diff options
Diffstat (limited to 'lib/PublicInbox/Config.pm')
-rw-r--r-- | lib/PublicInbox/Config.pm | 325 |
1 files changed, 229 insertions, 96 deletions
diff --git a/lib/PublicInbox/Config.pm b/lib/PublicInbox/Config.pm index d38f6586..d6300610 100644 --- a/lib/PublicInbox/Config.pm +++ b/lib/PublicInbox/Config.pm @@ -1,4 +1,4 @@ -# Copyright (C) 2014-2021 all contributors <meta@public-inbox.org> +# Copyright (C) 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 @@ -10,26 +10,28 @@ package PublicInbox::Config; use strict; use v5.10.1; +use parent qw(Exporter); +our @EXPORT_OK = qw(glob2re rel2abs_collapsed); use PublicInbox::Inbox; -use PublicInbox::Spawn qw(popen_rd); +use PublicInbox::Spawn qw(popen_rd run_qx); our $LD_PRELOAD = $ENV{LD_PRELOAD}; # only valid at startup +our $DEDUPE; # set to {} to dedupe or clear cache sub _array ($) { 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, $errfh) = @_; + my ($class, $file, $lei) = @_; $file //= default_file(); - 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", '='); - bless $self, $class; - } else { - $self = git_config_dump($class, $file, $errfh); - $self->{'-f'} = $file; - } + my ($self, $set_dedupe); + if (-f $file && $DEDUPE) { + $file = rel2abs_collapsed($file); + $self = $DEDUPE->{$file} and return $self; + $set_dedupe = 1; + } + $self = git_config_dump($class, $file, $lei); + $self->{-f} = $file; # caches $self->{-by_addr} = {}; $self->{-by_list_id} = {}; @@ -38,8 +40,7 @@ sub new { $self->{-by_eidx_key} = {}; $self->{-no_obfuscate} = {}; $self->{-limiters} = {}; - $self->{-code_repos} = {}; # nick => PublicInbox::Git object - $self->{-cgitrc_unparsed} = $self->{'publicinbox.cgitrc'}; + $self->{-coderepos} = {}; # nick => PublicInbox::Git object if (my $no = delete $self->{'publicinbox.noobfuscate'}) { $no = _array($no); @@ -62,7 +63,7 @@ sub new { if (my $css = delete $self->{'publicinbox.css'}) { $self->{css} = _array($css); } - + $DEDUPE->{$file} = $self if $set_dedupe; $self; } @@ -123,9 +124,9 @@ sub lookup_newsgroup { sub limiter { my ($self, $name) = @_; $self->{-limiters}->{$name} //= do { - require PublicInbox::Qspawn; + require PublicInbox::Limiter; my $max = $self->{"publicinboxlimiter.$name.max"} || 1; - my $limiter = PublicInbox::Qspawn::Limiter->new($max); + my $limiter = PublicInbox::Limiter->new($max); $limiter->setup_rlimit($name, $self); $limiter; }; @@ -143,8 +144,11 @@ sub config_fh_parse ($$$) { local $/ = $rs; while (defined($line = <$fh>)) { # perf critical with giant configs $i = index($line, $fs); + # $i may be -1 if $fs not found and it's a key-only entry + # (meaning boolean true). Either way the -1 will drop the + # $rs either from $k or $v. $k = substr($line, 0, $i); - $v = substr($line, $i + 1, -1); # chop off $fs + $v = $i >= 0 ? substr($line, $i + 1, -1) : 1; $section = substr($k, 0, rindex($k, '.')); $seen{$section} //= push(@section_order, $section); @@ -163,13 +167,34 @@ sub config_fh_parse ($$$) { \%rv; } +sub tmp_cmd_opt ($$) { + my ($env, $opt) = @_; + # quiet global and system gitconfig if supported by installed git, + # but normally harmless if too noisy (NOGLOBAL no longer exists) + $env->{GIT_CONFIG_NOSYSTEM} = 1; + $env->{GIT_CONFIG_GLOBAL} = '/dev/null'; # git v2.32+ + $opt->{-C} = '/'; # avoid $worktree/.git/config on MOST systems :P +} + sub git_config_dump { - my ($class, $file, $errfh) = @_; - return bless {}, $class unless -e $file; - my $cmd = [ qw(git config -z -l --includes), "--file=$file" ]; - my $fh = popen_rd($cmd, undef, { 2 => $errfh // 2 }); + my ($class, $file, $lei) = @_; + my @opt_c = map { ('-c', $_) } @{$lei->{opt}->{c} // []}; + $file = undef if !-e $file; + # XXX should we set {-f} if !-e $file? + return bless {}, $class if (!@opt_c && !defined($file)); + my %env; + my $opt = { 2 => $lei->{2} // 2 }; + if (@opt_c) { + unshift(@opt_c, '-c', "include.path=$file") if defined($file); + tmp_cmd_opt(\%env, $opt); + } + my @cmd = ('git', @opt_c, qw(config -z -l --includes)); + push(@cmd, '-f', $file) if !@opt_c && defined($file); + my $fh = popen_rd(\@cmd, \%env, $opt); my $rv = config_fh_parse($fh, "\0", "\n"); - close $fh or die "@$cmd failed: \$?=$?\n"; + $fh->close or die "@cmd failed: \$?=$?\n"; + $rv->{-opt_c} = \@opt_c if @opt_c; # for ->urlmatch + $rv->{-f} = $file; bless $rv, $class; } @@ -220,7 +245,6 @@ sub cgit_repo_merge ($$$) { $rel =~ s!/?\.git\z!!; } $self->{"coderepo.$rel.dir"} //= $path; - $self->{"coderepo.$rel.cgiturl"} //= _array($rel); } sub is_git_dir ($) { @@ -256,10 +280,11 @@ sub scan_tree_coderepo ($$) { scan_path_coderepo($self, $path, $path); } -sub scan_projects_coderepo ($$$) { - my ($self, $list, $path) = @_; - open my $fh, '<', $list or do { - warn "failed to open cgit projectlist=$list: $!\n"; +sub scan_projects_coderepo ($$) { + my ($self, $path) = @_; + my $l = $self->{-cgit_project_list} // die 'BUG: no cgit_project_list'; + open my $fh, '<', $l or do { + warn "failed to open cgit project-list=$l: $!\n"; return; }; while (<$fh>) { @@ -268,8 +293,20 @@ sub scan_projects_coderepo ($$$) { } } +sub apply_cgit_scan_path { + my ($self, @paths) = @_; + @paths or @paths = @{$self->{-cgit_scan_path}}; + if (defined($self->{-cgit_project_list})) { + for my $p (@paths) { scan_projects_coderepo($self, $p) } + } else { + for my $p (@paths) { scan_tree_coderepo($self, $p) } + } +} + sub parse_cgitrc { my ($self, $cgitrc, $nesting) = @_; + $cgitrc //= $self->{'publicinbox.cgitrc'} // + $ENV{CGIT_CONFIG} // return; if ($nesting == 0) { # defaults: my %s = map { $_ => 1 } qw(/cgit.css /cgit.png @@ -309,51 +346,41 @@ sub parse_cgitrc { my ($k, $v) = ($1, $2); $k =~ tr/-/_/; $self->{"-cgit_$k"} = $v; + delete $self->{-cgit_scan_path} if $k eq 'project_list'; } elsif (m!\Ascan-path=(.+)\z!) { - if (defined(my $list = $self->{-cgit_project_list})) { - scan_projects_coderepo($self, $list, $1); - } else { - scan_tree_coderepo($self, $1); - } + # this depends on being after project-list in the + # config file, just like cgit.c + push @{$self->{-cgit_scan_path}}, $1; + apply_cgit_scan_path($self, $1); } elsif (m!\A(?:css|favicon|logo|repo\.logo)=(/.+)\z!) { # absolute paths for static files via PublicInbox::Cgit $self->{-cgit_static}->{$1} = 1; + } elsif (s!\Asnapshots=\s*!!) { + $self->{'coderepo.snapshots'} = $_; } } cgit_repo_merge($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"; - - 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")}); +sub valid_dir ($$) { + my $dir = get_1($_[0], $_[1]) // return; + index($dir, "\n") < 0 ? $dir : do { + warn "E: `$_[1]=$dir' must not contain `\\n'\n"; + undef; } +} +# parse a code repo, only git is supported at the moment +sub fill_coderepo { + my ($self, $nick) = @_; + my $pfx = "coderepo.$nick"; + my $git = PublicInbox::Git->new(valid_dir($self, "$pfx.dir") // return); 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; - } } - + my %dedupe = ($nick => undef); + ($git->{nick}) = keys %dedupe; $git; } @@ -378,7 +405,7 @@ sub git_bool { # is sufficient and doesn't leave "/.." or "/../" sub rel2abs_collapsed { require File::Spec; - my $p = File::Spec->rel2abs($_[-1]); + my $p = File::Spec->rel2abs(@_); return $p if substr($p, -3, 3) ne '/..' && index($p, '/../') < 0; require Cwd; Cwd::abs_path($p); @@ -394,11 +421,12 @@ sub get_1 { sub repo_objs { my ($self, $ibxish) = @_; - my $ibx_code_repos = $ibxish->{coderepo} or return; - $ibxish->{-repo_objs} //= do { - my $code_repos = $self->{-code_repos}; + $ibxish->{-repo_objs} // do { + my $ibx_coderepos = $ibxish->{coderepo} // return; + parse_cgitrc($self, undef, 0); + my $coderepos = $self->{-coderepos}; my @repo_objs; - for my $nick (@$ibx_code_repos) { + for my $nick (@$ibx_coderepos) { my @parts = split(m!/!, $nick); for (@parts) { @parts = () unless valid_foo_name($_); @@ -407,15 +435,18 @@ sub repo_objs { warn "invalid coderepo name: `$nick'\n"; next; } - my $repo = $code_repos->{$nick} //= - _fill_code_repo($self, $nick); - push @repo_objs, $repo if $repo; + my $repo = $coderepos->{$nick} //= + fill_coderepo($self, $nick); + $repo ? push(@repo_objs, $repo) : + warn("coderepo.$nick.dir unset\n"); } if (scalar @repo_objs) { - \@repo_objs; + for (@repo_objs) { + push @{$_->{ibx_names}}, $ibxish->{name}; + } + $ibxish->{-repo_objs} = \@repo_objs; } else { delete $ibxish->{coderepo}; - undef; } } } @@ -428,18 +459,15 @@ sub _fill_ibx { my $v = $self->{"$pfx.$k"}; $ibx->{$k} = $v if defined $v; } - for my $k (qw(filter inboxdir newsgroup replyto httpbackendmax feedmax + for my $k (qw(filter newsgroup replyto httpbackendmax feedmax indexlevel indexsequentialshard boost)) { my $v = get_1($self, "$pfx.$k") // next; $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; - } + my $dir = $ibx->{inboxdir} = valid_dir($self, "$pfx.inboxdir") // + valid_dir($self, "$pfx.mainrepo") // return; for my $k (qw(obfuscate)) { my $v = $self->{"$pfx.$k"} // next; if (defined(my $bval = git_bool($v))) { @@ -452,13 +480,15 @@ sub _fill_ibx { # more things to encourage decentralization for my $k (qw(address altid nntpmirror imapmirror coderepo hide listid url - infourl watchheader nntpserver imapserver)) { + infourl watchheader + nntpserver imapserver pop3server)) { my $v = $self->{"$pfx.$k"} // next; $ibx->{$k} = _array($v); } return unless valid_foo_name($name, 'publicinbox'); - $ibx->{name} = $name; + my %dedupe = ($name => undef); + ($ibx->{name}) = keys %dedupe; # used as a key everywhere $ibx->{-pi_cfg} = $self; $ibx = PublicInbox::Inbox->new($ibx); foreach (@{$ibx->{address}}) { @@ -486,9 +516,16 @@ sub _fill_ibx { delete $ibx->{newsgroup}; warn "newsgroup name invalid: `$ngname'\n"; } else { + my $lc = $ibx->{newsgroup} = lc $ngname; + warn <<EOM if $lc ne $ngname; +W: newsgroup=`$ngname' lowercased to `$lc' +EOM # PublicInbox::NNTPD does stricter ->nntp_usable # checks, keep this lean for startup speed - $self->{-by_newsgroup}->{$ngname} = $ibx; + my $cur = $self->{-by_newsgroup}->{$lc} //= $ibx; + warn <<EOM if $cur != $ibx; +W: newsgroup=`$lc' is used by both `$cur->{name}' and `$ibx->{name}' +EOM } } unless (defined $ibx->{newsgroup}) { # for ->eidx_key @@ -508,19 +545,18 @@ sub _fill_ibx { require PublicInbox::Isearch; $ibx->{isrch} = PublicInbox::Isearch->new($ibx, $es); } - $self->{-by_eidx_key}->{$ibx->eidx_key} = $ibx; + my $cur = $self->{-by_eidx_key}->{my $ekey = $ibx->eidx_key} //= $ibx; + $cur == $ibx or warn + "W: `$ekey' used by both `$cur->{name}' and `$ibx->{name}'\n"; + $ibx; } sub _fill_ei ($$) { my ($self, $name) = @_; eval { require PublicInbox::ExtSearch } or return; my $pfx = "extindex.$name"; - my $d = $self->{"$pfx.topdir"} // return; + my $d = valid_dir($self, "$pfx.topdir") // return; -d $d or return; - if (index($d, "\n") >= 0) { - warn "E: `$d' must not contain `\\n'\n"; - return; - } my $es = PublicInbox::ExtSearch->new($d); for my $k (qw(indexlevel indexsequentialshard)) { my $v = get_1($self, "$pfx.$k") // next; @@ -535,23 +571,76 @@ sub _fill_ei ($$) { $es; } +sub _fill_csrch ($$) { + my ($self, $name) = @_; # "" is a valid name for cindex + return if $name ne '' && !valid_foo_name($name, 'cindex'); + eval { require PublicInbox::CodeSearch } or return; + my $pfx = "cindex.$name"; + my $d = valid_dir($self, "$pfx.topdir") // return; + -d $d or return; + my $csrch = PublicInbox::CodeSearch->new($d, $self); + for my $k (qw(localprefix)) { + my $v = $self->{"$pfx.$k"} // next; + $csrch->{$k} = _array($v); + } + $csrch->{name} = $name; + $csrch; +} + +sub lookup_cindex ($$) { + my ($self, $name) = @_; + $self->{-csrch_by_name}->{$name} //= _fill_csrch($self, $name); +} + +sub each_cindex { + my ($self, $cb, @arg) = @_; + my @csrch = map { + lookup_cindex($self, substr($_, length('cindex.'))) // () + } grep(m!\Acindex\.[^\./]*\z!, @{$self->{-section_order}}); + if (ref($cb) eq 'CODE') { + $cb->($_, @arg) for @csrch; + } else { # string function + $_->$cb(@arg) for @csrch; + } +} + +sub config_cmd { + my ($self, $env, $opt) = @_; + my $f = $self->{-f} // default_file(); + my @opt_c = @{$self->{-opt_c} // []}; + my @cmd = ('git', @opt_c, 'config'); + @opt_c ? tmp_cmd_opt($env, $opt) : push(@cmd, '-f', $f); + \@cmd; +} + sub urlmatch { - my ($self, $key, $url) = @_; + my $self = shift; + my @bool = $_[0] eq '--bool' ? (shift) : (); + my ($key, $url, $try_git) = @_; state $urlmatch_broken; # requires git 1.8.5 return if $urlmatch_broken; - my $file = $self->{'-f'} // 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; + my (%env, %opt); + my $cmd = $self->config_cmd(\%env, \%opt); + push @$cmd, @bool, qw(--includes -z --get-urlmatch), $key, $url; + my $val = run_qx($cmd, \%env, \%opt); + if ($?) { + undef $val; + if (@bool && ($? >> 8) == 128) { # not boolean + } elsif (($? >> 8) != 1) { + $urlmatch_broken = 1; + } elsif ($try_git) { # n.b. this takes cwd into account + $val = run_qx([qw(git config), @bool, + qw(-z --get-urlmatch), $key, $url]); + undef $val if $?; + } + } + $? = 0; # don't influence lei exit status + if (defined($val)) { + local $/ = "\0"; + chomp $val; + $val = git_bool($val) if @bool; } + $val; } sub json { @@ -575,4 +664,48 @@ sub squote_maybe ($) { $val; } +my %re_map = ( '*' => '[^/]*?', '?' => '[^/]', + '/**' => '/.*', '**/' => '.*/', '/**/' => '(?:/.*?/|/)', + '[' => '[', ']' => ']', ',' => ',' ); + +sub glob2re ($) { + my ($re) = @_; + my $p = ''; + my $in_bracket = 0; + my $qm = 0; + my $schema_host_port = ''; + + # don't glob URL-looking things that look like IPv6 + if ($re =~ s!\A([a-z0-9\+]+://\[[a-f0-9\:]+\](?::[0-9]+)?/)!!i) { + $schema_host_port = quotemeta $1; # "http://[::1]:1234" + } + my $changes = ($re =~ s!(/\*\*/|\A\*\*/|/\*\*\z|.)! + $re_map{$p eq '\\' ? '' : do { + if ($1 eq '[') { ++$in_bracket } + elsif ($1 eq ']') { --$in_bracket } + elsif ($1 eq ',') { ++$qm } # no change + $p = $1; + }} // do { + $p = $1; + ($p eq '-' && $in_bracket) ? $p : (++$qm, "\Q$p") + }!sge); + # bashism (also supported by curl): {a,b,c} => (a|b|c) + $changes += ($re =~ s/([^\\]*)\\\{([^,]*,[^\\]*)\\\}/ + (my $in_braces = $2) =~ tr!,!|!; + $1."($in_braces)"; + /sge); + ($changes - $qm) ? $schema_host_port.$re : undef; +} + +sub get_coderepo { + my ($self, $nick) = @_; + $self->{-coderepos}->{$nick} // do { + defined($self->{-cgit_scan_path}) ? do { + apply_cgit_scan_path($self); + my $cr = fill_coderepo($self, $nick); + $cr ? ($self->{-coderepos}->{$nick} = $cr) : undef; + } : undef; + }; +} + 1; |