X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FConfig.pm;h=113975dd9e2816b7e32366df030423eabecad3d9;hb=be940983157a1f8bd353cb1891f6971645c73e5d;hp=1844f8b24132152becfd2cf695c76c2ae0d98a5f;hpb=525555d14118f92f86be54c683f797089c52a78d;p=public-inbox.git diff --git a/lib/PublicInbox/Config.pm b/lib/PublicInbox/Config.pm index 1844f8b2..113975dd 100644 --- a/lib/PublicInbox/Config.pm +++ b/lib/PublicInbox/Config.pm @@ -1,4 +1,4 @@ -# Copyright (C) 2014-2020 all contributors +# Copyright (C) 2014-2021 all contributors # License: AGPL-3.0+ # # Used throughout the project for reading configuration @@ -26,6 +26,7 @@ sub new { $self = config_fh_parse($fh, "\n", '='); } else { $self = git_config_dump($file); + $self->{'-f'} = $file; } bless $self, $class; # caches @@ -87,12 +88,12 @@ sub lookup_list_id { sub lookup_name ($$) { my ($self, $name) = @_; - $self->{-by_name}->{$name} // _fill($self, "publicinbox.$name"); + $self->{-by_name}->{$name} // _fill_ibx($self, $name); } sub lookup_ei { my ($self, $name) = @_; - $self->{-ei_by_name}->{$name} //= _fill_ei($self, "extindex.$name"); + $self->{-ei_by_name}->{$name} //= _fill_ei($self, $name); } # special case for [extindex "all"] @@ -132,20 +133,16 @@ sub default_file { sub config_fh_parse ($$$) { 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 { @@ -163,16 +160,15 @@ 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: $?"; $rv; } -sub valid_inbox_name ($) { - my ($name) = @_; +sub valid_foo_name ($;$) { + my ($name, $pfx) = @_; # Similar rules found in git.git/remote.c::valid_remote_nick # and git.git/refs.c::check_refname_component @@ -180,6 +176,7 @@ sub valid_inbox_name ($) { if ($name eq '' || $name =~ /\@\{/ || $name =~ /\.\./ || $name =~ m![/:\?\[\]\^~\s\f[:cntrl:]\*]! || $name =~ /\A\./ || $name =~ /\.\z/) { + warn "invalid $pfx name: `$name'\n" if $pfx; return 0; } @@ -369,37 +366,46 @@ sub git_bool { } } -sub _fill { - my ($self, $pfx) = @_; - my $ibx = {}; +# 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 _one_val { + my ($self, $pfx, $k) = @_; + my $v = $self->{"$pfx.$k"} // return; + return $v if !ref($v); + warn "W: $pfx.$k has multiple values, only using `$v->[-1]'\n"; + $v->[-1]; +} + +sub _fill_ibx { + my ($self, $name) = @_; + my $pfx = "publicinbox.$name"; + my $ibx = {}; for my $k (qw(watch nntpserver)) { my $v = $self->{"$pfx.$k"}; $ibx->{$k} = $v if defined $v; } for my $k (qw(filter inboxdir newsgroup replyto httpbackendmax feedmax indexlevel indexsequentialshard)) { - if (defined(my $v = $self->{"$pfx.$k"})) { - if (ref($v) eq 'ARRAY') { - warn <[-1]' -EOF - $ibx->{$k} = $v->[-1]; - } else { - $ibx->{$k} = $v; - } - } + my $v = _one_val($self, $pfx, $k) // next; + $ibx->{$k} = $v; } - # 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)) { - my $v = $self->{"$pfx.$k"}; - defined $v or next; + for my $k (qw(obfuscate)) { + my $v = $self->{"$pfx.$k"} // next; if (defined(my $bval = git_bool($v))) { $ibx->{$k} = $bval; } else { @@ -408,24 +414,15 @@ EOF } # TODO: more arrays, we should support multi-value for # more things to encourage decentralization - foreach my $k (qw(address altid nntpmirror coderepo hide listid url + for my $k (qw(address altid nntpmirror coderepo hide listid url infourl watchheader)) { - if (defined(my $v = $self->{"$pfx.$k"})) { - $ibx->{$k} = _array($v); - } - } - - return unless defined($ibx->{inboxdir}); - my $name = $pfx; - $name =~ s/\Apublicinbox\.//; - - if (!valid_inbox_name($name)) { - warn "invalid inbox name: '$name'\n"; - return; + my $v = $self->{"$pfx.$k"} // next; + $ibx->{$k} = _array($v); } + return unless valid_foo_name($name, 'publicinbox'); $ibx->{name} = $name; - $ibx->{-pi_config} = $self; + $ibx->{-pi_cfg} = $self; $ibx = PublicInbox::Inbox->new($ibx); foreach (@{$ibx->{address}}) { my $lc_addr = lc($_); @@ -438,7 +435,7 @@ EOF $self->{-by_list_id}->{lc($list_id)} = $ibx; } } - if (my $ngname = $ibx->{newsgroup}) { + if (defined(my $ngname = $ibx->{newsgroup})) { if (ref($ngname)) { delete $ibx->{newsgroup}; warn 'multiple newsgroups not supported: '. @@ -447,7 +444,8 @@ EOF # wildmat-exact and RFC 3501 (IMAP) ATOM-CHAR. # Leave out a few chars likely to cause problems or conflicts: # '|', '<', '>', ';', '#', '$', '&', - } elsif ($ngname =~ m![^A-Za-z0-9/_\.\-\~\@\+\=:]!) { + } elsif ($ngname =~ m![^A-Za-z0-9/_\.\-\~\@\+\=:]! || + $ngname eq '') { delete $ibx->{newsgroup}; warn "newsgroup name invalid: `$ngname'\n"; } else { @@ -456,20 +454,26 @@ EOF $self->{-by_newsgroup}->{$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 $ibx_code_repos = $ibx->{coderepo}) { my $code_repos = $self->{-code_repos}; my $repo_objs = $ibx->{-repo_objs} = []; foreach my $nick (@$ibx_code_repos) { my @parts = split(m!/!, $nick); my $valid = 0; - $valid += valid_inbox_name($_) foreach (@parts); + $valid += valid_foo_name($_) foreach (@parts); $valid == scalar(@parts) or next; my $repo = $code_repos->{$nick} //= @@ -485,17 +489,30 @@ EOF } sub _fill_ei ($$) { - my ($self, $pfx) = @_; - require PublicInbox::ExtSearch; - my $d = $self->{"$pfx.topdir"}; - defined($d) && -d $d ? PublicInbox::ExtSearch->new($d) : undef; + my ($self, $name) = @_; + eval { require PublicInbox::ExtSearch } or return; + my $pfx = "extindex.$name"; + my $d = $self->{"$pfx.topdir"} // return; + -d $d or return; + my $es = PublicInbox::ExtSearch->new($d); + for my $k (qw(indexlevel indexsequentialshard)) { + my $v = _one_val($self, $pfx, $k) // next; + $es->{$k} = $v; + } + for my $k (qw(altid coderepo hide url infourl)) { + my $v = $self->{"$pfx.$k"} // next; + $es->{$k} = _array($v); + } + return unless valid_foo_name($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 = default_file(); + my $file = $self->{'-f'} // default_file(); my $cmd = [qw/git config -z --includes --get-urlmatch/, "--file=$file", $key, $url ]; my $fh = popen_rd($cmd);