X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FImport.pm;h=95d654f667221711de6897ffd632b197bd6d10cf;hb=6ae5319be740b48370f32fe043d112bf09dd18da;hp=81a38fb6987d4d403bc1be376d610b8305d69fe7;hpb=8c925f2e250853b62fdb2a4ebdd45c2bba71544e;p=public-inbox.git diff --git a/lib/PublicInbox/Import.pm b/lib/PublicInbox/Import.pm index 81a38fb6..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; @@ -106,7 +103,7 @@ sub _cat_blob ($$$) { local $/ = "\n"; my $info = <$r>; defined $info or die "EOF from fast-import / cat-blob: $!"; - $info =~ /\A[a-f0-9]{40} blob (\d+)\n\z/ or return; + $info =~ /\A[a-f0-9]{40} blob ([0-9]+)\n\z/ or return; my $left = $1; my $offset = 0; my $buf = ''; @@ -178,14 +175,14 @@ sub _update_git_info ($$) { 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 $zone"; } -sub extract_author_info ($) { - my ($mime) = @_; +sub extract_cmt_info ($;$) { + my ($mime, $smsg) = @_; my $sender = ''; my $from = $mime->header('From'); @@ -296,6 +293,10 @@ sub extract_author_info ($) { } } 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 { @@ -314,7 +315,21 @@ 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 @@ -359,21 +374,9 @@ sub clean_tree_v2 ($$$) { # returns undef on duplicate # returns the :MARK of the most recent commit sub add { - my ($self, $mime, $check_cb) = @_; # mime = Email::MIME - - my ($name, $email) = extract_author_info($mime); - my $hdr = $mime->header_obj; - my @at = msg_datestamp($hdr); - my @ct = msg_timestamp($hdr); - my $author_time_raw = git_timestamp(@at); - my $commit_time_raw = git_timestamp(@ct); - - my $subject = $mime->header('Subject'); - $subject = '(no subject)' unless defined $subject; - # Mime decoding can create nulls replace them with spaces to protect git - $subject =~ tr/\0/ /; - utf8::encode($subject); + my ($self, $mime, $check_cb, $smsg) = @_; # mime = Email::MIME + my ($name, $email, $at, $ct, $subject) = extract_cmt_info($mime, $smsg); my $path_type = $self->{path_type}; my $path; if ($path_type eq '2/38') { @@ -396,16 +399,17 @@ sub add { } my $blob = $self->{mark}++; - my $str = $mime->as_string; - my $n = length($str); + my $raw_email = $mime->{-public_inbox_raw} // $mime->as_string; + my $n = length($raw_email); $self->{bytes_added} += $n; print $w "blob\nmark :$blob\ndata ", $n, "\n" or wfail; - print $w $str, "\n" or wfail; + print $w $raw_email, "\n" or wfail; # v2: we need this for Xapian - if ($self->{want_object_info}) { - my $oid = $self->get_mark(":$blob"); - $self->{last_object} = [ $oid, $n, \$str ]; + if ($smsg) { + $smsg->{blob} = $self->get_mark(":$blob"); + $smsg->{bytes} = $n; + $smsg->{-raw_email} = \$raw_email; } my $ref = $self->{ref}; my $commit = $self->{mark}++; @@ -416,8 +420,8 @@ sub add { } print $w "commit $ref\nmark :$commit\n", - "author $name <$email> $author_time_raw\n", - "committer $self->{ident} $commit_time_raw\n" or wfail; + "author $name <$email> $at\n", + "committer $self->{ident} $ct\n" or wfail; print $w "data ", (length($subject) + 1), "\n", $subject, "\n\n" or wfail; if ($tip ne '') { @@ -432,19 +436,35 @@ sub add { sub run_die ($;$$) { 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 { @@ -486,33 +506,45 @@ sub digest2mid ($$) { "$dt.$b64" . '@z'; } -sub clean_purge_buffer { - my ($oids, $buf) = @_; - my $cmt_msg = 'purged '.join(' ',@$oids)."\n"; +sub rewrite_commit ($$$$) { + 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 .* (\d+ [\+-]?\d+)$/) { - $buf->[$i] = "author <> $1\n"; - } elsif ($l =~ /^data (\d+)/) { - $buf->[$i++] = "data " . length($cmt_msg) . "\n"; - $buf->[$i] = $cmt_msg; + 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; } } } -sub purge_oids { - my ($self, $purge) = @_; - my $tmp = "refs/heads/purge-".((keys %$purge)[0]); +# 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 $npurge = 0; + my $nreplace = 0; my @oids; my ($done, $mark); my $tree = $self->{-tree}; @@ -525,7 +557,7 @@ sub purge_oids { @buf = (); } push @buf, "commit $tmp\n"; - } elsif (/^data (\d+)/) { + } elsif (/^data ([0-9]+)/) { # only commit message, so $len is small: my $len = $1; # + 1 for trailing "\n" push @buf, $_; @@ -535,10 +567,13 @@ sub purge_oids { } elsif (/^M 100644 ([a-f0-9]+) (\w+)/) { my ($oid, $path) = ($1, $2); $tree->{$path} = 1; - if ($purge->{$oid}) { + my $sref = $replace_map->{$oid}; + if (defined $sref) { push @oids, $oid; - my $cmd = "M 100644 inline $path\ndata 0\n\n"; - push @buf, $cmd; + 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, $_; } @@ -547,17 +582,19 @@ sub purge_oids { 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); - $npurge++; + if (!$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") { $done = 1; - } elsif (/^mark :(\d+)$/) { + } elsif (/^mark :([0-9]+)$/) { push @buf, $_; $mark = $1; } else { @@ -569,28 +606,30 @@ sub purge_oids { $w->print(@buf) or wfail; } die 'done\n not seen from fast-export' unless $done; - chomp(my $cmt = $self->get_mark(":$mark")) if $npurge; + 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 $npurge; + run_die([@git, qw(update-ref), $old, $tmp]) if $nreplace; run_die([@git, qw(update-ref -d), $tmp]); - return if $npurge == 0; + return if $nreplace == 0; + + run_die([@git, qw(-c gc.reflogExpire=now gc --prune=all --quiet)]); - run_die([@git, qw(-c gc.reflogExpire=now gc --prune=all)]); + # check that old OIDs are gone my $err = 0; - foreach my $oid (keys %$purge) { + foreach my $oid (keys %$replace_map) { my @info = $git->check($oid); if (@info) { - warn "$oid not purged\n"; + warn "$oid not replaced\n"; $err++; } } _update_git_info($self, 0); - die "Failed to purge $err object(s)\n" if $err; + die "Failed to replace $err object(s)\n" if $err; $cmt; } @@ -606,7 +645,7 @@ PublicInbox::Import - message importer for public-inbox v1 inboxes version 1.0 -=head1 SYNOPSYS +=head1 SYNOPSIS use Email::MIME; use PublicInbox::Git;