X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FConfig.pm;h=4f63bc937667d04a468d4152256ef99164d69d17;hb=af0b0fb7a454470a32c452119d0392e0dedb3fe1;hp=b7e03af37e652b9e758a2b0646ed2fdab530c3c7;hpb=1317fb7b4ace03f6d9dfb1a42ee5f9371a1bf913;p=public-inbox.git diff --git a/lib/PublicInbox/Config.pm b/lib/PublicInbox/Config.pm index b7e03af3..4f63bc93 100644 --- a/lib/PublicInbox/Config.pm +++ b/lib/PublicInbox/Config.pm @@ -1,4 +1,4 @@ -# Copyright (C) 2014-2019 all contributors +# Copyright (C) 2014-2021 all contributors # License: AGPL-3.0+ # # Used throughout the project for reading configuration @@ -9,8 +9,8 @@ package PublicInbox::Config; use strict; -use warnings; -require PublicInbox::Inbox; +use v5.10.1; +use PublicInbox::Inbox; use PublicInbox::Spawn qw(popen_rd); sub _array ($) { ref($_[0]) eq 'ARRAY' ? $_[0] : [ $_[0] ] } @@ -19,7 +19,7 @@ sub _array ($) { ref($_[0]) eq 'ARRAY' ? $_[0] : [ $_[0] ] } # if keys may be multi-value, the value is an array ref containing all values sub new { my ($class, $file) = @_; - $file = default_file() unless defined($file); + $file //= default_file(); my $self; if (ref($file) eq 'SCALAR') { # used by some tests open my $fh, '<', $file or die; # PerlIO::scalar @@ -29,13 +29,14 @@ sub new { } bless $self, $class; # caches - $self->{-by_addr} ||= {}; - $self->{-by_list_id} ||= {}; - $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'}) { @@ -63,97 +64,58 @@ sub new { $self; } +sub noop {} +sub fill_all ($) { each_inbox($_[0], \&noop) } + +sub _lookup_fill ($$$) { + my ($self, $cache, $key) = @_; + $self->{$cache}->{$key} // do { + fill_all($self); + $self->{$cache}->{$key}; + } +} + sub lookup { my ($self, $recipient) = @_; - my $addr = lc($recipient); - my $ibx = $self->{-by_addr}->{$addr}; - return $ibx if $ibx; - - my $pfx; - - foreach my $k (keys %$self) { - $k =~ m!\A(publicinbox\.[^/]+)\.address\z! or next; - my $v = $self->{$k}; - if (ref($v) eq "ARRAY") { - foreach my $alias (@$v) { - (lc($alias) eq $addr) or next; - $pfx = $1; - last; - } - } else { - (lc($v) eq $addr) or next; - $pfx = $1; - last; - } - } - defined $pfx or return; - _fill($self, $pfx); + _lookup_fill($self, '-by_addr', lc($recipient)); } sub lookup_list_id { my ($self, $list_id) = @_; - $list_id = lc($list_id); - my $ibx = $self->{-by_list_id}->{$list_id}; - return $ibx if $ibx; - - my $pfx; - - foreach my $k (keys %$self) { - $k =~ /\A(publicinbox\.[\w-]+)\.listid\z/ or next; - my $v = $self->{$k}; - if (ref($v) eq "ARRAY") { - foreach my $alias (@$v) { - (lc($alias) eq $list_id) or next; - $pfx = $1; - last; - } - } else { - (lc($v) eq $list_id) or next; - $pfx = $1; - last; - } - } - defined $pfx or return; - _fill($self, $pfx); + _lookup_fill($self, '-by_list_id', lc($list_id)); } sub lookup_name ($$) { my ($self, $name) = @_; - $self->{-by_name}->{$name} || _fill($self, "publicinbox.$name"); + $self->{-by_name}->{$name} // _fill($self, "publicinbox.$name"); } +sub lookup_ei { + my ($self, $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, $cb) = @_; + my ($self, $cb, @arg) = @_; # may auto-vivify if config file is non-existent: foreach my $section (@{$self->{-section_order}}) { next if $section !~ m!\Apublicinbox\.([^/]+)\z!; - $self->{"publicinbox.$1.mainrepo"} or next; my $ibx = lookup_name($self, $1) or next; - $cb->($ibx); + $cb->($ibx, @arg); } } sub lookup_newsgroup { my ($self, $ng) = @_; - $ng = lc($ng); - my $ibx = $self->{-by_newsgroup}->{$ng}; - return $ibx if $ibx; - - foreach my $k (keys %$self) { - $k =~ m!\A(publicinbox\.[^/]+)\.newsgroup\z! or next; - my $v = $self->{$k}; - my $pfx = $1; - if ($v eq $ng) { - $ibx = _fill($self, $pfx); - return $ibx; - } - } - undef; + _lookup_fill($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"} || 1; my $limiter = PublicInbox::Qspawn::Limiter->new($max); @@ -162,30 +124,24 @@ sub 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 config_fh_parse ($$$) { my ($fh, $rs, $fs) = @_; - my %rv; - my (%section_seen, @section_order); + my (%rv, %seen, @section_order, $line, $k, $v, $section, $cur, $i); local $/ = $rs; - while (defined(my $line = <$fh>)) { - chomp $line; - my ($k, $v) = split($fs, $line, 2); - my ($section) = ($k =~ /\A(\S+)\.[^\.]+\z/); - unless (defined $section_seen{$section}) { - $section_seen{$section} = 1; - push @section_order, $section; - } - - my $cur = $rv{$k}; - if (defined $cur) { + while (defined($line = <$fh>)) { # perf critical with giant configs + $i = index($line, $fs); + $k = substr($line, 0, $i); + $v = substr($line, $i + 1, -1); # chop off $fs + $section = substr($k, 0, rindex($k, '.')); + $seen{$section} //= push(@section_order, $section); + + if (defined($cur = $rv{$k})) { if (ref($cur) eq "ARRAY") { push @$cur, $v; } else { @@ -203,11 +159,10 @@ sub config_fh_parse ($$$) { sub git_config_dump { my ($file) = @_; return {} unless -e $file; - my @cmd = (qw/git config -z -l/, "--file=$file"); - my $cmd = join(' ', @cmd); - my $fh = popen_rd(\@cmd) or die "popen_rd failed for $file: $!\n"; + 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; } @@ -237,6 +192,9 @@ sub cgit_repo_merge ($$$) { return unless -e "$path/$se"; } return if -e "$path/noweb"; + # this comes from the cgit config, and AFAIK cgit only allows + # repos to have one URL, but that's just the PATH_INFO component, + # not the Host: portion # $repo = { url => 'foo.git', dir => '/path/to/foo.git' } my $rel = $repo->{url}; unless (defined $rel) { @@ -253,8 +211,8 @@ sub cgit_repo_merge ($$$) { $self->{-cgit_remove_suffix} and $rel =~ s!/?\.git\z!!; } - $self->{"coderepo.$rel.dir"} ||= $path; - $self->{"coderepo.$rel.cgiturl"} ||= $rel; + $self->{"coderepo.$rel.dir"} //= $path; + $self->{"coderepo.$rel.cgiturl"} //= _array($rel); } sub is_git_dir ($) { @@ -296,7 +254,7 @@ sub scan_projects_coderepo ($$$) { warn "failed to open cgit projectlist=$list: $!\n"; return; }; - foreach (<$fh>) { + while (<$fh>) { chomp; scan_path_coderepo($self, $path, "$path/$_"); } @@ -321,7 +279,7 @@ sub parse_cgitrc { # FIXME: this doesn't support macro expansion via $VARS, yet my $repo; - foreach (<$fh>) { + while (<$fh>) { chomp; if (m!\Arepo\.url=(.+?)/*\z!) { my $nick = $1; @@ -379,13 +337,14 @@ sub _fill_code_repo { _array($self->{lc("$pfx.${t}UrlFormat")}); } - if (my $cgits = $self->{lc("$pfx.cgitUrl")}) { + if (defined(my $cgits = $self->{"$pfx.cgiturl"})) { $git->{cgit_url} = $cgits = _array($cgits); + $self->{"$pfx.cgiturl"} = $cgits; # 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 { + $git->{$t.'_url_format'} //= map { "$_/$t/?id=%s" } @$cgits; } @@ -394,8 +353,8 @@ sub _fill_code_repo { $git; } -sub _git_config_bool ($) { - my ($val) = @_; +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) { @@ -405,20 +364,48 @@ sub _git_config_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 = {}; - foreach my $k (qw(mainrepo filter url newsgroup - infourl watch watchheader httpbackendmax - replyto feedmax nntpserver indexlevel)) { + 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; + } + } + } + + # "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; - if (defined(my $bval = _git_config_bool($v))) { + if (defined(my $bval = git_bool($v))) { $ibx->{$k} = $bval; } else { warn "Ignoring $pfx.$k=$v in config, not boolean\n"; @@ -426,23 +413,21 @@ sub _fill { } # TODO: more arrays, we should support multi-value for # more things to encourage decentralization - foreach my $k (qw(address altid nntpmirror coderepo hide listid)) { + foreach 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 $ibx->{mainrepo}; - 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($_); @@ -450,18 +435,42 @@ sub _fill { $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}->{$list_id} = $ibx; + $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; } } - if (my $ng = $ibx->{newsgroup}) { - $self->{-by_newsgroup}->{$ng} = $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}; - each_inbox($self, sub {}); # noop to populate -no_obfuscate + fill_all($self); # noop to populate -no_obfuscate } if (my $ibx_code_repos = $ibx->{coderepo}) { @@ -473,13 +482,54 @@ sub _fill { $valid += valid_inbox_name($_) foreach (@parts); $valid == scalar(@parts) or next; - my $repo = $code_repos->{$nick} ||= + my $repo = $code_repos->{$nick} //= _fill_code_repo($self, $nick); push @$repo_objs, $repo if $repo; } } + 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 ($$) { + my ($self, $pfx) = @_; + require PublicInbox::ExtSearch; + my $d = $self->{"$pfx.topdir"}; + defined($d) && -d $d ? PublicInbox::ExtSearch->new($d) : undef; +} - $ibx +sub urlmatch { + my ($self, $key, $url) = @_; + state $urlmatch_broken; # requires git 1.8.5 + return if $urlmatch_broken; + my $file = 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; + } +} + +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;