X-Git-Url: http://www.git.stargrave.org/?p=public-inbox.git;a=blobdiff_plain;f=lib%2FPublicInbox%2FImport.pm;h=b25427ee552628237bc094225f2daf24e98dcdac;hp=e50f1156ca37380eaaa419d40599fb1fd347c0f6;hb=0bf744b91df2d40580ff5776311d57dcede850b0;hpb=baae46ba22d283706dd821bea19aa9d985d0081d diff --git a/lib/PublicInbox/Import.pm b/lib/PublicInbox/Import.pm index e50f1156..b25427ee 100644 --- a/lib/PublicInbox/Import.pm +++ b/lib/PublicInbox/Import.pm @@ -11,9 +11,10 @@ use base qw(PublicInbox::Lock); use PublicInbox::Spawn qw(spawn); use PublicInbox::MID qw(mids mid_mime mid2path); use PublicInbox::Address; -use PublicInbox::MsgTime qw(msg_timestamp); +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, $ibx) = @_; @@ -49,7 +50,14 @@ sub gfi_start { $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 @@ -88,19 +96,13 @@ sub _check_path ($$$$) { $info =~ /\Amissing / ? undef : $info; } -sub check_remove_v1 { - my ($r, $w, $tip, $path, $mime) = @_; - - my $info = _check_path($r, $w, $tip, $path) or return ('MISSING',undef); - $info =~ m!\A100644 blob ([a-f0-9]{40})\t!s or die "not blob: $info"; - my $blob = $1; - - print $w "cat-blob $blob\n" or wfail; +sub _cat_blob ($$$) { + 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 = ''; @@ -115,7 +117,26 @@ sub check_remove_v1 { $n = read($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 = $mime->header('Subject'); @@ -185,6 +206,7 @@ sub get_mark { my ($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); $oid; } @@ -203,7 +225,7 @@ sub remove { my ($r, $w) = $self->gfi_start; my $tip = $self->{tip}; if ($path_type eq '2/38') { - $path = mid2path(mid_mime($mime)); + $path = mid2path(v1_mid0($mime)); ($err, $cur) = check_remove_v1($r, $w, $tip, $path, $mime); return ($err, $cur) if $err; } else { @@ -238,15 +260,15 @@ sub remove { if (defined $path) { print $w "D $path\n\n" or wfail; } else { - print $w "M 100644 :$blob _/D\n\n" or wfail; + clean_tree_v2($self, $w, 'd'); + print $w "M 100644 :$blob d\n\n" or wfail; } $self->{nchg}++; (($self->{tip} = ":$commit"), $cur); } -sub parse_date ($) { - my ($mime) = @_; - my ($ts, $zone) = msg_timestamp($mime->header_obj); +sub git_timestamp { + my ($ts, $zone) = @_; $ts = 0 if $ts < 0; # git uses unsigned times "$ts $zone"; } @@ -289,25 +311,63 @@ sub extract_author_info ($) { ($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 = ($keep => 1); +} + # returns undef on duplicate # returns the :MARK of the most recent commit sub add { my ($self, $mime, $check_cb) = @_; # mime = Email::MIME my ($name, $email) = extract_author_info($mime); - my $date_raw = parse_date($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 $path_type = $self->{path_type}; my $path; if ($path_type eq '2/38') { - my $mids = mids($mime->header_obj); - if (!scalar(@$mids)) { - my $dig = content_digest($mime); - @$mids = (digest2mid($dig)); - } - $path = mid2path($mids->[0]); + $path = mid2path(v1_mid0($mime)); } else { # v2 layout, one file: $path = 'm'; } @@ -318,9 +378,7 @@ sub add { _check_path($r, $w, $tip, $path) and return; } - # kill potentially confusing/misleading headers - $mime->header_set($_) for qw(bytes lines content-length status); - $mime->header_set($_) for @PublicInbox::MDA::BAD_HEADERS; + drop_unwanted_headers($mime); # spam check: if ($check_cb) { @@ -336,7 +394,7 @@ sub add { # v2: we need this for Xapian if ($self->{want_object_info}) { - chomp(my $oid = $self->get_mark(":$blob")); + my $oid = $self->get_mark(":$blob"); $self->{last_object} = [ $oid, $n, \$str ]; } my $ref = $self->{ref}; @@ -349,21 +407,22 @@ sub add { utf8::encode($subject); print $w "commit $ref\nmark :$commit\n", - "author $name <$email> $date_raw\n", - "committer $self->{ident} ", now_raw(), "\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, $env, undef); +sub run_die ($;$$) { + my ($cmd, $env, $rdr) = @_; + my $pid = spawn($cmd, $env, $rdr); defined $pid or die "spawning ".join(' ', @$cmd)." failed: $!"; waitpid($pid, 0) == $pid or die join(' ', @$cmd) .' did not finish'; $? == 0 or die join(' ', @$cmd) . " failed: $?\n"; @@ -390,18 +449,125 @@ sub atfork_child { } } -sub digest2mid ($) { - my ($dig) = @_; +sub digest2mid ($$) { + 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; - # We can make this more meaningful with a date prefix or other things, - # but this is only needed for crap that fails to generate a Message-ID - # or reuses one. In other words, it's usually spammers who hit this - # so they don't deserve nice Message-IDs :P - $b64 . '@localhost'; + # 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] = $cmt_msg; + last; + } + } +} + +sub purge_oids { + my ($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;