X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FImport.pm;h=572e9bb9899fc464671510dc26275d51d6b7ce8c;hb=55b707d788ce13696e4411389583e720ea6dab01;hp=fd4255cf867d6ca1a40dcce1fe19265f536803e6;hpb=a9cab9c477b74b3b828c26aa64e70d88c9d6744c;p=public-inbox.git diff --git a/lib/PublicInbox/Import.pm b/lib/PublicInbox/Import.pm index fd4255cf..572e9bb9 100644 --- a/lib/PublicInbox/Import.pm +++ b/lib/PublicInbox/Import.pm @@ -10,7 +10,7 @@ use strict; use warnings; use base qw(PublicInbox::Lock); use PublicInbox::Spawn qw(spawn); -use PublicInbox::MID qw(mids mid_mime mid2path); +use PublicInbox::MID qw(mids mid2path); use PublicInbox::Address; use PublicInbox::MsgTime qw(msg_timestamp msg_datestamp); use PublicInbox::ContentId qw(content_digest); @@ -18,19 +18,22 @@ 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 => $ibx, path_type => '2/38', # or 'v2' lock_path => "$git->{git_dir}/ssoma.lock", # v2 changes this bytes_added => 0, @@ -63,7 +66,7 @@ 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 $rdr = { 0 => $out_r, 1 => $in_w }; my $pid = spawn(\@cmd, undef, $rdr); die "spawn fast-import failed: $!" unless defined $pid; $out_w->autoflush(1); @@ -103,7 +106,7 @@ sub _cat_blob ($$$) { local $/ = "\n"; my $info = <$r>; defined $info or die "EOF from fast-import / cat-blob: $!"; - $info =~ /\A[a-f0-9]{40} blob (\d+)\n\z/ or return; + $info =~ /\A[a-f0-9]{40} blob ([0-9]+)\n\z/ or return; my $left = $1; my $offset = 0; my $buf = ''; @@ -175,14 +178,14 @@ sub _update_git_info ($$) { 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 $do_gc; } sub barrier { @@ -274,7 +277,7 @@ sub git_timestamp { "$ts $zone"; } -sub extract_author_info ($) { +sub extract_cmt_info ($) { my ($mime) = @_; my $sender = ''; @@ -311,7 +314,17 @@ sub extract_author_info ($) { $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)); + ($name, $email, $at, $ct, $subject); } # kill potentially confusing/misleading headers @@ -358,16 +371,8 @@ sub clean_tree_v2 ($$$) { sub add { my ($self, $mime, $check_cb) = @_; # mime = Email::MIME - my ($name, $email) = extract_author_info($mime); - my $hdr = $mime->header_obj; - my @at = msg_datestamp($hdr); - my @ct = msg_timestamp($hdr); - my $author_time_raw = git_timestamp(@at); - my $commit_time_raw = git_timestamp(@ct); - my $subject = $mime->header('Subject'); - $subject = '(no subject)' unless defined $subject; + my ($name, $email, $at, $ct, $subject) = extract_cmt_info($mime); my $path_type = $self->{path_type}; - my $path; if ($path_type eq '2/38') { $path = mid2path(v1_mid0($mime)); @@ -389,16 +394,16 @@ sub add { } my $blob = $self->{mark}++; - my $str = $mime->as_string; - my $n = length($str); + my $raw_email = $mime->{-public_inbox_raw} // $mime->as_string; + my $n = length($raw_email); $self->{bytes_added} += $n; print $w "blob\nmark :$blob\ndata ", $n, "\n" or wfail; - print $w $str, "\n" or wfail; + print $w $raw_email, "\n" or wfail; # v2: we need this for Xapian if ($self->{want_object_info}) { my $oid = $self->get_mark(":$blob"); - $self->{last_object} = [ $oid, $n, \$str ]; + $self->{last_object} = [ $oid, $n, \$raw_email ]; } my $ref = $self->{ref}; my $commit = $self->{mark}++; @@ -408,12 +413,9 @@ sub add { print $w "reset $ref\n" or wfail; } - # Mime decoding can create nulls replace them with spaces to protect git - $subject =~ tr/\0/ /; - utf8::encode($subject); print $w "commit $ref\nmark :$commit\n", - "author $name <$email> $author_time_raw\n", - "committer $self->{ident} $commit_time_raw\n" or wfail; + "author $name <$email> $at\n", + "committer $self->{ident} $ct\n" or wfail; print $w "data ", (length($subject) + 1), "\n", $subject, "\n\n" or wfail; if ($tip ne '') { @@ -433,6 +435,16 @@ sub run_die ($;$$) { $? == 0 or die join(' ', @$cmd) . " failed: $?\n"; } +sub init_bare { + my ($dir) = @_; + my @cmd = (qw(git init --bare -q), $dir); + run_die(\@cmd); + # set a reasonable default: + @cmd = (qw/git config/, "--file=$dir/config", + 'repack.writeBitmaps', 'true'); + run_die(\@cmd); +} + sub done { my ($self) = @_; my $w = delete $self->{out} or return; @@ -472,33 +484,45 @@ 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, $pid) = $git->popen(@export); + 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}; @@ -511,7 +535,7 @@ 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, $_; @@ -521,10 +545,13 @@ 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, $_; } @@ -533,49 +560,54 @@ 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 { 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 $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; } @@ -585,13 +617,13 @@ __END__ =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;