use rel2abs_collapsed when loading Inbox objects

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

diff --git a/lib/PublicInbox/Config.pm b/lib/PublicInbox/Config.pm
index d425cc9b162d0d4ab7b3dcd76b7fa3f3a03c863c..577337dc8a024d375be2db4f72cffb0365be2ffb 100644 (file)
--- a/lib/PublicInbox/Config.pm
+++ b/lib/PublicInbox/Config.pm
@@ -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
@@ -91,9 +92,12 @@ sub lookup_name ($$) {
 
 sub lookup_ei {
        my ($self, $name) = @_;
-       $self->{-ei_by_name}->{$name} //= _fill_ei($self, "eindex.$name");
+       $self->{-ei_by_name}->{$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:
@@ -159,11 +163,10 @@ 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 +368,16 @@ 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 +400,10 @@ 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)) {
@@ -411,7 +424,6 @@ EOF
                }
        }
 
-       return unless defined($ibx->{inboxdir});
        my $name = $pfx;
        $name =~ s/\Apublicinbox\.//;
 
@@ -421,7 +433,7 @@ EOF
        }
 
        $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 +446,31 @@ 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 +493,11 @@ 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 +526,16 @@ 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;