X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FImport.pm;h=95d654f667221711de6897ffd632b197bd6d10cf;hb=6ae5319be740b48370f32fe043d112bf09dd18da;hp=12df7d598fc71d38088d4aeaebd0ed6d8ed3e37d;hpb=2d9a41bf4f3ecddda07128711c41c3eb3411246b;p=public-inbox.git diff --git a/lib/PublicInbox/Import.pm b/lib/PublicInbox/Import.pm index 12df7d59..95d654f6 100644 --- a/lib/PublicInbox/Import.pm +++ b/lib/PublicInbox/Import.pm @@ -1,34 +1,41 @@ -# Copyright (C) 2016-2018 all contributors +# Copyright (C) 2016-2020 all contributors # License: AGPL-3.0+ # # git fast-import-based ssoma-mda MDA replacement -# This is only ever run by public-inbox-mda and public-inbox-learn, -# not the WWW or NNTP code which only requires read-only access. +# This is only ever run by public-inbox-mda, public-inbox-learn +# and public-inbox-watch. Not the WWW or NNTP code which only +# requires read-only access. package PublicInbox::Import; use strict; use warnings; -use Fcntl qw(:flock :DEFAULT); -use PublicInbox::Spawn qw(spawn); -use PublicInbox::MID qw(mid_mime mid2path); +use base qw(PublicInbox::Lock); +use PublicInbox::Spawn qw(spawn popen_rd); +use PublicInbox::MID qw(mids 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 { + # we can't change arg order, this is documented in POD + # and external projects may rely on it: 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}; + $git ||= $ibx->git; } bless { git => $git, ident => "$name <$email>", mark => 1, ref => $ref, - inbox => $ibx, + -inbox => $ibx, path_type => '2/38', # or 'v2' - ssoma_lock => 1, # disable for v2 + lock_path => "$git->{git_dir}/ssoma.lock", # v2 changes this bytes_added => 0, }, $class } @@ -39,33 +46,29 @@ sub gfi_start { return ($self->{in}, $self->{out}) if $self->{pid}; - my ($in_r, $in_w, $out_r, $out_w); - pipe($in_r, $in_w) or die "pipe failed: $!"; + my ($out_r, $out_w); pipe($out_r, $out_w) or die "pipe failed: $!"; my $git = $self->{git}; - my $git_dir = $git->{git_dir}; - my $lockfh; - if ($self->{ssoma_lock}) { - my $lockpath = "$git_dir/ssoma.lock"; - sysopen($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=raw)); - my $rdr = { 0 => fileno($out_r), 1 => fileno($in_w) }; - my $pid = spawn(\@cmd, undef, $rdr); - die "spawn fast-import failed: $!" unless defined $pid; + my ($in_r, $pid) = popen_rd(\@cmd, undef, { 0 => $out_r }); $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: $!"; @@ -94,19 +97,13 @@ 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 ([0-9]+)\n\z/ or return; my $left = $1; my $offset = 0; my $buf = ''; @@ -121,7 +118,26 @@ 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'); @@ -159,14 +175,14 @@ sub _update_git_info ($$) { 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 { + run_die([@cmd, 'update-server-info']); + my $ibx = $self->{-inbox}; + ($ibx && $self->{path_type} eq '2/38') and eval { require PublicInbox::SearchIdx; - my $inbox = $self->{inbox} || $git_dir; - my $s = PublicInbox::SearchIdx->new($inbox); + my $s = PublicInbox::SearchIdx->new($ibx); $s->index_sync({ ref => $self->{ref} }); }; - eval { run_die([@cmd, qw(gc --auto)], undef) } if $do_gc; + eval { run_die([@cmd, qw(gc --auto)]) } if $do_gc; } sub barrier { @@ -191,6 +207,7 @@ 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; } @@ -209,7 +226,7 @@ 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 { @@ -244,28 +261,30 @@ 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"; } -sub extract_author_info ($) { - my ($mime) = @_; +sub extract_cmt_info ($;$) { + my ($mime, $smsg) = @_; my $sender = ''; my $from = $mime->header('From'); + $from ||= ''; my ($email) = PublicInbox::Address::emails($from); my ($name) = PublicInbox::Address::names($from); if (!defined($name) || !defined($email)) { $sender = $mime->header('Sender'); + $sender ||= ''; if (!defined($name)) { ($name) = PublicInbox::Address::names($sender); } @@ -274,6 +293,10 @@ sub extract_author_info ($) { } } if (defined $email) { + # Email::Address::XS may leave quoted '<' in addresses, + # which git-fast-import doesn't like + $email =~ tr/<>//d; + # quiet down wide character warnings with utf8::encode utf8::encode($email); } else { @@ -292,23 +315,72 @@ sub extract_author_info ($) { $name = ''; warn "no name in From: $from or Sender: $sender\n"; } - ($name, $email); + + my $hdr = $mime->header_obj; + + my $subject = $hdr->header('Subject'); + $subject = '(no subject)' unless defined $subject; + # Mime decoding can create nulls replace them with spaces to protect git + $subject =~ tr/\0/ /; + utf8::encode($subject); + my $at = git_timestamp(my @at = msg_datestamp($hdr)); + my $ct = git_timestamp(my @ct = msg_timestamp($hdr)); + if ($smsg) { + $smsg->{ds} = $at[0]; + $smsg->{ts} = $ct[0]; + } + ($name, $email, $at, $ct, $subject); +} + +# 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 ($self, $mime, $check_cb, $smsg) = @_; # mime = Email::MIME - my ($name, $email) = extract_author_info($mime); - my $date_raw = parse_date($mime); - my $subject = $mime->header('Subject'); - $subject = '(no subject)' unless defined $subject; + my ($name, $email, $at, $ct, $subject) = extract_cmt_info($mime, $smsg); my $path_type = $self->{path_type}; - my $path; if ($path_type eq '2/38') { - $path = mid2path(mid_mime($mime)); + $path = mid2path(v1_mid0($mime)); } else { # v2 layout, one file: $path = 'm'; } @@ -319,8 +391,7 @@ 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); + drop_unwanted_headers($mime); # spam check: if ($check_cb) { @@ -328,16 +399,17 @@ sub add { } my $blob = $self->{mark}++; - my $str = $mime->as_string; - my $n = length($str); + my $raw_email = $mime->{-public_inbox_raw} // $mime->as_string; + my $n = length($raw_email); $self->{bytes_added} += $n; print $w "blob\nmark :$blob\ndata ", $n, "\n" or wfail; - print $w $str, "\n" or wfail; + print $w $raw_email, "\n" or wfail; # v2: we need this for Xapian - if ($self->{want_object_info}) { - chomp(my $oid = $self->get_mark(":$blob")); - $self->{last_object} = [ $oid, $n, \$str ]; + if ($smsg) { + $smsg->{blob} = $self->get_mark(":$blob"); + $smsg->{bytes} = $n; + $smsg->{-raw_email} = \$raw_email; } my $ref = $self->{ref}; my $commit = $self->{mark}++; @@ -347,28 +419,54 @@ sub add { print $w "reset $ref\n" or wfail; } - 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> $at\n", + "committer $self->{ident} $ct\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); - defined $pid or die "spawning ".join(' ', @$cmd)." failed: $!"; +sub run_die ($;$$) { + my ($cmd, $env, $rdr) = @_; + my $pid = spawn($cmd, $env, $rdr); waitpid($pid, 0) == $pid or die join(' ', @$cmd) .' did not finish'; $? == 0 or die join(' ', @$cmd) . " failed: $?\n"; } +my @INIT_FILES = ('HEAD' => "ref: refs/heads/master\n", + 'description' => < <{git}->{git_dir} if ref($dir); + require File::Path; + File::Path::mkpath([ map { "$dir/$_" } qw(objects/info refs/heads) ]); + for (my $i = 0; $i < @INIT_FILES; $i++) { + my $f = $dir.'/'.$INIT_FILES[$i++]; + next if -f $f; + open my $fh, '>', $f or die "open $f: $!"; + print $fh $INIT_FILES[$i] or die "print $f: $!"; + close $fh or die "close $f: $!"; + } +} + sub done { my ($self) = @_; my $w = delete $self->{out} or return; @@ -380,32 +478,174 @@ sub done { _update_git_info($self, 1) if delete $self->{nchg}; - $self->{ssoma_lock} or return; - 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: $!"; + $self->lock_release; + + $self->{git}->cleanup; } sub atfork_child { my ($self) = @_; foreach my $f (qw(in out)) { + next unless defined($self->{$f}); close $self->{$f} or die "failed to close import[$f]: $!\n"; } } +sub digest2mid ($$) { + my ($dig, $hdr) = @_; + my $b64 = $dig->clone->b64digest; + # Make our own URLs nicer: + # See "Base 64 Encoding with URL and Filename Safe Alphabet" in RFC4648 + $b64 =~ tr!+/=!-_!d; + + # Add a date prefix to prevent a leading '-' in case that trips + # up some tools (e.g. if a Message-ID were a expected as a + # command-line arg) + my $dt = msg_datestamp($hdr); + $dt = POSIX::strftime('%Y%m%d%H%M%S', gmtime($dt)); + "$dt.$b64" . '@z'; +} + +sub rewrite_commit ($$$$) { + my ($self, $oids, $buf, $mime) = @_; + my ($name, $email, $at, $ct, $subject); + if ($mime) { + ($name, $email, $at, $ct, $subject) = extract_cmt_info($mime); + } else { + $name = $email = ''; + $subject = 'purged '.join(' ', @$oids); + } + @$oids = (); + $subject .= "\n"; + foreach my $i (0..$#$buf) { + my $l = $buf->[$i]; + if ($l =~ /^author .* ([0-9]+ [\+-]?[0-9]+)$/) { + $at //= $1; + $buf->[$i] = "author $name <$email> $at\n"; + } elsif ($l =~ /^committer .* ([0-9]+ [\+-]?[0-9]+)$/) { + $ct //= $1; + $buf->[$i] = "committer $self->{ident} $ct\n"; + } elsif ($l =~ /^data ([0-9]+)/) { + $buf->[$i++] = "data " . length($subject) . "\n"; + $buf->[$i] = $subject; + last; + } + } +} + +# returns the new commit OID if a replacement was done +# returns undef if nothing was done +sub replace_oids { + my ($self, $mime, $replace_map) = @_; # oid => raw string + my $tmp = "refs/heads/replace-".((keys %$replace_map)[0]); + my $old = $self->{'ref'}; + my $git = $self->{git}; + my @export = (qw(fast-export --no-data --use-done-feature), $old); + my $rd = $git->popen(@export); + my ($r, $w) = $self->gfi_start; + my @buf; + my $nreplace = 0; + my @oids; + my ($done, $mark); + my $tree = $self->{-tree}; + while (<$rd>) { + if (/^reset (?:.+)/) { + push @buf, "reset $tmp\n"; + } elsif (/^commit (?:.+)/) { + if (@buf) { + $w->print(@buf) or wfail; + @buf = (); + } + push @buf, "commit $tmp\n"; + } elsif (/^data ([0-9]+)/) { + # only commit message, so $len is small: + my $len = $1; # + 1 for trailing "\n" + push @buf, $_; + my $n = read($rd, my $buf, $len) or die "read: $!"; + $len == $n or die "short read ($n < $len)"; + push @buf, $buf; + } elsif (/^M 100644 ([a-f0-9]+) (\w+)/) { + my ($oid, $path) = ($1, $2); + $tree->{$path} = 1; + my $sref = $replace_map->{$oid}; + if (defined $sref) { + push @oids, $oid; + my $n = length($$sref); + push @buf, "M 100644 inline $path\ndata $n\n"; + push @buf, $$sref; # hope CoW works... + push @buf, "\n"; + } else { + push @buf, $_; + } + } elsif (/^D (\w+)/) { + my $path = $1; + push @buf, $_ if $tree->{$path}; + } elsif ($_ eq "\n") { + if (@oids) { + if (!$mime) { + my $out = join('', @buf); + $out =~ s/^/# /sgm; + warn "purge rewriting\n", $out, "\n"; + } + rewrite_commit($self, \@oids, \@buf, $mime); + $nreplace++; + } + $w->print(@buf, "\n") or wfail; + @buf = (); + } elsif ($_ eq "done\n") { + $done = 1; + } elsif (/^mark :([0-9]+)$/) { + push @buf, $_; + $mark = $1; + } else { + push @buf, $_; + } + } + close $rd or die "close fast-export failed: $?"; + 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 $nreplace; + $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 $nreplace; + + run_die([@git, qw(update-ref -d), $tmp]); + + return if $nreplace == 0; + + run_die([@git, qw(-c gc.reflogExpire=now gc --prune=all --quiet)]); + + # check that old OIDs are gone + my $err = 0; + foreach my $oid (keys %$replace_map) { + my @info = $git->check($oid); + if (@info) { + warn "$oid not replaced\n"; + $err++; + } + } + _update_git_info($self, 0); + die "Failed to replace $err object(s)\n" if $err; + $cmt; +} + 1; __END__ =pod =head1 NAME -PublicInbox::Import - message importer for public-inbox +PublicInbox::Import - message importer for public-inbox v1 inboxes =head1 VERSION version 1.0 -=head1 SYNOPSYS +=head1 SYNOPSIS use Email::MIME; use PublicInbox::Git; @@ -450,8 +690,8 @@ version 1.0 =head1 DESCRIPTION An importer and remover for public-inboxes which takes L -messages as input and stores them in a ssoma repository as -documented in L, +messages as input and stores them in a git repository as +documented in L, except it does not allow duplicate Message-IDs. It requires L and L to be installed.