update copyrights for 2021

[public-inbox.git] / lib / PublicInbox / Config.pm

diff --git a/lib/PublicInbox/Config.pm b/lib/PublicInbox/Config.pm
index d2010f7af8f629b896be5c19030ecfc499220334..4f63bc937667d04a468d4152256ef99164d69d17 100644 (file)
--- a/lib/PublicInbox/Config.pm
+++ b/lib/PublicInbox/Config.pm
@@ -1,4 +1,4 @@
-# Copyright (C) 2014-2020 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
@@ -33,6 +33,7 @@ sub new {
        $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
@@ -94,6 +95,9 @@ sub lookup_ei {
        $self->{-ei_by_name}->{$name} //= _fill_ei($self, "extindex.$name");
 }
 
+# special case for [extindex "all"]
+sub ALL { lookup_ei($_[0], 'all') }
+
 sub each_inbox {
        my ($self, $cb, @arg) = @_;
        # may auto-vivify if config file is non-existent:
@@ -128,20 +132,16 @@ sub default_file {
 
 sub config_fh_parse ($$$) {
        my ($fh, $rs, $fs) = @_;
-       my %rv;
-       my (%section_seen, @section_order);
+       my (%rv, %seen, @section_order, $line, $k, $v, $section, $cur, $i);
        local $/ = $rs;
-       while (defined(my $line = <$fh>)) {
-               chomp $line;
-               my ($k, $v) = split($fs, $line, 2);
-               my ($section) = ($k =~ /\A(\S+)\.[^\.]+\z/);
-               unless (defined $section_seen{$section}) {
-                       $section_seen{$section} = 1;
-                       push @section_order, $section;
-               }
-
-               my $cur = $rv{$k};
-               if (defined $cur) {
+       while (defined($line = <$fh>)) { # perf critical with giant configs
+               $i = index($line, $fs);
+               $k = substr($line, 0, $i);
+               $v = substr($line, $i + 1, -1); # chop off $fs
+               $section = substr($k, 0, rindex($k, '.'));
+               $seen{$section} //= push(@section_order, $section);
+
+               if (defined($cur = $rv{$k})) {
                        if (ref($cur) eq "ARRAY") {
                                push @$cur, $v;
                        } else {
@@ -159,11 +159,10 @@ sub config_fh_parse ($$$) {
 sub git_config_dump {
        my ($file) = @_;
        return {} unless -e $file;
-       my @cmd = (qw/git config -z -l --includes/, "--file=$file");
-       my $cmd = join(' ', @cmd);
-       my $fh = popen_rd(\@cmd);
+       my $cmd = [ qw(git config -z -l --includes), "--file=$file" ];
+       my $fh = popen_rd($cmd);
        my $rv = config_fh_parse($fh, "\0", "\n");
-       close $fh or die "failed to close ($cmd) pipe: $?";
+       close $fh or die "failed to close (@$cmd) pipe: $?";
        $rv;
 }
 
@@ -365,6 +364,16 @@ sub git_bool {
        }
 }
 
+# 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 $ibx = {};
@@ -387,10 +396,10 @@ EOF
                }
        }
 
-       # backwards compatibility:
-       $ibx->{inboxdir} //= $self->{"$pfx.mainrepo"};
-       if (($ibx->{inboxdir} // '') =~ /\n/s) {
-               warn "E: `$ibx->{inboxdir}' must not contain `\\n'\n";
+       # "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;
        }
        foreach my $k (qw(obfuscate)) {
@@ -411,17 +420,14 @@ EOF
                }
        }
 
-       return unless defined($ibx->{inboxdir});
-       my $name = $pfx;
-       $name =~ s/\Apublicinbox\.//;
-
+       my $name = substr($pfx, length('publicinbox.'));
        if (!valid_inbox_name($name)) {
                warn "invalid inbox name: '$name'\n";
                return;
        }
 
        $ibx->{name} = $name;
-       $ibx->{-pi_config} = $self;
+       $ibx->{-pi_cfg} = $self;
        $ibx = PublicInbox::Inbox->new($ibx);
        foreach (@{$ibx->{address}}) {
                my $lc_addr = lc($_);
@@ -434,8 +440,31 @@ EOF
                        $self->{-by_list_id}->{lc($list_id)} = $ibx;
                }
        }
-       if (my $ng = $ibx->{newsgroup}) {
-               $self->{-by_newsgroup}->{$ng} = $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}) {
@@ -458,8 +487,11 @@ EOF
                        push @$repo_objs, $repo if $repo;
                }
        }
-
-       $ibx
+       if (my $es = ALL($self)) {
+               require PublicInbox::Isearch;
+               $ibx->{isrch} = PublicInbox::Isearch->new($ibx, $es);
+       }
+       $self->{-by_eidx_key}->{$ibx->eidx_key} = $ibx;
 }
 
 sub _fill_ei ($$) {
@@ -488,4 +520,16 @@ sub urlmatch {
        }
 }
 
+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;
+       };
+}
+
 1;