-# Copyright (C) 2018-2019 all contributors <meta@public-inbox.org>
+# Copyright (C) 2018-2020 all contributors <meta@public-inbox.org>
# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
# This interface wraps and mimics PublicInbox::Import
use PublicInbox::Msgmap;
use PublicInbox::Spawn qw(spawn popen_rd);
use PublicInbox::SearchIdx;
+use PublicInbox::MsgTime qw(msg_timestamp msg_datestamp);
+use PublicInbox::MultiMidQueue;
use IO::Handle; # ->autoflush
use File::Temp qw(tempfile);
}
# indexes a message, returns true if checkpointing is needed
-sub do_idx ($$$$$$$) {
- my ($self, $msgref, $mime, $len, $num, $oid, $mid0) = @_;
- $self->{over}->add_overview($mime, $len, $num, $oid, $mid0);
- my $idx = idx_shard($self, $num % $self->{shards});
- $idx->index_raw($len, $msgref, $num, $oid, $mid0, $mime);
- my $n = $self->{transact_bytes} += $len;
+sub do_idx ($$$$) {
+ my ($self, $msgref, $mime, $smsg) = @_;
+ $smsg->{ds} //= msg_datestamp($mime->header_obj, $self->{autime});
+ $smsg->{ts} //= msg_timestamp($mime->header_obj, $self->{cotime});
+ $self->{over}->add_overview($mime, $smsg);
+ my $idx = idx_shard($self, $smsg->{num} % $self->{shards});
+ $idx->index_raw($msgref, $mime, $smsg);
+ my $n = $self->{transact_bytes} += $smsg->{bytes};
$n >= (PublicInbox::SearchIdx::BATCH_BYTES * $self->{shards});
}
defined $num or return; # duplicate
defined $mid0 or die "BUG: $mid0 undefined\n";
my $im = $self->importer;
- my $cmt = $im->add($mime);
+ my $smsg = bless { mid => $mid0, num => $num }, 'PublicInbox::Smsg';
+ my $cmt = $im->add($mime, undef, $smsg); # sets $smsg->{ds|ts|blob}
$cmt = $im->get_mark($cmt);
$self->{last_commit}->[$self->{epoch_max}] = $cmt;
- my ($oid, $len, $msgref) = @{$im->{last_object}};
- if (do_idx($self, $msgref, $mime, $len, $num, $oid, $mid0)) {
+ my $msgref = delete $smsg->{-raw_email};
+ if (do_idx($self, $msgref, $mime, $smsg)) {
$self->checkpoint;
}
# crap, Message-ID is already known, hope somebody just resent:
foreach my $m (@$mids) {
# read-only lookup now safe to do after above barrier
- my $existing = lookup_content($self, $mime, $m);
# easy, don't store duplicates
# note: do not add more diagnostic info here since
# it gets noisy on public-inbox-watch restarts
- return () if $existing;
+ return () if content_exists($self, $mime, $m);
}
# AltId may pre-populate article numbers (e.g. X-Mail-Count
}
my $over = $self->{over};
my $cids = content_ids($old_mime);
- my $removed;
+ my @removed;
my $mids = mids($old_mime->header_obj);
# We avoid introducing new blobs into git since the raw content
my $mark;
foreach my $mid (@$mids) {
- my %gone; # num => [ smsg, raw ]
+ my %gone; # num => [ smsg, $mime, raw ]
my ($id, $prev);
while (my $smsg = $over->next_by_mid($mid, \$id, \$prev)) {
my $msg = get_blob($self, $smsg);
my $orig = $$msg;
my $cur = PublicInbox::MIME->new($msg);
if (content_matches($cids, $cur)) {
- $smsg->{mime} = $cur;
- $gone{$smsg->{num}} = [ $smsg, \$orig ];
+ $gone{$smsg->{num}} = [ $smsg, $cur, \$orig ];
}
}
my $n = scalar keys %gone;
join(',', sort keys %gone), "\n";
}
foreach my $num (keys %gone) {
- my ($smsg, $orig) = @{$gone{$num}};
- # $removed should only be set once assuming
+ my ($smsg, $mime, $orig) = @{$gone{$num}};
+ # @removed should only be set once assuming
# no bugs in our deduplication code:
- $removed = $smsg;
+ @removed = (undef, $mime, $smsg);
my $oid = $smsg->{blob};
if ($replace_map) {
$replace_map->{$oid} = $sref;
} else {
($mark, undef) = $im->remove($orig, $cmt_msg);
+ $removed[0] = $mark;
}
$orig = undef;
if ($need_reindex) { # ->replace
my $rewrites = _replace_oids($self, $new_mime, $replace_map);
return { rewrites => $rewrites, need_reindex => $need_reindex };
}
- $removed;
+ defined($mark) ? @removed : undef;
}
-# public
+# public (see PublicInbox::Import->remove), but note the 3rd element
+# (retval[2]) is not part of the stable API shared with Import->remove
sub remove {
my ($self, $mime, $cmt_msg) = @_;
+ my @ret;
$self->{-inbox}->with_umask(sub {
- rewrite_internal($self, $mime, $cmt_msg);
+ @ret = rewrite_internal($self, $mime, $cmt_msg);
});
+ defined($ret[0]) ? @ret : undef;
}
sub _replace ($$;$$) {
}
# 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,
+ bytes => $bytes,
+ num => $smsg->{num},
+ mid => $smsg->{mid},
+ }, 'PublicInbox::Smsg';
+ do_idx($self, \$raw, $new_mime, $new_smsg);
}
$rewritten->{rewrites};
}
my ($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;
$ibx->msg_by_smsg($smsg);
}
-sub lookup_content ($$$) {
+sub content_exists ($$$) {
my ($self, $mime, $mid) = @_;
my $over = $self->{over};
my $cids = content_ids($mime);
next;
}
my $cur = PublicInbox::MIME->new($msg);
- if (content_matches($cids, $cur)) {
- $smsg->{mime} = $cur;
- return $smsg;
- }
-
+ return 1 if content_matches($cids, $cur);
# XXX DEBUG_DIFF is experimental and may be removed
diff($mid, $cur, $mime) if $ENV{DEBUG_DIFF};
}
}
$sync->{nr}++;
- if (do_idx($self, $msgref, $mime, $len, $num, $oid, $mid0)) {
+ my $smsg = bless {
+ bytes => $len,
+ num => $num,
+ blob => $oid,
+ mid => $mid0,
+ }, 'PublicInbox::Smsg';
+ if (do_idx($self, $msgref, $mime, $smsg)) {
reindex_checkpoint($self, $sync, $git);
}
}
$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, $self);
}
}
# do not delete from {mm_tmp}, since another
# single-MID message may use it.
} else { # handle them at the end:
- multi_mid_q_push($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 {
+ bytes => $len,
+ num => $num,
+ blob => $oid,
+ mid => $mid0,
+ }, 'PublicInbox::Smsg';
+ if (do_idx($self, $msgref, $mime, $smsg)) {
reindex_checkpoint($self, $sync, $git);
}
}
$pr->("$i.git indexing $range\n");
}
- my @cmd = qw(log --raw -r --pretty=tformat:%H
+ my @cmd = qw(log --raw -r --pretty=tformat:%H.%at.%ct
--no-notes --no-color --no-abbrev --no-renames);
my $fh = $self->{reindex_pipe} = $git->popen(@cmd, $range);
my $cmt;
while (<$fh>) {
chomp;
$self->{current_info} = "$i.git $_";
- if (/\A$x40$/o && !defined($cmt)) {
- $cmt = $_;
+ if (/\A($x40)\.([0-9]+)\.([0-9]+)$/o) {
+ $cmt //= $1;
+ $self->{autime} = $2;
+ $self->{cotime} = $3;
} elsif (/\A:\d{6} 100644 $x40 ($x40) [AM]\tm$/o) {
reindex_oid($self, $sync, $git, $1);
} elsif (/\A:\d{6} 100644 $x40 ($x40) [AM]\td$/o) {
}
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);
}
}