-# Copyright (C) 2015-2019 all contributors <meta@public-inbox.org>
+# 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
#
# This writes to the search index.
package PublicInbox::SearchIdx;
use strict;
-use warnings;
-use base qw(PublicInbox::Search PublicInbox::Lock);
-use PublicInbox::MIME;
+use v5.10.1;
+use parent qw(PublicInbox::Search PublicInbox::Lock Exporter);
+use PublicInbox::Eml;
use PublicInbox::InboxWritable;
-use PublicInbox::MID qw/mid_clean id_compress mid_mime mids_for_index/;
+use PublicInbox::MID qw(mids_for_index mids);
use PublicInbox::MsgIter;
+use PublicInbox::IdxStack;
use Carp qw(croak);
use POSIX qw(strftime);
use PublicInbox::OverIdx;
-use PublicInbox::Spawn qw(spawn);
+use PublicInbox::Spawn qw(spawn nodatacow_dir);
use PublicInbox::Git qw(git_unquote);
+use PublicInbox::MsgTime qw(msg_timestamp msg_datestamp);
+our @EXPORT_OK = qw(crlf_adjust log2stack is_ancestor check_size);
my $X = \%PublicInbox::Search::X;
my ($DB_CREATE_OR_OPEN, $DB_OPEN);
-use constant {
- BATCH_BYTES => defined($ENV{XAPIAN_FLUSH_THRESHOLD}) ?
- 0x7fffffff : 1_000_000,
- DEBUG => !!$ENV{DEBUG},
-};
+our $DB_NO_SYNC = 0;
+our $BATCH_BYTES = $ENV{XAPIAN_FLUSH_THRESHOLD} ? 0x7fffffff : 1_000_000;
+use constant DEBUG => !!$ENV{DEBUG};
my $xapianlevels = qr/\A(?:full|medium)\z/;
+my $hex = '[a-f0-9]';
+my $OID = $hex .'{40,}';
sub new {
my ($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} || 1;
+ my $version = $ibx->version;
my $indexlevel = 'full';
my $altid = $ibx->{altid};
if ($altid) {
}
$ibx = PublicInbox::InboxWritable->new($ibx);
my $self = bless {
- inboxdir => $inboxdir,
- -inbox => $ibx,
- git => $ibx->git,
+ ibx => $ibx,
+ xpfx => $inboxdir, # for xpfx_init
-altid => $altid,
- version => $version,
+ ibx_ver => $version,
indexlevel => $indexlevel,
}, $class;
+ $self->xpfx_init;
+ $self->{-set_indexlevel_once} = 1 if $indexlevel eq 'medium';
+ if ($ibx->{-skip_docdata}) {
+ $self->{-set_skip_docdata_once} = 1;
+ $self->{-skip_docdata} = 1;
+ }
$ibx->umask_prepare;
if ($version == 1) {
$self->{lock_path} = "$inboxdir/ssoma.lock";
my $dir = $self->xdir;
- $self->{over} = PublicInbox::OverIdx->new("$dir/over.sqlite3");
+ $self->{oidx} = PublicInbox::OverIdx->new("$dir/over.sqlite3");
+ $self->{oidx}->{-no_fsync} = 1 if $ibx->{-no_fsync};
} elsif ($version == 2) {
defined $shard or die "shard is required for v2\n";
# shard is a number
sub need_xapian ($) { $_[0]->{indexlevel} =~ $xapianlevels }
-sub _xdb_release {
- my ($self) = @_;
+sub idx_release {
+ my ($self, $wake) = @_;
if (need_xapian($self)) {
my $xdb = delete $self->{xdb} or croak 'not acquired';
$xdb->close;
}
- $self->lock_release if $self->{creat};
+ $self->lock_release($wake) if $self->{creat};
undef;
}
*sortable_serialise = $xap.'::sortable_serialise';
$DB_CREATE_OR_OPEN = eval($xap.'::DB_CREATE_OR_OPEN()');
$DB_OPEN = eval($xap.'::DB_OPEN()');
+ my $ver = (eval($xap.'::major_version()') << 16) |
+ (eval($xap.'::minor_version()') << 8);
+ $DB_NO_SYNC = 0x4 if $ver >= 0x10400;
1;
}
-sub _xdb_acquire {
+sub idx_acquire {
my ($self) = @_;
my $flag;
my $dir = $self->xdir;
# 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))) {
+ if (!-d $dir && (!$is_shard ||
+ ($is_shard && need_xapian($self)))) {
File::Path::mkpath($dir);
+ nodatacow_dir($dir);
+ $self->{-set_has_threadid_once} = 1;
}
}
return unless defined $flag;
+ $flag |= $DB_NO_SYNC if $self->{ibx}->{-no_fsync};
my $xdb = eval { ($X->{WritableDatabase})->new($dir, $flag) };
- if ($@) {
- die "Failed opening $dir: ", $@;
- }
+ croak "Failed opening $dir: $@" if $@;
$self->{xdb} = $xdb;
}
$doc->add_value($col, $num);
}
-sub index_text ($$$$)
-{
- my ($self, $field, $n, $text) = @_;
- my $tg = $self->term_generator;
+sub term_generator ($) { # write-only
+ my ($self) = @_;
+
+ $self->{term_generator} //= do {
+ my $tg = $X->{TermGenerator}->new;
+ $tg->set_stemmer($self->stemmer);
+ $tg;
+ }
+}
+
+sub index_text ($$$$) {
+ my ($self, $text, $wdf_inc, $prefix) = @_;
+ my $tg = term_generator($self); # man Search::Xapian::TermGenerator
if ($self->{indexlevel} eq 'full') {
- $tg->index_text($field, $n, $text);
+ $tg->index_text($text, $wdf_inc, $prefix);
$tg->increase_termpos;
} else {
- $tg->index_text_without_positions($field, $n, $text);
+ $tg->index_text_without_positions($text, $wdf_inc, $prefix);
}
}
-sub index_users ($$) {
+sub index_headers ($$) {
my ($self, $smsg) = @_;
-
- my $from = $smsg->from;
- my $to = $smsg->to;
- my $cc = $smsg->cc;
-
- $self->index_text($from, 1, 'A'); # A - author
- $self->index_text($to, 1, 'XTO') if $to ne '';
- $self->index_text($cc, 1, 'XCC') if $cc ne '';
+ my @x = (from => 'A', # Author
+ subject => 'S', to => 'XTO', cc => 'XCC');
+ while (my ($field, $pfx) = splice(@x, 0, 2)) {
+ my $val = $smsg->{$field};
+ index_text($self, $val, 1, $pfx) if $val ne '';
+ }
}
sub index_diff_inc ($$$$) {
my ($self, $text, $pfx, $xnq) = @_;
if (@$xnq) {
- $self->index_text(join("\n", @$xnq), 1, 'XNQ');
+ index_text($self, join("\n", @$xnq), 1, 'XNQ');
@$xnq = ();
}
- $self->index_text($text, 1, $pfx);
+ index_text($self, $text, 1, $pfx);
}
sub index_old_diff_fn {
$fb = join('/', @fb);
if ($fa eq $fb) {
unless ($seen->{$fa}++) {
- $self->index_diff_inc($fa, 'XDFN', $xnq);
+ index_diff_inc($self, $fa, 'XDFN', $xnq);
}
return 1;
}
}
sub index_diff ($$$) {
- my ($self, $lines, $doc) = @_;
+ my ($self, $txt, $doc) = @_;
my %seen;
my $in_diff;
my @xnq;
my $xnq = \@xnq;
- foreach (@$lines) {
+ foreach (split(/\n/, $txt)) {
if ($in_diff && s/^ //) { # diff context
- $self->index_diff_inc($_, 'XDFCTX', $xnq);
+ index_diff_inc($self, $_, '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 $self->index_diff_inc($fn, 'XDFN', $xnq);
- $fn = (split('/', git_unquote($fb), 2))[1];
- $seen{$fn}++ or $self->index_diff_inc($fn, 'XDFN', $xnq);
+ } elsif (m!^diff --git "?[^/]+/.+ "?[^/]+/.+\z!) {
+ # wait until "---" and "+++" to capture filenames
$in_diff = 1;
# traditional diff:
} elsif (m/^diff -(.+) (\S+) (\S+)$/) {
push @xnq, $_;
# only support unified:
next unless $opt =~ /[uU]/;
- $in_diff = $self->index_old_diff_fn(\%seen, $fa, $fb,
+ $in_diff = index_old_diff_fn($self, \%seen, $fa, $fb,
$xnq);
- } elsif (m!^--- ("?a/.+)!) {
+ } elsif (m!^--- ("?[^/]+/.+)!) {
my $fn = $1;
$fn = (split('/', git_unquote($fn), 2))[1];
- $seen{$fn}++ or $self->index_diff_inc($fn, 'XDFN', $xnq);
+ $seen{$fn}++ or index_diff_inc($self, $fn, 'XDFN', $xnq);
$in_diff = 1;
- } elsif (m!^\+\+\+ ("?b/.+)!) {
+ } elsif (m!^\+\+\+ ("?[^/]+/.+)!) {
my $fn = $1;
$fn = (split('/', git_unquote($fn), 2))[1];
- $seen{$fn}++ or $self->index_diff_inc($fn, 'XDFN', $xnq);
+ $seen{$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 = $self->index_old_diff_fn(\%seen, $in_diff, $1,
- $xnq);
+ $in_diff = index_old_diff_fn($self, \%seen, $in_diff,
+ $1, $xnq);
} elsif ($in_diff && s/^\+//) { # diff added
- $self->index_diff_inc($_, 'XDFB', $xnq);
+ index_diff_inc($self, $_, 'XDFB', $xnq);
} elsif ($in_diff && s/^-//) { # diff removed
- $self->index_diff_inc($_, 'XDFA', $xnq);
+ index_diff_inc($self, $_, 'XDFA', $xnq);
} elsif (m!^index ([a-f0-9]+)\.\.([a-f0-9]+)!) {
my ($ba, $bb) = ($1, $2);
index_git_blob_id($doc, 'XDFPRE', $ba);
# traditional diff w/o -p
} elsif (/^@@ (?:\S+) (?:\S+) @@\s*(\S+.*)$/) {
# hunk header context
- $self->index_diff_inc($1, 'XDFHH', $xnq);
+ index_diff_inc($self, $1, 'XDFHH', $xnq);
# ignore the following lines:
} elsif (/^(?:dis)similarity index/ ||
/^(?:old|new) mode/ ||
}
}
- $self->index_text(join("\n", @xnq), 1, 'XNQ');
-}
-
-sub index_body ($$$) {
- my ($self, $lines, $doc) = @_;
- my $txt = join("\n", @$lines);
- if ($doc) {
- # does it look like a diff?
- if ($txt =~ /^(?:diff|---|\+\+\+) /ms) {
- $txt = undef;
- $self->index_diff($lines, $doc);
- } else {
- $self->index_text($txt, 1, 'XNQ');
- }
- } else {
- $self->index_text($txt, 0, 'XQUOT');
- }
- @$lines = ();
+ index_text($self, join("\n", @xnq), 1, 'XNQ');
}
sub index_xapian { # msg_iter callback
- my ($part, $depth, @idx) = @{$_[0]};
+ my $part = $_[0]->[0]; # ignore $depth and $idx
my ($self, $doc) = @{$_[1]};
my $ct = $part->content_type || 'text/plain';
my $fn = $part->filename;
if (defined $fn && $fn ne '') {
- $self->index_text($fn, 1, 'XFN');
+ index_text($self, $fn, 1, 'XFN');
+ }
+ if ($part->{is_submsg}) {
+ my $mids = mids_for_index($part);
+ index_ids($self, $doc, $part, $mids);
+ my $smsg = bless {}, 'PublicInbox::Smsg';
+ $smsg->populate($part);
+ index_headers($self, $smsg);
}
my ($s, undef) = msg_part_text($part, $ct);
defined $s or return;
-
- my (@orig, @quot);
- my @lines = split(/\n/, $s);
- while (defined(my $l = shift @lines)) {
- if ($l =~ /^>/) {
- $self->index_body(\@orig, $doc) if @orig;
- push @quot, $l;
+ $_[0]->[0] = $part = undef; # free memory
+
+ # split off quoted and unquoted blocks:
+ my @sections = PublicInbox::MsgIter::split_quotes($s);
+ undef $s; # free memory
+ for my $txt (@sections) {
+ if ($txt =~ /\A>/) {
+ index_text($self, $txt, 0, 'XQUOT');
} else {
- $self->index_body(\@quot, 0) if @quot;
- push @orig, $l;
+ # does it look like a diff?
+ if ($txt =~ /^(?:diff|---|\+\+\+) /ms) {
+ index_diff($self, $txt, $doc);
+ } else {
+ index_text($self, $txt, 1, 'XNQ');
+ }
}
+ undef $txt; # free memory
+ }
+}
+
+sub index_ids ($$$$) {
+ my ($self, $doc, $hdr, $mids) = @_;
+ for my $mid (@$mids) {
+ index_text($self, $mid, 1, 'XM');
+
+ # because too many Message-IDs are prefixed with
+ # "Pine.LNX."...
+ if ($mid =~ /\w{12,}/) {
+ my @long = ($mid =~ /(\w{3,}+)/g);
+ index_text($self, join(' ', @long), 1, 'XM');
+ }
+ }
+ $doc->add_boolean_term('Q' . $_) for @$mids;
+ for my $l ($hdr->header_raw('List-Id')) {
+ $l =~ /<([^>]+)>/ or next;
+ my $lid = $1;
+ $doc->add_boolean_term('G' . $lid);
+ index_text($self, $lid, 1, 'XL'); # probabilistic
}
- $self->index_body(\@quot, 0) if @quot;
- $self->index_body(\@orig, $doc) if @orig;
}
-sub add_xapian ($$$$$) {
- my ($self, $mime, $num, $oid, $mids, $mid0) = @_;
- my $smsg = PublicInbox::SearchMsg->new($mime);
+sub add_xapian ($$$$) {
+ my ($self, $eml, $smsg, $mids) = @_;
my $doc = $X->{Document}->new;
- my $subj = $smsg->subject;
- add_val($doc, PublicInbox::Search::TS(), $smsg->ts);
- my @ds = gmtime($smsg->ds);
+ 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);
+ add_val($doc, PublicInbox::Search::BYTES(), $smsg->{bytes});
+ add_val($doc, PublicInbox::Search::UID(), $smsg->{num});
+ add_val($doc, PublicInbox::Search::THREADID, $smsg->{tid});
- my $tg = $self->term_generator;
-
+ my $tg = term_generator($self);
$tg->set_document($doc);
- $self->index_text($subj, 1, 'S') if $subj;
- $self->index_users($smsg);
+ index_headers($self, $smsg);
- msg_iter($mime, \&index_xapian, [ $self, $doc ]);
- foreach my $mid (@$mids) {
- $self->index_text($mid, 1, 'XM');
+ msg_iter($eml, \&index_xapian, [ $self, $doc ]);
+ index_ids($self, $doc, $eml, $mids);
- # 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');
- }
+ # by default, we maintain compatibility with v1.5.0 and earlier
+ # by writing to docdata.glass, users who never exect to downgrade can
+ # use --skip-docdata
+ if (!$self->{-skip_docdata}) {
+ # WWW doesn't need {to} or {cc}, only NNTP
+ $smsg->{to} = $smsg->{cc} = '';
+ PublicInbox::OverIdx::parse_references($smsg, $eml, $mids);
+ my $data = $smsg->to_doc_data;
+ $doc->set_data($data);
}
- $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};
}
}
}
- $doc->add_boolean_term('Q' . $_) foreach @$mids;
- $self->{xdb}->replace_document($num, $doc);
+ $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;
+ my $rw = $self->{ibx}->{-no_fsync} ? 2 : 1;
+ PublicInbox::Msgmap->new($self->{ibx}->{inboxdir}, $rw);
+ };
}
sub add_message {
- # mime = Email::MIME object
- my ($self, $mime, $bytes, $num, $oid, $mid0) = @_;
- my $mids = mids_for_index($mime->header_obj);
- $mid0 = $mids->[0] unless defined $mid0; # v1 compatibility
- unless (defined $num) { # v1
- $self->_msgmap_init;
- $num = index_mm($self, $mime);
- }
+ # mime = PublicInbox::Eml or Email::MIME object
+ my ($self, $mime, $smsg, $sync) = @_;
+ my $mids = mids_for_index($mime);
+ $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, $smsg->{blob}, $sync);
+ };
+
+ # v1 and tests only:
+ $smsg->populate($mime, $sync);
+ $smsg->{bytes} //= length($mime->as_string);
+
eval {
- if (need_xapian($self)) {
- $self->add_xapian($mime, $num, $oid, $mids, $mid0)
+ # 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 $oidx = $self->{oidx}) { # v1 only
+ $oidx->add_overview($mime, $smsg);
}
- if (my $over = $self->{over}) {
- $over->add_overview($mime, $bytes, $num, $oid, $mid0);
+ if (need_xapian($self)) {
+ add_xapian($self, $mime, $smsg, $mids);
}
};
warn "failed to index message <".join('> <',@$mids).">: $@\n";
return undef;
}
- $num;
-}
-
-# returns begin and end PostingIterator
-sub find_doc_ids {
- my ($self, $termval) = @_;
- my $db = $self->{xdb};
-
- ($db->postlist_begin($termval), $db->postlist_end($termval));
+ $smsg->{num};
}
-# 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);
- }
-}
-
-# 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";
+sub xdb_remove {
+ my ($self, $oid, @removed) = @_;
+ my $xdb = $self->{xdb} or return;
+ for my $num (@removed) {
+ my $doc = eval { $xdb->get_document($num) };
+ unless ($doc) {
+ warn "E: $@\n" if $@;
+ warn "E: #$num $oid missing in Xapian\n";
+ next;
}
- }
- 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";
- }
-}
-
-# MID is a hint in V2
-sub remove_by_oid {
- my ($self, $oid, $mid) = @_;
-
- $self->{over}->remove_oid($oid, $mid) if $self->{over};
-
- return unless need_xapian($self);
- my $db = $self->{xdb};
-
- # 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;
-
- # 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::SearchMsg->wrap($mid);
+ my $smsg = bless {}, 'PublicInbox::Smsg';
$smsg->load_expand($doc);
- if ($smsg->{blob} eq $oid) {
- push(@delete, $docid);
+ my $blob = $smsg->{blob} // '(unset)';
+ if ($blob eq $oid) {
+ $xdb->delete_document($num);
+ } else {
+ warn "E: #$num $oid != $blob in Xapian\n";
}
}
- $db->delete_document($_) foreach @delete;
- scalar(@delete);
}
-sub term_generator { # write-only
- my ($self) = @_;
-
- my $tg = $self->{term_generator};
- return $tg if $tg;
-
- $tg = $X->{TermGenerator}->new;
- $tg->set_stemmer($self->stemmer);
-
- $self->{term_generator} = $tg;
+sub remove_by_oid {
+ my ($self, $oid, $num) = @_;
+ die "BUG: remove_by_oid is v2-only\n" if $self->{oidx};
+ $self->begin_txn_lazy;
+ xdb_remove($self, $oid, $num) if need_xapian($self);
}
sub index_git_blob_id {
}
}
-sub unindex_blob {
- my ($self, $mime) = @_;
- my $mid = eval { mid_clean(mid_mime($mime)) };
- $self->remove_message($mid) if defined $mid;
+# v1 only
+sub unindex_eml {
+ my ($self, $oid, $eml) = @_;
+ my $mids = mids($eml);
+ my $nr = 0;
+ my %tmp;
+ for my $mid (@$mids) {
+ my @removed = $self->{oidx}->remove_oid($oid, $mid);
+ $nr += scalar @removed;
+ $tmp{$_}++ for @removed;
+ }
+ if (!$nr) {
+ $mids = join('> <', @$mids);
+ warn "W: <$mids> missing for removal from overview\n";
+ }
+ while (my ($num, $nr) = each %tmp) {
+ warn "BUG: $num appears >1 times ($nr) for $oid\n" if $nr != 1;
+ }
+ if ($nr) {
+ $self->{mm}->num_delete($_) for (keys %tmp);
+ } else { # just in case msgmap and over.sqlite3 become desynched:
+ $self->{mm}->mid_delete($mids->[0]);
+ }
+ xdb_remove($self, $oid, keys %tmp) if need_xapian($self);
}
sub index_mm {
- my ($self, $mime) = @_;
- my $mid = mid_clean(mid_mime($mime));
+ my ($self, $mime, $oid, $sync) = @_;
+ my $mids = mids($mime);
my $mm = $self->{mm};
- 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;
- }
+ if ($sync->{reindex}) {
+ my $oidx = $self->{oidx};
+ for my $mid (@$mids) {
+ my ($num, undef) = $oidx->num_mid0_for_oid($oid, $mid);
+ return $num if defined $num;
}
+ $mm->num_for($mids->[0]) // $mm->mid_insert($mids->[0]);
+ } else {
+ # fallback to num_for since filters like RubyLang set the number
+ $mm->mid_insert($mids->[0]) // $mm->num_for($mids->[0]);
}
-
- $num = $mm->mid_insert($mid) and return $num;
-
- # fallback to num_for since filters like RubyLang set the number
- $mm->num_for($mid);
}
-sub unindex_mm {
- my ($self, $mime) = @_;
- $self->{mm}->mid_delete(mid_clean(mid_mime($mime)));
+# returns the number of bytes to add if given a non-CRLF arg
+sub crlf_adjust ($) {
+ if (index($_[0], "\r\n") < 0) {
+ # common case is LF-only, every \n needs an \r;
+ # so favor a cheap tr// over an expensive m//g
+ $_[0] =~ tr/\n/\n/;
+ } else { # count number of '\n' w/o '\r', expensive:
+ scalar(my @n = ($_[0] =~ m/(?<!\r)\n/g));
+ }
}
-sub index_both {
- my ($self, $mime, $bytes, $blob) = @_;
- my $num = index_mm($self, $mime);
- add_message($self, $mime, $bytes, $num, $blob);
+sub index_both { # git->cat_async callback
+ my ($bref, $oid, $type, $size, $sync) = @_;
+ my ($nr, $max) = @$sync{qw(nr max)};
+ ++$$nr;
+ $$max -= $size;
+ $size += crlf_adjust($$bref);
+ my $smsg = bless { bytes => $size, blob => $oid }, 'PublicInbox::Smsg';
+ my $self = $sync->{sidx};
+ my $eml = PublicInbox::Eml->new($bref);
+ $smsg->{num} = index_mm($self, $eml, $oid, $sync) or
+ die "E: could not generate NNTP article number for $oid";
+ add_message($self, $eml, $smsg, $sync);
}
-sub unindex_both {
- my ($self, $mime) = @_;
- unindex_blob($self, $mime);
- unindex_mm($self, $mime);
-}
-
-sub do_cat_mail {
- my ($git, $blob, $sizeref) = @_;
- my $mime = eval {
- my $str = $git->cat_file($blob, $sizeref);
- # fixup bugs from import:
- $$str =~ s/\A[\r\n]*From [^\r\n]*\r?\n//s;
- PublicInbox::MIME->new($str);
- };
- $@ ? undef : $mime;
+sub unindex_both { # git->cat_async callback
+ my ($bref, $oid, $type, $size, $self) = @_;
+ unindex_eml($self, $oid, PublicInbox::Eml->new($bref));
}
# called by public-inbox-index
sub index_sync {
- my ($self, $opts) = @_;
- delete $self->{lock_path} if $opts->{-skip_lock};
- $self->{-inbox}->with_umask(sub { $self->_index_sync($opts) })
+ my ($self, $opt) = @_;
+ delete $self->{lock_path} if $opt->{-skip_lock};
+ $self->{ibx}->with_umask(\&_index_sync, $self, $opt);
+ if ($opt->{reindex}) {
+ my %again = %$opt;
+ delete @again{qw(rethread reindex)};
+ index_sync($self, \%again);
+ }
}
-sub batch_adjust ($$$$$) {
- my ($max, $bytes, $batch_cb, $latest, $nr) = @_;
- $$max -= $bytes;
- if ($$max <= 0) {
- $$max = BATCH_BYTES;
- $batch_cb->($nr, $latest);
+sub check_size { # check_async cb for -index --max-size=...
+ my ($oid, $type, $size, $arg, $git) = @_;
+ (($type // '') eq 'blob') or die "E: bad $oid in $git->{git_dir}";
+ if ($size <= $arg->{max_size}) {
+ $git->cat_async($oid, $arg->{index_oid}, $arg);
+ } else {
+ warn "W: skipping $oid ($size > $arg->{max_size})\n";
}
}
-# only for v1
-sub read_log {
- my ($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}$!;
- 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;
- batch_adjust(\$max, $bytes, $batch_cb, $latest, ++$nr);
- $add_cb->($self, $mime, $bytes, $blob);
- } elsif ($line =~ /$delmsg/o) {
- my $blob = $1;
- $D{$blob} = 1;
- } elsif ($line =~ /^commit ($h40)/o) {
- $latest = $1;
- $newest ||= $latest;
+sub v1_checkpoint ($$;$) {
+ my ($self, $sync, $stk) = @_;
+ $self->{ibx}->git->check_async_wait;
+ $self->{ibx}->git->cat_async_wait;
+
+ # latest_cmt may be undef
+ my $newest = $stk ? $stk->{latest_cmt} : undef;
+ if ($newest) {
+ my $cur = $self->{mm}->last_commit || '';
+ if (need_update($self, $cur, $newest)) {
+ $self->{mm}->last_commit($newest);
+ }
+ } else {
+ ${$sync->{max}} = $self->{batch_bytes};
+ }
+
+ $self->{mm}->{dbh}->commit;
+ if ($newest && need_xapian($self)) {
+ my $xdb = $self->{xdb};
+ my $cur = $xdb->get_metadata('last_commit');
+ if (need_update($self, $cur, $newest)) {
+ $xdb->set_metadata('last_commit', $newest);
+ }
+
+ # let SearchView know a full --reindex was done so it can
+ # generate ->has_threadid-dependent links
+ if ($sync->{reindex} && !ref($sync->{reindex})) {
+ my $n = $xdb->get_metadata('has_threadid');
+ $xdb->set_metadata('has_threadid', '1') if $n ne '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);
+
+ $self->{oidx}->rethread_done($sync->{-opt}) if $newest; # all done
+ commit_txn_lazy($self);
+ $self->{ibx}->git->cleanup;
+ my $nr = ${$sync->{nr}};
+ idx_release($self, $nr);
+ # let another process do some work...
+ if (my $pr = $sync->{-opt}->{-progress}) {
+ $pr->("indexed $nr/$sync->{ntodo}\n") if $nr;
+ }
+ if (!$stk) { # more to come
+ begin_txn_lazy($self);
+ $self->{mm}->{dbh}->begin_work;
}
- $batch_cb->($nr, $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;
- PublicInbox::Msgmap->new($self->{inboxdir}, 1);
- };
+# only for v1
+sub process_stack {
+ my ($self, $sync, $stk) = @_;
+ my $git = $self->{ibx}->git;
+ my $max = $self->{batch_bytes};
+ my $nr = 0;
+ $sync->{nr} = \$nr;
+ $sync->{max} = \$max;
+ $sync->{sidx} = $self;
+
+ $self->{mm}->{dbh}->begin_work;
+ if (my @leftovers = keys %{delete($sync->{D}) // {}}) {
+ warn('W: unindexing '.scalar(@leftovers)." leftovers\n");
+ for my $oid (@leftovers) {
+ $oid = unpack('H*', $oid);
+ $git->cat_async($oid, \&unindex_both, $self);
+ }
+ }
+ if ($sync->{max_size} = $sync->{-opt}->{max_size}) {
+ $sync->{index_oid} = \&index_both;
+ }
+ while (my ($f, $at, $ct, $oid) = $stk->pop_rec) {
+ if ($f eq 'm') {
+ my $arg = { %$sync, autime => $at, cotime => $ct };
+ if ($sync->{max_size}) {
+ $git->check_async($oid, \&check_size, $arg);
+ } else {
+ $git->cat_async($oid, \&index_both, $arg);
+ }
+ v1_checkpoint($self, $sync) if $max <= 0;
+ } elsif ($f eq 'd') {
+ $git->cat_async($oid, \&unindex_both, $self);
+ }
+ }
+ v1_checkpoint($self, $sync, $stk);
}
-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;
- }
+sub log2stack ($$$$) {
+ my ($sync, $git, $range, $ibx) = @_;
+ my $D = $sync->{D}; # OID_BIN => NR (if reindexing, undef otherwise)
+ my ($add, $del);
+ if ($ibx->version == 1) {
+ my $path = $hex.'{2}/'.$hex.'{38}';
+ $add = qr!\A:000000 100644 \S+ ($OID) A\t$path$!;
+ $del = qr!\A:100644 000000 ($OID) \S+ D\t$path$!;
+ } else {
+ $del = qr!\A:\d{6} 100644 $OID ($OID) [AM]\td$!;
+ $add = qr!\A:\d{6} 100644 $OID ($OID) [AM]\tm$!;
}
# Count the new files so they can be added newest to oldest
# and still have numbers increasing from oldest to newest
- my $fcount = 0;
- my $pr = $opts->{-progress};
- $pr->("counting changes\n\t$range ... ") if $pr;
- # can't use 'rev-list --count' if we use --diff-filter
- my $fh = $git->popen(qw(log --pretty=tformat:%h
- --no-notes --no-color --no-renames
- --diff-filter=AM), $range);
- ++$fcount while <$fh>;
+ my $fh = $git->popen(qw(log --raw -r --pretty=tformat:%at-%ct-%H
+ --no-notes --no-color --no-renames --no-abbrev),
+ $range);
+ my ($at, $ct, $stk);
+ while (<$fh>) {
+ if (/\A([0-9]+)-([0-9]+)-($OID)$/o) {
+ ($at, $ct) = ($1 + 0, $2 + 0);
+ $stk //= PublicInbox::IdxStack->new($3);
+ } elsif (/$del/) {
+ my $oid = $1;
+ if ($D) { # reindex case
+ $D->{pack('H*', $oid)}++;
+ } else { # non-reindex case:
+ $stk->push_rec('d', $at, $ct, $oid);
+ }
+ } elsif (/$add/) {
+ my $oid = $1;
+ if ($D) {
+ my $oid_bin = pack('H*', $oid);
+ my $nr = --$D->{$oid_bin};
+ delete($D->{$oid_bin}) if $nr <= 0;
+
+ # nr < 0 (-1) means it never existed
+ $stk->push_rec('m', $at, $ct, $oid) if $nr < 0;
+ } else {
+ $stk->push_rec('m', $at, $ct, $oid);
+ }
+ }
+ }
close $fh or die "git log failed: \$?=$?";
- my $high = $self->{mm}->num_highwater;
- $pr->("$fcount\n") if $pr; # continue previous line
- $self->{ntodo} = $fcount;
+ $stk //= PublicInbox::IdxStack->new;
+ $stk->read_prepare;
+}
+
+sub prepare_stack ($$$) {
+ my ($self, $sync, $range) = @_;
+ my $git = $self->{ibx}->git;
if (index($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;
+ # don't show annoying git errors to users who run -index
+ # on empty inboxes
+ $git->qx(qw(rev-parse -q --verify), "$range^0");
+ return PublicInbox::IdxStack->new->read_prepare if $?;
}
-
- $git->popen(qw/log --no-notes --no-color --no-renames
- --raw -r --no-abbrev/, $range);
+ $sync->{D} = $sync->{reindex} ? {} : undef; # OID_BIN => NR
+ log2stack($sync, $git, $range, $self->{ibx});
}
# --is-ancestor requires git 1.8.0+
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};
+ my $git = $self->{ibx}->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));
$lx = $lm;
}
# Use last_commit from msgmap if it is older or unset
- if (!$lm || ($lx && $lm && is_ancestor($self->{git}, $lm, $lx))) {
+ if (!$lm || ($lx && $lm && is_ancestor($self->{ibx}->git, $lm, $lx))) {
$lx = $lm;
}
$lx;
# indexes all unindexed messages (v1 only)
sub _index_sync {
- my ($self, $opts) = @_;
- my $tip = $opts->{ref} || 'HEAD';
- my ($last_commit, $lx, $xlog);
- my $git = $self->{git};
+ my ($self, $opt) = @_;
+ my $tip = $opt->{ref} || 'HEAD';
+ my $git = $self->{ibx}->git;
+ $self->{batch_bytes} = $opt->{batch_size} // $BATCH_BYTES;
$git->batch_prepare;
- my $pr = $opts->{-progress};
-
+ my $pr = $opt->{-progress};
+ my $sync = { reindex => $opt->{reindex}, -opt => $opt };
my $xdb = $self->begin_txn_lazy;
+ $self->{oidx}->rethread_prepare($opt);
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 $dbh;
+ if ($sync->{reindex}) {
+ my $last = $mm->last_commit;
+ if ($last) {
+ $tip = $last;
+ } else {
+ # somebody just blindly added --reindex when indexing
+ # for the first time, allow it:
+ undef $sync->{reindex};
}
- };
-
- $dbh->begin_work;
- read_log($self, $xlog, *index_both, *unindex_both, $cb);
+ }
+ my $last_commit = _last_x_commit($self, $mm);
+ my $lx = reindex_from($sync->{reindex}, $last_commit);
+ my $range = $lx eq '' ? $tip : "$lx..$tip";
+ $pr->("counting changes\n\t$range ... ") if $pr;
+ my $stk = prepare_stack($self, $sync, $range);
+ $sync->{ntodo} = $stk ? $stk->num_records : 0;
+ $pr->("$sync->{ntodo}\n") if $pr; # continue previous line
+ process_stack($self, $sync, $stk);
}
sub DESTROY {
$_[0]->{lockfh} = undef;
}
-# remote_* subs are only used by SearchIdxPart
-sub remote_commit {
+sub _begin_txn {
my ($self) = @_;
- if (my $w = $self->{w}) {
- print $w "commit\n" or die "failed to write commit: $!";
- } else {
- $self->commit_txn_lazy;
- }
+ my $xdb = $self->{xdb} || idx_acquire($self);
+ $self->{oidx}->begin_lazy if $self->{oidx};
+ $xdb->begin_transaction if $xdb;
+ $self->{txn} = 1;
+ $xdb;
}
-sub remote_close {
+sub begin_txn_lazy {
my ($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};
- }
+ $self->{ibx}->with_umask(\&_begin_txn, $self) if !$self->{txn};
}
-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, $mid);
+# store 'indexlevel=medium' in v2 shard=0 and v1 (only one shard)
+# This metadata is read by Admin::detect_indexlevel:
+sub set_metadata_once {
+ my ($self) = @_;
+
+ return if $self->{shard}; # only continue if undef or 0, not >0
+ my $xdb = $self->{xdb};
+
+ if (delete($self->{-set_has_threadid_once})) {
+ $xdb->set_metadata('has_threadid', '1');
+ }
+ if (delete($self->{-set_indexlevel_once})) {
+ my $level = $xdb->get_metadata('indexlevel');
+ if (!$level || $level ne 'medium') {
+ $xdb->set_metadata('indexlevel', 'medium');
+ }
+ }
+ if (delete($self->{-set_skip_docdata_once})) {
+ $xdb->get_metadata('skip_docdata') or
+ $xdb->set_metadata('skip_docdata', '1');
}
}
-sub begin_txn_lazy {
+sub _commit_txn {
my ($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;
- });
+ if (my $xdb = $self->{xdb}) {
+ set_metadata_once($self);
+ $xdb->commit_transaction;
+ }
+ $self->{oidx}->commit_lazy if $self->{oidx};
}
sub commit_txn_lazy {
my ($self) = @_;
- delete $self->{txn} or return;
- $self->{-inbox}->with_umask(sub {
- if (my $xdb = $self->{xdb}) {
-
- # store 'indexlevel=medium' in v2 shard=0 and
- # v1 (only one shard)
- # This metadata is read by Admin::detect_indexlevel:
- if (!$self->{shard} # undef or 0, not >0
- && $self->{indexlevel} eq 'medium') {
- $xdb->set_metadata('indexlevel', 'medium');
- }
-
- $xdb->commit_transaction;
- }
- $self->{over}->commit_lazy if $self->{over};
- });
+ delete($self->{txn}) and
+ $self->{ibx}->with_umask(\&_commit_txn, $self);
}
sub worker_done {