X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FImport.pm;h=13671a4fa3313f79e3c4d53813ab1cb815ecb032;hb=3fc59df0d633a17e0c5e43d633d12e8772c06ec3;hp=27f36a7e486b84337e1e4e4586ab9ec5251e4c65;hpb=40782735e74e427997b5b900d60cc07597e330c3;p=public-inbox.git diff --git a/lib/PublicInbox/Import.pm b/lib/PublicInbox/Import.pm index 27f36a7e..13671a4f 100644 --- a/lib/PublicInbox/Import.pm +++ b/lib/PublicInbox/Import.pm @@ -10,14 +10,16 @@ use warnings; use Fcntl qw(:flock :DEFAULT); use PublicInbox::Spawn qw(spawn); use PublicInbox::MID qw(mid_mime mid2path); +use PublicInbox::Address; sub new { - my ($class, $git, $name, $email) = @_; + my ($class, $git, $name, $email, $inbox) = @_; bless { git => $git, ident => "$name <$email>", mark => 1, ref => 'refs/heads/master', + inbox => $inbox, }, $class } @@ -38,6 +40,7 @@ sub gfi_start { # wait for other processes to be done flock($lockfh, LOCK_EX) or die "lock failed: $!\n"; + local $/ = "\n"; chomp($self->{tip} = $git->qx(qw(rev-parse --revs-only), $self->{ref})); my @cmd = ('git', "--git-dir=$git_dir", qw(fast-import @@ -72,6 +75,15 @@ sub norm_body ($) { $b } +sub _check_path ($$$$) { + my ($r, $w, $tip, $path) = @_; + return if $tip eq ''; + print $w "ls $tip $path\n" or wfail; + local $/ = "\n"; + defined(my $info = <$r>) or die "EOF from fast-import: $!"; + $info =~ /\Amissing / ? undef : $info; +} + # returns undef on non-existent # ('MISMATCH', msg) on mismatch # (:MARK, msg) on success @@ -83,20 +95,16 @@ sub remove { my ($r, $w) = $self->gfi_start; my $tip = $self->{tip}; - return ('MISSING', undef) if $tip eq ''; - - print $w "ls $tip $path\n" or wfail; - local $/ = "\n"; - my $check = <$r>; - defined $check or die "EOF from fast-import / ls: $!"; - return ('MISSING', undef) if $check =~ /\Amissing /; - $check =~ m!\A100644 blob ([a-f0-9]{40})\t!s or die "not blob: $check"; + 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; - $check = <$r>; - defined $check or die "EOF from fast-import / cat-blob: $!"; - $check =~ /\A[a-f0-9]{40} blob (\d+)\n\z/ or - die "unexpected cat-blob response: $check"; + local $/ = "\n"; + $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"; my $left = $1; my $offset = 0; my $buf = ''; @@ -111,7 +119,7 @@ sub remove { $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 = Email::MIME->new($buf); + my $cur = PublicInbox::MIME->new($buf); my $cur_s = $cur->header('Subject'); $cur_s = '' unless defined $cur_s; my $cur_m = $mime->header('Subject'); @@ -143,14 +151,13 @@ sub add { my ($self, $mime, $check_cb) = @_; # mime = Email::MIME my $from = $mime->header('From'); - my ($email) = ($from =~ /([^<\s]+\@[^>\s]+)/g); - my $name = $from; - $name =~ s/\s*\S+\@\S+\s*\z//; + my ($email) = PublicInbox::Address::emails($from); + my ($name) = PublicInbox::Address::names($from); # git gets confused with: # "'A U Thor ' via foo" # ref: # - $name =~ tr/<>// and $name = $email; + $name =~ tr/<>//d; my $date = $mime->header('Date'); my $subject = $mime->header('Subject'); @@ -160,13 +167,7 @@ sub add { my ($r, $w) = $self->gfi_start; my $tip = $self->{tip}; - if ($tip ne '') { - print $w "ls $tip $path\n" or wfail; - local $/ = "\n"; - my $check = <$r>; - defined $check or die "EOF from fast-import: $!"; - return unless $check =~ /\Amissing /; - } + _check_path($r, $w, $tip, $path) and return; # kill potentially confusing/misleading headers $mime->header_set($_) for qw(bytes lines content-length status); @@ -203,6 +204,14 @@ sub add { $self->{tip} = ":$commit"; } +sub run_die ($$) { + my ($cmd, $env) = @_; + my $pid = spawn($cmd, $env, undef); + 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: $?\n"; +} + sub done { my ($self) = @_; my $w = delete $self->{out} or return; @@ -221,23 +230,18 @@ sub done { if ($nchg && !$ENV{FAST}) { my $index = "$git_dir/ssoma.index"; my $env = { GIT_INDEX_FILE => $index }; - my @rt = (@cmd, qw(read-tree -m -v -i), $self->{ref}); - $pid = spawn(\@rt, $env, undef); - defined $pid or die "spawn read-tree failed: $!"; - waitpid($pid, 0) == $pid or die 'read-tree did not finish'; - $? == 0 or die "failed to update $git_dir/ssoma.index: $?\n"; + run_die([@cmd, qw(read-tree -m -v -i), $self->{ref}], $env); } if ($nchg) { - $pid = spawn([@cmd, 'update-server-info'], undef, undef); - defined $pid or die "spawn update-server-info failed: $!\n"; - waitpid($pid, 0) == $pid or - die 'update-server-info did not finish'; - $? == 0 or die "failed to update-server-info: $?\n"; - + run_die([@cmd, 'update-server-info'], undef); eval { require PublicInbox::SearchIdx; - PublicInbox::SearchIdx->new($git_dir, 2)->index_sync; + my $inbox = $self->{inbox} || $git_dir; + my $s = PublicInbox::SearchIdx->new($inbox); + $s->index_sync({ ref => $self->{ref} }); }; + + eval { run_die([@cmd, qw(gc --auto)], undef) }; } my $lockfh = delete $self->{lockfh} or die "BUG: not locked: $!";