-# 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
#
use base qw(PublicInbox::Search PublicInbox::Lock);
use PublicInbox::MIME;
use PublicInbox::InboxWritable;
-use PublicInbox::MID qw/mid_clean id_compress mid_mime mids_for_index/;
+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, $DB_OPEN);
use constant {
BATCH_BYTES => defined($ENV{XAPIAN_FLUSH_THRESHOLD}) ?
0x7fffffff : 1_000_000,
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) {
-inbox => $ibx,
git => $ibx->git,
-altid => $altid,
- version => $version,
+ ibx_ver => $version,
indexlevel => $indexlevel,
}, $class;
$ibx->umask_prepare;
undef;
}
+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;
+}
+
sub _xdb_acquire {
my ($self) = @_;
my $flag;
my $dir = $self->xdir;
if (need_xapian($self)) {
croak 'already acquired' if $self->{xdb};
- PublicInbox::Search::load_xapian();
- require Search::Xapian::WritableDatabase;
- $flag = $self->{creat} ?
- Search::Xapian::DB_CREATE_OR_OPEN() :
- Search::Xapian::DB_OPEN();
+ load_xapian_writable();
+ $flag = $self->{creat} ? $DB_CREATE_OR_OPEN : $DB_OPEN;
}
if ($self->{creat}) {
require File::Path;
}
}
return unless defined $flag;
- my $xdb = eval { Search::Xapian::WritableDatabase->new($dir, $flag) };
+ my $xdb = eval { ($X->{WritableDatabase})->new($dir, $flag) };
if ($@) {
die "Failed opening $dir: ", $@;
}
sub add_val ($$$) {
my ($doc, $col, $num) = @_;
- $num = Search::Xapian::sortable_serialise($num);
+ $num = sortable_serialise($num);
$doc->add_value($col, $num);
}
-sub index_text ($$$$)
-{
- my ($self, $field, $n, $text) = @_;
- my $tg = $self->term_generator;
+sub term_generator ($) { # write-only
+ my ($self) = @_;
+
+ $self->{term_generator} //= do {
+ my $tg = $X->{TermGenerator}->new;
+ $tg->set_stemmer($self->stemmer);
+ $tg;
+ }
+}
+
+sub index_text ($$$$) {
+ my ($self, $text, $wdf_inc, $prefix) = @_;
+ my $tg = term_generator($self); # man Search::Xapian::TermGenerator
if ($self->{indexlevel} eq 'full') {
- $tg->index_text($field, $n, $text);
+ $tg->index_text($text, $wdf_inc, $prefix);
$tg->increase_termpos;
} else {
- $tg->index_text_without_positions($field, $n, $text);
+ $tg->index_text_without_positions($text, $wdf_inc, $prefix);
}
}
my $to = $smsg->to;
my $cc = $smsg->cc;
- $self->index_text($from, 1, 'A'); # A - author
- $self->index_text($to, 1, 'XTO') if $to ne '';
- $self->index_text($cc, 1, 'XCC') if $cc ne '';
+ index_text($self, $from, 1, 'A'); # A - author
+ index_text($self, $to, 1, 'XTO') if $to ne '';
+ index_text($self, $cc, 1, 'XCC') if $cc ne '';
}
sub index_diff_inc ($$$$) {
my ($self, $text, $pfx, $xnq) = @_;
if (@$xnq) {
- $self->index_text(join("\n", @$xnq), 1, 'XNQ');
+ index_text($self, join("\n", @$xnq), 1, 'XNQ');
@$xnq = ();
}
- $self->index_text($text, 1, $pfx);
+ index_text($self, $text, 1, $pfx);
}
sub index_old_diff_fn {
$fb = join('/', @fb);
if ($fa eq $fb) {
unless ($seen->{$fa}++) {
- $self->index_diff_inc($fa, 'XDFN', $xnq);
+ index_diff_inc($self, $fa, 'XDFN', $xnq);
}
return 1;
}
}
sub index_diff ($$$) {
- 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/.+)!) {
- my $fn = (split('/', git_unquote($1), 2))[1];
- $seen{$fn}++ or $self->index_diff_inc($fn, 'XDFN', $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!^\+\+\+ ("?b/.+)!) {
- my $fn = (split('/', git_unquote($1), 2))[1];
- $seen{$fn}++ or $self->index_diff_inc($fn, 'XDFN', $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 (/^--- (\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/ ||
/^Binary files .* differ/) {
push @xnq, $_;
} elsif ($_ eq '') {
- $in_diff = undef;
+ # 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 {
push @xnq, $_;
warn "non-diff line: $_\n" if DEBUG && $_ ne '';
}
}
- $self->index_text(join("\n", @xnq), 1, 'XNQ');
+ index_text($self, join("\n", @xnq), 1, 'XNQ');
}
sub index_body ($$$) {
- my ($self, $lines, $doc) = @_;
- my $txt = join("\n", @$lines);
+ my ($self, $txt, $doc) = @_;
if ($doc) {
# does it look like a diff?
if ($txt =~ /^(?:diff|---|\+\+\+) /ms) {
- $txt = undef;
- $self->index_diff($lines, $doc);
+ index_diff($self, $txt, $doc);
} else {
- $self->index_text($txt, 1, 'XNQ');
+ index_text($self, $txt, 1, 'XNQ');
}
} else {
- $self->index_text($txt, 0, 'XQUOT');
+ index_text($self, $txt, 0, 'XQUOT');
}
- @$lines = ();
}
-sub add_xapian ($$$$$) {
- my ($self, $mime, $num, $oid, $mids, $mid0) = @_;
- my $smsg = PublicInbox::SearchMsg->new($mime);
- my $doc = Search::Xapian::Document->new;
+sub index_xapian { # msg_iter callback
+ my ($part, $depth, @idx) = @{$_[0]};
+ my ($self, $doc) = @{$_[1]};
+ my $ct = $part->content_type || 'text/plain';
+ my $fn = $part->filename;
+ if (defined $fn && $fn ne '') {
+ index_text($self, $fn, 1, 'XFN');
+ }
+
+ my ($s, undef) = msg_part_text($part, $ct);
+ defined $s or return;
+
+ # split off quoted and unquoted blocks:
+ my @sections = split(/((?:^>[^\n]*\n)+)/sm, $s);
+ $part = $s = undef;
+ index_body($self, $_, /\A>/ ? 0 : $doc) for @sections;
+}
+
+sub add_xapian ($$$$) {
+ my ($self, $mime, $smsg, $mids) = @_;
+ $smsg->{mime} = $mime; # XXX dangerous
+ my $hdr = $mime->header_obj;
+ $smsg->{ds} = msg_datestamp($hdr, $self->{autime});
+ $smsg->{ts} = msg_timestamp($hdr, $self->{cotime});
+ 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);
- 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);
-
- msg_iter($mime, sub {
- my ($part, $depth, @idx) = @{$_[0]};
- my $ct = $part->content_type || 'text/plain';
- my $fn = $part->filename;
- if (defined $fn && $fn ne '') {
- $self->index_text($fn, 1, 'XFN');
- }
-
- 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;
- } else {
- $self->index_body(\@quot, 0) if @quot;
- push @orig, $l;
- }
- }
- $self->index_body(\@quot, 0) if @quot;
- $self->index_body(\@orig, $doc) if @orig;
- });
+ index_text($self, $subj, 1, 'S') if $subj;
+ index_users($self, $smsg);
+ msg_iter($mime, \&index_xapian, [ $self, $doc ]);
foreach my $mid (@$mids) {
- $self->index_text($mid, 1, 'XM');
+ 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);
- $self->index_text(join(' ', @long), 1, 'XM');
+ index_text($self, join(' ', @long), 1, 'XM');
}
}
- $smsg->{to} = $smsg->{cc} = '';
- PublicInbox::OverIdx::parse_references($smsg, $mid0, $mids);
- my $data = $smsg->to_doc_data($oid, $mid0);
+ $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) {
}
}
$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;
+ $self->{mm} //= eval {
+ require PublicInbox::Msgmap;
+ PublicInbox::Msgmap->new($self->{inboxdir}, 1);
+ };
}
sub add_message {
# mime = Email::MIME object
- my ($self, $mime, $bytes, $num, $oid, $mid0) = @_;
+ my ($self, $mime, $smsg) = @_;
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);
- }
+ $smsg //= bless { blob => '' }, 'PublicInbox::Smsg'; # test-only compat
+ $smsg->{mid} //= $mids->[0]; # v1 compatibility
+ $smsg->{num} //= do { # v1
+ _msgmap_init($self);
+ index_mm($self, $mime);
+ };
eval {
- if (need_xapian($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 $over = $self->{over}) { # v1 only
+ $over->add_overview($mime, $smsg, $self);
}
- 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;
+ $smsg->{num};
}
# returns begin and end PostingIterator
my ($head, $tail) = $self->find_doc_ids($termval);
return if $head == $tail;
my @ids;
- for (; $head != $tail && @ids < $batch_size; $head->inc) {
+ for (; $head != $tail && @ids < $batch_size; $head++) {
push @ids, $head->get_docid;
}
$cb->(\@ids);
batch_do($self, 'Q' . $mid, sub {
my ($ids) = @_;
$db->delete_document($_) for @$ids;
- $nr = scalar @$ids;
+ $nr += scalar @$ids;
});
};
if ($@) {
# there is only ONE element in @delete unless we
# have bugs in our v2writable deduplication check
my @delete;
- for (; $head != $tail; $head->inc) {
+ for (; $head != $tail; $head++) {
my $docid = $head->get_docid;
my $doc = $db->get_document($docid);
- my $smsg = PublicInbox::SearchMsg->wrap($mid);
+ my $smsg = PublicInbox::Smsg->wrap($mid);
$smsg->load_expand($doc);
if ($smsg->{blob} eq $oid) {
push(@delete, $docid);
scalar(@delete);
}
-sub term_generator { # write-only
- my ($self) = @_;
-
- my $tg = $self->{term_generator};
- return $tg if $tg;
-
- $tg = Search::Xapian::TermGenerator->new;
- $tg->set_stemmer($self->stemmer);
-
- $self->{term_generator} = $tg;
-}
-
sub index_git_blob_id {
my ($doc, $pfx, $objid) = @_;
}
sub index_both {
- my ($self, $mime, $bytes, $blob) = @_;
+ my ($self, $mime, $smsg) = @_;
my $num = index_mm($self, $mime);
- add_message($self, $mime, $bytes, $num, $blob);
+ $smsg->{num} = $num;
+ add_message($self, $mime, $smsg);
}
sub unindex_both {
next;
}
my $mime = do_cat_mail($git, $blob, \$bytes) or next;
+ my $smsg = bless {}, 'PublicInbox::Smsg';
batch_adjust(\$max, $bytes, $batch_cb, $latest, ++$nr);
- $add_cb->($self, $mime, $bytes, $blob);
+ $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->{over}->{autime} = $self->{autime} = $1;
+ } elsif ($line =~ /^committer .*? ([0-9]+) [\-\+][0-9]+$/) {
+ $self->{over}->{cotime} = $self->{cotime} = $1;
}
}
close($log) or die "git log failed: \$?=$?";
$batch_cb->($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);
- };
-}
-
sub _git_log {
my ($self, $opts, $range) = @_;
my $git = $self->{git};
$self->{regen_down} = $high + $fcount;
}
- $git->popen(qw/log --no-notes --no-color --no-renames
+ $git->popen(qw/log --pretty=raw --no-notes --no-color --no-renames
--raw -r --no-abbrev/, $range);
}
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;
}