X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FGit.pm;h=9059584086ca57ecfb3411cb2cae12b87cc9496b;hb=46baf956987dca495ed44b1050e64939fae5c8ab;hp=a61cb31b7f903bd1252badaf7cb15eadddf09ed9;hpb=afd27ef5d80792091de97363c563679880083d54;p=public-inbox.git diff --git a/lib/PublicInbox/Git.pm b/lib/PublicInbox/Git.pm index a61cb31b..90595840 100644 --- a/lib/PublicInbox/Git.pm +++ b/lib/PublicInbox/Git.pm @@ -1,4 +1,4 @@ -# Copyright (C) 2014-2018 all contributors +# Copyright (C) 2014-2019 all contributors # License: GPLv2 or later # # Used to read files from a git repository without excessive forking. @@ -12,9 +12,15 @@ use warnings; use POSIX qw(dup2); require IO::Handle; use PublicInbox::Spawn qw(spawn popen_rd); +use PublicInbox::Tmpfile; use base qw(Exporter); our @EXPORT_OK = qw(git_unquote git_quote); +use constant MAX_INFLIGHT => + ($^O eq 'linux' ? 4096 : POSIX::_POSIX_PIPE_BUF()) + / + 65; # SHA-256 hex size + "\n" in preparation for git using non-SHA1 + my %GIT_ESC = ( a => "\a", b => "\b", @@ -50,13 +56,27 @@ sub new { my ($class, $git_dir) = @_; my @st; $st[7] = $st[10] = 0; - # may contain {-wt} field (working-tree (File::Temp::Dir)) - bless { git_dir => $git_dir, st => \@st }, $class + # may contain {-tmp} field for File::Temp::Dir + bless { git_dir => $git_dir, st => \@st, -git_path => {} }, $class +} + +sub git_path ($$) { + my ($self, $path) = @_; + $self->{-git_path}->{$path} ||= do { + local $/ = "\n"; + chomp(my $str = $self->qx(qw(rev-parse --git-path), $path)); + + # git prior to 2.5.0 did not understand --git-path + if ($str eq "--git-path\n$path") { + $str = "$self->{git_dir}/$path"; + } + $str; + }; } sub alternates_changed { my ($self) = @_; - my $alt = "$self->{git_dir}/objects/info/alternates"; + my $alt = git_path($self, 'objects/info/alternates'); my @st = stat($alt) or return 0; my $old_st = $self->{st}; # 10 - ctime, 7 - size @@ -92,10 +112,12 @@ sub _bidi_pipe { fcntl($in_w, 1031, 4096) if $batch eq '--batch-check'; } - my @cmd = ('git', "--git-dir=$self->{git_dir}", qw(cat-file), $batch); + my @cmd = (qw(git), "--git-dir=$self->{git_dir}", + qw(-c core.abbrev=40 cat-file), $batch); my $redir = { 0 => fileno($out_r), 1 => fileno($in_w) }; if ($err) { - open(my $fh, '+>', undef) or fail($self, "open.err failed: $!"); + my $id = "git.$self->{git_dir}$batch.err"; + my $fh = tmpfile($id) or fail($self, "tmpfile($id): $!"); $self->{$err} = $fh; $redir->{2} = fileno($fh); } @@ -107,10 +129,50 @@ sub _bidi_pipe { $self->{$in} = $in_r; } +sub read_cat_in_full ($$$) { + 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 ($$$) { + my ($self, $inflight, $in) = @_; + my $cb = shift @$inflight or die 'BUG: inflight empty'; + local $/ = "\n"; + my $head = $in->getline; + return eval { $cb->(undef) } if $head =~ / missing$/; + + $head =~ /^([0-9a-f]{40}) (\S+) ([0-9]+)$/ or + fail($self, "Unexpected result from async git cat-file: $head"); + my ($oid_hex, $type, $size) = ($1, $2, $3 + 0); + my $bref = read_cat_in_full($self, $in, $size); + eval { $cb->($bref, $oid_hex, $type, $size) }; +} + +sub cat_async_wait ($) { + my ($self) = @_; + my $inflight = delete $self->{inflight} or return; + my $in = $self->{in}; + while (scalar(@$inflight)) { + _cat_async_step($self, $inflight, $in); + } +} + sub cat_file { my ($self, $obj, $ref) = @_; my ($retried, $in, $head); - + cat_async_wait($self); again: batch_prepare($self); $self->{out}->print($obj, "\n") or fail($self, "write error: $!"); @@ -126,47 +188,12 @@ again: } return; } - $head =~ /^[0-9a-f]{40} \S+ (\d+)$/ or + $head =~ /^[0-9a-f]{40} \S+ ([0-9]+)$/ or fail($self, "Unexpected result from git cat-file: $head"); my $size = $1; - my $ref_type = $ref ? ref($ref) : ''; - - my $rv; - my $left = $size; - $$ref = $size if ($ref_type eq 'SCALAR'); - my $cb_err; - - if ($ref_type eq 'CODE') { - $rv = eval { $ref->($in, \$left) }; - $cb_err = $@; - # drain the rest - my $max = 8192; - while ($left > 0) { - my $r = read($in, my $x, $left > $max ? $max : $left); - defined($r) or fail($self, "read failed: $!"); - $r == 0 and fail($self, 'exited unexpectedly'); - $left -= $r; - } - } else { - 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; - } - $rv = \$buf; - } - - my $r = read($in, my $buf, 1); - defined($r) or fail($self, "read failed: $!"); - fail($self, 'newline missing after blob') if ($r != 1 || $buf ne "\n"); - die $cb_err if $cb_err; - - $rv; + $$ref = $size if $ref; + read_cat_in_full($self, $in, $size); } sub batch_prepare ($) { _bidi_pipe($_[0], qw(--batch in out pid)) } @@ -178,11 +205,13 @@ sub check { local $/ = "\n"; chomp(my $line = $self->{in_c}->getline); my ($hex, $type, $size) = split(' ', $line); - return if $type eq 'missing'; - # "dead" in git.git shows "dangling 4\ndead\n", not sure why - # https://public-inbox.org/git/20190118033845.s2vlrb3wd3m2jfzu@dcvr/ - # so handle the oddball stuff just in case + # 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); @@ -194,17 +223,25 @@ sub check { } sub _destroy { - my ($self, $in, $out, $pid) = @_; + my ($self, $in, $out, $pid, $err) = @_; my $p = delete $self->{$pid} or return; - foreach my $f ($in, $out) { - delete $self->{$f}; - } - waitpid $p, 0; + 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) = @_; - cleanup($self); + $self->{inflight} ? cat_async_abort($self) : cleanup($self); die $msg; } @@ -224,10 +261,12 @@ sub qx { <$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)); + _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 @@ -236,7 +275,8 @@ sub cleanup { sub packed_bytes { my ($self) = @_; my $n = 0; - foreach my $p (glob("$self->{git_dir}/objects/pack/*.pack")) { + my $pack_dir = git_path($self, 'objects/pack'); + foreach my $p (glob("$pack_dir/*.pack")) { $n += -s $p; } $n @@ -254,25 +294,67 @@ sub local_nick ($) { wantarray ? ($ret) : $ret; } -# show the blob URL for cgit/gitweb/whatever -sub src_blob_url { - my ($self, $oid) = @_; - # blob_url_format = "https://example.com/foo.git/blob/%s" - if (my $bfu = $self->{blob_url_format}) { - return map { sprintf($_, $oid) } @$bfu if wantarray; - return sprintf($bfu->[0], $oid); - } - local_nick($self); +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) = @_; + my ($self, $env) = @_; if (my $urls = $self->{cgit_url}) { - return @$urls; + 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 ($$$) { + my ($self, $oid, $cb) = @_; + my $inflight = $self->{inflight} or die 'BUG: not in async'; + if (scalar(@$inflight) >= MAX_INFLIGHT) { + _cat_async_step($self, $inflight, $self->{in}); + } + + $self->{out}->print($oid, "\n") or fail($self, "write error: $!"); + push @$inflight, $cb; +} + +sub commit_title ($$) { + my ($self, $oid) = @_; # PublicInbox::Git, $sha1hex + my $buf = cat_file($self, $oid) or return; + utf8::decode($$buf); + ($$buf =~ /\r?\n\r?\n([^\r\n]+)\r?\n?/)[0] +} + +# 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)); + defined $fh or return $modified; + local $/ = "\n"; + foreach my $oid (<$fh>) { + chomp $oid; + my $buf = cat_file($self, $oid) or next; + $$buf =~ /^committer .*?> ([0-9]+) [\+\-]?[0-9]+/sm or next; + my $cmt_time = $1 + 0; + $modified = $cmt_time if $cmt_time > $modified; + } + $modified || time; +} + 1; __END__ =pod