X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FSearchIdx.pm;h=c33a48c3bd2d5708d2414a008d25aabd40c3aca2;hb=95bdac7f09c69036efed537a4d03d5bdd2ae4eb6;hp=62e836e0d2d936ed849eec108cca7852b554cb14;hpb=da1ae9ccd829966195bfe59f17e416f218746def;p=public-inbox.git

diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm
index 62e836e0..c33a48c3 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
 #
@@ -12,7 +12,7 @@ use warnings;
 use base qw(PublicInbox::Search PublicInbox::Lock);
 use PublicInbox::MIME;
 use PublicInbox::InboxWritable;
-use PublicInbox::MID qw/mid_clean id_compress mid_mime mids_for_index/;
+use PublicInbox::MID qw/mid_clean mid_mime mids_for_index/;
 use PublicInbox::MsgIter;
 use Carp qw(croak);
 use POSIX qw(strftime);
@@ -34,7 +34,7 @@ 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 +54,7 @@ sub new {
 		-inbox => $ibx,
 		git => $ibx->git,
 		-altid => $altid,
-		version => $version,
+		ibx_ver => $version,
 		indexlevel => $indexlevel,
 	}, $class;
 	$ibx->umask_prepare;
@@ -144,14 +144,14 @@ sub term_generator ($) { # write-only
 }
 
 sub index_text ($$$$) {
-	my ($self, $field, $n, $text) = @_;
-	my $tg = term_generator($self);
+	my ($self, $text, $wdf_inc, $prefix) = @_;
+	my $tg = term_generator($self); # man Search::Xapian::TermGenerator
 
 	if ($self->{indexlevel} eq 'full') {
-		$tg->index_text($field, $n, $text);
+		$tg->index_text($text, $wdf_inc, $prefix);
 		$tg->increase_termpos;
 	} else {
-		$tg->index_text_without_positions($field, $n, $text);
+		$tg->index_text_without_positions($text, $wdf_inc, $prefix);
 	}
 }
 
@@ -199,22 +199,18 @@ sub index_old_diff_fn {
 }
 
 sub index_diff ($$$) {
-	my ($self, $lines, $doc) = @_;
+	my ($self, $txt, $doc) = @_;
 	my %seen;
 	my $in_diff;
 	my @xnq;
 	my $xnq = \@xnq;
-	foreach (@$lines) {
+	foreach (split(/\n/, $txt)) {
 		if ($in_diff && s/^ //) { # diff context
 			index_diff_inc($self, $_, 'XDFCTX', $xnq);
 		} elsif (/^-- $/) { # email signature begins
 			$in_diff = undef;
-		} elsif (m!^diff --git ("?a/.+) ("?b/.+)\z!) {
-			my ($fa, $fb) = ($1, $2);
-			my $fn = (split('/', git_unquote($fa), 2))[1];
-			$seen{$fn}++ or index_diff_inc($self, $fn, 'XDFN', $xnq);
-			$fn = (split('/', git_unquote($fb), 2))[1];
-			$seen{$fn}++ or index_diff_inc($self, $fn, 'XDFN', $xnq);
+		} elsif (m!^diff --git "?[^/]+/.+ "?[^/]+/.+\z!) {
+			# wait until "---" and "+++" to capture filenames
 			$in_diff = 1;
 		# traditional diff:
 		} elsif (m/^diff -(.+) (\S+) (\S+)$/) {
@@ -224,12 +220,12 @@ sub index_diff ($$$) {
 			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);
@@ -278,20 +274,17 @@ sub index_diff ($$$) {
 }
 
 sub index_body ($$$) {
-	my ($self, $lines, $doc) = @_;
-	my $txt = join("\n", @$lines);
+	my ($self, $txt, $doc) = @_;
 	if ($doc) {
 		# does it look like a diff?
 		if ($txt =~ /^(?:diff|---|\+\+\+) /ms) {
-			$txt = undef;
-			index_diff($self, $lines, $doc);
+			index_diff($self, $txt, $doc);
 		} else {
 			index_text($self, $txt, 1, 'XNQ');
 		}
 	} else {
 		index_text($self, $txt, 0, 'XQUOT');
 	}
-	@$lines = ();
 }
 
 sub index_xapian { # msg_iter callback
@@ -306,19 +299,10 @@ sub index_xapian { # msg_iter callback
 	my ($s, undef) = msg_part_text($part, $ct);
 	defined $s or return;
 
-	my (@orig, @quot);
-	my @lines = split(/\n/, $s);
-	while (defined(my $l = shift @lines)) {
-		if ($l =~ /^>/) {
-			index_body($self, \@orig, $doc) if @orig;
-			push @quot, $l;
-		} else {
-			index_body($self, \@quot, 0) if @quot;
-			push @orig, $l;
-		}
-	}
-	index_body($self, \@quot, 0) if @quot;
-	index_body($self, \@orig, $doc) if @orig;
+	# split off quoted and unquoted blocks:
+	my @sections = split(/((?:^>[^\n]*\n)+)/sm, $s);
+	$part = $s = undef;
+	index_body($self, $_, /\A>/ ? 0 : $doc) for @sections;
 }
 
 sub add_xapian ($$$$$$) {
@@ -370,7 +354,7 @@ sub add_xapian ($$$$$$) {
 
 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);
@@ -445,7 +429,7 @@ sub remove_message {
 		batch_do($self, 'Q' . $mid, sub {
 			my ($ids) = @_;
 			$db->delete_document($_) for @$ids;
-			$nr = scalar @$ids;
+			$nr += scalar @$ids;
 		});
 	};
 	if ($@) {
@@ -678,7 +662,6 @@ sub is_ancestor ($$$) {
 	my $cmd = [ 'git', "--git-dir=$git->{git_dir}",
 		qw(merge-base --is-ancestor), $cur, $tip ];
 	my $pid = spawn($cmd);
-	defined $pid or die "spawning ".join(' ', @$cmd)." failed: $!";
 	waitpid($pid, 0) == $pid or die join(' ', @$cmd) .' did not finish';
 	$? == 0;
 }