+ $pr->("$fcount\n") if $pr; # continue previous line
+ $self->{ntodo} = $fcount;
+
+ if (index($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;
}
- close $log;
- $db->set_metadata('last_commit', $latest) if defined $latest;
- };
- if ($@) {
- warn "indexing failed: $@\n";
- $db->cancel_transaction;
} else {
- $db->commit_transaction;
+ # Give oldest messages the smallest numbers
+ $self->{regen_down} = $high + $fcount;
}
+
+ $git->popen(qw/log --pretty=raw --no-notes --no-color --no-renames
+ --raw -r --no-abbrev/, $range);
}
-# this will create a ghost as necessary
-sub _resolve_mid_to_tid {
- my ($self, $mid) = @_;
+# --is-ancestor requires git 1.8.0+
+sub is_ancestor ($$$) {
+ my ($git, $cur, $tip) = @_;
+ return 0 unless $git->check($cur);
+ my $cmd = [ 'git', "--git-dir=$git->{git_dir}",
+ qw(merge-base --is-ancestor), $cur, $tip ];
+ my $pid = spawn($cmd);
+ waitpid($pid, 0) == $pid or die join(' ', @$cmd) .' did not finish';
+ $? == 0;
+}
- my $smsg = $self->lookup_message($mid) || $self->create_ghost($mid);
- $smsg->thread_id;
+sub need_update ($$$) {
+ 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 '' || $n > 0);
}
-sub create_ghost {
- my ($self, $mid, $tid) = @_;
+# The last git commit we indexed with Xapian or SQLite (msgmap)
+# This needs to account for cases where Xapian or SQLite is
+# out-of-date with respect to the other.
+sub _last_x_commit {
+ my ($self, $mm) = @_;
+ my $lm = $mm->last_commit || '';
+ my $lx = '';
+ if (need_xapian($self)) {
+ $lx = $self->{xdb}->get_metadata('last_commit') || '';
+ } else {
+ $lx = $lm;
+ }
+ # Use last_commit from msgmap if it is older or unset
+ if (!$lm || ($lx && $lm && is_ancestor($self->{git}, $lm, $lx))) {
+ $lx = $lm;
+ }
+ $lx;
+}
- $mid = mid_compress($mid);
- $tid = $self->next_thread_id unless defined $tid;
+sub reindex_from ($$) {
+ my ($reindex, $last_commit) = @_;
+ return $last_commit unless $reindex;
+ ref($reindex) eq 'HASH' ? $reindex->{from} : '';
+}
- my $doc = Search::Xapian::Document->new;
- $doc->add_term(xpfx('mid') . $mid);
- $doc->add_term(xpfx('thread') . $tid);
- $doc->add_term(xpfx('type') . 'ghost');
+# indexes all unindexed messages (v1 only)
+sub _index_sync {
+ my ($self, $opts) = @_;
+ my $tip = $opts->{ref} || 'HEAD';
+ my ($last_commit, $lx, $xlog);
+ my $git = $self->{git};
+ $git->batch_prepare;
+ my $pr = $opts->{-progress};
+
+ my $xdb = $self->begin_txn_lazy;
+ my $mm = _msgmap_init($self);
+ do {
+ if ($xlog) {
+ close($xlog) or die "git log failed: \$?=$?";
+ $xlog = undef;
+ }
+ $last_commit = _last_x_commit($self, $mm);
+ $lx = reindex_from($opts->{reindex}, $last_commit);
+
+ $self->{over}->rollback_lazy;
+ $self->{over}->disconnect;
+ $git->cleanup;
+ delete $self->{txn};
+ $xdb->cancel_transaction if $xdb;
+ $xdb = _xdb_release($self);
+
+ # ensure we leak no FDs to "git log" with Xapian <= 1.2
+ my $range = $lx eq '' ? $tip : "$lx..$tip";
+ $xlog = _git_log($self, $opts, $range);
+
+ $xdb = $self->begin_txn_lazy;
+ } while (_last_x_commit($self, $mm) ne $last_commit);
+
+ my $dbh = $mm->{dbh} if $mm;
+ my $cb = sub {
+ my ($nr, $commit, $newest) = @_;
+ if ($dbh) {
+ if ($newest) {
+ my $cur = $mm->last_commit || '';
+ if (need_update($self, $cur, $newest)) {
+ $mm->last_commit($newest);
+ }
+ }
+ $dbh->commit;
+ }
+ if ($newest && need_xapian($self)) {
+ my $cur = $xdb->get_metadata('last_commit');
+ if (need_update($self, $cur, $newest)) {
+ $xdb->set_metadata('last_commit', $newest);
+ }
+ }
+ $self->commit_txn_lazy;
+ $git->cleanup;
+ $xdb = _xdb_release($self);
+ # let another process do some work... <
+ $pr->("indexed $nr/$self->{ntodo}\n") if $pr && $nr;
+ if (!$newest) {
+ $xdb = $self->begin_txn_lazy;
+ $dbh->begin_work if $dbh;
+ }
+ };
- my $smsg = PublicInbox::SearchMsg->wrap($doc, $mid);
- $self->link_message($smsg, 1);
- $self->{xdb}->add_document($doc);
+ $dbh->begin_work;
+ read_log($self, $xlog, *index_both, *unindex_both, $cb);
+}
- $smsg;
+sub DESTROY {
+ # order matters for unlocking
+ $_[0]->{xdb} = undef;
+ $_[0]->{lockfh} = undef;
}
-sub merge_threads {
- my ($self, $winner_tid, $loser_tid) = @_;
- my ($head, $tail) = $self->find_doc_ids('thread', $loser_tid);
- my $thread_pfx = xpfx('thread');
- my $db = $self->{xdb};
+# 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;
+ }
+}
- for (; $head != $tail; $head->inc) {
- my $docid = $head->get_docid;
- my $doc = $db->get_document($docid);
- $doc->remove_term($thread_pfx . $loser_tid);
- $doc->add_term($thread_pfx . $winner_tid);
- $db->replace_document($docid, $doc);
+sub remote_close {
+ my ($self) = @_;
+ if (my $w = delete $self->{w}) {
+ my $pid = delete $self->{pid} or die "no process to wait on\n";
+ print $w "close\n" or die "failed to write to pid:$pid: $!\n";
+ close $w or die "failed to close pipe for pid:$pid: $!\n";
+ waitpid($pid, 0) == $pid or die "remote process did not finish";
+ $? == 0 or die ref($self)." pid:$pid exited with: $?";
+ } else {
+ die "transaction in progress $self\n" if $self->{txn};
+ $self->_xdb_release if $self->{xdb};
+ }
+}
+
+sub remote_remove {
+ my ($self, $oid, $mid) = @_;
+ if (my $w = $self->{w}) {
+ # triggers remove_by_oid in a shard
+ print $w "D $oid $mid\n" or die "failed to write remove $!";
+ } else {
+ $self->begin_txn_lazy;
+ $self->remove_by_oid($oid, $mid);
}
}
-sub _read_git_config_perm {
+sub begin_txn_lazy {
+ my ($self) = @_;
+ return if $self->{txn};
+
+ $self->{-inbox}->with_umask(sub {
+ my $xdb = $self->{xdb} || $self->_xdb_acquire;
+ $self->{over}->begin_lazy if $self->{over};
+ $xdb->begin_transaction if $xdb;
+ $self->{txn} = 1;
+ $xdb;
+ });
+}
+
+# store 'indexlevel=medium' in v2 shard=0 and v1 (only one shard)
+# This metadata is read by Admin::detect_indexlevel:
+sub set_indexlevel {
my ($self) = @_;
- my @cmd = ('git', "--git-dir=$self->{git_dir}",
- qw(config core.sharedRepository));
- my $pid = open(my $fh, '-|', @cmd) or
- die('open `'.join(' ', @cmd) . " pipe failed: $!\n");
- my $perm = <$fh>;
- close $fh;
- chomp $perm if defined $perm;
- $perm;
-}
-
-sub _git_config_perm {
- my $self = shift;
- my $perm = scalar @_ ? $_[0] : _read_git_config_perm($self);
- return PERM_GROUP if (!defined($perm) || !length($perm));
- return PERM_UMASK if ($perm eq 'umask');
- return PERM_GROUP if ($perm eq 'group');
- if ($perm =~ /\A(?:all|world|everybody)\z/) {
- return PERM_EVERYBODY;
- }
- return PERM_GROUP if ($perm =~ /\A(?:true|yes|on|1)\z/);
- return PERM_UMASK if ($perm =~ /\A(?:false|no|off|0)\z/);
-
- my $i = oct($perm);
- return PERM_UMASK if ($i == PERM_UMASK);
- return PERM_GROUP if ($i == OLD_PERM_GROUP);
- return PERM_EVERYBODY if ($i == OLD_PERM_EVERYBODY);
-
- if (($i & 0600) != 0600) {
- die "core.sharedRepository mode invalid: ".
- sprintf('%.3o', $i) . "\nOwner must have permissions\n";
- }
- ($i & 0666);
-}
-
-sub _umask_for {
- my ($perm) = @_; # _git_config_perm return value
- my $rv = $perm;
- return umask if $rv == 0;
-
- # set +x bit if +r or +w were set
- $rv |= 0100 if ($rv & 0600);
- $rv |= 0010 if ($rv & 0060);
- $rv |= 0001 if ($rv & 0006);
- (~$rv & 0777);
-}
-
-sub with_umask {
- my ($self, $cb) = @_;
- my $old = umask $self->{umask};
- my $rv = eval { $cb->() };
- my $err = $@;
- umask $old;
- die $err if $@;
- $rv;
+
+ if (!$self->{shard} && # undef or 0, not >0
+ delete($self->{-set_indexlevel_once})) {
+ my $xdb = $self->{xdb};
+ my $level = $xdb->get_metadata('indexlevel');
+ if (!$level || $level ne 'medium') {
+ $xdb->set_metadata('indexlevel', 'medium');
+ }
+ }
+}
+
+sub commit_txn_lazy {
+ my ($self) = @_;
+ delete $self->{txn} or return;
+ $self->{-inbox}->with_umask(sub {
+ if (my $xdb = $self->{xdb}) {
+ set_indexlevel($self);
+ $xdb->commit_transaction;
+ }
+ $self->{over}->commit_lazy if $self->{over};
+ });
+}
+
+sub worker_done {
+ my ($self) = @_;
+ if (need_xapian($self)) {
+ die "$$ $0 xdb not released\n" if $self->{xdb};
+ }
+ die "$$ $0 still in transaction\n" if $self->{txn};
}
1;