#
# Indexes mail with Xapian and our (SQLite-based) ::Msgmap for use
# with the web and NNTP interfaces. This index maintains thread
-# relationships for use by Mail::Thread. This writes to the search
-# index.
+# relationships for use by PublicInbox::SearchThread.
+# This writes to the search index.
package PublicInbox::SearchIdx;
use strict;
use warnings;
use Fcntl qw(:flock :DEFAULT);
-use Email::MIME;
+use PublicInbox::MIME;
use Email::MIME::ContentType;
$Email::MIME::ContentType::STRICT_PARAMS = 0;
use base qw(PublicInbox::Search);
use PublicInbox::MID qw/mid_clean id_compress mid_mime/;
use PublicInbox::MsgIter;
use Carp qw(croak);
+use POSIX qw(strftime);
require PublicInbox::Git;
-*xpfx = *PublicInbox::Search::xpfx;
-use constant MAX_MID_SIZE => 244; # max term size - 1 in Xapian
use constant {
+ MAX_MID_SIZE => 244, # max term size - 1 in Xapian
PERM_UMASK => 0,
OLD_PERM_GROUP => 1,
OLD_PERM_EVERYBODY => 2,
PERM_GROUP => 0660,
PERM_EVERYBODY => 0664,
+ BATCH_BYTES => 1_000_000,
};
sub new {
require File::Path;
_lock_acquire($self);
File::Path::mkpath($dir);
- $self->{batch_size} = 100;
$flag = Search::Xapian::DB_CREATE_OR_OPEN;
}
$self->{xdb} = Search::Xapian::WritableDatabase->new($dir, $flag);
close $lockfh or die "close failed: $!\n";
}
-sub add_val {
+sub add_val ($$$) {
my ($doc, $col, $num) = @_;
$num = Search::Xapian::sortable_serialise($num);
$doc->add_value($col, $num);
}
+sub add_values ($$$) {
+ my ($smsg, $bytes, $num) = @_;
+
+ my $ts = $smsg->ts;
+ my $doc = $smsg->{doc};
+ add_val($doc, &PublicInbox::Search::TS, $ts);
+
+ defined($num) and add_val($doc, &PublicInbox::Search::NUM, $num);
+
+ defined($bytes) and add_val($doc, &PublicInbox::Search::BYTES, $bytes);
+
+ add_val($doc, &PublicInbox::Search::LINES,
+ $smsg->{mime}->body_raw =~ tr!\n!\n!);
+
+ my $yyyymmdd = strftime('%Y%m%d', gmtime($ts));
+ add_val($doc, PublicInbox::Search::YYYYMMDD, $yyyymmdd);
+}
+
+sub index_users ($$) {
+ my ($tg, $smsg) = @_;
+
+ my $from = $smsg->from;
+ my $to = $smsg->to;
+ my $cc = $smsg->cc;
+
+ $tg->index_text($from, 1, 'A'); # A - author
+ $tg->increase_termpos;
+ $tg->index_text($to, 1, 'XTO') if $to ne '';
+ $tg->increase_termpos;
+ $tg->index_text($cc, 1, 'XCC') if $cc ne '';
+ $tg->increase_termpos;
+}
+
+sub index_body ($$$) {
+ my ($tg, $lines, $inc) = @_;
+ $tg->index_text(join("\n", @$lines), $inc, $inc ? 'XNQ' : 'XQUOT');
+ @$lines = ();
+ $tg->increase_termpos;
+}
+
sub add_message {
my ($self, $mime, $bytes, $num, $blob) = @_; # mime = Email::MIME object
my $db = $self->{xdb};
my ($doc_id, $old_tid);
my $mid = mid_clean(mid_mime($mime));
- my $ct_msg = $mime->header('Content-Type') || 'text/plain';
eval {
die 'Message-ID too long' if length($mid) > MAX_MID_SIZE;
if ($smsg) {
# convert a ghost to a regular message
# it will also clobber any existing regular message
- $doc_id = $smsg->doc_id;
+ $doc_id = $smsg->{doc_id};
$old_tid = $smsg->thread_id;
}
$smsg = PublicInbox::SearchMsg->new($mime);
my $doc = $smsg->{doc};
- $doc->add_term(xpfx('mid') . $mid);
+ $doc->add_term('Q' . $mid);
my $subj = $smsg->subject;
if ($subj ne '') {
my $path = $self->subject_path($subj);
- $doc->add_term(xpfx('path') . id_compress($path));
+ $doc->add_term('XPATH' . id_compress($path));
}
- add_val($doc, &PublicInbox::Search::TS, $smsg->ts);
-
- defined($num) and
- add_val($doc, &PublicInbox::Search::NUM, $num);
-
- defined($bytes) and
- add_val($doc, &PublicInbox::Search::BYTES, $bytes);
-
- add_val($doc, &PublicInbox::Search::LINES,
- $mime->body_raw =~ tr!\n!\n!);
+ add_values($smsg, $bytes, $num);
my $tg = $self->term_generator;
$tg->set_document($doc);
$tg->index_text($subj, 1, 'S') if $subj;
$tg->increase_termpos;
- $tg->index_text($subj) if $subj;
- $tg->increase_termpos;
- $tg->index_text($smsg->from);
- $tg->increase_termpos;
+ index_users($tg, $smsg);
msg_iter($mime, sub {
my ($part, $depth, @idx) = @{$_[0]};
- my $ct = $part->content_type || $ct_msg;
+ my $ct = $part->content_type || 'text/plain';
+ my $fn = $part->filename;
+ if (defined $fn && $fn ne '') {
+ $tg->index_text($fn, 1, 'XFN');
+ }
- # account for filter bugs...
- $ct =~ m!\btext/plain\b!i or return;
+ return if $ct =~ m!\btext/x?html\b!i;
+
+ my $s = eval { $part->body_str };
+ if ($@) {
+ if ($ct =~ m!\btext/plain\b!i) {
+ # Try to assume UTF-8 because Alpine
+ # seems to do wacky things and set
+ # charset=X-UNKNOWN
+ $part->charset_set('UTF-8');
+ $s = eval { $part->body_str };
+ $s = $part->body if $@;
+ }
+ }
+ defined $s or return;
my (@orig, @quot);
my $body = $part->body;
- $part->body_set('');
my @lines = split(/\n/, $body);
while (defined(my $l = shift @lines)) {
- if ($l =~ /^\s*>/) {
+ if ($l =~ /^>/) {
+ index_body($tg, \@orig, 1) if @orig;
push @quot, $l;
} else {
+ index_body($tg, \@quot, 0) if @quot;
push @orig, $l;
}
}
- if (@quot) {
- $tg->index_text(join("\n", @quot), 0);
- @quot = ();
- $tg->increase_termpos;
- }
- if (@orig) {
- $tg->index_text(join("\n", @orig));
- @orig = ();
- $tg->increase_termpos;
- }
+ index_body($tg, \@quot, 0) if @quot;
+ index_body($tg, \@orig, 1) if @orig;
});
link_message($self, $smsg, $old_tid);
- $tg->index_text($mid, 1);
+ $tg->index_text($mid, 1, 'XMID');
$doc->set_data($smsg->to_doc_data($blob));
if (my $altid = $self->{-altid}) {
my ($self, $smsg, $old_tid) = @_;
my $doc = $smsg->{doc};
my $mid = $smsg->mid;
- my $mime = $smsg->mime;
+ my $mime = $smsg->{mime};
my $hdr = $mime->header_obj;
- my $refs = $hdr->header_raw('References');
- my @refs = $refs ? ($refs =~ /<([^>]+)>/g) : ();
- if (my $irt = $hdr->header_raw('In-Reply-To')) {
- # last References should be $irt
- # we will de-dupe later
- push @refs, mid_clean($irt);
- }
+
+ # 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) {
push @refs, $ref;
}
}
+
if (@refs) {
$smsg->{references} = '<'.join('> <', @refs).'>';
merge_threads($self, $tid, $ptid);
}
} else {
- $tid = $self->next_thread_id;
+ $tid = defined $old_tid ? $old_tid : $self->next_thread_id;
}
- $doc->add_term(xpfx('thread') . $tid);
+ $doc->add_term('G' . $tid);
}
sub index_blob {
my $str = $git->cat_file($blob, $sizeref);
# fixup bugs from import:
$$str =~ s/\A[\r\n]*From [^\r\n]*\r?\n//s;
- Email::MIME->new($str);
+ PublicInbox::MIME->new($str);
};
$@ ? undef : $mime;
}
with_umask($self, sub { $self->_index_sync($opts) });
}
+sub batch_adjust ($$$$) {
+ my ($max, $bytes, $batch_cb, $latest) = @_;
+ $$max -= $bytes;
+ if ($$max <= 0) {
+ $$max = BATCH_BYTES;
+ $batch_cb->($latest, 1);
+ }
+}
+
sub rlog {
my ($self, $log, $add_cb, $del_cb, $batch_cb) = @_;
my $hex = '[a-f0-9]';
my $git = $self->{git};
my $latest;
my $bytes;
- my $max = $self->{batch_size}; # may be undef
+ my $max = BATCH_BYTES;
local $/ = "\n";
my $line;
while (defined($line = <$log>)) {
if ($line =~ /$addmsg/o) {
my $blob = $1;
my $mime = do_cat_mail($git, $blob, \$bytes) or next;
+ batch_adjust(\$max, $bytes, $batch_cb, $latest);
$add_cb->($self, $mime, $bytes, $blob);
} elsif ($line =~ /$delmsg/o) {
my $blob = $1;
- my $mime = do_cat_mail($git, $blob) or next;
+ my $mime = do_cat_mail($git, $blob, \$bytes) or next;
+ batch_adjust(\$max, $bytes, $batch_cb, $latest);
$del_cb->($self, $mime);
} elsif ($line =~ /^commit ($h40)/o) {
- if (defined $max && --$max <= 0) {
- $max = $self->{batch_size};
- $batch_cb->($latest, 1);
- }
$latest = $1;
}
}
my $mm = _msgmap_init($self);
my $dbh = $mm->{dbh} if $mm;
+ my $mm_only;
my $cb = sub {
my ($commit, $more) = @_;
if ($dbh) {
$mm->last_commit($commit) if $commit;
$dbh->commit;
}
- $xdb->set_metadata($mkey, $commit) if $mkey && $commit;
- $xdb->commit_transaction;
- $xdb = _xdb_release($self);
+ if (!$mm_only) {
+ $xdb->set_metadata($mkey, $commit) if $mkey && $commit;
+ $xdb->commit_transaction;
+ $xdb = _xdb_release($self);
+ }
# let another process do some work... <
if ($more) {
- $xdb = _xdb_acquire($self);
- $xdb->begin_transaction;
+ if (!$mm_only) {
+ $xdb = _xdb_acquire($self);
+ $xdb->begin_transaction;
+ }
$dbh->begin_work if $dbh;
}
};
my $mkey_prev = $mkey;
$mkey = undef; # ignore xapian, for now
my $mlog = _git_log($self, $r);
+ $mm_only = 1;
rlog($self, $mlog, *index_mm, *unindex_mm, $cb);
- $mlog = undef;
+ $mm_only = $mlog = undef;
# now deal with Xapian
$mkey = $mkey_prev;
$dbh = undef;
- $xdb = _xdb_acquire($self);
- $xdb->begin_transaction;
rlog($self, $xlog, *index_mm2, *unindex_mm2, $cb);
}
} else {
my $tid = $self->next_thread_id;
my $doc = Search::Xapian::Document->new;
- $doc->add_term(xpfx('mid') . $mid);
- $doc->add_term(xpfx('thread') . $tid);
- $doc->add_term(xpfx('type') . 'ghost');
+ $doc->add_term('Q' . $mid);
+ $doc->add_term('G' . $tid);
+ $doc->add_term('T' . 'ghost');
my $smsg = PublicInbox::SearchMsg->wrap($doc, $mid);
$self->{xdb}->add_document($doc);
sub merge_threads {
my ($self, $winner_tid, $loser_tid) = @_;
return if $winner_tid == $loser_tid;
- my ($head, $tail) = $self->find_doc_ids('thread', $loser_tid);
- my $thread_pfx = xpfx('thread');
+ my ($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);
- $doc->remove_term($thread_pfx . $loser_tid);
- $doc->add_term($thread_pfx . $winner_tid);
+ $doc->remove_term('G' . $loser_tid);
+ $doc->add_term('G' . $winner_tid);
$db->replace_document($docid, $doc);
}
}
my $rv = eval { $cb->() };
my $err = $@;
umask $old;
- die $err if $@;
+ die $err if $err;
$rv;
}