X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FConfig.pm;h=f2e5d5f0801e4c0f566f51ae654bdc55a5112c38;hb=1d6ebab439828dce8b7e8cbb99dfbc237e9d5a74;hp=355e64bfec6a19036519054b17a716641d2c7310;hpb=ca0a28d52d43609cd6cabf5af085260032e5afa9;p=public-inbox.git

diff --git a/lib/PublicInbox/Config.pm b/lib/PublicInbox/Config.pm
index 355e64bf..f2e5d5f0 100644
--- a/lib/PublicInbox/Config.pm
+++ b/lib/PublicInbox/Config.pm
@@ -1,4 +1,4 @@
-# Copyright (C) 2014-2018 all contributors <meta@public-inbox.org>
+# Copyright (C) 2014-2021 all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 #
 # Used throughout the project for reading configuration
@@ -9,30 +9,40 @@
 
 package PublicInbox::Config;
 use strict;
-use warnings;
-require PublicInbox::Inbox;
+use v5.10.1;
+use PublicInbox::Inbox;
 use PublicInbox::Spawn qw(popen_rd);
+our $LD_PRELOAD = $ENV{LD_PRELOAD}; # only valid at startup
 
 sub _array ($) { ref($_[0]) eq 'ARRAY' ? $_[0] : [ $_[0] ] }
 
 # returns key-value pairs of config directives in a hash
 # if keys may be multi-value, the value is an array ref containing all values
 sub new {
-	my ($class, $file) = @_;
-	$file = default_file() unless defined($file);
-	$file = ref $file ? $file : git_config_dump($file);
-	my $self = bless $file, $class;
-
+	my ($class, $file, $errfh) = @_;
+	$file //= default_file();
+	my $self;
+	if (ref($file) eq 'SCALAR') { # used by some tests
+		open my $fh, '<', $file or die;  # PerlIO::scalar
+		$self = config_fh_parse($fh, "\n", '=');
+		bless $self, $class;
+	} else {
+		$self = git_config_dump($class, $file, $errfh);
+		$self->{'-f'} = $file;
+	}
 	# caches
-	$self->{-by_addr} ||= {};
-	$self->{-by_name} ||= {};
-	$self->{-by_newsgroup} ||= {};
-	$self->{-no_obfuscate} ||= {};
-	$self->{-limiters} ||= {};
-	$self->{-code_repos} ||= {}; # nick => PublicInbox::Git object
+	$self->{-by_addr} = {};
+	$self->{-by_list_id} = {};
+	$self->{-by_name} = {};
+	$self->{-by_newsgroup} = {};
+	$self->{-by_eidx_key} = {};
+	$self->{-no_obfuscate} = {};
+	$self->{-limiters} = {};
+	$self->{-code_repos} = {}; # nick => PublicInbox::Git object
+	$self->{-cgitrc_unparsed} = $self->{'publicinbox.cgitrc'};
 
 	if (my $no = delete $self->{'publicinbox.noobfuscate'}) {
-		$no = [ $no ] if ref($no) ne 'ARRAY';
+		$no = _array($no);
 		my @domains;
 		foreach my $n (@$no) {
 			my @n = split(/\s+/, $n);
@@ -49,103 +59,96 @@ sub new {
 		my $nod = join('|', @domains);
 		$self->{-no_obfuscate_re} = qr/(?:$nod)\z/i;
 	}
+	if (my $css = delete $self->{'publicinbox.css'}) {
+		$self->{css} = _array($css);
+	}
 
 	$self;
 }
 
+sub noop {}
+sub fill_all ($) { each_inbox($_[0], \&noop) }
+
+sub _lookup_fill ($$$) {
+	my ($self, $cache, $key) = @_;
+	$self->{$cache}->{$key} // do {
+		fill_all($self);
+		$self->{$cache}->{$key};
+	}
+}
+
 sub lookup {
 	my ($self, $recipient) = @_;
-	my $addr = lc($recipient);
-	my $inbox = $self->{-by_addr}->{$addr};
-	return $inbox if $inbox;
-
-	my $pfx;
-
-	foreach my $k (keys %$self) {
-		$k =~ m!\A(publicinbox\.[^/]+)\.address\z! or next;
-		my $v = $self->{$k};
-		if (ref($v) eq "ARRAY") {
-			foreach my $alias (@$v) {
-				(lc($alias) eq $addr) or next;
-				$pfx = $1;
-				last;
-			}
-		} else {
-			(lc($v) eq $addr) or next;
-			$pfx = $1;
-			last;
-		}
-	}
-	defined $pfx or return;
-	_fill($self, $pfx);
+	_lookup_fill($self, '-by_addr', lc($recipient));
+}
+
+sub lookup_list_id {
+	my ($self, $list_id) = @_;
+	_lookup_fill($self, '-by_list_id', lc($list_id));
 }
 
 sub lookup_name ($$) {
 	my ($self, $name) = @_;
-	$self->{-by_name}->{$name} || _fill($self, "publicinbox.$name");
+	$self->{-by_name}->{$name} // _fill_ibx($self, $name);
+}
+
+sub lookup_ei {
+	my ($self, $name) = @_;
+	$self->{-ei_by_name}->{$name} //= _fill_ei($self, $name);
+}
+
+sub lookup_eidx_key {
+	my ($self, $eidx_key) = @_;
+	_lookup_fill($self, '-by_eidx_key', $eidx_key);
 }
 
+# special case for [extindex "all"]
+sub ALL { lookup_ei($_[0], 'all') }
+
 sub each_inbox {
-	my ($self, $cb) = @_;
-	my %seen;
-	foreach my $k (keys %$self) {
-		$k =~ m!\Apublicinbox\.([^/]+)\.mainrepo\z! or next;
-		next if $seen{$1};
-		$seen{$1} = 1;
+	my ($self, $cb, @arg) = @_;
+	# may auto-vivify if config file is non-existent:
+	foreach my $section (@{$self->{-section_order}}) {
+		next if $section !~ m!\Apublicinbox\.([^/]+)\z!;
 		my $ibx = lookup_name($self, $1) or next;
-		$cb->($ibx);
+		$cb->($ibx, @arg);
 	}
 }
 
 sub lookup_newsgroup {
 	my ($self, $ng) = @_;
-	$ng = lc($ng);
-	my $rv = $self->{-by_newsgroup}->{$ng};
-	return $rv if $rv;
-
-	foreach my $k (keys %$self) {
-		$k =~ m!\A(publicinbox\.[^/]+)\.newsgroup\z! or next;
-		my $v = $self->{$k};
-		my $pfx = $1;
-		if ($v eq $ng) {
-			$rv = _fill($self, $pfx);
-			return $rv;
-		}
-	}
-	undef;
+	_lookup_fill($self, '-by_newsgroup', lc($ng));
 }
 
 sub limiter {
 	my ($self, $name) = @_;
-	$self->{-limiters}->{$name} ||= do {
+	$self->{-limiters}->{$name} //= do {
 		require PublicInbox::Qspawn;
-		my $max = $self->{"publicinboxlimiter.$name.max"};
-		PublicInbox::Qspawn::Limiter->new($max);
+		my $max = $self->{"publicinboxlimiter.$name.max"} || 1;
+		my $limiter = PublicInbox::Qspawn::Limiter->new($max);
+		$limiter->setup_rlimit($name, $self);
+		$limiter;
 	};
 }
 
-sub config_dir { $ENV{PI_DIR} || "$ENV{HOME}/.public-inbox" }
+sub config_dir { $ENV{PI_DIR} // "$ENV{HOME}/.public-inbox" }
 
 sub default_file {
-	my $f = $ENV{PI_CONFIG};
-	return $f if defined $f;
-	config_dir() . '/config';
+	$ENV{PI_CONFIG} // (config_dir() . '/config');
 }
 
-sub git_config_dump {
-	my ($file) = @_;
-	my ($in, $out);
-	my @cmd = (qw/git config/, "--file=$file", '-l');
-	my $cmd = join(' ', @cmd);
-	my $fh = popen_rd(\@cmd) or die "popen_rd failed for $file: $!\n";
-	my %rv;
-	local $/ = "\n";
-	while (defined(my $line = <$fh>)) {
-		chomp $line;
-		my ($k, $v) = split(/=/, $line, 2);
-		my $cur = $rv{$k};
-
-		if (defined $cur) {
+sub config_fh_parse ($$$) {
+	my ($fh, $rs, $fs) = @_;
+	my (%rv, %seen, @section_order, $line, $k, $v, $section, $cur, $i);
+	local $/ = $rs;
+	while (defined($line = <$fh>)) { # perf critical with giant configs
+		$i = index($line, $fs);
+		$k = substr($line, 0, $i);
+		$v = substr($line, $i + 1, -1); # chop off $fs
+		$section = substr($k, 0, rindex($k, '.'));
+		$seen{$section} //= push(@section_order, $section);
+
+		if (defined($cur = $rv{$k})) {
 			if (ref($cur) eq "ARRAY") {
 				push @$cur, $v;
 			} else {
@@ -155,13 +158,23 @@ sub git_config_dump {
 			$rv{$k} = $v;
 		}
 	}
-	close $fh or die "failed to close ($cmd) pipe: $?";
+	$rv{-section_order} = \@section_order;
 
 	\%rv;
 }
 
-sub valid_inbox_name ($) {
-	my ($name) = @_;
+sub git_config_dump {
+	my ($class, $file, $errfh) = @_;
+	return bless {}, $class unless -e $file;
+	my $cmd = [ qw(git config -z -l --includes), "--file=$file" ];
+	my $fh = popen_rd($cmd, undef, { 2 => $errfh // 2 });
+	my $rv = config_fh_parse($fh, "\0", "\n");
+	close $fh or die "@$cmd failed: \$?=$?\n";
+	bless $rv, $class;
+}
+
+sub valid_foo_name ($;$) {
+	my ($name, $pfx) = @_;
 
 	# Similar rules found in git.git/remote.c::valid_remote_nick
 	# and git.git/refs.c::check_refname_component
@@ -169,6 +182,7 @@ sub valid_inbox_name ($) {
 	if ($name eq '' || $name =~ /\@\{/ ||
 	    $name =~ /\.\./ || $name =~ m![/:\?\[\]\^~\s\f[:cntrl:]\*]! ||
 	    $name =~ /\A\./ || $name =~ /\.\z/) {
+		warn "invalid $pfx name: `$name'\n" if $pfx;
 		return 0;
 	}
 
@@ -177,109 +191,372 @@ sub valid_inbox_name ($) {
 	1;
 }
 
+# XXX needs testing for cgit compatibility
+# cf. cgit/scan-tree.c::add_repo
+sub cgit_repo_merge ($$$) {
+	my ($self, $base, $repo) = @_;
+	my $path = $repo->{dir};
+	if (defined(my $se = $self->{-cgit_strict_export})) {
+		return unless -e "$path/$se";
+	}
+	return if -e "$path/noweb";
+	# this comes from the cgit config, and AFAIK cgit only allows
+	# repos to have one URL, but that's just the PATH_INFO component,
+	# not the Host: portion
+	# $repo = { url => 'foo.git', dir => '/path/to/foo.git' }
+	my $rel = $repo->{url};
+	unless (defined $rel) {
+		my $off = index($path, $base, 0);
+		if ($off != 0) {
+			$rel = $path;
+		} else {
+			$rel = substr($path, length($base) + 1);
+		}
+
+		$rel =~ s!/\.git\z!! or
+			$rel =~ s!/+\z!!;
+
+		$self->{-cgit_remove_suffix} and
+			$rel =~ s!/?\.git\z!!;
+	}
+	$self->{"coderepo.$rel.dir"} //= $path;
+	$self->{"coderepo.$rel.cgiturl"} //= _array($rel);
+}
+
+sub is_git_dir ($) {
+	my ($git_dir) = @_;
+	-d "$git_dir/objects" && -f "$git_dir/HEAD";
+}
+
+# XXX needs testing for cgit compatibility
+sub scan_path_coderepo {
+	my ($self, $base, $path) = @_;
+	opendir(my $dh, $path) or do {
+		warn "error opening directory: $path\n";
+		return
+	};
+	my $git_dir = $path;
+	if (is_git_dir($git_dir) || is_git_dir($git_dir .= '/.git')) {
+		my $repo = { dir => $git_dir };
+		cgit_repo_merge($self, $base, $repo);
+		return;
+	}
+	while (defined(my $dn = readdir $dh)) {
+		next if $dn eq '.' || $dn eq '..';
+		if (index($dn, '.') == 0 && !$self->{-cgit_scan_hidden_path}) {
+			next;
+		}
+		my $dir = "$path/$dn";
+		scan_path_coderepo($self, $base, $dir) if -d $dir;
+	}
+}
+
+sub scan_tree_coderepo ($$) {
+	my ($self, $path) = @_;
+	scan_path_coderepo($self, $path, $path);
+}
+
+sub scan_projects_coderepo ($$$) {
+	my ($self, $list, $path) = @_;
+	open my $fh, '<', $list or do {
+		warn "failed to open cgit projectlist=$list: $!\n";
+		return;
+	};
+	while (<$fh>) {
+		chomp;
+		scan_path_coderepo($self, $path, "$path/$_");
+	}
+}
+
+sub parse_cgitrc {
+	my ($self, $cgitrc, $nesting) = @_;
+	if ($nesting == 0) {
+		# defaults:
+		my %s = map { $_ => 1 } qw(/cgit.css /cgit.png
+						/favicon.ico /robots.txt);
+		$self->{-cgit_static} = \%s;
+	}
+
+	# same limit as cgit/configfile.c::parse_configfile
+	return if $nesting > 8;
+
+	open my $fh, '<', $cgitrc or do {
+		warn "failed to open cgitrc=$cgitrc: $!\n";
+		return;
+	};
+
+	# FIXME: this doesn't support macro expansion via $VARS, yet
+	my $repo;
+	while (<$fh>) {
+		chomp;
+		if (m!\Arepo\.url=(.+?)/*\z!) {
+			my $nick = $1;
+			cgit_repo_merge($self, $repo->{dir}, $repo) if $repo;
+			$repo = { url => $nick };
+		} elsif (m!\Arepo\.path=(.+)\z!) {
+			if (defined $repo) {
+				$repo->{dir} = $1;
+			} else {
+				warn "$_ without repo.url\n";
+			}
+		} elsif (m!\Ainclude=(.+)\z!) {
+			parse_cgitrc($self, $1, $nesting + 1);
+		} elsif (m!\A(scan-hidden-path|remove-suffix)=([0-9]+)\z!) {
+			my ($k, $v) = ($1, $2);
+			$k =~ tr/-/_/;
+			$self->{"-cgit_$k"} = $v;
+		} elsif (m!\A(project-list|strict-export)=(.+)\z!) {
+			my ($k, $v) = ($1, $2);
+			$k =~ tr/-/_/;
+			$self->{"-cgit_$k"} = $v;
+		} elsif (m!\Ascan-path=(.+)\z!) {
+			if (defined(my $list = $self->{-cgit_project_list})) {
+				scan_projects_coderepo($self, $list, $1);
+			} else {
+				scan_tree_coderepo($self, $1);
+			}
+		} elsif (m!\A(?:css|favicon|logo|repo\.logo)=(/.+)\z!) {
+			# absolute paths for static files via PublicInbox::Cgit
+			$self->{-cgit_static}->{$1} = 1;
+		}
+	}
+	cgit_repo_merge($self, $repo->{dir}, $repo) if $repo;
+}
+
 # parse a code repo
 # Only git is supported at the moment, but SVN and Hg are possibilities
 sub _fill_code_repo {
 	my ($self, $nick) = @_;
 	my $pfx = "coderepo.$nick";
-
-	my $dir = $self->{"$pfx.dir"}; # aka "GIT_DIR"
-	unless (defined $dir) {
-		warn "$pfx.repodir unset";
+	my $dir = $self->{"$pfx.dir"} // do { # aka "GIT_DIR"
+		warn "$pfx.dir unset\n";
 		return;
-	}
-
+	};
 	my $git = PublicInbox::Git->new($dir);
-	foreach my $t (qw(blob commit tree tag)) {
-		$git->{$t.'_url_format'} =
-				_array($self->{lc("$pfx.${t}UrlFormat")});
+	if (defined(my $cgits = $self->{"$pfx.cgiturl"})) {
+		$git->{cgit_url} = $cgits = _array($cgits);
+		$self->{"$pfx.cgiturl"} = $cgits;
 	}
 
-	if (my $cgits = $self->{lc("$pfx.cgitUrl")}) {
-		$git->{cgit_url} = $cgits = _array($cgits);
+	$git;
+}
 
-		# cgit supports "/blob/?id=%s", but it's only a plain-text
-		# display and requires an unabbreviated id=
-		foreach my $t (qw(blob commit tag)) {
-			$git->{$t.'_url_format'} ||= map {
-				"$_/$t/?id=%s"
-			} @$cgits;
-		}
+sub get_all {
+	my ($self, $key) = @_;
+	my $v = $self->{$key} // return;
+	_array($v);
+}
+
+sub git_bool {
+	my ($val) = $_[-1]; # $_[0] may be $self, or $val
+	if ($val =~ /\A(?:false|no|off|[\-\+]?(?:0x)?0+)\z/i) {
+		0;
+	} elsif ($val =~ /\A(?:true|yes|on|[\-\+]?(?:0x)?[0-9]+)\z/i) {
+		1;
+	} else {
+		undef;
 	}
-	# TODO: support gitweb and other repository viewers?
-	# TODO: parse cgitrc
+}
 
-	$git;
+# abs_path resolves symlinks, so we want to avoid it if rel2abs
+# is sufficient and doesn't leave "/.." or "/../"
+sub rel2abs_collapsed {
+	require File::Spec;
+	my $p = File::Spec->rel2abs($_[-1]);
+	return $p if substr($p, -3, 3) ne '/..' && index($p, '/../') < 0;
+	require Cwd;
+	Cwd::abs_path($p);
 }
 
-sub _fill {
-	my ($self, $pfx) = @_;
-	my $rv = {};
+sub get_1 {
+	my ($self, $key) = @_;
+	my $v = $self->{$key};
+	return $v if !ref($v);
+	warn "W: $key has multiple values, only using `$v->[-1]'\n";
+	$v->[-1];
+}
 
-	foreach my $k (qw(mainrepo filter url newsgroup
-			infourl watch watchheader httpbackendmax
-			replyto feedmax nntpserver indexlevel)) {
-		my $v = $self->{"$pfx.$k"};
-		$rv->{$k} = $v if defined $v;
+sub repo_objs {
+	my ($self, $ibxish) = @_;
+	my $ibx_code_repos = $ibxish->{coderepo} or return;
+	$ibxish->{-repo_objs} //= do {
+		my $code_repos = $self->{-code_repos};
+		my @repo_objs;
+		for my $nick (@$ibx_code_repos) {
+			my @parts = split(m!/!, $nick);
+			for (@parts) {
+				@parts = () unless valid_foo_name($_);
+			}
+			unless (@parts) {
+				warn "invalid coderepo name: `$nick'\n";
+				next;
+			}
+			my $repo = $code_repos->{$nick} //=
+						_fill_code_repo($self, $nick);
+			push @repo_objs, $repo if $repo;
+		}
+		if (scalar @repo_objs) {
+			\@repo_objs;
+		} else {
+			delete $ibxish->{coderepo};
+			undef;
+		}
 	}
-	foreach my $k (qw(obfuscate)) {
+}
+
+sub _fill_ibx {
+	my ($self, $name) = @_;
+	my $pfx = "publicinbox.$name";
+	my $ibx = {};
+	for my $k (qw(watch)) {
 		my $v = $self->{"$pfx.$k"};
-		defined $v or next;
-		if ($v =~ /\A(?:false|no|off|0)\z/) {
-			$rv->{$k} = 0;
-		} elsif ($v =~ /\A(?:true|yes|on|1)\z/) {
-			$rv->{$k} = 1;
+		$ibx->{$k} = $v if defined $v;
+	}
+	for my $k (qw(filter inboxdir newsgroup replyto httpbackendmax feedmax
+			indexlevel indexsequentialshard boost)) {
+		my $v = get_1($self, "$pfx.$k") // next;
+		$ibx->{$k} = $v;
+	}
+
+	# "mainrepo" is backwards compatibility:
+	my $dir = $ibx->{inboxdir} //= $self->{"$pfx.mainrepo"} // return;
+	if (index($dir, "\n") >= 0) {
+		warn "E: `$dir' must not contain `\\n'\n";
+		return;
+	}
+	for my $k (qw(obfuscate)) {
+		my $v = $self->{"$pfx.$k"} // next;
+		if (defined(my $bval = git_bool($v))) {
+			$ibx->{$k} = $bval;
 		} else {
 			warn "Ignoring $pfx.$k=$v in config, not boolean\n";
 		}
 	}
 	# TODO: more arrays, we should support multi-value for
 	# more things to encourage decentralization
-	foreach my $k (qw(address altid nntpmirror coderepo)) {
-		if (defined(my $v = $self->{"$pfx.$k"})) {
-			$rv->{$k} = _array($v);
-		}
+	for my $k (qw(address altid nntpmirror imapmirror
+			coderepo hide listid url
+			infourl watchheader nntpserver imapserver)) {
+		my $v = $self->{"$pfx.$k"} // next;
+		$ibx->{$k} = _array($v);
 	}
 
-	return unless $rv->{mainrepo};
-	my $name = $pfx;
-	$name =~ s/\Apublicinbox\.//;
+	return unless valid_foo_name($name, 'publicinbox');
+	$ibx->{name} = $name;
+	$ibx->{-pi_cfg} = $self;
+	$ibx = PublicInbox::Inbox->new($ibx);
+	foreach (@{$ibx->{address}}) {
+		my $lc_addr = lc($_);
+		$self->{-by_addr}->{$lc_addr} = $ibx;
+		$self->{-no_obfuscate}->{$lc_addr} = 1;
+	}
+	if (my $listids = $ibx->{listid}) {
+		# RFC2919 section 6 stipulates "case insensitive equality"
+		foreach my $list_id (@$listids) {
+			$self->{-by_list_id}->{lc($list_id)} = $ibx;
+		}
+	}
+	if (defined(my $ngname = $ibx->{newsgroup})) {
+		if (ref($ngname)) {
+			delete $ibx->{newsgroup};
+			warn 'multiple newsgroups not supported: '.
+				join(', ', @$ngname). "\n";
+		# Newsgroup name needs to be compatible with RFC 3977
+		# wildmat-exact and RFC 3501 (IMAP) ATOM-CHAR.
+		# Leave out a few chars likely to cause problems or conflicts:
+		# '|', '<', '>', ';', '#', '$', '&',
+		} elsif ($ngname =~ m![^A-Za-z0-9/_\.\-\~\@\+\=:]! ||
+				$ngname eq '') {
+			delete $ibx->{newsgroup};
+			warn "newsgroup name invalid: `$ngname'\n";
+		} else {
+			# PublicInbox::NNTPD does stricter ->nntp_usable
+			# checks, keep this lean for startup speed
+			$self->{-by_newsgroup}->{$ngname} = $ibx;
+		}
+	}
+	unless (defined $ibx->{newsgroup}) { # for ->eidx_key
+		my $abs = rel2abs_collapsed($dir);
+		if ($abs ne $dir) {
+			warn "W: `$dir' canonicalized to `$abs'\n";
+			$ibx->{inboxdir} = $abs;
+		}
+	}
+	$self->{-by_name}->{$name} = $ibx;
+	if ($ibx->{obfuscate}) {
+		$ibx->{-no_obfuscate} = $self->{-no_obfuscate};
+		$ibx->{-no_obfuscate_re} = $self->{-no_obfuscate_re};
+		fill_all($self); # noop to populate -no_obfuscate
+	}
+	if (my $es = ALL($self)) {
+		require PublicInbox::Isearch;
+		$ibx->{isrch} = PublicInbox::Isearch->new($ibx, $es);
+	}
+	$self->{-by_eidx_key}->{$ibx->eidx_key} = $ibx;
+}
 
-	if (!valid_inbox_name($name)) {
-		warn "invalid inbox name: '$name'\n";
+sub _fill_ei ($$) {
+	my ($self, $name) = @_;
+	eval { require PublicInbox::ExtSearch } or return;
+	my $pfx = "extindex.$name";
+	my $d = $self->{"$pfx.topdir"} // return;
+	-d $d or return;
+	if (index($d, "\n") >= 0) {
+		warn "E: `$d' must not contain `\\n'\n";
 		return;
 	}
-
-	$rv->{name} = $name;
-	$rv->{-pi_config} = $self;
-	$rv = PublicInbox::Inbox->new($rv);
-	foreach (@{$rv->{address}}) {
-		my $lc_addr = lc($_);
-		$self->{-by_addr}->{$lc_addr} = $rv;
-		$self->{-no_obfuscate}->{$lc_addr} = 1;
+	my $es = PublicInbox::ExtSearch->new($d);
+	for my $k (qw(indexlevel indexsequentialshard)) {
+		my $v = get_1($self, "$pfx.$k") // next;
+		$es->{$k} = $v;
 	}
-	if (my $ng = $rv->{newsgroup}) {
-		$self->{-by_newsgroup}->{$ng} = $rv;
+	for my $k (qw(coderepo hide url infourl)) {
+		my $v = $self->{"$pfx.$k"} // next;
+		$es->{$k} = _array($v);
 	}
-	$self->{-by_name}->{$name} = $rv;
-	if ($rv->{obfuscate}) {
-		$rv->{-no_obfuscate} = $self->{-no_obfuscate};
-		$rv->{-no_obfuscate_re} = $self->{-no_obfuscate_re};
-		each_inbox($self, sub {}); # noop to populate -no_obfuscate
+	return unless valid_foo_name($name, 'extindex');
+	$es->{name} = $name;
+	$es;
+}
+
+sub urlmatch {
+	my ($self, $key, $url) = @_;
+	state $urlmatch_broken; # requires git 1.8.5
+	return if $urlmatch_broken;
+	my $file = $self->{'-f'} // default_file();
+	my $cmd = [qw/git config -z --includes --get-urlmatch/,
+		"--file=$file", $key, $url ];
+	my $fh = popen_rd($cmd);
+	local $/ = "\0";
+	my $val = <$fh>;
+	if (close($fh)) {
+		chomp($val);
+		$val;
+	} else {
+		$urlmatch_broken = 1 if (($? >> 8) != 1);
+		undef;
 	}
+}
 
-	if (my $ibx_code_repos = $rv->{coderepo}) {
-		my $code_repos = $self->{-code_repos};
-		my $repo_objs = $rv->{-repo_objs} = [];
-		foreach my $nick (@$ibx_code_repos) {
-			valid_inbox_name($nick) or next;
-			my $repo = $code_repos->{$nick} ||=
-						_fill_code_repo($self, $nick);
-			push @$repo_objs, $repo if $repo;
+sub json {
+	state $json;
+	$json //= do {
+		for my $mod (qw(Cpanel::JSON::XS JSON::MaybeXS JSON JSON::PP)) {
+			eval "require $mod" or next;
+			# ->ascii encodes non-ASCII to "\uXXXX"
+			$json = $mod->new->ascii(1) and last;
 		}
-	}
+		$json;
+	};
+}
 
-	$rv
+sub squote_maybe ($) {
+	my ($val) = @_;
+	if ($val =~ m{([^\w@\./,\%\+\-])}) {
+		$val =~ s/(['!])/'\\$1'/g; # '!' for csh
+		return "'$val'";
+	}
+	$val;
 }
 
 1;