-# Copyright (C) 2015 all contributors <meta@public-inbox.org>
-# License: AGPLv3 or later (https://www.gnu.org/licenses/agpl-3.0.txt)
+# Copyright (C) 2015-2018 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
use warnings;
use Fcntl qw(:flock :DEFAULT);
use PublicInbox::MIME;
-use Email::MIME::ContentType;
-$Email::MIME::ContentType::STRICT_PARAMS = 0;
use base qw(PublicInbox::Search);
-use PublicInbox::MID qw/mid_clean id_compress mid_mime/;
+use PublicInbox::MID qw/mid_clean id_compress mid_mime mids references/;
use PublicInbox::MsgIter;
use Carp qw(croak);
use POSIX qw(strftime);
}
sub new {
- my ($class, $inbox, $creat) = @_;
- my $git_dir = $inbox;
- my $altid;
- if (ref $inbox) {
- $git_dir = $inbox->{mainrepo};
- $altid = $inbox->{altid};
+ my ($class, $ibx, $creat, $part) = @_;
+ my $mainrepo = $ibx; # for "public-inbox-index" w/o entry in config
+ my $git_dir = $mainrepo;
+ my ($altid, $git);
+ my $version = 1;
+ if (ref $ibx) {
+ $mainrepo = $ibx->{mainrepo};
+ $altid = $ibx->{altid};
+ $version = $ibx->{version} || 1;
if ($altid) {
require PublicInbox::AltId;
$altid = [ map {
- PublicInbox::AltId->new($inbox, $_);
+ PublicInbox::AltId->new($ibx, $_);
} @$altid ];
}
+ $git = $ibx->git;
+ } else {
+ $git = PublicInbox::Git->new($git_dir); # v1 only
}
require Search::Xapian::WritableDatabase;
- my $self = bless { git_dir => $git_dir, -altid => $altid }, $class;
+ my $self = bless {
+ mainrepo => $mainrepo,
+ git => $git,
+ -altid => $altid,
+ version => $version,
+ }, $class;
my $perm = $self->_git_config_perm;
my $umask = _umask_for($perm);
$self->{umask} = $umask;
- $self->{lock_path} = "$git_dir/ssoma.lock";
- $self->{git} = PublicInbox::Git->new($git_dir);
+ if ($version == 1) {
+ $self->{lock_path} = "$mainrepo/ssoma.lock";
+ } elsif ($version == 2) {
+ defined $part or die "partition is required for v2\n";
+ # partition is a number or "all"
+ $self->{partition} = $part;
+ $self->{lock_path} = undef;
+ $self->{msgmap_path} = "$mainrepo/msgmap.sqlite3";
+ } else {
+ die "unsupported inbox version=$version\n";
+ }
$self->{creat} = ($creat || 0) == 1;
$self;
}
sub _xdb_acquire {
my ($self) = @_;
croak 'already acquired' if $self->{xdb};
- my $dir = PublicInbox::Search->xdir($self->{git_dir});
+ my $dir = $self->xdir;
my $flag = Search::Xapian::DB_OPEN;
if ($self->{creat}) {
require File::Path;
sub _lock_acquire {
my ($self) = @_;
croak 'already locked' if $self->{lockfh};
- sysopen(my $lockfh, $self->{lock_path}, O_WRONLY|O_CREAT) or
- die "failed to open lock $self->{lock_path}: $!\n";
+ my $lock_path = $self->{lock_path} or return;
+ sysopen(my $lockfh, $lock_path, O_WRONLY|O_CREAT) or
+ die "failed to open lock $lock_path: $!\n";
flock($lockfh, LOCK_EX) or die "lock failed: $!\n";
$self->{lockfh} = $lockfh;
}
sub _lock_release {
my ($self) = @_;
+ return unless $self->{lock_path};
my $lockfh = delete $self->{lockfh} or croak 'not locked';
flock($lockfh, LOCK_UN) or die "unlock failed: $!\n";
close $lockfh or die "close failed: $!\n";
$doc->add_value($col, $num);
}
-sub add_values ($$$) {
- my ($smsg, $bytes, $num) = @_;
+sub add_values ($$) {
+ my ($doc, $values) = @_;
- my $ts = $smsg->ts;
- my $doc = $smsg->{doc};
- add_val($doc, &PublicInbox::Search::TS, $ts);
+ my $ts = $values->[PublicInbox::Search::TS];
+ add_val($doc, PublicInbox::Search::TS, $ts);
- defined($num) and add_val($doc, &PublicInbox::Search::NUM, $num);
+ my $num = $values->[PublicInbox::Search::NUM];
+ defined($num) and add_val($doc, PublicInbox::Search::NUM, $num);
- defined($bytes) and add_val($doc, &PublicInbox::Search::BYTES, $bytes);
+ my $bytes = $values->[PublicInbox::Search::BYTES];
+ defined($bytes) and add_val($doc, PublicInbox::Search::BYTES, $bytes);
- add_val($doc, &PublicInbox::Search::LINES,
- $smsg->{mime}->body_raw =~ tr!\n!\n!);
+ my $lines = $values->[PublicInbox::Search::LINES];
+ add_val($doc, PublicInbox::Search::LINES, $lines);
my $yyyymmdd = strftime('%Y%m%d', gmtime($ts));
add_val($doc, PublicInbox::Search::YYYYMMDD, $yyyymmdd);
my $db = $self->{xdb};
my ($doc_id, $old_tid);
- my $mid = mid_clean(mid_mime($mime));
+ my @mids = mid_mime($mime);
+ if (@mids > 1) {
+ warn "Multi-MID: ( ",join(' | ', @mids)," )\n";
+ }
+ my $mid = mid_clean($mids[0]);
+ my $skel = $self->{skeleton};
eval {
die 'Message-ID too long' if length($mid) > MAX_MID_SIZE;
# convert a ghost to a regular message
# it will also clobber any existing regular message
$doc_id = $smsg->{doc_id};
- $old_tid = $smsg->thread_id;
+ $old_tid = $smsg->thread_id unless $skel;
}
$smsg = PublicInbox::SearchMsg->new($mime);
my $doc = $smsg->{doc};
- $doc->add_term('Q' . $mid);
+ $doc->add_term('XMID' . $mid);
my $subj = $smsg->subject;
+ my $xpath;
if ($subj ne '') {
- my $path = $self->subject_path($subj);
- $doc->add_term('XPATH' . id_compress($path));
+ $xpath = $self->subject_path($subj);
+ $xpath = id_compress($xpath);
+ $doc->add_term('XPATH' . $xpath);
}
- add_values($smsg, $bytes, $num);
+ my $lines = $mime->body_raw =~ tr!\n!\n!;
+ my @values = ($smsg->ts, $num, $bytes, $lines);
+ add_values($doc, \@values);
my $tg = $self->term_generator;
index_body($tg, \@orig, $doc) if @orig;
});
- link_message($self, $smsg, $old_tid);
- $tg->index_text($mid, 1, 'XMID');
- $doc->set_data($smsg->to_doc_data($blob));
+ # populates smsg->references for smsg->to_doc_data
+ my $refs = parse_references($smsg);
+ my $data = $smsg->to_doc_data($blob);
+ if ($skel) {
+ push @values, $mid, $xpath, $data;
+ $skel->index_skeleton(\@values);
+ } else {
+ link_message($self, $smsg, $refs, $old_tid);
+ }
+ $tg->index_text($mid, 1, 'XM');
+ $doc->set_data($data);
if (my $altid = $self->{-altid}) {
foreach my $alt (@$altid) {
$mid = mid_clean($mid);
eval {
- $doc_id = $self->find_unique_doc_id('mid', $mid);
- $db->delete_document($doc_id) if defined $doc_id;
+ my ($head, $tail) = $self->find_doc_ids('XMID' . $mid);
+ if ($head->equal($tail)) {
+ warn "cannot remove non-existent <$mid>\n";
+ }
+ for (; $head != $tail; $head->inc) {
+ my $docid = $head->get_docid;
+ $db->delete_document($docid);
+ }
};
if ($@) {
}
# increments last_thread_id counter
-# returns a 64-bit integer represented as a hex string
+# returns a 64-bit integer represented as a decimal string
sub next_thread_id {
my ($self) = @_;
my $db = $self->{xdb};
$last_thread_id;
}
-sub link_message {
- my ($self, $smsg, $old_tid) = @_;
- my $doc = $smsg->{doc};
- my $mid = $smsg->mid;
+sub parse_references ($) {
+ my ($smsg) = @_;
my $mime = $smsg->{mime};
my $hdr = $mime->header_obj;
-
- # last References should be IRT, but some mail clients do things
- # out of order, so trust IRT over References iff IRT exists
- my @refs = ($hdr->header_raw('References'),
- $hdr->header_raw('In-Reply-To'));
- @refs = ((join(' ', @refs)) =~ /<([^>]+)>/g);
-
- my $tid;
- if (@refs) {
- my %uniq = ($mid => 1);
- my @orig_refs = @refs;
- @refs = ();
-
- # prevent circular references via References: here:
- foreach my $ref (@orig_refs) {
- if (length($ref) > MAX_MID_SIZE) {
- warn "References: <$ref> too long, ignoring\n";
- }
- next if $uniq{$ref};
- $uniq{$ref} = 1;
- push @refs, $ref;
+ 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) {
+ # FIXME: this is an archive-prevention vector like X-No-Archive
+ if (length($ref) > MAX_MID_SIZE) {
+ warn "References: <$ref> too long, ignoring\n";
}
+ next if $mids{$ref};
+ push @keep, $ref;
}
+ $smsg->{references} = '<'.join('> <', @keep).'>' if @keep;
+ \@keep;
+}
+
+sub link_message {
+ my ($self, $smsg, $refs, $old_tid) = @_;
+ my $tid;
- if (@refs) {
- $smsg->{references} = '<'.join('> <', @refs).'>';
+ if (@$refs) {
# first ref *should* be the thread root,
# but we can never trust clients to do the right thing
- my $ref = shift @refs;
+ my $ref = shift @$refs;
$tid = $self->_resolve_mid_to_tid($ref);
$self->merge_threads($tid, $old_tid) if defined $old_tid;
# the rest of the refs should point to this tid:
- foreach $ref (@refs) {
+ foreach $ref (@$refs) {
my $ptid = $self->_resolve_mid_to_tid($ref);
merge_threads($self, $tid, $ptid);
}
} else {
$tid = defined $old_tid ? $old_tid : $self->next_thread_id;
}
- $doc->add_term('G' . $tid);
-}
-
-sub index_blob {
- my ($self, $mime, $bytes, $num, $blob) = @_;
- $self->add_message($mime, $bytes, $num, $blob);
+ $smsg->{doc}->add_term('G' . $tid);
}
sub index_git_blob_id {
sub index_mm {
my ($self, $mime) = @_;
- $self->{mm}->mid_insert(mid_clean(mid_mime($mime)));
+ my $mid = mid_clean(mid_mime($mime));
+ my $mm = $self->{mm};
+ my $num = $mm->mid_insert($mid);
+ return $num if defined $num;
+
+ # fallback to num_for since filters like RubyLang set the number
+ $mm->num_for($mid);
}
sub unindex_mm {
sub index_mm2 {
my ($self, $mime, $bytes, $blob) = @_;
my $num = $self->{mm}->num_for(mid_clean(mid_mime($mime)));
- index_blob($self, $mime, $bytes, $num, $blob);
+ add_message($self, $mime, $bytes, $num, $blob);
}
sub unindex_mm2 {
sub index_both {
my ($self, $mime, $bytes, $blob) = @_;
my $num = index_mm($self, $mime);
- index_blob($self, $mime, $bytes, $num, $blob);
+ add_message($self, $mime, $bytes, $num, $blob);
}
sub unindex_both {
}
}
+# only for v1
sub rlog {
my ($self, $log, $add_cb, $del_cb, $batch_cb) = @_;
my $hex = '[a-f0-9]';
sub _msgmap_init {
my ($self) = @_;
- $self->{mm} = eval {
+ $self->{mm} ||= eval {
require PublicInbox::Msgmap;
- PublicInbox::Msgmap->new($self->{git_dir}, 1);
+ my $msgmap_path = $self->{msgmap_path};
+ if (defined $msgmap_path) { # v2
+ PublicInbox::Msgmap->new_file($msgmap_path, 1);
+ } else {
+ PublicInbox::Msgmap->new($self->{mainrepo}, 1);
+ }
};
}
}
} else {
# user didn't install DBD::SQLite and DBI
- rlog($self, $xlog, *index_blob, *unindex_blob, $cb);
+ rlog($self, $xlog, *add_message, *unindex_blob, $cb);
}
}
my $tid = $self->next_thread_id;
my $doc = Search::Xapian::Document->new;
- $doc->add_term('Q' . $mid);
+ $doc->add_term('XMID' . $mid);
$doc->add_term('G' . $tid);
$doc->add_term('T' . 'ghost');
sub merge_threads {
my ($self, $winner_tid, $loser_tid) = @_;
return if $winner_tid == $loser_tid;
- my ($head, $tail) = $self->find_doc_ids('G' . $loser_tid);
my $db = $self->{xdb};
- for (; $head != $tail; $head->inc) {
- my $docid = $head->get_docid;
- my $doc = $db->get_document($docid);
- $doc->remove_term('G' . $loser_tid);
- $doc->add_term('G' . $winner_tid);
- $db->replace_document($docid, $doc);
+ my $batch_size = 1000; # don't let @ids grow too large to avoid OOM
+ while (1) {
+ my ($head, $tail) = $self->find_doc_ids('G' . $loser_tid);
+ return if $head == $tail;
+ my @ids;
+ for (; $head != $tail && @ids < $batch_size; $head->inc) {
+ push @ids, $head->get_docid;
+ }
+ foreach my $docid (@ids) {
+ my $doc = $db->get_document($docid);
+ $doc->remove_term('G' . $loser_tid);
+ $doc->add_term('G' . $winner_tid);
+ $db->replace_document($docid, $doc);
+ }
}
}
sub _read_git_config_perm {
my ($self) = @_;
- my @cmd = qw(config core.sharedRepository);
- my $fh = PublicInbox::Git->new($self->{git_dir})->popen(@cmd);
+ my @cmd = qw(config);
+ if ($self->{version} == 2) {
+ push @cmd, "--file=$self->{mainrepo}/inbox-config";
+ }
+ my $fh = $self->{git}->popen(@cmd, 'core.sharedRepository');
local $/ = "\n";
my $perm = <$fh>;
chomp $perm if defined $perm;
$_[0]->{lockfh} = undef;
}
+# remote_* subs are only used by SearchIdxPart and SearchIdxSkeleton
+sub remote_commit {
+ my ($self) = @_;
+ print { $self->{w} } "commit\n" or die "failed to write commit: $!";
+}
+
+sub remote_close {
+ my ($self) = @_;
+ my $pid = delete $self->{pid} or die "no process to wait on\n";
+ my $w = delete $self->{w} or die "no pipe to write to\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: $?";
+}
+
1;