X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FImport.pm;h=95d654f667221711de6897ffd632b197bd6d10cf;hb=6ae5319be740b48370f32fe043d112bf09dd18da;hp=137b2b7800c403c188db050f0dd1df3a5583b28a;hpb=3b508de80a200e9a32adbdc437434339187dde88;p=public-inbox.git diff --git a/lib/PublicInbox/Import.pm b/lib/PublicInbox/Import.pm index 137b2b78..95d654f6 100644 --- a/lib/PublicInbox/Import.pm +++ b/lib/PublicInbox/Import.pm @@ -1,4 +1,4 @@ -# Copyright (C) 2016-2019 all contributors +# Copyright (C) 2016-2020 all contributors # License: AGPL-3.0+ # # git fast-import-based ssoma-mda MDA replacement @@ -9,8 +9,8 @@ package PublicInbox::Import; use strict; use warnings; use base qw(PublicInbox::Lock); -use PublicInbox::Spawn qw(spawn); -use PublicInbox::MID qw(mids mid_mime mid2path); +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::ContentId qw(content_digest); @@ -46,8 +46,7 @@ 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}; @@ -66,9 +65,7 @@ sub gfi_start { 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; @@ -178,14 +175,14 @@ sub _update_git_info ($$) { my $env = { GIT_INDEX_FILE => $index }; run_die([@cmd, qw(read-tree -m -v -i), $self->{ref}], $env); } - run_die([@cmd, 'update-server-info'], undef); - ($self->{path_type} eq '2/38') and eval { + run_die([@cmd, 'update-server-info']); + my $ibx = $self->{-inbox}; + ($ibx && $self->{path_type} eq '2/38') and eval { require PublicInbox::SearchIdx; - my $ibx = $self->{-inbox} || $git_dir; my $s = PublicInbox::SearchIdx->new($ibx); $s->index_sync({ ref => $self->{ref} }); }; - eval { run_die([@cmd, qw(gc --auto)], undef) } if $do_gc; + eval { run_die([@cmd, qw(gc --auto)]) } if $do_gc; } sub barrier { @@ -277,8 +274,8 @@ sub git_timestamp { "$ts $zone"; } -sub extract_cmt_info ($) { - my ($mime) = @_; +sub extract_cmt_info ($;$) { + my ($mime, $smsg) = @_; my $sender = ''; my $from = $mime->header('From'); @@ -296,6 +293,10 @@ sub extract_cmt_info ($) { } } if (defined $email) { + # Email::Address::XS may leave quoted '<' in addresses, + # which git-fast-import doesn't like + $email =~ tr/<>//d; + # quiet down wide character warnings with utf8::encode utf8::encode($email); } else { @@ -324,6 +325,10 @@ sub extract_cmt_info ($) { utf8::encode($subject); my $at = git_timestamp(my @at = msg_datestamp($hdr)); my $ct = git_timestamp(my @ct = msg_timestamp($hdr)); + if ($smsg) { + $smsg->{ds} = $at[0]; + $smsg->{ts} = $ct[0]; + } ($name, $email, $at, $ct, $subject); } @@ -369,9 +374,9 @@ sub clean_tree_v2 ($$$) { # 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, $at, $ct, $subject) = extract_cmt_info($mime); + 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') { @@ -394,16 +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}) { - 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 = $self->{mark}++; @@ -430,19 +436,35 @@ sub add { sub run_die ($;$$) { 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: $?\n"; } +my @INIT_FILES = ('HEAD' => "ref: refs/heads/master\n", + 'description' => < <{git}->{git_dir} if ref($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 { @@ -595,7 +617,7 @@ sub replace_oids { return if $nreplace == 0; - run_die([@git, qw(-c gc.reflogExpire=now gc --prune=all)]); + run_die([@git, qw(-c gc.reflogExpire=now gc --prune=all --quiet)]); # check that old OIDs are gone my $err = 0; @@ -623,7 +645,7 @@ PublicInbox::Import - message importer for public-inbox v1 inboxes version 1.0 -=head1 SYNOPSYS +=head1 SYNOPSIS use Email::MIME; use PublicInbox::Git;