X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FSearchIdx.pm;h=30d3fe926a14cef02834bfe3511ac37022e14bee;hb=970eb1fd83b93c790d2faed6bf64a97d6d5fe126;hp=25452daec4280eae41a3d8f311c49bd2d5c0cbde;hpb=6ca633a1360a0974a8ebb117554a856022d797c6;p=public-inbox.git

diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm
index 25452dae..30d3fe92 100644
--- a/lib/PublicInbox/SearchIdx.pm
+++ b/lib/PublicInbox/SearchIdx.pm
@@ -4,13 +4,13 @@
 #
 # 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);
@@ -19,15 +19,15 @@ 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 {
@@ -72,7 +72,6 @@ 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);
@@ -117,7 +116,7 @@ sub add_values ($$$) {
 			$smsg->{mime}->body_raw =~ tr!\n!\n!);
 
 	my $yyyymmdd = strftime('%Y%m%d', gmtime($ts));
-	$doc->add_value(&PublicInbox::Search::YYYYMMDD, $yyyymmdd);
+	add_val($doc, PublicInbox::Search::YYYYMMDD, $yyyymmdd);
 }
 
 sub index_users ($$) {
@@ -135,13 +134,19 @@ sub index_users ($$) {
 	$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($mid) > MAX_MID_SIZE;
@@ -149,17 +154,17 @@ sub add_message {
 		if ($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_values($smsg, $bytes, $num);
@@ -174,34 +179,41 @@ sub add_message {
 
 		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 =~ /^>/) {
+					index_body($tg, \@orig, 1) if @orig;
 					push @quot, $l;
 				} else {
+					index_body($tg, \@quot, 0) if @quot;
 					push @orig, $l;
 				}
 			}
-			if (@quot) {
-				my $s = join("\n", @quot);
-				@quot = ();
-				$tg->index_text($s, 0, 'XQUOT');
-				$tg->increase_termpos;
-			}
-			if (@orig) {
-				my $s = join("\n", @orig);
-				@orig = ();
-				$tg->index_text($s, 1, 'XNQ');
-				$tg->increase_termpos;
-			}
+			index_body($tg, \@quot, 0) if @quot;
+			index_body($tg, \@orig, 1) if @orig;
 		});
 
 		link_message($self, $smsg, $old_tid);
@@ -276,15 +288,14 @@ sub link_message {
 	my ($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) {
@@ -302,6 +313,7 @@ sub link_message {
 			push @refs, $ref;
 		}
 	}
+
 	if (@refs) {
 		$smsg->{references} = '<'.join('> <', @refs).'>';
 
@@ -317,9 +329,9 @@ 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 {
@@ -373,7 +385,7 @@ sub do_cat_mail {
 		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 : $mime;
 }
@@ -383,6 +395,15 @@ sub index_sync {
 	with_umask($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]';
@@ -392,23 +413,21 @@ 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;
 		}
 	}
@@ -529,9 +548,9 @@ 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);
@@ -542,15 +561,14 @@ 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);
 	}
 }
@@ -607,7 +625,7 @@ sub with_umask {
 	my $rv = eval { $cb->() };
 	my $err = $@;
 	umask $old;
-	die $err if $@;
+	die $err if $err;
 	$rv;
 }