X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FSearchIdx.pm;h=63be68101b40c8ae7f4f8d8e39ee94492594a589;hb=3cda6050b7c8f73e7fd86f88efc5cd42d0c13f73;hp=87243268a8ad71aa6c85494a5c608fcbdfabd3a2;hpb=d51d7261fb75b9a2c378e3d46c6c370397e44c8f;p=public-inbox.git

diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm
index 87243268..63be6810 100644
--- a/lib/PublicInbox/SearchIdx.pm
+++ b/lib/PublicInbox/SearchIdx.pm
@@ -1,13 +1,20 @@
 # Copyright (C) 2015 all contributors <meta@public-inbox.org>
 # License: AGPLv3 or later (https://www.gnu.org/licenses/agpl-3.0.txt)
 # based on notmuch, but with no concept of folders, files or flags
+#
+# 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.
 package PublicInbox::SearchIdx;
 use strict;
 use warnings;
 use base qw(PublicInbox::Search);
-use PublicInbox::MID qw/mid_clean mid_compress/;
+use PublicInbox::MID qw/mid_clean id_compress mid_mime/;
+require PublicInbox::Git;
 *xpfx = *PublicInbox::Search::xpfx;
 
+use constant MAX_MID_SIZE => 244; # max term size - 1 in Xapian
 use constant {
 	PERM_UMASK => 0,
 	OLD_PERM_GROUP => 1,
@@ -36,16 +43,23 @@ sub new {
 	$self;
 }
 
+sub add_val {
+	my ($doc, $col, $num) = @_;
+	$num = Search::Xapian::sortable_serialise($num);
+	$doc->add_value($col, $num);
+}
+
 sub add_message {
-	my ($self, $mime) = @_; # mime = Email::MIME object
+	my ($self, $mime, $bytes, $num) = @_; # mime = Email::MIME object
 	my $db = $self->{xdb};
 
 	my $doc_id;
-	my $mid = mid_clean($mime->header('Message-ID'));
+	my $mid = mid_clean(mid_mime($mime));
 	my $was_ghost = 0;
 	my $ct_msg = $mime->header('Content-Type') || 'text/plain';
 
 	eval {
+		die 'Message-ID too long' if length($mid) > MAX_MID_SIZE;
 		my $smsg = $self->lookup_message($mid);
 		my $doc;
 
@@ -74,14 +88,20 @@ sub add_message {
 		my $subj = $smsg->subject;
 
 		if ($subj ne '') {
-			$doc->add_term(xpfx('subject') . $subj);
-
 			my $path = $self->subject_path($subj);
-			$doc->add_term(xpfx('path') . mid_compress($path));
+			$doc->add_term(xpfx('path') . id_compress($path));
 		}
 
-		my $ts = Search::Xapian::sortable_serialise($smsg->ts);
-		$doc->add_value(PublicInbox::Search::TS, $ts);
+		add_val($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!);
 
 		my $tg = $self->term_generator;
 
@@ -91,7 +111,7 @@ sub add_message {
 		$tg->index_text($subj) if $subj;
 		$tg->increase_termpos;
 
-		$tg->index_text($smsg->from->format);
+		$tg->index_text($smsg->from);
 		$tg->increase_termpos;
 
 		$mime->walk_parts(sub {
@@ -202,9 +222,10 @@ sub link_message_to_parents {
 	my $doc = $smsg->{doc};
 	my $mid = $smsg->mid;
 	my $mime = $smsg->mime;
-	my $refs = $mime->header('References');
+	my $hdr = $mime->header_obj;
+	my $refs = $hdr->header_raw('References');
 	my @refs = $refs ? ($refs =~ /<([^>]+)>/g) : ();
-	if (my $irt = $mime->header('In-Reply-To')) {
+	if (my $irt = $hdr->header_raw('In-Reply-To')) {
 		# last References should be $irt
 		# we will de-dupe later
 		push @refs, mid_clean($irt);
@@ -218,13 +239,16 @@ sub link_message_to_parents {
 
 		# prevent circular references via References: here:
 		foreach my $ref (@orig_refs) {
+			if (length($ref) > MAX_MID_SIZE) {
+				warn "References: <$ref> too long, ignoring\n";
+			}
 			next if $uniq{$ref};
 			$uniq{$ref} = 1;
 			push @refs, $ref;
 		}
 	}
 	if (@refs) {
-		$smsg->{references_sorted} = '<'.join('><', @refs).'>';
+		$smsg->{references} = '<'.join('> <', @refs).'>';
 
 		# first ref *should* be the thread root,
 		# but we can never trust clients to do the right thing
@@ -245,30 +269,42 @@ sub link_message_to_parents {
 }
 
 sub index_blob {
-	my ($self, $git, $mime) = @_;
-	$self->add_message($mime);
+	my ($self, $git, $mime, $bytes, $num) = @_;
+	$self->add_message($mime, $bytes, $num);
 }
 
 sub unindex_blob {
 	my ($self, $git, $mime) = @_;
-	my $mid = mid_clean($mime->header('Message-ID'));
+	my $mid = eval { mid_clean(mid_mime($mime)) };
 	$self->remove_message($mid) if defined $mid;
 }
 
 sub index_mm {
 	my ($self, $git, $mime) = @_;
-	$self->{mm}->mid_insert(mid_clean($mime->header('Message-ID')));
+	$self->{mm}->mid_insert(mid_clean(mid_mime($mime)));
 }
 
 sub unindex_mm {
 	my ($self, $git, $mime) = @_;
-	$self->{mm}->mid_delete(mid_clean($mime->header('Message-ID')));
+	$self->{mm}->mid_delete(mid_clean(mid_mime($mime)));
 }
 
-sub index_both {
+sub index_mm2 {
+	my ($self, $git, $mime, $bytes) = @_;
+	my $num = $self->{mm}->num_for(mid_clean(mid_mime($mime)));
+	index_blob($self, $git, $mime, $bytes, $num);
+}
+
+sub unindex_mm2 {
 	my ($self, $git, $mime) = @_;
-	index_blob($self, $git, $mime);
-	index_mm($self, $git, $mime);
+	$self->{mm}->mid_delete(mid_clean(mid_mime($mime)));
+	unindex_blob($self, $git, $mime);
+}
+
+sub index_both {
+	my ($self, $git, $mime, $bytes) = @_;
+	my $num = index_mm($self, $git, $mime);
+	index_blob($self, $git, $mime, $bytes, $num);
 }
 
 sub unindex_both {
@@ -278,9 +314,9 @@ sub unindex_both {
 }
 
 sub do_cat_mail {
-	my ($git, $blob) = @_;
+	my ($git, $blob, $sizeref) = @_;
 	my $mime = eval {
-		my $str = $git->cat_file($blob);
+		my $str = $git->cat_file($blob, $sizeref);
 		Email::MIME->new($str);
 	};
 	$@ ? undef : $mime;
@@ -297,19 +333,15 @@ sub rlog {
 	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_dir = $self->{git_dir};
-	require PublicInbox::GitCatFile;
-	my $git = PublicInbox::GitCatFile->new($git_dir);
-	my @cmd = ('git', "--git-dir=$git_dir", "log",
-		    qw/--reverse --no-notes --no-color --raw -r --no-abbrev/,
-		    $range);
+	my $git = PublicInbox::Git->new($self->{git_dir});
+	my $log = $git->popen(qw/log --reverse --no-notes --no-color
+				--raw -r --no-abbrev/, $range);
 	my $latest;
-	my $pid = open(my $log, '-|', @cmd) or
-		die('open` '.join(' ', @cmd) . " pipe failed: $!\n");
-	while (my $line = <$log>) {
+	my $bytes;
+	while (defined(my $line = <$log>)) {
 		if ($line =~ /$addmsg/o) {
-			my $mime = do_cat_mail($git, $1) or next;
-			$add_cb->($self, $git, $mime);
+			my $mime = do_cat_mail($git, $1, \$bytes) or next;
+			$add_cb->($self, $git, $mime, $bytes);
 		} elsif ($line =~ /$delmsg/o) {
 			my $mime = do_cat_mail($git, $1) or next;
 			$del_cb->($self, $git, $mime);
@@ -317,7 +349,6 @@ sub rlog {
 			$latest = $1;
 		}
 	}
-	close $log;
 	$latest;
 }
 
@@ -354,11 +385,11 @@ sub _index_sync {
 			$mm->{dbh}->commit;
 			$mm->last_commit($lm) if defined $lm;
 
-			goto xapian_only;
+			$lx = $self->rlog($range, *index_mm2, *unindex_mm2);
+			$db->set_metadata('last_commit', $lx) if defined $lx;
 		}
 	} else {
 		# user didn't install DBD::SQLite and DBI
-xapian_only:
 		$lx = $self->rlog($range, *index_blob, *unindex_blob);
 		$db->set_metadata('last_commit', $lx) if defined $lx;
 	}
@@ -412,12 +443,9 @@ sub merge_threads {
 
 sub _read_git_config_perm {
 	my ($self) = @_;
-	my @cmd = ('git', "--git-dir=$self->{git_dir}",
-		   qw(config core.sharedRepository));
-	my $pid = open(my $fh, '-|', @cmd) or
-		die('open `'.join(' ', @cmd) . " pipe failed: $!\n");
+	my @cmd = qw(config core.sharedRepository);
+	my $fh = PublicInbox::Git->new($self->{git_dir})->popen(@cmd);
 	my $perm = <$fh>;
-	close $fh;
 	chomp $perm if defined $perm;
 	$perm;
 }