-# Copyright (C) 2014-2019 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
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] : [ $_[0] ] }
# if keys may be multi-value, the value is an array ref containing all values
sub new {
my ($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
$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
$self->{-by_name}->{$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, $arg) = @_;
+ my ($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);
+ $cb->($ibx, @arg);
}
}
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 {
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;
}
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) {
$rel =~ s!/?\.git\z!!;
}
$self->{"coderepo.$rel.dir"} //= $path;
- $self->{"coderepo.$rel.cgiturl"} //= $rel;
+ $self->{"coderepo.$rel.cgiturl"} //= _array($rel);
}
sub is_git_dir ($) {
warn "failed to open cgit projectlist=$list: $!\n";
return;
};
- foreach (<$fh>) {
+ while (<$fh>) {
chomp;
scan_path_coderepo($self, $path, "$path/$_");
}
# 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;
_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=
$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) {
}
}
+# 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(inboxdir 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 <<EOF;
+W: $pfx.$k has multiple values, only using `$v->[-1]'
+EOF
+ $ibx->{$k} = $v->[-1];
+ } else {
+ $ibx->{$k} = $v;
+ }
+ }
+ }
- # backwards compatibility:
- $ibx->{inboxdir} //= $self->{"$pfx.mainrepo"};
-
+ # "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";
}
# 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 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($_);
$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 (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}) {
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;
+}
+
+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;
+ }
+}
- $ibx
+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;