-# Copyright (C) 2014-2015 all contributors <meta@public-inbox.org>
-# License: AGPLv3 or later (https://www.gnu.org/licenses/agpl-3.0.txt)
+# Copyright (C) 2014-2020 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
+#
+# Note: I hate camelCase; but git-config(1) uses it, but it's better
+# than alllowercasewithoutunderscores, so use lc('configKey') where
+# applicable for readability
+
package PublicInbox::Config;
use strict;
use warnings;
-require PublicInbox::Inbox;
+use PublicInbox::Inbox;
use PublicInbox::Spawn qw(popen_rd);
-use File::Path::Expand qw/expand_filename/;
+
+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 $self;
+ if (ref($file) eq 'SCALAR') { # used by some tests
+ open my $fh, '<', $file or die; # PerlIO::scalar
+ $self = config_fh_parse($fh, "\n", '=');
+ } else {
+ $self = git_config_dump($file);
+ }
+ bless $self, $class;
# caches
- $self->{-by_addr} ||= {};
- $self->{-by_name} ||= {};
- $self->{-by_newsgroup} ||= {};
+ $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->{-cgitrc_unparsed} = $self->{'publicinbox.cgitrc'};
+
+ if (my $no = delete $self->{'publicinbox.noobfuscate'}) {
+ $no = _array($no);
+ my @domains;
+ foreach my $n (@$no) {
+ my @n = split(/\s+/, $n);
+ foreach (@n) {
+ if (/\S+@\S+/) { # full address
+ $self->{-no_obfuscate}->{lc $_} = 1;
+ } else {
+ # allow "example.com" or "@example.com"
+ s/\A@//;
+ push @domains, quotemeta($_);
+ }
+ }
+ }
+ 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 ($$$) {
+ my ($self, $cache, $key) = @_;
+ $self->{$cache}->{$key} // do {
+ fill_all($self);
+ $self->{$cache}->{$key};
+ }
+}
+
sub lookup {
my ($self, $recipient) = @_;
- my $addr = lc($recipient);
- my $inbox = $self->{-by_addr}->{$addr};
- return $inbox if $inbox;
-
- my $pfx;
-
- foreach my $k (keys %$self) {
- $k =~ /\A(publicinbox\.[\w-]+)\.address\z/ or next;
- my $v = $self->{$k};
- if (ref($v) eq "ARRAY") {
- foreach my $alias (@$v) {
- (lc($alias) eq $addr) or next;
- $pfx = $1;
- last;
- }
- } else {
- (lc($v) eq $addr) or next;
- $pfx = $1;
- last;
- }
- }
- defined $pfx or return;
- _fill($self, $pfx);
+ _lookup_fill($self, '-by_addr', lc($recipient));
+}
+
+sub lookup_list_id {
+ my ($self, $list_id) = @_;
+ _lookup_fill($self, '-by_list_id', lc($list_id));
}
-sub lookup_name {
+sub lookup_name ($$) {
my ($self, $name) = @_;
- my $rv = $self->{-by_name}->{$name};
- return $rv if $rv;
- $rv = _fill($self, "publicinbox.$name") or return;
+ $self->{-by_name}->{$name} // _fill($self, "publicinbox.$name");
}
-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 =~ /\A(publicinbox\.[\w-]+)\.newsgroup\z/ or next;
- my $v = $self->{$k};
- my $pfx = $1;
- if ($v eq $ng) {
- $rv = _fill($self, $pfx);
- return $rv;
- }
+sub each_inbox {
+ my ($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, $arg);
}
- undef;
}
-sub get {
- my ($self, $inbox, $key) = @_;
+sub lookup_newsgroup {
+ my ($self, $ng) = @_;
+ _lookup_fill($self, '-by_newsgroup', lc($ng));
+}
- $self->{"publicinbox.$inbox.$key"};
+sub limiter {
+ my ($self, $name) = @_;
+ $self->{-limiters}->{$name} //= do {
+ require PublicInbox::Qspawn;
+ 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} || expand_filename('~/.public-inbox') }
+sub config_dir { $ENV{PI_DIR} // "$ENV{HOME}/.public-inbox" }
sub default_file {
my $f = $ENV{PI_CONFIG};
config_dir() . '/config';
}
-sub git_config_dump {
- my ($file) = @_;
- my ($in, $out);
- my @cmd = (qw/git config/, "--file=$file", '-l');
- my $cmd = join(' ', @cmd);
- my $fh = popen_rd(\@cmd);
+sub config_fh_parse ($$$) {
+ my ($fh, $rs, $fs) = @_;
my %rv;
- local $/ = "\n";
- foreach my $line (<$fh>) {
+ my (%section_seen, @section_order);
+ local $/ = $rs;
+ while (defined(my $line = <$fh>)) {
chomp $line;
- my ($k, $v) = split(/=/, $line, 2);
- my $cur = $rv{$k};
+ 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 $cur) {
if (ref($cur) eq "ARRAY") {
push @$cur, $v;
$rv{$k} = $v;
}
}
- close $fh or die "failed to close ($cmd) pipe: $?";
+ $rv{-section_order} = \@section_order;
+
\%rv;
}
+sub git_config_dump {
+ my ($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 $rv = config_fh_parse($fh, "\0", "\n");
+ close $fh or die "failed to close ($cmd) pipe: $?";
+ $rv;
+}
+
+sub valid_inbox_name ($) {
+ my ($name) = @_;
+
+ # Similar rules found in git.git/remote.c::valid_remote_nick
+ # and git.git/refs.c::check_refname_component
+ # We don't reject /\.lock\z/, however, since we don't lock refs
+ if ($name eq '' || $name =~ /\@\{/ ||
+ $name =~ /\.\./ || $name =~ m![/:\?\[\]\^~\s\f[:cntrl:]\*]! ||
+ $name =~ /\A\./ || $name =~ /\.\z/) {
+ return 0;
+ }
+
+ # Note: we allow URL-unfriendly characters; users may configure
+ # non-HTTP-accessible inboxes
+ 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";
+
+ # TODO: support gitweb and other repository viewers?
+ if (defined(my $cgitrc = delete $self->{-cgitrc_unparsed})) {
+ parse_cgitrc($self, $cgitrc, 0);
+ }
+ my $dir = $self->{"$pfx.dir"}; # aka "GIT_DIR"
+ unless (defined $dir) {
+ warn "$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;
+
+ # 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;
+ }
+ }
+
+ $git;
+}
+
+sub _git_config_bool ($) {
+ my ($val) = @_;
+ if ($val =~ /\A(?:false|no|off|[\-\+]?(?:0x)?0+)\z/i) {
+ 0;
+ } elsif ($val =~ /\A(?:true|yes|on|[\-\+]?(?:0x)?[0-9]+)\z/i) {
+ 1;
+ } else {
+ undef;
+ }
+}
+
sub _fill {
my ($self, $pfx) = @_;
- my $rv = {};
+ my $ibx = {};
- foreach my $k (qw(mainrepo address filter url newsgroup)) {
+ foreach my $k (qw(inboxdir filter newsgroup
+ watch httpbackendmax
+ replyto feedmax nntpserver indexlevel)) {
my $v = $self->{"$pfx.$k"};
- $rv->{$k} = $v if defined $v;
+ $ibx->{$k} = $v if defined $v;
}
- return unless $rv->{mainrepo};
+
+ # backwards compatibility:
+ $ibx->{inboxdir} //= $self->{"$pfx.mainrepo"};
+
+ foreach my $k (qw(obfuscate)) {
+ my $v = $self->{"$pfx.$k"};
+ defined $v or next;
+ if (defined(my $bval = _git_config_bool($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 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\.//;
- $rv->{name} = $name;
- my $v = $rv->{address} ||= 'public-inbox@example.com';
- my $p = $rv->{-primary_address} = ref($v) eq 'ARRAY' ? $v->[0] : $v;
- $rv->{domain} = ($p =~ /\@(\S+)\z/) ? $1 : 'localhost';
- $rv = PublicInbox::Inbox->new($rv);
- if (ref($v) eq 'ARRAY') {
- $self->{-by_addr}->{lc($_)} = $rv foreach @$v;
- } else {
- $self->{-by_addr}->{lc($v)} = $rv;
+
+ if (!valid_inbox_name($name)) {
+ warn "invalid inbox name: '$name'\n";
+ return;
+ }
+
+ $ibx->{name} = $name;
+ $ibx->{-pi_config} = $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}) {
+ foreach my $list_id (@$listids) {
+ $self->{-by_list_id}->{$list_id} = $ibx;
+ }
+ }
+ if (my $ng = $ibx->{newsgroup}) {
+ $self->{-by_newsgroup}->{$ng} = $ibx;
}
- if (my $ng = $rv->{newsgroup}) {
- $self->{-by_newsgroup}->{$ng} = $rv;
+ $self->{-by_name}->{$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
}
- $self->{-by_name}->{$name} = $rv;
+
+ 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 == scalar(@parts) or next;
+
+ my $repo = $code_repos->{$nick} //=
+ _fill_code_repo($self, $nick);
+ push @$repo_objs, $repo if $repo;
+ }
+ }
+
+ $ibx
}
1;