X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FImport.pm;h=ee5ca2ea11b4f383e514ecdf117ac1dabe2c14c1;hb=94ae705673cb03045a109041eec9a6704b8a735b;hp=1a7ed9ce87850852f21444c5fdcb9b2703263684;hpb=7d05666ef3a5750c85e481a0c034f1c34f1b70b9;p=public-inbox.git diff --git a/lib/PublicInbox/Import.pm b/lib/PublicInbox/Import.pm index 1a7ed9ce..ee5ca2ea 100644 --- a/lib/PublicInbox/Import.pm +++ b/lib/PublicInbox/Import.pm @@ -12,7 +12,8 @@ use v5.10.1; use PublicInbox::Spawn qw(spawn popen_rd); use PublicInbox::MID qw(mids mid2path); use PublicInbox::Address; -use PublicInbox::MsgTime qw(msg_timestamp msg_datestamp); +use PublicInbox::Smsg; +use PublicInbox::MsgTime qw(msg_datestamp); use PublicInbox::ContentHash qw(content_digest); use PublicInbox::MDA; use PublicInbox::Eml; @@ -34,7 +35,7 @@ sub new { ident => "$name <$email>", mark => 1, ref => $ref, - -inbox => $ibx, + ibx => $ibx, path_type => '2/38', # or 'v2' lock_path => "$git->{git_dir}/ssoma.lock", # v2 changes this bytes_added => 0, @@ -47,34 +48,35 @@ sub gfi_start { return ($self->{in}, $self->{out}) if $self->{pid}; - my ($out_r, $out_w); + my (@ret, $out_r, $out_w); pipe($out_r, $out_w) or die "pipe failed: $!"; - my $git = $self->{git}; $self->lock_acquire; - - local $/ = "\n"; - 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 { $_ => 1 } @tree }; + eval { + my ($git, $ref) = @$self{qw(git ref)}; + local $/ = "\n"; + chomp($self->{tip} = $git->qx(qw(rev-parse --revs-only), $ref)); + if ($self->{path_type} ne '2/38' && $self->{tip}) { + local $/ = "\0"; + my @t = $git->qx(qw(ls-tree -r -z --name-only), $ref); + chomp @t; + $self->{-tree} = { map { $_ => 1 } @t }; + } + my @cmd = ('git', "--git-dir=$git->{git_dir}", + qw(fast-import --quiet --done --date-format=raw)); + my ($in_r, $pid) = popen_rd(\@cmd, undef, { 0 => $out_r }); + $out_w->autoflush(1); + $self->{in} = $in_r; + $self->{out} = $out_w; + $self->{pid} = $pid; + $self->{nchg} = 0; + @ret = ($in_r, $out_w); + }; + if ($@) { + $self->lock_release; + die $@; } - - my $git_dir = $git->{git_dir}; - my @cmd = ('git', "--git-dir=$git_dir", qw(fast-import - --quiet --done --date-format=raw)); - my ($in_r, $pid) = popen_rd(\@cmd, undef, { 0 => $out_r }); - $out_w->autoflush(1); - $self->{in} = $in_r; - $self->{out} = $out_w; - $self->{pid} = $pid; - $self->{nchg} = 0; - binmode $out_w, ':raw' or die "binmode :raw failed: $!"; - binmode $in_r, ':raw' or die "binmode :raw failed: $!"; - ($in_r, $out_w); + @ret; } sub wfail () { die "write to fast-import failed: $!" } @@ -176,13 +178,16 @@ 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']); - my $ibx = $self->{-inbox}; - ($ibx && $self->{path_type} eq '2/38') and eval { - require PublicInbox::SearchIdx; - my $s = PublicInbox::SearchIdx->new($ibx); - $s->index_sync({ ref => $self->{ref} }); - }; + eval { run_die([@cmd, 'update-server-info']) }; + my $ibx = $self->{ibx}; + if ($ibx && $ibx->version == 1 && -d "$ibx->{inboxdir}/public-inbox" && + eval { require PublicInbox::SearchIdx }) { + eval { + my $s = PublicInbox::SearchIdx->new($ibx); + $s->index_sync({ ref => $self->{ref} }); + }; + warn "$ibx->{inboxdir} index failed: $@\n" if $@; + } eval { run_die([@cmd, qw(gc --auto)]) } if $do_gc; } @@ -269,8 +274,8 @@ sub remove { (($self->{tip} = ":$commit"), $cur); } -sub git_timestamp { - my ($ts, $zone) = @_; +sub git_timestamp ($) { + my ($ts, $zone) = @{$_[0]}; $ts = 0 if $ts < 0; # git uses unsigned times "$ts $zone"; } @@ -278,14 +283,16 @@ sub git_timestamp { sub extract_cmt_info ($;$) { my ($mime, $smsg) = @_; # $mime is PublicInbox::Eml, but remains Email::MIME-compatible + $smsg //= bless {}, 'PublicInbox::Smsg'; + + $smsg->populate($mime); my $sender = ''; - my $hdr = $mime->header_obj; - my $from = $hdr->header('From') // ''; + my $from = delete($smsg->{From}) // ''; my ($email) = PublicInbox::Address::emails($from); my ($name) = PublicInbox::Address::names($from); if (!defined($name) || !defined($email)) { - $sender = $hdr->header('Sender') // ''; + $sender = $mime->header('Sender') // ''; $name //= (PublicInbox::Address::names($sender))[0]; $email //= (PublicInbox::Address::emails($sender))[0]; } @@ -313,24 +320,18 @@ sub extract_cmt_info ($;$) { warn "no name in From: $from or Sender: $sender\n"; } - my $subject = $hdr->header('Subject') // '(no subject)'; - # MIME decoding can create nulls replace them with spaces to protect git - $subject =~ tr/\0/ /; + my $subject = delete($smsg->{Subject}) // '(no subject)'; 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); + my $at = git_timestamp(delete $smsg->{-ds}); + my $ct = git_timestamp(delete $smsg->{-ts}); + ("$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 qw(Bytes Lines Content-Length Status); $mime->header_set($_) for @PublicInbox::MDA::BAD_HEADERS; } @@ -344,13 +345,12 @@ sub append_mid ($$) { } sub v1_mid0 ($) { - my ($mime) = @_; - my $hdr = $mime->header_obj; - my $mids = mids($hdr); + my ($eml) = @_; + my $mids = mids($eml); if (!scalar(@$mids)) { # spam often has no Message-ID - my $mid0 = digest2mid(content_digest($mime), $hdr); - append_mid($hdr, $mid0); + my $mid0 = digest2mid(content_digest($eml), $eml); + append_mid($eml, $mid0); return $mid0; } $mids->[0]; @@ -370,7 +370,7 @@ sub clean_tree_v2 ($$$) { sub add { my ($self, $mime, $check_cb, $smsg) = @_; - my ($name, $email, $at, $ct, $subject) = extract_cmt_info($mime, $smsg); + my ($author, $at, $ct, $subject) = extract_cmt_info($mime, $smsg); my $path_type = $self->{path_type}; my $path; if ($path_type eq '2/38') { @@ -389,7 +389,7 @@ sub add { # spam check: if ($check_cb) { - $mime = $check_cb->($mime) or return; + $mime = $check_cb->($mime, $self->{ibx}) or return; } my $blob = $self->{mark}++; @@ -402,7 +402,7 @@ sub add { # v2: we need this for Xapian if ($smsg) { $smsg->{blob} = $self->get_mark(":$blob"); - $smsg->{bytes} = $n; + $smsg->{raw_bytes} = $n; $smsg->{-raw_email} = \$raw_email; } my $ref = $self->{ref}; @@ -414,7 +414,7 @@ sub add { } print $w "commit $ref\nmark :$commit\n", - "author $name <$email> $at\n", + "author $author $at\n", "committer $self->{ident} $ct\n" or wfail; print $w "data ", (length($subject) + 1), "\n", $subject, "\n\n" or wfail; @@ -461,20 +461,29 @@ sub init_bare { } } +# true if locked and active +sub active { !!$_[0]->{out} } + sub done { my ($self) = @_; my $w = delete $self->{out} or return; - my $r = delete $self->{in} or die 'BUG: missing {in} when done'; - print $w "done\n" or wfail; - 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: $?"; - - _update_git_info($self, 1) if delete $self->{nchg}; - - $self->lock_release; - + eval { + my $r = delete $self->{in} or die 'BUG: missing {in} when done'; + print $w "done\n" or wfail; + 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 $wait_err = $@; + my $nchg = delete $self->{nchg}; + if ($nchg && !$wait_err) { + eval { _update_git_info($self, 1) }; + warn "E: $self->{git}->{git_dir} update info: $@\n" if $@; + } + $self->lock_release(!!$nchg); $self->{git}->cleanup; + die $wait_err if $wait_err; } sub atfork_child { @@ -502,11 +511,11 @@ sub digest2mid ($$) { sub rewrite_commit ($$$$) { my ($self, $oids, $buf, $mime) = @_; - my ($name, $email, $at, $ct, $subject); + my ($author, $at, $ct, $subject); if ($mime) { - ($name, $email, $at, $ct, $subject) = extract_cmt_info($mime); + ($author, $at, $ct, $subject) = extract_cmt_info($mime); } else { - $name = $email = ''; + $author = '<>'; $subject = 'purged '.join(' ', @$oids); } @$oids = (); @@ -515,7 +524,7 @@ sub rewrite_commit ($$$$) { my $l = $buf->[$i]; if ($l =~ /^author .* ([0-9]+ [\+-]?[0-9]+)$/) { $at //= $1; - $buf->[$i] = "author $name <$email> $at\n"; + $buf->[$i] = "author $author $at\n"; } elsif ($l =~ /^committer .* ([0-9]+ [\+-]?[0-9]+)$/) { $ct //= $1; $buf->[$i] = "committer $self->{ident} $ct\n"; @@ -663,8 +672,7 @@ version 1.0 my $parsed = PublicInbox::Eml->new($message); my $ret = $im->add($parsed); if (!defined $ret) { - warn "duplicate: ", - $parsed->header_obj->header_raw('Message-ID'), "\n"; + warn "duplicate: ", $parsed->header_raw('Message-ID'), "\n"; } else { print "imported at mark $ret\n"; }