# Copyright (C) 2014-2020 all contributors # License: GPLv2 or later # # Used to read files from a git repository without excessive forking. # Used in our web interfaces as well as our -nntpd server. # This is based on code in Git.pm which is GPLv2+, but modified to avoid # dependence on environment variables for compatibility with mod_perl. # There are also API changes to simplify our usage and data set. package PublicInbox::Git; use strict; use warnings; use POSIX (); use IO::Handle; # ->autoflush use File::Glob qw(bsd_glob GLOB_NOSORT); use PublicInbox::Spawn qw(popen_rd); use PublicInbox::Tmpfile; use base qw(Exporter); our @EXPORT_OK = qw(git_unquote git_quote); use constant MAX_INFLIGHT => ($^O eq 'linux' ? 4096 : POSIX::_POSIX_PIPE_BUF()) / 65; # SHA-256 hex size + "\n" in preparation for git using non-SHA1 my %GIT_ESC = ( a => "\a", b => "\b", f => "\f", n => "\n", r => "\r", t => "\t", v => "\013", '"' => '"', '\\' => '\\', ); my %ESC_GIT = map { $GIT_ESC{$_} => $_ } keys %GIT_ESC; # unquote pathnames used by git, see quote.c::unquote_c_style.c in git.git sub git_unquote ($) { return $_[0] unless ($_[0] =~ /\A"(.*)"\z/); $_[0] = $1; $_[0] =~ s/\\([\\"abfnrtv])/$GIT_ESC{$1}/g; $_[0] =~ s/\\([0-7]{1,3})/chr(oct($1))/ge; $_[0]; } sub git_quote ($) { if ($_[0] =~ s/([\\"\a\b\f\n\r\t\013]|[^[:print:]])/ '\\'.($ESC_GIT{$1}||sprintf("%0o",ord($1)))/egs) { return qq{"$_[0]"}; } $_[0]; } sub new { my ($class, $git_dir) = @_; my @st; $st[7] = $st[10] = 0; # may contain {-tmp} field for File::Temp::Dir bless { git_dir => $git_dir, st => \@st, -git_path => {} }, $class } sub git_path ($$) { my ($self, $path) = @_; $self->{-git_path}->{$path} ||= do { local $/ = "\n"; chomp(my $str = $self->qx(qw(rev-parse --git-path), $path)); # git prior to 2.5.0 did not understand --git-path if ($str eq "--git-path\n$path") { $str = "$self->{git_dir}/$path"; } $str; }; } sub alternates_changed { my ($self) = @_; my $alt = git_path($self, 'objects/info/alternates'); my @st = stat($alt) or return 0; my $old_st = $self->{st}; # 10 - ctime, 7 - size return 0 if ($st[10] == $old_st->[10] && $st[7] == $old_st->[7]); $self->{st} = \@st; } sub last_check_err { my ($self) = @_; my $fh = $self->{err_c} or return; sysseek($fh, 0, 0) or fail($self, "sysseek failed: $!"); defined(sysread($fh, my $buf, -s $fh)) or fail($self, "sysread failed: $!"); $buf; } sub _bidi_pipe { my ($self, $batch, $in, $out, $pid, $err) = @_; if ($self->{$pid}) { if (defined $err) { # "err_c" my $fh = $self->{$err}; sysseek($fh, 0, 0) or fail($self, "sysseek failed: $!"); truncate($fh, 0) or fail($self, "truncate failed: $!"); } return; } my ($out_r, $out_w); pipe($out_r, $out_w) or fail($self, "pipe failed: $!"); my @cmd = (qw(git), "--git-dir=$self->{git_dir}", qw(-c core.abbrev=40 cat-file), $batch); my $redir = { 0 => $out_r }; if ($err) { my $id = "git.$self->{git_dir}$batch.err"; my $fh = tmpfile($id) or fail($self, "tmpfile($id): $!"); $self->{$err} = $fh; $redir->{2} = $fh; } my ($in_r, $p) = popen_rd(\@cmd, undef, $redir); $self->{$pid} = $p; $out_w->autoflush(1); if ($^O eq 'linux') { # 1031: F_SETPIPE_SZ fcntl($out_w, 1031, 4096); fcntl($in_r, 1031, 4096) if $batch eq '--batch-check'; } $self->{$out} = $out_w; $self->{$in} = $in_r; } sub read_cat_in_full ($$$) { my ($self, $in, $left) = @_; my $offset = 0; my $buf = ''; while ($left > 0) { my $r = read($in, $buf, $left, $offset); defined($r) or fail($self, "read failed: $!"); $r == 0 and fail($self, 'exited unexpectedly'); $left -= $r; $offset += $r; } my $r = read($in, my $lf, 1); defined($r) or fail($self, "read failed: $!"); fail($self, 'newline missing after blob') if ($r != 1 || $lf ne "\n"); \$buf; } sub _cat_async_step ($$$) { my ($self, $inflight, $in) = @_; my $pair = shift @$inflight or die 'BUG: inflight empty'; my ($cb, $arg) = @$pair; local $/ = "\n"; my $head = $in->getline; $head =~ / missing$/ and return eval { $cb->(undef, undef, undef, undef, $arg) }; $head =~ /^([0-9a-f]{40}) (\S+) ([0-9]+)$/ or fail($self, "Unexpected result from async git cat-file: $head"); my ($oid_hex, $type, $size) = ($1, $2, $3 + 0); my $bref = read_cat_in_full($self, $in, $size); eval { $cb->($bref, $oid_hex, $type, $size, $arg) }; } sub cat_async_wait ($) { my ($self) = @_; my $inflight = delete $self->{inflight} or return; my $in = $self->{in}; while (scalar(@$inflight)) { _cat_async_step($self, $inflight, $in); } } sub cat_file { my ($self, $obj, $ref) = @_; my ($retried, $in, $head); cat_async_wait($self); again: batch_prepare($self); $self->{out}->print($obj, "\n") or fail($self, "write error: $!"); $in = $self->{in}; local $/ = "\n"; $head = $in->getline; if ($head =~ / missing$/) { if (!$retried && alternates_changed($self)) { $retried = 1; cleanup($self); goto again; } return; } $head =~ /^[0-9a-f]{40} \S+ ([0-9]+)$/ or fail($self, "Unexpected result from git cat-file: $head"); my $size = $1; $$ref = $size if $ref; read_cat_in_full($self, $in, $size); } sub batch_prepare ($) { _bidi_pipe($_[0], qw(--batch in out pid)) } sub check { my ($self, $obj) = @_; _bidi_pipe($self, qw(--batch-check in_c out_c pid_c err_c)); $self->{out_c}->print($obj, "\n") or fail($self, "write error: $!"); local $/ = "\n"; chomp(my $line = $self->{in_c}->getline); my ($hex, $type, $size) = split(' ', $line); # Future versions of git.git may show 'ambiguous', but for now, # we must handle 'dangling' below (and maybe some other oddball # stuff): # https://public-inbox.org/git/20190118033845.s2vlrb3wd3m2jfzu@dcvr/T/ return if $type eq 'missing' || $type eq 'ambiguous'; if ($hex eq 'dangling' || $hex eq 'notdir' || $hex eq 'loop') { $size = $type + length("\n"); my $r = read($self->{in_c}, my $buf, $size); defined($r) or fail($self, "read failed: $!"); return; } ($hex, $type, $size); } sub _destroy { my ($self, $in, $out, $pid, $err) = @_; my $p = delete $self->{$pid} or return; delete @$self{($in, $out)}; delete $self->{$err} if $err; # `err_c' # PublicInbox::DS may not be loaded eval { PublicInbox::DS::dwaitpid($p, undef, undef) }; waitpid($p, 0) if $@; # wait synchronously if not in event loop } sub cat_async_abort ($) { my ($self) = @_; my $inflight = delete $self->{inflight} or die 'BUG: not in async'; cleanup($self); } sub fail { my ($self, $msg) = @_; $self->{inflight} ? cat_async_abort($self) : cleanup($self); die $msg; } sub popen { my ($self, @cmd) = @_; @cmd = ('git', "--git-dir=$self->{git_dir}", @cmd); popen_rd(\@cmd); } sub qx { my ($self, @cmd) = @_; my $fh = $self->popen(@cmd); local $/ = "\n"; return <$fh> if wantarray; local $/; <$fh> } # returns true if there are pending "git cat-file" processes sub cleanup { my ($self) = @_; _destroy($self, qw(in out pid)); _destroy($self, qw(in_c out_c pid_c err_c)); !!($self->{pid} || $self->{pid_c}); } # assuming a well-maintained repo, this should be a somewhat # accurate estimation of its size # TODO: show this in the WWW UI as a hint to potential cloners sub packed_bytes { my ($self) = @_; my $n = 0; my $pack_dir = git_path($self, 'objects/pack'); foreach my $p (bsd_glob("$pack_dir/*.pack", GLOB_NOSORT)) { $n += -s $p; } $n } sub DESTROY { cleanup(@_) } sub local_nick ($) { my ($self) = @_; my $ret = '???'; # don't show full FS path, basename should be OK: if ($self->{git_dir} =~ m!/([^/]+)(?:/\.git)?\z!) { $ret = "/path/to/$1"; } wantarray ? ($ret) : $ret; } sub host_prefix_url ($$) { my ($env, $url) = @_; return $url if index($url, '//') >= 0; my $scheme = $env->{'psgi.url_scheme'}; my $host_port = $env->{HTTP_HOST} // "$env->{SERVER_NAME}:$env->{SERVER_PORT}"; "$scheme://$host_port". ($env->{SCRIPT_NAME} || '/') . $url; } sub pub_urls { my ($self, $env) = @_; if (my $urls = $self->{cgit_url}) { return map { host_prefix_url($env, $_) } @$urls; } local_nick($self); } sub cat_async_begin { my ($self) = @_; cleanup($self) if alternates_changed($self); batch_prepare($self); die 'BUG: already in async' if $self->{inflight}; $self->{inflight} = []; } sub cat_async ($$$;$) { my ($self, $oid, $cb, $arg) = @_; my $inflight = $self->{inflight} or die 'BUG: not in async'; if (scalar(@$inflight) >= MAX_INFLIGHT) { _cat_async_step($self, $inflight, $self->{in}); } $self->{out}->print($oid, "\n") or fail($self, "write error: $!"); push(@$inflight, [ $cb, $arg ]); } sub extract_cmt_time { my ($bref, undef, undef, undef, $modified) = @_; if ($$bref =~ /^committer .*?> ([0-9]+) [\+\-]?[0-9]+/sm) { my $cmt_time = $1 + 0; $$modified = $cmt_time if $cmt_time > $$modified; } } # returns the modified time of a git repo, same as the "modified" field # of a grokmirror manifest sub modified ($) { my ($self) = @_; my $modified = 0; my $fh = popen($self, qw(rev-parse --branches)); cat_async_begin($self); local $/ = "\n"; while (my $oid = <$fh>) { chomp $oid; cat_async($self, $oid, \&extract_cmt_time, \$modified); } cat_async_wait($self); $modified || time; } 1; __END__ =pod =head1 NAME PublicInbox::Git - git wrapper =head1 VERSION version 1.0 =head1 SYNOPSIS use PublicInbox::Git; chomp(my $git_dir = `git rev-parse --git-dir`); $git_dir or die "GIT_DIR= must be specified\n"; my $git = PublicInbox::Git->new($git_dir); =head1 DESCRIPTION Unstable API outside of the L method. It requires L to be installed. =head1 METHODS =cut =head2 new my $git = PublicInbox::Git->new($git_dir); Initialize a new PublicInbox::Git object for use with L This is the only public API method we support. Everything else in this module is subject to change. =head1 SEE ALSO L, L =head1 CONTACT All feedback welcome via plain-text mail to L The mail archives are hosted at L =head1 COPYRIGHT Copyright (C) 2016 all contributors L License: AGPL-3.0+ L =cut