diff options
Diffstat (limited to 'lib/PublicInbox/Import.pm')
| -rw-r--r-- | lib/PublicInbox/Import.pm | 493 |
1 files changed, 405 insertions, 88 deletions
diff --git a/lib/PublicInbox/Import.pm b/lib/PublicInbox/Import.pm index 8eec17eb..b25427ee 100644 --- a/lib/PublicInbox/Import.pm +++ b/lib/PublicInbox/Import.pm @@ -7,19 +7,32 @@ package PublicInbox::Import; use strict; use warnings; -use Fcntl qw(:flock :DEFAULT); +use base qw(PublicInbox::Lock); use PublicInbox::Spawn qw(spawn); -use PublicInbox::MID qw(mid_mime mid2path); +use PublicInbox::MID qw(mids mid_mime mid2path); use PublicInbox::Address; +use PublicInbox::MsgTime qw(msg_timestamp msg_datestamp); +use PublicInbox::ContentId qw(content_digest); +use PublicInbox::MDA; +use POSIX qw(strftime); sub new { - my ($class, $git, $name, $email, $inbox) = @_; + my ($class, $git, $name, $email, $ibx) = @_; + my $ref = 'refs/heads/master'; + if ($ibx) { + $ref = $ibx->{ref_head} || 'refs/heads/master'; + $name ||= $ibx->{name}; + $email ||= $ibx->{-primary_address}; + } bless { git => $git, ident => "$name <$email>", mark => 1, - ref => 'refs/heads/master', - inbox => $inbox, + ref => $ref, + inbox => $ibx, + path_type => '2/38', # or 'v2' + lock_path => "$git->{git_dir}/ssoma.lock", # v2 changes this + bytes_added => 0, }, $class } @@ -33,25 +46,28 @@ sub gfi_start { pipe($in_r, $in_w) or die "pipe failed: $!"; pipe($out_r, $out_w) or die "pipe failed: $!"; my $git = $self->{git}; - my $git_dir = $git->{git_dir}; - my $lockpath = "$git_dir/ssoma.lock"; - sysopen(my $lockfh, $lockpath, O_WRONLY|O_CREAT) or - die "failed to open lock $lockpath: $!"; - # wait for other processes to be done - flock($lockfh, LOCK_EX) or die "lock failed: $!\n"; + $self->lock_acquire; + local $/ = "\n"; - chomp($self->{tip} = $git->qx(qw(rev-parse --revs-only), $self->{ref})); + my $ref = $self->{ref}; + chomp($self->{tip} = $git->qx(qw(rev-parse --revs-only), $ref)); + if ($self->{path_type} ne '2/38' && $self->{tip}) { + local $/ = "\0"; + my @tree = $git->qx(qw(ls-tree -r -z --name-only), $ref); + chomp @tree; + $self->{-tree} = { map { $_ => 1 } @tree }; + } + my $git_dir = $git->{git_dir}; my @cmd = ('git', "--git-dir=$git_dir", qw(fast-import - --quiet --done --date-format=rfc2822)); + --quiet --done --date-format=raw)); my $rdr = { 0 => fileno($out_r), 1 => fileno($in_w) }; my $pid = spawn(\@cmd, undef, $rdr); die "spawn fast-import failed: $!" unless defined $pid; $out_w->autoflush(1); $self->{in} = $in_r; $self->{out} = $out_w; - $self->{lockfh} = $lockfh; $self->{pid} = $pid; $self->{nchg} = 0; binmode $out_w, ':raw' or die "binmode :raw failed: $!"; @@ -61,14 +77,7 @@ sub gfi_start { sub wfail () { die "write to fast-import failed: $!" } -sub now2822 () { - my @t = gmtime(time); - my $day = qw(Sun Mon Tue Wed Thu Fri Sat)[$t[6]]; - my $mon = qw(Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec)[$t[4]]; - - sprintf('%s, %2d %s %d %02d:%02d:%02d +0000', - $day, $t[3], $mon, $t[5] + 1900, $t[2], $t[1], $t[0]); -} +sub now_raw () { time . ' +0000' } sub norm_body ($) { my ($mime) = @_; @@ -77,6 +86,7 @@ sub norm_body ($) { $b } +# only used for v1 (ssoma) inboxes sub _check_path ($$$$) { my ($r, $w, $tip, $path) = @_; return if $tip eq ''; @@ -86,27 +96,13 @@ sub _check_path ($$$$) { $info =~ /\Amissing / ? undef : $info; } -# returns undef on non-existent -# ('MISMATCH', msg) on mismatch -# (:MARK, msg) on success -sub remove { - my ($self, $mime, $msg) = @_; # mime = Email::MIME - - my $mid = mid_mime($mime); - my $path = mid2path($mid); - - my ($r, $w) = $self->gfi_start; - my $tip = $self->{tip}; - my $info = _check_path($r, $w, $tip, $path) or return ('MISSING',undef); - $info =~ m!\A100644 blob ([a-f0-9]{40})\t!s or die "not blob: $info"; - my $blob = $1; - - print $w "cat-blob $blob\n" or wfail; +sub _cat_blob ($$$) { + my ($r, $w, $oid) = @_; + print $w "cat-blob $oid\n" or wfail; local $/ = "\n"; - $info = <$r>; + my $info = <$r>; defined $info or die "EOF from fast-import / cat-blob: $!"; - $info =~ /\A[a-f0-9]{40} blob (\d+)\n\z/ or - die "unexpected cat-blob response: $info"; + $info =~ /\A[a-f0-9]{40} blob (\d+)\n\z/ or return; my $left = $1; my $offset = 0; my $buf = ''; @@ -121,7 +117,26 @@ sub remove { $n = read($r, my $lf, 1); defined($n) or die "read final byte of cat-blob failed: $!"; die "bad read on final byte: <$lf>" if $lf ne "\n"; - my $cur = PublicInbox::MIME->new($buf); + + # fixup some bugginess in old versions: + $buf =~ s/\A[\r\n]*From [^\r\n]*\r?\n//s; + \$buf; +} + +sub cat_blob { + my ($self, $oid) = @_; + my ($r, $w) = $self->gfi_start; + _cat_blob($r, $w, $oid); +} + +sub check_remove_v1 { + my ($r, $w, $tip, $path, $mime) = @_; + + my $info = _check_path($r, $w, $tip, $path) or return ('MISSING',undef); + $info =~ m!\A100644 blob ([a-f0-9]{40})\t!s or die "not blob: $info"; + my $oid = $1; + my $msg = _cat_blob($r, $w, $oid) or die "BUG: cat-blob $1 failed"; + my $cur = PublicInbox::MIME->new($msg); my $cur_s = $cur->header('Subject'); $cur_s = '' unless defined $cur_s; my $cur_m = $mime->header('Subject'); @@ -129,6 +144,103 @@ sub remove { if ($cur_s ne $cur_m || norm_body($cur) ne norm_body($mime)) { return ('MISMATCH', $cur); } + (undef, $cur); +} + +sub checkpoint { + my ($self) = @_; + return unless $self->{pid}; + print { $self->{out} } "checkpoint\n" or wfail; + undef; +} + +sub progress { + my ($self, $msg) = @_; + return unless $self->{pid}; + print { $self->{out} } "progress $msg\n" or wfail; + $self->{in}->getline eq "progress $msg\n" or die + "progress $msg not received\n"; + undef; +} + +sub _update_git_info ($$) { + my ($self, $do_gc) = @_; + # for compatibility with existing ssoma installations + # we can probably remove this entirely by 2020 + my $git_dir = $self->{git}->{git_dir}; + my @cmd = ('git', "--git-dir=$git_dir"); + my $index = "$git_dir/ssoma.index"; + if (-e $index && !$ENV{FAST}) { + my $env = { GIT_INDEX_FILE => $index }; + run_die([@cmd, qw(read-tree -m -v -i), $self->{ref}], $env); + } + run_die([@cmd, 'update-server-info'], undef); + ($self->{path_type} eq '2/38') and eval { + require PublicInbox::SearchIdx; + my $inbox = $self->{inbox} || $git_dir; + my $s = PublicInbox::SearchIdx->new($inbox); + $s->index_sync({ ref => $self->{ref} }); + }; + eval { run_die([@cmd, qw(gc --auto)], undef) } if $do_gc; +} + +sub barrier { + my ($self) = @_; + + # For safety, we ensure git checkpoint is complete before because + # the data in git is still more important than what is in Xapian + # in v2. Performance may be gained by delaying the ->progress + # call but we lose safety + if ($self->{nchg}) { + $self->checkpoint; + $self->progress('checkpoint'); + _update_git_info($self, 0); + $self->{nchg} = 0; + } +} + +# used for v2 +sub get_mark { + my ($self, $mark) = @_; + die "not active\n" unless $self->{pid}; + my ($r, $w) = $self->gfi_start; + print $w "get-mark $mark\n" or wfail; + defined(my $oid = <$r>) or die "get-mark failed, need git 2.6.0+\n"; + chomp($oid); + $oid; +} + +# returns undef on non-existent +# ('MISMATCH', Email::MIME) on mismatch +# (:MARK, Email::MIME) on success +# +# v2 callers should check with Xapian before calling this as +# it is not idempotent. +sub remove { + my ($self, $mime, $msg) = @_; # mime = Email::MIME + + my $path_type = $self->{path_type}; + my ($path, $err, $cur, $blob); + + my ($r, $w) = $self->gfi_start; + my $tip = $self->{tip}; + if ($path_type eq '2/38') { + $path = mid2path(v1_mid0($mime)); + ($err, $cur) = check_remove_v1($r, $w, $tip, $path, $mime); + return ($err, $cur) if $err; + } else { + my $sref; + if (ref($mime) eq 'SCALAR') { # optimization used by V2Writable + $sref = $mime; + } else { # XXX should not be necessary: + my $str = $mime->as_string; + $sref = \$str; + } + my $len = length($$sref); + $blob = $self->{mark}++; + print $w "blob\nmark :$blob\ndata $len\n", + $$sref, "\n" or wfail; + } my $ref = $self->{ref}; my $commit = $self->{mark}++; @@ -137,7 +249,7 @@ sub remove { print $w "reset $ref\n" or wfail; } my $ident = $self->{ident}; - my $now = now2822(); + my $now = now_raw(); $msg ||= 'rm'; my $len = length($msg) + 1; print $w "commit $ref\nmark :$commit\n", @@ -145,44 +257,146 @@ sub remove { "committer $ident $now\n", "data $len\n$msg\n\n", 'from ', ($parent ? $parent : $tip), "\n" or wfail; - print $w "D $path\n\n" or wfail; + if (defined $path) { + print $w "D $path\n\n" or wfail; + } else { + clean_tree_v2($self, $w, 'd'); + print $w "M 100644 :$blob d\n\n" or wfail; + } $self->{nchg}++; (($self->{tip} = ":$commit"), $cur); } -# returns undef on duplicate -sub add { - my ($self, $mime, $check_cb) = @_; # mime = Email::MIME +sub git_timestamp { + my ($ts, $zone) = @_; + $ts = 0 if $ts < 0; # git uses unsigned times + "$ts $zone"; +} +sub extract_author_info ($) { + my ($mime) = @_; + + my $sender = ''; my $from = $mime->header('From'); my ($email) = PublicInbox::Address::emails($from); my ($name) = PublicInbox::Address::names($from); + if (!defined($name) || !defined($email)) { + $sender = $mime->header('Sender'); + if (!defined($name)) { + ($name) = PublicInbox::Address::names($sender); + } + if (!defined($email)) { + ($email) = PublicInbox::Address::emails($sender); + } + } + if (defined $email) { + # quiet down wide character warnings with utf8::encode + utf8::encode($email); + } else { + $email = ''; + warn "no email in From: $from or Sender: $sender\n"; + } + # git gets confused with: # "'A U Thor <u@example.com>' via foo" <foo@example.com> # ref: # <CAD0k6qSUYANxbjjbE4jTW4EeVwOYgBD=bXkSu=akiYC_CB7Ffw@mail.gmail.com> - $name =~ tr/<>//d; + if (defined $name) { + $name =~ tr/<>//d; + utf8::encode($name); + } else { + $name = ''; + warn "no name in From: $from or Sender: $sender\n"; + } + ($name, $email); +} + +# kill potentially confusing/misleading headers +sub drop_unwanted_headers ($) { + my ($mime) = @_; + + $mime->header_set($_) for qw(bytes lines content-length status); + $mime->header_set($_) for @PublicInbox::MDA::BAD_HEADERS; +} + +# used by V2Writable, too +sub append_mid ($$) { + my ($hdr, $mid0) = @_; + # @cur is likely empty if we need to call this sub, but it could + # have random unparseable crap which we'll preserve, too. + my @cur = $hdr->header_raw('Message-ID'); + $hdr->header_set('Message-ID', @cur, "<$mid0>"); +} + +sub v1_mid0 ($) { + my ($mime) = @_; + my $hdr = $mime->header_obj; + my $mids = mids($hdr); + + if (!scalar(@$mids)) { # spam often has no Message-Id + my $mid0 = digest2mid(content_digest($mime), $hdr); + append_mid($hdr, $mid0); + return $mid0; + } + $mids->[0]; +} +sub clean_tree_v2 ($$$) { + my ($self, $w, $keep) = @_; + my $tree = $self->{-tree} or return; #v2 only + delete $tree->{$keep}; + foreach (keys %$tree) { + print $w "D $_\n" or wfail; + } + %$tree = ($keep => 1); +} - my $date = $mime->header('Date'); +# returns undef on duplicate +# returns the :MARK of the most recent commit +sub add { + my ($self, $mime, $check_cb) = @_; # mime = Email::MIME + + my ($name, $email) = extract_author_info($mime); + my $hdr = $mime->header_obj; + my @at = msg_datestamp($hdr); + my @ct = msg_timestamp($hdr); + my $author_time_raw = git_timestamp(@at); + my $commit_time_raw = git_timestamp(@ct); my $subject = $mime->header('Subject'); $subject = '(no subject)' unless defined $subject; - my $mid = mid_mime($mime); - my $path = mid2path($mid); + my $path_type = $self->{path_type}; + + my $path; + if ($path_type eq '2/38') { + $path = mid2path(v1_mid0($mime)); + } else { # v2 layout, one file: + $path = 'm'; + } my ($r, $w) = $self->gfi_start; my $tip = $self->{tip}; - _check_path($r, $w, $tip, $path) and return; + if ($path_type eq '2/38') { + _check_path($r, $w, $tip, $path) and return; + } - # kill potentially confusing/misleading headers - $mime->header_set($_) for qw(bytes lines content-length status); + drop_unwanted_headers($mime); + + # spam check: if ($check_cb) { $mime = $check_cb->($mime) or return; } - $mime = $mime->as_string; my $blob = $self->{mark}++; - print $w "blob\nmark :$blob\ndata ", length($mime), "\n" or wfail; - print $w $mime, "\n" or wfail; + my $str = $mime->as_string; + my $n = length($str); + $self->{bytes_added} += $n; + print $w "blob\nmark :$blob\ndata ", $n, "\n" or wfail; + print $w $str, "\n" or wfail; + + # v2: we need this for Xapian + if ($self->{want_object_info}) { + my $oid = $self->get_mark(":$blob"); + $self->{last_object} = [ $oid, $n, \$str ]; + } my $ref = $self->{ref}; my $commit = $self->{mark}++; my $parent = $tip =~ /\A:/ ? $tip : undef; @@ -191,26 +405,24 @@ sub add { print $w "reset $ref\n" or wfail; } - utf8::encode($email); - utf8::encode($name); utf8::encode($subject); - # quiet down wide character warnings: print $w "commit $ref\nmark :$commit\n", - "author $name <$email> $date\n", - "committer $self->{ident} ", now2822(), "\n" or wfail; + "author $name <$email> $author_time_raw\n", + "committer $self->{ident} $commit_time_raw\n" or wfail; print $w "data ", (length($subject) + 1), "\n", $subject, "\n\n" or wfail; if ($tip ne '') { print $w 'from ', ($parent ? $parent : $tip), "\n" or wfail; } + clean_tree_v2($self, $w, $path); print $w "M 100644 :$blob $path\n\n" or wfail; $self->{nchg}++; $self->{tip} = ":$commit"; } -sub run_die ($$) { - my ($cmd, $env) = @_; - my $pid = spawn($cmd, $env, undef); +sub run_die ($;$$) { + my ($cmd, $env, $rdr) = @_; + my $pid = spawn($cmd, $env, $rdr); defined $pid or die "spawning ".join(' ', @$cmd)." failed: $!"; waitpid($pid, 0) == $pid or die join(' ', @$cmd) .' did not finish'; $? == 0 or die join(' ', @$cmd) . " failed: $?\n"; @@ -224,33 +436,138 @@ sub done { my $pid = delete $self->{pid} or die 'BUG: missing {pid} when done'; waitpid($pid, 0) == $pid or die 'fast-import did not finish'; $? == 0 or die "fast-import failed: $?"; - my $nchg = delete $self->{nchg}; - # for compatibility with existing ssoma installations - # we can probably remove this entirely by 2020 - my $git_dir = $self->{git}->{git_dir}; - # XXX: change the following scope to: if (-e $index) # in 2018 or so.. - my @cmd = ('git', "--git-dir=$git_dir"); - if ($nchg && !$ENV{FAST}) { - my $index = "$git_dir/ssoma.index"; - my $env = { GIT_INDEX_FILE => $index }; - run_die([@cmd, qw(read-tree -m -v -i), $self->{ref}], $env); + _update_git_info($self, 1) if delete $self->{nchg}; + + $self->lock_release; +} + +sub atfork_child { + my ($self) = @_; + foreach my $f (qw(in out)) { + close $self->{$f} or die "failed to close import[$f]: $!\n"; } - if ($nchg) { - run_die([@cmd, 'update-server-info'], undef); - eval { - require PublicInbox::SearchIdx; - my $inbox = $self->{inbox} || $git_dir; - my $s = PublicInbox::SearchIdx->new($inbox); - $s->index_sync({ ref => $self->{ref} }); - }; - - eval { run_die([@cmd, qw(gc --auto)], undef) }; +} + +sub digest2mid ($$) { + my ($dig, $hdr) = @_; + my $b64 = $dig->clone->b64digest; + # Make our own URLs nicer: + # See "Base 64 Encoding with URL and Filename Safe Alphabet" in RFC4648 + $b64 =~ tr!+/=!-_!d; + + # Add a date prefix to prevent a leading '-' in case that trips + # up some tools (e.g. if a Message-ID were a expected as a + # command-line arg) + my $dt = msg_datestamp($hdr); + $dt = POSIX::strftime('%Y%m%d%H%M%S', gmtime($dt)); + "$dt.$b64" . '@z'; +} + +sub clean_purge_buffer { + my ($oids, $buf) = @_; + my $cmt_msg = 'purged '.join(' ',@$oids)."\n"; + @$oids = (); + + foreach my $i (0..$#$buf) { + my $l = $buf->[$i]; + if ($l =~ /^author .* (\d+ [\+-]?\d+)$/) { + $buf->[$i] = "author <> $1\n"; + } elsif ($l =~ /^data (\d+)/) { + $buf->[$i++] = "data " . length($cmt_msg) . "\n"; + $buf->[$i] = $cmt_msg; + last; + } } +} - my $lockfh = delete $self->{lockfh} or die "BUG: not locked: $!"; - flock($lockfh, LOCK_UN) or die "unlock failed: $!"; - close $lockfh or die "close lock failed: $!"; +sub purge_oids { + my ($self, $purge) = @_; + my $tmp = "refs/heads/purge-".((keys %$purge)[0]); + my $old = $self->{'ref'}; + my $git = $self->{git}; + my @export = (qw(fast-export --no-data --use-done-feature), $old); + my ($rd, $pid) = $git->popen(@export); + my ($r, $w) = $self->gfi_start; + my @buf; + my $npurge = 0; + my @oids; + my ($done, $mark); + my $tree = $self->{-tree}; + while (<$rd>) { + if (/^reset (?:.+)/) { + push @buf, "reset $tmp\n"; + } elsif (/^commit (?:.+)/) { + if (@buf) { + $w->print(@buf) or wfail; + @buf = (); + } + push @buf, "commit $tmp\n"; + } elsif (/^data (\d+)/) { + # only commit message, so $len is small: + my $len = $1; # + 1 for trailing "\n" + push @buf, $_; + my $n = read($rd, my $buf, $len) or die "read: $!"; + $len == $n or die "short read ($n < $len)"; + push @buf, $buf; + } elsif (/^M 100644 ([a-f0-9]+) (\w+)/) { + my ($oid, $path) = ($1, $2); + if ($purge->{$oid}) { + push @oids, $oid; + delete $tree->{$path}; + } else { + $tree->{$path} = 1; + push @buf, $_; + } + } elsif (/^D (\w+)/) { + my $path = $1; + push @buf, $_ if $tree->{$path}; + } elsif ($_ eq "\n") { + if (@oids) { + my $out = join('', @buf); + $out =~ s/^/# /sgm; + warn "purge rewriting\n", $out, "\n"; + clean_purge_buffer(\@oids, \@buf); + $npurge++; + } + $w->print(@buf, "\n") or wfail; + @buf = (); + } elsif ($_ eq "done\n") { + $done = 1; + } elsif (/^mark :(\d+)$/) { + push @buf, $_; + $mark = $1; + } else { + push @buf, $_; + } + } + if (@buf) { + $w->print(@buf) or wfail; + } + die 'done\n not seen from fast-export' unless $done; + chomp(my $cmt = $self->get_mark(":$mark")) if $npurge; + $self->{nchg} = 0; # prevent _update_git_info until update-ref: + $self->done; + my @git = ('git', "--git-dir=$git->{git_dir}"); + + run_die([@git, qw(update-ref), $old, $tmp]) if $npurge; + + run_die([@git, qw(update-ref -d), $tmp]); + + return if $npurge == 0; + + run_die([@git, qw(-c gc.reflogExpire=now gc --prune=all)]); + my $err = 0; + foreach my $oid (keys %$purge) { + my @info = $git->check($oid); + if (@info) { + warn "$oid not purged\n"; + $err++; + } + } + _update_git_info($self, 0); + die "Failed to purge $err object(s)\n" if $err; + $cmt; } 1; |