X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FSearch.pm;h=1c6482990d6105be88b3df1999dde848a4d05049;hb=4c7baaa7dcacf1108c7db6e0ce484ab76c4a018a;hp=55eee41ca4a88c43594e9e0899c3dba25e77771e;hpb=62f1de1b4e2a936ef71a0d1f7d64e71a5aabb44d;p=public-inbox.git

diff --git a/lib/PublicInbox/Search.pm b/lib/PublicInbox/Search.pm
index 55eee41c..1c648299 100644
--- a/lib/PublicInbox/Search.pm
+++ b/lib/PublicInbox/Search.pm
@@ -5,16 +5,50 @@
 # Read-only search interface for use by the web and NNTP interfaces
 package PublicInbox::Search;
 use strict;
+use parent qw(Exporter);
+our @EXPORT_OK = qw(mdocid);
 
-# values for searching
+# values for searching, changing the numeric value breaks
+# compatibility with old indices (so don't change them it)
 use constant {
 	TS => 0, # Received: header in Unix time (IMAP INTERNALDATE)
 	YYYYMMDD => 1, # Date: header for searching in the WWW UI
 	DT => 2, # Date: YYYYMMDDHHMMSS
+
+	# added for public-inbox 1.6.0+
 	BYTES => 3, # IMAP RFC822.SIZE
 	UID => 4, # IMAP UID == NNTP article number == Xapian docid
+
 	# TODO
-	# REPLYCNT => 4, # IMAP ANSWERED
+	# THREADID => ?
+	# REPLYCNT => ?, # IMAP ANSWERED
+
+	# SCHEMA_VERSION history
+	# 0 - initial
+	# 1 - subject_path is lower-cased
+	# 2 - subject_path is id_compress in the index, only
+	# 3 - message-ID is compressed if it includes '%' (hack!)
+	# 4 - change "Re: " normalization, avoid circular Reference ghosts
+	# 5 - subject_path drops trailing '.'
+	# 6 - preserve References: order in document data
+	# 7 - remove references and inreplyto terms
+	# 8 - remove redundant/unneeded document data
+	# 9 - disable Message-ID compression (SHA-1)
+	# 10 - optimize doc for NNTP overviews
+	# 11 - merge threads when vivifying ghosts
+	# 12 - change YYYYMMDD value column to numeric
+	# 13 - fix threading for empty References/In-Reply-To
+	#      (commit 83425ef12e4b65cdcecd11ddcb38175d4a91d5a0)
+	# 14 - fix ghost root vivification
+	# 15 - see public-inbox-v2-format(5)
+	#      further bumps likely unnecessary, we'll suggest in-place
+	#      "--reindex" use for further fixes and tweaks:
+	#
+	#      public-inbox v1.5.0 adds (still SCHEMA_VERSION=15):
+	#      * "lid:" and "l:" for List-Id searches
+	#
+	#      v1.6.0 adds BYTES and UID values
+	SCHEMA_VERSION => 15,
 };
 
 use PublicInbox::Smsg;
@@ -61,33 +95,6 @@ sub load_xapian () {
 # a prefix common in patch emails
 our $LANG = 'english';
 
-use constant {
-	# SCHEMA_VERSION history
-	# 0 - initial
-	# 1 - subject_path is lower-cased
-	# 2 - subject_path is id_compress in the index, only
-	# 3 - message-ID is compressed if it includes '%' (hack!)
-	# 4 - change "Re: " normalization, avoid circular Reference ghosts
-	# 5 - subject_path drops trailing '.'
-	# 6 - preserve References: order in document data
-	# 7 - remove references and inreplyto terms
-	# 8 - remove redundant/unneeded document data
-	# 9 - disable Message-ID compression (SHA-1)
-	# 10 - optimize doc for NNTP overviews
-	# 11 - merge threads when vivifying ghosts
-	# 12 - change YYYYMMDD value column to numeric
-	# 13 - fix threading for empty References/In-Reply-To
-	#      (commit 83425ef12e4b65cdcecd11ddcb38175d4a91d5a0)
-	# 14 - fix ghost root vivification
-	# 15 - see public-inbox-v2-format(5)
-	#      further bumps likely unnecessary, we'll suggest in-place
-	#      "--reindex" use for further fixes and tweaks
-	#
-	#      public-inbox v1.5.0 adds (still SCHEMA_VERSION=15):
-	#      * "lid:" and "l:" for List-Id searches
-	SCHEMA_VERSION => 15,
-};
-
 # note: the non-X term prefix allocations are shared with
 # Xapian omega, see xapian-applications/omega/docs/termprefixes.rst
 my %bool_pfx_external = (
@@ -164,15 +171,10 @@ chomp @HELP;
 
 sub xdir ($;$) {
 	my ($self, $rdonly) = @_;
-	if ($self->{ibx_ver} == 1) {
-		"$self->{inboxdir}/public-inbox/xapian" . SCHEMA_VERSION;
-	} else {
-		my $dir = "$self->{inboxdir}/xap" . SCHEMA_VERSION;
-		return $dir if $rdonly;
-
-		my $shard = $self->{shard};
-		defined $shard or die "shard not given";
-		$dir .= "/$shard";
+	if ($rdonly || !defined($self->{shard})) {
+		$self->{xpfx};
+	} else { # v2 only:
+		"$self->{xpfx}/$self->{shard}";
 	}
 }
 
@@ -182,19 +184,24 @@ sub _xdb ($) {
 	my ($xdb, $slow_phrase);
 	my $qpf = \($self->{qp_flags} ||= $QP_FLAGS);
 	if ($self->{ibx_ver} >= 2) {
-		my $n = 0;
-		foreach my $shard (<$dir/*>) {
-			-d $shard && $shard =~ m!/[0-9]+\z! or next;
-			my $sub = $X{Database}->new($shard);
-			if ($xdb) {
-				$xdb->add_database($sub);
-			} else {
-				$xdb = $sub;
+		my @xdb;
+		opendir(my $dh, $dir) or return; # not initialized yet
+
+		# We need numeric sorting so shard[0] is first for reading
+		# Xapian metadata, if needed
+		for (sort { $a <=> $b } grep(/\A[0-9]+\z/, readdir($dh))) {
+			my $shard_dir = "$dir/$_";
+			if (-d $shard_dir && -r _) {
+				push @xdb, $X{Database}->new($shard_dir);
+				$slow_phrase ||= -f "$shard_dir/iamchert";
+			} else { # gaps from missing epochs throw off mdocid()
+				warn "E: $shard_dir missing or unreadable\n";
+				return;
 			}
-			$slow_phrase ||= -f "$shard/iamchert";
-			++$n;
 		}
-		$self->{nshard} = $n;
+		$self->{nshard} = scalar(@xdb);
+		$xdb = shift @xdb;
+		$xdb->add_database($_) for @xdb;
 	} else {
 		$slow_phrase = -f "$dir/iamchert";
 		$xdb = $X{Database}->new($dir);
@@ -220,14 +227,24 @@ sub xdb ($) {
 	};
 }
 
+sub xpfx_init ($) {
+	my ($self) = @_;
+	if ($self->{ibx_ver} == 1) {
+		$self->{xpfx} .= '/public-inbox/xapian' . SCHEMA_VERSION;
+	} else {
+		$self->{xpfx} .= '/xap'.SCHEMA_VERSION;
+	}
+}
+
 sub new {
 	my ($class, $ibx) = @_;
 	ref $ibx or die "BUG: expected PublicInbox::Inbox object: $ibx";
 	my $self = bless {
-		inboxdir => $ibx->{inboxdir},
+		xpfx => $ibx->{inboxdir}, # for xpfx_init
 		altid => $ibx->{altid},
 		ibx_ver => $ibx->version,
 	}, $class;
+	xpfx_init($self);
 	my $dir = xdir($self, 1);
 	$self->{over_ro} = PublicInbox::Over->new("$dir/over.sqlite3");
 	$self;
@@ -248,7 +265,7 @@ sub query {
 	if ($query_string eq '' && !$opts->{mset}) {
 		$self->{over_ro}->recent($opts);
 	} else {
-		my $qp = qp($self);
+		my $qp = $self->{qp} //= qparse_new($self);
 		my $qp_flags = $self->{qp_flags};
 		my $query = $qp->parse_query($query_string, $qp_flags);
 		$opts->{relevance} = 1 unless exists $opts->{relevance};
@@ -307,27 +324,27 @@ sub _enquire_once { # retry_reopen callback
 	my $limit = $opts->{limit} || 50;
 	my $mset = $enquire->get_mset($offset, $limit);
 	return $mset if $opts->{mset};
-	my @msgs = map { PublicInbox::Smsg::from_mitem($_) } $mset->items;
-	return \@msgs unless wantarray;
-
-	($mset->get_matches_estimated, \@msgs)
+	my $nshard = $self->{nshard} // 1;
+	my $i = 0;
+	my %order = map { mdocid($nshard, $_) => ++$i } $mset->items;
+	my @msgs = sort {
+		$order{$a->{num}} <=> $order{$b->{num}}
+	} @{$self->{over_ro}->get_all(keys %order)};
+	wantarray ? ($mset->get_matches_estimated, \@msgs) : \@msgs;
 }
 
 # read-write
 sub stemmer { $X{Stem}->new($LANG) }
 
 # read-only
-sub qp {
+sub qparse_new ($) {
 	my ($self) = @_;
 
-	my $qp = $self->{query_parser};
-	return $qp if $qp;
 	my $xdb = xdb($self);
-	# new parser
-	$qp = $X{QueryParser}->new;
+	my $qp = $X{QueryParser}->new;
 	$qp->set_default_op(OP_AND());
 	$qp->set_database($xdb);
-	$qp->set_stemmer($self->stemmer);
+	$qp->set_stemmer(stemmer($self));
 	$qp->set_stemming_strategy(STEM_SOME());
 	$qp->set_max_wildcard_expansion(100);
 	my $nvrp = $X{NumberValueRangeProcessor};
@@ -365,13 +382,12 @@ EOF
 	while (my ($name, $prefix) = each %prob_prefix) {
 		$qp->add_prefix($name, $_) foreach split(/ /, $prefix);
 	}
-
-	$self->{query_parser} = $qp;
+	$qp;
 }
 
 sub help {
 	my ($self) = @_;
-	$self->qp; # parse altids
+	$self->{qp} //= qparse_new($self); # parse altids
 	my @ret = @HELP;
 	if (my $user_pfx = $self->{-user_pfx}) {
 		push @ret, @$user_pfx;