use base qw(PublicInbox::Lock);
use 5.010_001;
use PublicInbox::SearchIdxShard;
-use PublicInbox::MIME;
+use PublicInbox::Eml;
use PublicInbox::Git;
use PublicInbox::Import;
use PublicInbox::MID qw(mids references);
-use PublicInbox::ContentId qw(content_id content_digest);
+use PublicInbox::ContentHash qw(content_hash content_digest);
use PublicInbox::Inbox;
use PublicInbox::OverIdx;
use PublicInbox::Msgmap;
use PublicInbox::Spawn qw(spawn popen_rd);
use PublicInbox::SearchIdx;
+use PublicInbox::MultiMidQueue;
use IO::Handle; # ->autoflush
use File::Temp qw(tempfile);
# Also, shard count may change while -watch is running
# due to "xcpdb --reshard"
if (-d $xpfx) {
- require PublicInbox::Search;
- PublicInbox::Search::load_xapian();
- my $XapianDatabase = $PublicInbox::Search::X{Database};
+ my $XapianDatabase;
foreach my $shard (<$xpfx/*>) {
-d $shard && $shard =~ m!/[0-9]+\z! or next;
+ $XapianDatabase //= do {
+ require PublicInbox::Search;
+ PublicInbox::Search::load_xapian();
+ $PublicInbox::Search::X{Database};
+ };
eval {
$XapianDatabase->new($shard)->close;
$n++;
im => undef, # PublicInbox::Import
parallel => 1,
transact_bytes => 0,
+ total_bytes => 0,
current_info => '',
xpfx => $xpfx,
over => PublicInbox::OverIdx->new("$xpfx/over.sqlite3", 1),
last_commit => [], # git repo -> commit
};
$self->{shards} = count_shards($self) || nproc_shards($creat);
+ $self->{index_max_size} = $v2ibx->{index_max_size};
bless $self, $class;
}
# public (for now?)
sub init_inbox {
- my ($self, $shards, $skip_epoch) = @_;
+ my ($self, $shards, $skip_epoch, $skip_artnum) = @_;
if (defined $shards) {
$self->{parallel} = 0 if $shards == 0;
$self->{shards} = $shards if $shards > 0;
}
$self->idx_init;
+ $self->{mm}->skip_artnum($skip_artnum) if defined $skip_artnum;
my $epoch_max = -1;
git_dir_latest($self, \$epoch_max);
if (defined $skip_epoch && $epoch_max == -1) {
}
# indexes a message, returns true if checkpointing is needed
-sub do_idx ($$$$$$$) {
- my ($self, $msgref, $mime, $len, $num, $oid, $mid0) = @_;
- $self->{over}->add_overview($mime, $len, $num, $oid, $mid0, $self);
- my $idx = idx_shard($self, $num % $self->{shards});
- $idx->index_raw($len, $msgref, $num, $oid, $mid0, $mime, $self);
- my $n = $self->{transact_bytes} += $len;
- $n >= (PublicInbox::SearchIdx::BATCH_BYTES * $self->{shards});
+sub do_idx ($$$$) {
+ my ($self, $msgref, $mime, $smsg) = @_;
+ $smsg->{bytes} = $smsg->{raw_bytes} +
+ PublicInbox::SearchIdx::crlf_adjust($$msgref);
+ $self->{over}->add_overview($mime, $smsg);
+ my $idx = idx_shard($self, $smsg->{num} % $self->{shards});
+ $idx->index_raw($msgref, $mime, $smsg);
+ my $n = $self->{transact_bytes} += $smsg->{raw_bytes};
+ $n >= ($PublicInbox::SearchIdx::BATCH_BYTES * $self->{shards});
}
sub _add {
# spam check:
if ($check_cb) {
- $mime = $check_cb->($mime) or return;
+ $mime = $check_cb->($mime, $self->{-inbox}) or return;
}
# All pipes (> $^F) known to Perl 5.6+ have FD_CLOEXEC set,
my ($num, $mid0) = v2_num_for($self, $mime);
defined $num or return; # duplicate
- defined $mid0 or die "BUG: $mid0 undefined\n";
+ defined $mid0 or die "BUG: \$mid0 undefined\n";
my $im = $self->importer;
- my $cmt = $im->add($mime);
+ my $smsg = bless { mid => $mid0, num => $num }, 'PublicInbox::Smsg';
+ my $cmt = $im->add($mime, undef, $smsg); # sets $smsg->{ds|ts|blob}
$cmt = $im->get_mark($cmt);
$self->{last_commit}->[$self->{epoch_max}] = $cmt;
- my ($oid, $len, $msgref) = @{$im->{last_object}};
- if (do_idx($self, $msgref, $mime, $len, $num, $oid, $mid0)) {
+ my $msgref = delete $smsg->{-raw_email};
+ if (do_idx($self, $msgref, $mime, $smsg)) {
$self->checkpoint;
}
$rewrites;
}
-sub content_ids ($) {
+sub content_hashes ($) {
my ($mime) = @_;
- my @cids = ( content_id($mime) );
+ my @chashes = ( content_hash($mime) );
+ # We still support Email::MIME, here, and
# Email::MIME->as_string doesn't always round-trip, so we may
- # use a second content_id
- my $rt = content_id(PublicInbox::MIME->new(\($mime->as_string)));
- push @cids, $rt if $cids[0] ne $rt;
- \@cids;
+ # use a second content_hash
+ my $rt = content_hash(PublicInbox::Eml->new(\($mime->as_string)));
+ push @chashes, $rt if $chashes[0] ne $rt;
+ \@chashes;
}
sub content_matches ($$) {
- my ($cids, $existing) = @_;
- my $cid = content_id($existing);
- foreach (@$cids) {
- return 1 if $_ eq $cid
+ my ($chashes, $existing) = @_;
+ my $chash = content_hash($existing);
+ foreach (@$chashes) {
+ return 1 if $_ eq $chash
}
0
}
$im = $self->importer;
}
my $over = $self->{over};
- my $cids = content_ids($old_mime);
+ my $chashes = content_hashes($old_mime);
my @removed;
my $mids = mids($old_mime->header_obj);
# We avoid introducing new blobs into git since the raw content
# can be slightly different, so we do not need the user-supplied
- # message now that we have the mids and content_id
+ # message now that we have the mids and content_hash
$old_mime = undef;
my $mark;
next; # continue
}
my $orig = $$msg;
- my $cur = PublicInbox::MIME->new($msg);
- if (content_matches($cids, $cur)) {
+ my $cur = PublicInbox::Eml->new($msg);
+ if (content_matches($chashes, $cur)) {
$gone{$smsg->{num}} = [ $smsg, $cur, \$orig ];
}
}
}
# make sure we really got the OID:
- my ($oid, $type, $len) = $self->{-inbox}->git->check($expect_oid);
- $oid eq $expect_oid or die "BUG: $expect_oid not found after replace";
+ my ($blob, $type, $bytes) = $self->{-inbox}->git->check($expect_oid);
+ $blob eq $expect_oid or die "BUG: $expect_oid not found after replace";
# don't leak FDs to Xapian:
$self->{-inbox}->git->cleanup;
# reindex modified messages:
for my $smsg (@$need_reindex) {
- my $num = $smsg->{num};
- my $mid0 = $smsg->{mid};
- do_idx($self, \$raw, $new_mime, $len, $num, $oid, $mid0);
+ my $new_smsg = bless {
+ blob => $blob,
+ raw_bytes => $bytes,
+ num => $smsg->{num},
+ mid => $smsg->{mid},
+ }, 'PublicInbox::Smsg';
+ my $v2w = { autime => $smsg->{ds}, cotime => $smsg->{ts} };
+ $new_smsg->populate($new_mime, $v2w);
+ do_idx($self, \$raw, $new_mime, $new_smsg);
}
$rewritten->{rewrites};
}
my $bnote = $self->{bnote} or return;
my $r = $bnote->[0];
while (scalar keys %$barrier) {
- defined(my $l = $r->getline) or die "EOF on barrier_wait: $!";
+ defined(my $l = readline($r)) or die "EOF on barrier_wait: $!";
$l =~ /\Abarrier (\d+)/ or die "bad line on barrier_wait: $l";
delete $barrier->{$1} or die "bad shard[$1] on barrier wait";
}
$dbh->begin_work;
}
+ $self->{total_bytes} += $self->{transact_bytes};
$self->{transact_bytes} = 0;
}
}
$self->{over}->disconnect;
delete $self->{bnote};
- $self->{transact_bytes} = 0;
- $self->lock_release if $shards;
+ my $nbytes = $self->{total_bytes};
+ $self->{total_bytes} = 0;
+ $self->lock_release(!!$nbytes) if $shards;
$self->{-inbox}->git->cleanup;
}
sub git_init {
my ($self, $epoch) = @_;
my $git_dir = "$self->{-inbox}->{inboxdir}/git/$epoch.git";
- my @cmd = (qw(git init --bare -q), $git_dir);
- PublicInbox::Import::run_die(\@cmd);
- @cmd = (qw/git config/, "--file=$git_dir/config",
+ PublicInbox::Import::init_bare($git_dir);
+ my @cmd = (qw/git config/, "--file=$git_dir/config",
'include.path', '../../all.git/config');
PublicInbox::Import::run_die(\@cmd);
fill_alternates($self, $epoch);
my ($self, $git, $packed_bytes, $tmp) = @_;
my $im = PublicInbox::Import->new($git, undef, undef, $self->{-inbox});
$im->{bytes_added} = int($packed_bytes / $PACKING_FACTOR);
- $im->{want_object_info} = 1;
$im->{lock_path} = undef;
$im->{path_type} = 'v2';
$self->{im} = $im unless $tmp;
sub content_exists ($$$) {
my ($self, $mime, $mid) = @_;
my $over = $self->{over};
- my $cids = content_ids($mime);
+ my $chashes = content_hashes($mime);
my ($id, $prev);
while (my $smsg = $over->next_by_mid($mid, \$id, \$prev)) {
my $msg = get_blob($self, $smsg);
warn "broken smsg for $mid\n";
next;
}
- my $cur = PublicInbox::MIME->new($msg);
- return 1 if content_matches($cids, $cur);
+ my $cur = PublicInbox::Eml->new($msg);
+ return 1 if content_matches($chashes, $cur);
# XXX DEBUG_DIFF is experimental and may be removed
diff($mid, $cur, $mime) if $ENV{DEBUG_DIFF};
sub mark_deleted ($$$$) {
my ($self, $sync, $git, $oid) = @_;
+ return if PublicInbox::SearchIdx::too_big($self, $git, $oid);
my $msgref = $git->cat_file($oid);
- my $mime = PublicInbox::MIME->new($$msgref);
+ my $mime = PublicInbox::Eml->new($$msgref);
my $mids = mids($mime->header_obj);
- my $cid = content_id($mime);
+ my $chash = content_hash($mime);
foreach my $mid (@$mids) {
- $sync->{D}->{"$mid\0$cid"} = $oid;
+ $sync->{D}->{"$mid\0$chash"} = $oid;
}
}
$self->{current_info} = "multi_mid $oid";
my ($num, $mid0, $len);
my $msgref = $git->cat_file($oid, \$len);
- my $mime = PublicInbox::MIME->new($$msgref);
+ my $mime = PublicInbox::Eml->new($$msgref);
my $mids = mids($mime->header_obj);
- my $cid = content_id($mime);
+ my $chash = content_hash($mime);
die "BUG: reindex_oid_m called for <=1 mids" if scalar(@$mids) <= 1;
for my $mid (reverse @$mids) {
- delete($sync->{D}->{"$mid\0$cid"}) and
+ delete($sync->{D}->{"$mid\0$chash"}) and
die "BUG: reindex_oid should handle <$mid> delete";
}
my $over = $self->{over};
}
}
$sync->{nr}++;
- if (do_idx($self, $msgref, $mime, $len, $num, $oid, $mid0)) {
+ my $smsg = bless {
+ raw_bytes => $len,
+ num => $num,
+ blob => $oid,
+ mid => $mid0,
+ }, 'PublicInbox::Smsg';
+ $smsg->populate($mime, $self);
+ if (do_idx($self, $msgref, $mime, $smsg)) {
reindex_checkpoint($self, $sync, $git);
}
}
}
}
-# reuse Msgmap to store num => oid mapping (rather than num => mid)
-sub multi_mid_q_new () {
- my ($fh, $fn) = tempfile('multi_mid-XXXXXXX', EXLOCK => 0, TMPDIR => 1);
- my $multi_mid = PublicInbox::Msgmap->new_file($fn, 1);
- $multi_mid->{dbh}->do('PRAGMA synchronous = OFF');
- # for Msgmap->DESTROY:
- $multi_mid->{tmp_name} = $fn;
- $multi_mid->{pid} = $$;
- close $fh or die "failed to close $fn: $!";
- $multi_mid
-}
-
-sub multi_mid_q_push ($$) {
- my ($sync, $oid) = @_;
- my $multi_mid = $sync->{multi_mid} //= multi_mid_q_new();
+sub multi_mid_q_push ($$$) {
+ my ($self, $sync, $oid) = @_;
+ my $multi_mid = $sync->{multi_mid} //= PublicInbox::MultiMidQueue->new;
if ($sync->{reindex}) { # no regen on reindex
- $multi_mid->mid_insert($oid);
+ $multi_mid->push_oid($oid, $self);
} else {
my $num = $sync->{regen}--;
die "BUG: ran out of article numbers" if $num <= 0;
- $multi_mid->mid_set($num, $oid);
+ $multi_mid->set_oid($num, $oid, $self);
}
}
sub reindex_oid ($$$$) {
my ($self, $sync, $git, $oid) = @_;
+ return if PublicInbox::SearchIdx::too_big($self, $git, $oid);
my ($num, $mid0, $len);
my $msgref = $git->cat_file($oid, \$len);
return if $len == 0; # purged
- my $mime = PublicInbox::MIME->new($$msgref);
+ my $mime = PublicInbox::Eml->new($$msgref);
my $mids = mids($mime->header_obj);
- my $cid = content_id($mime);
+ my $chash = content_hash($mime);
if (scalar(@$mids) == 0) {
warn "E: $oid has no Message-ID, skipping\n";
my $mid = $mids->[0];
# was the file previously marked as deleted?, skip if so
- if (delete($sync->{D}->{"$mid\0$cid"})) {
+ if (delete($sync->{D}->{"$mid\0$chash"})) {
if (!$sync->{reindex}) {
$num = $sync->{regen}--;
$self->{mm}->num_highwater($num);
} else { # multiple MIDs are a weird case:
my $del = 0;
for (@$mids) {
- $del += delete($sync->{D}->{"$_\0$cid"}) // 0;
+ $del += delete($sync->{D}->{"$_\0$chash"}) // 0;
}
if ($del) {
unindex_oid_remote($self, $oid, $_) for @$mids;
# do not delete from {mm_tmp}, since another
# single-MID message may use it.
} else { # handle them at the end:
- multi_mid_q_push($sync, $oid);
+ multi_mid_q_push($self, $sync, $oid);
}
return;
}
$sync->{mm_tmp}->mid_delete($mid0) or
die "failed to delete <$mid0> for article #$num\n";
$sync->{nr}++;
- if (do_idx($self, $msgref, $mime, $len, $num, $oid, $mid0)) {
+ my $smsg = bless {
+ raw_bytes => $len,
+ num => $num,
+ blob => $oid,
+ mid => $mid0,
+ }, 'PublicInbox::Smsg';
+ $smsg->populate($mime, $self);
+ if (do_idx($self, $msgref, $mime, $smsg)) {
reindex_checkpoint($self, $sync, $git);
}
}
my ($self, $git, $oid, $unindexed) = @_;
my $mm = $self->{mm};
my $msgref = $git->cat_file($oid);
- my $mime = PublicInbox::MIME->new($msgref);
+ my $mime = PublicInbox::Eml->new($msgref);
my $mids = mids($mime->header_obj);
$mime = $msgref = undef;
my $over = $self->{over};
}
}
close $fh or die "git log failed: \$?=$?";
- delete $self->{reindex_pipe};
+ delete @$self{qw(reindex_pipe autime cotime)};
update_last_commit($self, $git, $i, $cmt) if defined $cmt;
}
return unless defined $latest;
$self->idx_init($opt); # acquire lock
my $sync = {
- D => {}, # "$mid\0$cid" => $oid
+ D => {}, # "$mid\0$chash" => $oid
unindex_range => {}, # EPOCH => oid_old..oid_new
reindex => $opt->{reindex},
-opt => $opt
}
if (my $multi_mid = delete $sync->{multi_mid}) {
$git //= $self->{-inbox}->git;
- my ($min, $max) = $multi_mid->minmax;
+ my $min = $multi_mid->{min};
+ my $max = $multi_mid->{max};
if ($sync->{reindex}) {
# we may need to create new Message-IDs if mirrors
# were initially indexed with old versions
for (my $i = $max; $i >= $min; $i--) {
- my $oid = $multi_mid->mid_for($i);
+ my $oid;
+ $oid = $multi_mid->get_oid($i, $self) or next;
next unless defined $oid;
reindex_oid_m($self, $sync, $git, $oid);
}
} else { # regen on initial index
for my $num ($min..$max) {
- my $oid = $multi_mid->mid_for($num);
- next unless defined $oid;
+ my $oid;
+ $oid = $multi_mid->get_oid($num, $self) or next;
reindex_oid_m($self, $sync, $git, $oid, $num);
}
}