X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FSearchIdx.pm;h=69b7a6f6964bef876cfb5e41a62d02764b678b19;hb=1f15ff775a967794ff3e409722b72e5684f2c0a2;hp=d63dd7c742b4c21ef9420d810954df3e8332f45e;hpb=3fc59df0d633a17e0c5e43d633d12e8772c06ec3;p=public-inbox.git

diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm
index d63dd7c7..69b7a6f6 100644
--- a/lib/PublicInbox/SearchIdx.pm
+++ b/lib/PublicInbox/SearchIdx.pm
@@ -19,17 +19,37 @@ 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,
+	DEBUG => !!$ENV{DEBUG},
 };
 
+my %GIT_ESC = (
+	a => "\a",
+	b => "\b",
+	f => "\f",
+	n => "\n",
+	r => "\r",
+	t => "\t",
+	v => "\013",
+);
+
+sub git_unquote ($) {
+	my ($s) = @_;
+	return $s unless ($s =~ /\A"(.*)"\z/);
+	$s = $1;
+	$s =~ s/\\([abfnrtv])/$GIT_ESC{$1}/g;
+	$s =~ s/\\([0-7]{1,3})/chr(oct($1))/ge;
+	$s;
+}
+
 sub new {
 	my ($class, $inbox, $creat) = @_;
 	my $git_dir = $inbox;
@@ -72,7 +92,6 @@ sub _xdb_acquire {
 		require File::Path;
 		_lock_acquire($self);
 		File::Path::mkpath($dir);
-		$self->{batch_size} = 100;
 		$flag = Search::Xapian::DB_CREATE_OR_OPEN;
 	}
 	$self->{xdb} = Search::Xapian::WritableDatabase->new($dir, $flag);
@@ -135,11 +154,108 @@ sub index_users ($$) {
 	$tg->increase_termpos;
 }
 
+sub index_text_inc ($$$) {
+	my ($tg, $text, $pfx) = @_;
+	$tg->index_text($text, 1, $pfx);
+	$tg->increase_termpos;
+}
+
+sub index_old_diff_fn {
+	my ($tg, $seen, $fa, $fb) = @_;
+
+	# no renames or space support for traditional diffs,
+	# find the number of leading common paths to strip:
+	my @fa = split('/', $fa);
+	my @fb = split('/', $fb);
+	while (scalar(@fa) && scalar(@fb)) {
+		$fa = join('/', @fa);
+		$fb = join('/', @fb);
+		if ($fa eq $fb) {
+			index_text_inc($tg, $fa,'XDFN') unless $seen->{$fa}++;
+			return 1;
+		}
+		shift @fa;
+		shift @fb;
+	}
+	0;
+}
+
+sub index_diff ($$$) {
+	my ($tg, $lines, $doc) = @_;
+	my %seen;
+	my $in_diff;
+	foreach (@$lines) {
+		if ($in_diff && s/^ //) { # diff context
+			index_text_inc($tg, $_, 'XDFCTX');
+		} 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];
+			index_text_inc($tg, $fn, 'XDFN') unless $seen{$fn}++;
+			$fn = (split('/', git_unquote($fb), 2))[1];
+			index_text_inc($tg, $fn, 'XDFN') unless $seen{$fn}++;
+			$in_diff = 1;
+		# traditional diff:
+		} elsif (m/^diff -(.+) (\S+) (\S+)$/) {
+			my ($opt, $fa, $fb) = ($1, $2, $3);
+			# only support unified:
+			next unless $opt =~ /[uU]/;
+			$in_diff = index_old_diff_fn($tg, \%seen, $fa, $fb);
+		} elsif (m!^--- ("?a/.+)!) {
+			my $fn = (split('/', git_unquote($1), 2))[1];
+			index_text_inc($tg, $fn, 'XDFN') unless $seen{$fn}++;
+			$in_diff = 1;
+		} elsif (m!^\+\+\+ ("?b/.+)!)  {
+			my $fn = (split('/', git_unquote($1), 2))[1];
+			index_text_inc($tg, $fn, 'XDFN') unless $seen{$fn}++;
+			$in_diff = 1;
+		} elsif (/^--- (\S+)/) {
+			$in_diff = $1;
+		} elsif (defined $in_diff && /^\+\+\+ (\S+)/) {
+			$in_diff = index_old_diff_fn($tg, \%seen, $in_diff, $1);
+		} elsif ($in_diff && s/^\+//) { # diff added
+			index_text_inc($tg, $_, 'XDFB');
+		} elsif ($in_diff && s/^-//) { # diff removed
+			index_text_inc($tg, $_, 'XDFA');
+		} elsif (m!^index ([a-f0-9]+)\.\.([a-f0-9]+)!) {
+			my ($ba, $bb) = ($1, $2);
+			index_git_blob_id($doc, 'XDFPRE', $ba);
+			index_git_blob_id($doc, 'XDFPOST', $bb);
+			$in_diff = 1;
+		} elsif (/^@@ (?:\S+) (?:\S+) @@\s*$/) {
+			# traditional diff w/o -p
+		} elsif (/^@@ (?:\S+) (?:\S+) @@\s*(\S+.*)$/) {
+			# hunk header context
+			index_text_inc($tg, $1, 'XDFHH');
+		# ignore the following lines:
+		} elsif (/^(?:dis)similarity index/) {
+		} elsif (/^(?:old|new) mode/) {
+		} elsif (/^(?:deleted|new) file mode/) {
+		} elsif (/^(?:copy|rename) (?:from|to) /) {
+		} elsif (/^(?:dis)?similarity index /) {
+		} elsif (/^\\ No newline at end of file/) {
+		} elsif (/^Binary files .* differ/) {
+		} elsif ($_ eq '') {
+			$in_diff = undef;
+		} else {
+			warn "non-diff line: $_\n" if DEBUG && $_ ne '';
+			$in_diff = undef;
+		}
+	}
+}
+
 sub index_body ($$$) {
-	my ($tg, $lines, $inc) = @_;
-	$tg->index_text(join("\n", @$lines), $inc, $inc ? 'XNQ' : 'XQUOT');
-	@$lines = ();
+	my ($tg, $lines, $doc) = @_;
+	my $txt = join("\n", @$lines);
+	$tg->index_text($txt, !!$doc, $doc ? 'XNQ' : 'XQUOT');
 	$tg->increase_termpos;
+	# does it look like a diff?
+	if ($doc && $txt =~ /^(?:diff|---|\+\+\+) /ms) {
+		$txt = undef;
+		index_diff($tg, $lines, $doc);
+	}
+	@$lines = ();
 }
 
 sub add_message {
@@ -160,12 +276,12 @@ sub add_message {
 		}
 		$smsg = PublicInbox::SearchMsg->new($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_values($smsg, $bytes, $num);
@@ -206,7 +322,7 @@ sub add_message {
 			my @lines = split(/\n/, $body);
 			while (defined(my $l = shift @lines)) {
 				if ($l =~ /^>/) {
-					index_body($tg, \@orig, 1) if @orig;
+					index_body($tg, \@orig, $doc) if @orig;
 					push @quot, $l;
 				} else {
 					index_body($tg, \@quot, 0) if @quot;
@@ -214,7 +330,7 @@ sub add_message {
 				}
 			}
 			index_body($tg, \@quot, 0) if @quot;
-			index_body($tg, \@orig, 1) if @orig;
+			index_body($tg, \@orig, $doc) if @orig;
 		});
 
 		link_message($self, $smsg, $old_tid);
@@ -250,8 +366,12 @@ sub remove_message {
 	$mid = mid_clean($mid);
 
 	eval {
-		$doc_id = $self->find_unique_doc_id('mid', $mid);
-		$db->delete_document($doc_id) if defined $doc_id;
+		$doc_id = $self->find_unique_doc_id('Q' . $mid);
+		if (defined $doc_id) {
+			$db->delete_document($doc_id);
+		} else {
+			warn "cannot remove non-existent <$mid>\n";
+		}
 	};
 
 	if ($@) {
@@ -291,13 +411,12 @@ sub link_message {
 	my $mid = $smsg->mid;
 	my $mime = $smsg->{mime};
 	my $hdr = $mime->header_obj;
-	my $refs = $hdr->header_raw('References');
-	my @refs = $refs ? ($refs =~ /<([^>]+)>/g) : ();
-	my $irt = $hdr->header_raw('In-Reply-To');
-	if (defined $irt) {
-		$irt = mid_clean($irt);
-		$irt = undef if $mid eq $irt;
-	}
+
+	# last References should be IRT, but some mail clients do things
+	# out of order, so trust IRT over References iff IRT exists
+	my @refs = ($hdr->header_raw('References'),
+			$hdr->header_raw('In-Reply-To'));
+	@refs = ((join(' ', @refs)) =~ /<([^>]+)>/g);
 
 	my $tid;
 	if (@refs) {
@@ -305,15 +424,6 @@ sub link_message {
 		my @orig_refs = @refs;
 		@refs = ();
 
-		if (defined $irt) {
-			# to check MAX_MID_SIZE
-			push @orig_refs, $irt;
-
-			# below, we will ensure IRT (if specified)
-			# is the last References
-			$uniq{$irt} = 1;
-		}
-
 		# prevent circular references via References: here:
 		foreach my $ref (@orig_refs) {
 			if (length($ref) > MAX_MID_SIZE) {
@@ -325,10 +435,6 @@ sub link_message {
 		}
 	}
 
-	# last References should be IRT, but some mail clients do things
-	# out of order, so trust IRT over References iff IRT exists
-	push @refs, $irt if defined $irt;
-
 	if (@refs) {
 		$smsg->{references} = '<'.join('> <', @refs).'>';
 
@@ -344,9 +450,9 @@ sub link_message {
 			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 {
@@ -354,6 +460,16 @@ sub index_blob {
 	$self->add_message($mime, $bytes, $num, $blob);
 }
 
+sub index_git_blob_id {
+	my ($doc, $pfx, $objid) = @_;
+
+	my $len = length($objid);
+	for (my $len = length($objid); $len >= 7; ) {
+		$doc->add_term($pfx.$objid);
+		$objid = substr($objid, 0, --$len);
+	}
+}
+
 sub unindex_blob {
 	my ($self, $mime) = @_;
 	my $mid = eval { mid_clean(mid_mime($mime)) };
@@ -410,6 +526,15 @@ sub index_sync {
 	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]';
@@ -419,23 +544,21 @@ sub rlog {
 	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;
 		}
 	}
@@ -556,9 +679,9 @@ sub create_ghost {
 
 	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);
@@ -569,15 +692,14 @@ sub create_ghost {
 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);
 	}
 }
@@ -634,7 +756,7 @@ sub with_umask {
 	my $rv = eval { $cb->() };
 	my $err = $@;
 	umask $old;
-	die $err if $@;
+	die $err if $err;
 	$rv;
 }