X-Git-Url: http://www.git.stargrave.org/?p=public-inbox.git;a=blobdiff_plain;f=lib%2FPublicInbox%2FSearchIdx.pm;h=44b05813f9a43e371068071ac9b2b666c275d555;hp=cb5549125c4c0fdc0f5ab2b50e55e081ecf692e2;hb=b5bc3576af3d0ef0fa884ed32a674c7a703a19b2;hpb=9f5a583694396f84056b9d92255bba0197b52bc8

diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm
index cb554912..44b05813 100644
--- a/lib/PublicInbox/SearchIdx.pm
+++ b/lib/PublicInbox/SearchIdx.pm
@@ -1,4 +1,4 @@
-# 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
 #
@@ -19,6 +19,7 @@ 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 {
@@ -34,7 +35,7 @@ sub new {
 	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) {
@@ -54,7 +55,7 @@ sub new {
 		-inbox => $ibx,
 		git => $ibx->git,
 		-altid => $altid,
-		version => $version,
+		ibx_ver => $version,
 		indexlevel => $indexlevel,
 	}, $class;
 	$ibx->umask_prepare;
@@ -209,12 +210,8 @@ sub index_diff ($$$) {
 			index_diff_inc($self, $_, 'XDFCTX', $xnq);
 		} elsif (/^-- $/) { # email signature begins
 			$in_diff = undef;
-		} elsif (m!^diff --git ("?a/.+) ("?b/.+)\z!) {
-			my ($fa, $fb) = ($1, $2);
-			my $fn = (split('/', git_unquote($fa), 2))[1];
-			$seen{$fn}++ or index_diff_inc($self, $fn, 'XDFN', $xnq);
-			$fn = (split('/', git_unquote($fb), 2))[1];
-			$seen{$fn}++ or index_diff_inc($self, $fn, 'XDFN', $xnq);
+		} elsif (m!^diff --git "?[^/]+/.+ "?[^/]+/.+\z!) {
+			# wait until "---" and "+++" to capture filenames
 			$in_diff = 1;
 		# traditional diff:
 		} elsif (m/^diff -(.+) (\S+) (\S+)$/) {
@@ -224,12 +221,12 @@ sub index_diff ($$$) {
 			next unless $opt =~ /[uU]/;
 			$in_diff = index_old_diff_fn($self, \%seen, $fa, $fb,
 							$xnq);
-		} elsif (m!^--- ("?a/.+)!) {
+		} 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/.+)!)  {
+		} elsif (m!^\+\+\+ ("?[^/]+/.+)!)  {
 			my $fn = $1;
 			$fn = (split('/', git_unquote($fn), 2))[1];
 			$seen{$fn}++ or index_diff_inc($self, $fn, 'XDFN', $xnq);
@@ -309,13 +306,14 @@ sub index_xapian { # msg_iter callback
 	index_body($self, $_, /\A>/ ? 0 : $doc) for @sections;
 }
 
-sub add_xapian ($$$$$$) {
-	my ($self, $mime, $num, $oid, $mids, $mid0) = @_;
-	my $smsg = PublicInbox::SearchMsg->new($mime);
+sub add_xapian ($$$$) {
+	my ($self, $mime, $smsg, $mids) = @_;
+	$smsg->{mime} = $mime; # XXX dangerous
+	my $hdr = $mime->header_obj;
 	my $doc = $X->{Document}->new;
 	my $subj = $smsg->subject;
-	add_val($doc, PublicInbox::Search::TS(), $smsg->ts);
-	my @ds = gmtime($smsg->ds);
+	add_val($doc, PublicInbox::Search::TS(), $smsg->{ts});
+	my @ds = gmtime($smsg->{ds});
 	my $yyyymmdd = strftime('%Y%m%d', @ds);
 	add_val($doc, PublicInbox::Search::YYYYMMDD(), $yyyymmdd);
 	my $dt = strftime('%Y%m%d%H%M%S', @ds);
@@ -338,9 +336,9 @@ sub add_xapian ($$$$$$) {
 			index_text($self, join(' ', @long), 1, 'XM');
 		}
 	}
-	$smsg->{to} = $smsg->{cc} = '';
-	PublicInbox::OverIdx::parse_references($smsg, $mid0, $mids);
-	my $data = $smsg->to_doc_data($oid, $mid0);
+	$smsg->{to} = $smsg->{cc} = ''; # WWW doesn't need these, only NNTP
+	PublicInbox::OverIdx::parse_references($smsg, $hdr, $mids);
+	my $data = $smsg->to_doc_data;
 	$doc->set_data($data);
 	if (my $altid = $self->{-altid}) {
 		foreach my $alt (@$altid) {
@@ -353,12 +351,12 @@ sub add_xapian ($$$$$$) {
 		}
 	}
 	$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->{version} != 1;
+	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);
@@ -367,19 +365,31 @@ sub _msgmap_init ($) {
 
 sub add_message {
 	# mime = Email::MIME object
-	my ($self, $mime, $bytes, $num, $oid, $mid0) = @_;
-	my $mids = mids_for_index($mime->header_obj);
-	$mid0 //= $mids->[0]; # v1 compatibility
-	$num //= do { # v1
+	my ($self, $mime, $smsg) = @_;
+	my $hdr = $mime->header_obj;
+	my $mids = mids_for_index($hdr);
+	$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);
 	};
+
+	# v1 and tests only:
+	$smsg->{ds} //= msg_datestamp($hdr, $self->{autime});
+	$smsg->{ts} //= msg_timestamp($hdr, $self->{cotime});
+
 	eval {
-		if (need_xapian($self)) {
-			add_xapian($self, $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);
 		}
-		if (my $over = $self->{over}) {
-			$over->add_overview($mime, $bytes, $num, $oid, $mid0);
+		if (need_xapian($self)) {
+			add_xapian($self, $mime, $smsg, $mids);
 		}
 	};
 
@@ -387,7 +397,7 @@ sub add_message {
 		warn "failed to index message <".join('> <',@$mids).">: $@\n";
 		return undef;
 	}
-	$num;
+	$smsg->{num};
 }
 
 # returns begin and end PostingIterator
@@ -464,7 +474,7 @@ sub remove_by_oid {
 	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);
@@ -527,9 +537,10 @@ sub unindex_mm {
 }
 
 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 {
@@ -592,14 +603,21 @@ sub read_log {
 				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->{autime} = $1;
+		} elsif ($line =~ /^committer .*? ([0-9]+) [\-\+][0-9]+$/) {
+			$self->{cotime} = $1;
 		}
 	}
 	close($log) or die "git log failed: \$?=$?";
@@ -655,7 +673,7 @@ sub _git_log {
 		$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);
 }