X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FImport.pm;h=8c9d1cbad526a7d1e5dd3813f390685a0cd3713b;hb=7174681c0165008ac16ed1d323f6d95b6d0570a3;hp=5bae69df4d349f1e40a898df0bf3972684eff588;hpb=4284a260374b0c6d90a3f95b387b82a6f64f3125;p=public-inbox.git diff --git a/lib/PublicInbox/Import.pm b/lib/PublicInbox/Import.pm index 5bae69df..8c9d1cba 100644 --- a/lib/PublicInbox/Import.pm +++ b/lib/PublicInbox/Import.pm @@ -8,17 +8,18 @@ package PublicInbox::Import; use strict; use warnings; use Fcntl qw(:flock :DEFAULT); -use Email::Address; 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, }, $class } @@ -39,18 +40,22 @@ sub gfi_start { # wait for other processes to be done flock($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 --quiet --done --date-format=rfc2822)); my $rdr = { 0 => fileno($out_r), 1 => fileno($in_w) }; my $pid = spawn(\@cmd, undef, $rdr); - die "spawn failed: $!" unless defined $pid; + die "spawn fast-import failed: $!" unless defined $pid; $out_w->autoflush(1); $self->{in} = $in_r; $self->{out} = $out_w; $self->{lockfh} = $lockfh; $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); } @@ -65,47 +70,64 @@ sub now2822 () { $day, $t[3], $mon, $t[5] + 1900, $t[2], $t[1], $t[0]); } +sub norm_body ($) { + my ($mime) = @_; + my $b = $mime->body_raw; + $b =~ s/(\r?\n)+\z//s; + $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 -# (-1, msg) on mismatch +# ('MISMATCH', msg) on mismatch # (:MARK, msg) on success sub remove { - my ($self, $mime) = @_; # mime = Email::MIME + my ($self, $mime, $msg) = @_; # mime = Email::MIME my $mid = mid_mime($mime); my $path = mid2path($mid); my ($r, $w) = $self->gfi_start; my $tip = $self->{tip}; - return 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 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 = ''; + my $n; while ($left > 0) { - my $n = read($r, $buf, $left, $offset); + $n = read($r, $buf, $left, $offset); defined($n) or die "read cat-blob failed: $!"; $n == 0 and die 'fast-export (cat-blob) died'; $left -= $n; $offset += $n; } - read($r, my $lf, 1); + $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); - if ($cur->header('Subject') ne $mime->header('Subject') || - $cur->body ne $mime->body) { - return (-1, $cur); + my $cur = PublicInbox::MIME->new($buf); + my $cur_s = $cur->header('Subject'); + $cur_s = '' unless defined $cur_s; + my $cur_m = $mime->header('Subject'); + $cur_m = '' unless defined $cur_m; + if ($cur_s ne $cur_m || norm_body($cur) ne norm_body($mime)) { + return ('MISMATCH', $cur); } my $ref = $self->{ref}; @@ -116,23 +138,31 @@ sub remove { } my $ident = $self->{ident}; my $now = now2822(); + $msg ||= 'rm'; + my $len = length($msg) + 1; print $w "commit $ref\nmark :$commit\n", "author $ident $now\n", "committer $ident $now\n", - "data 3\nrm\n\n", + "data $len\n$msg\n\n", 'from ', ($parent ? $parent : $tip), "\n" or wfail; print $w "D $path\n\n" or wfail; + $self->{nchg}++; (($self->{tip} = ":$commit"), $cur); } # returns undef on duplicate sub add { - my ($self, $mime) = @_; # mime = Email::MIME + my ($self, $mime, $check_cb) = @_; # mime = Email::MIME my $from = $mime->header('From'); - my @from = Email::Address->parse($from); - my $name = $from[0]->name; - my $email = $from[0]->address; + my ($email) = PublicInbox::Address::emails($from); + my ($name) = PublicInbox::Address::names($from); + # git gets confused with: + # "'A U Thor ' via foo" + # ref: + # + $name =~ tr/<>//d; + my $date = $mime->header('Date'); my $subject = $mime->header('Subject'); $subject = '(no subject)' unless defined $subject; @@ -141,16 +171,14 @@ 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); + if ($check_cb) { + $mime = $check_cb->($mime) or return; + } + $mime = $mime->as_string; my $blob = $self->{mark}++; print $w "blob\nmark :$blob\ndata ", length($mime), "\n" or wfail; @@ -163,22 +191,31 @@ sub add { print $w "reset $ref\n" or wfail; } + utf8::encode($email); + utf8::encode($name); + utf8::encode($subject); # quiet down wide character warnings: - binmode $w, ':utf8' or die "binmode :utf8 failed: $!"; print $w "commit $ref\nmark :$commit\n", "author $name <$email> $date\n", - "committer $self->{ident} ", now2822(), "\n", - "data ", (bytes::length($subject) + 1), "\n", + "committer $self->{ident} ", now2822(), "\n" or wfail; + print $w "data ", (length($subject) + 1), "\n", $subject, "\n\n" or wfail; - binmode $w, ':raw' or die "binmode :raw failed: $!"; - if ($tip ne '') { print $w 'from ', ($parent ? $parent : $tip), "\n" or wfail; } print $w "M 100644 :$blob $path\n\n" or wfail; + $self->{nchg}++; $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; @@ -187,9 +224,152 @@ sub done { 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 $nchg = delete $self->{nchg}; + + # for compatibility with existing ssoma installations + # we can probably remove this entirely by 2020 + my $git_dir = $self->{git}->{git_dir}; + # XXX: change the following scope to: if (-e $index) # in 2018 or so.. + my @cmd = ('git', "--git-dir=$git_dir"); + if ($nchg && !$ENV{FAST}) { + my $index = "$git_dir/ssoma.index"; + my $env = { GIT_INDEX_FILE => $index }; + run_die([@cmd, qw(read-tree -m -v -i), $self->{ref}], $env); + } + if ($nchg) { + run_die([@cmd, 'update-server-info'], undef); + eval { + require PublicInbox::SearchIdx; + 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: $!"; flock($lockfh, LOCK_UN) or die "unlock failed: $!"; close $lockfh or die "close lock failed: $!"; } 1; +__END__ +=pod + +=head1 NAME + +PublicInbox::Import - message importer for public-inbox + +=head1 VERSION + +version 1.0 + +=head1 SYNOPSYS + + use Email::MIME; + use PublicInbox::Git; + use PublicInbox::Import; + + chomp(my $git_dir = `git rev-parse --git-dir`); + $git_dir or die "GIT_DIR= must be specified\n"; + my $git = PublicInbox::Git->new($git_dir); + my @committer = ('inbox', 'inbox@example.org'); + my $im = PublicInbox::Import->new($git, @committer); + + # to add a message: + my $message = "From: \n". + "Subject: test message \n" . + "Date: Thu, 01 Jan 1970 00:00:00 +0000\n" . + "Message-ID: \n". + "\ntest message"; + my $parsed = Email::MIME->new($message); + my $ret = $im->add($parsed); + if (!defined $ret) { + warn "duplicate: ", + $parsed->header_obj->header_raw('Message-ID'), "\n"; + } else { + print "imported at mark $ret\n"; + } + $im->done; + + # to remove a message + my $junk = Email::MIME->new($message); + my ($mark, $orig) = $im->remove($junk); + if ($mark eq 'MISSING') { + print "not found\n"; + } elsif ($mark eq 'MISMATCH') { + print "Message exists but does not match\n\n", + $orig->as_string, "\n",; + } else { + print "removed at mark $mark\n\n", + $orig->as_string, "\n"; + } + $im->done; + +=head1 DESCRIPTION + +An importer and remover for public-inboxes which takes L +messages as input and stores them in a ssoma repository as +documented in L, +except it does not allow duplicate Message-IDs. + +It requires L and L to be installed. + +=head1 METHODS + +=cut + +=head2 new + + my $im = PublicInbox::Import->new($git, @committer); + +Initialize a new PublicInbox::Import object. + +=head2 add + + my $parsed = Email::MIME->new($message); + $im->add($parsed); + +Adds a message to to the git repository. This will acquire +C<$GIT_DIR/ssoma.lock> and start L if necessary. + +Messages added will not be visible to other processes until L +is called, but L may be called on them. + +=head2 remove + + my $junk = Email::MIME->new($message); + my ($code, $orig) = $im->remove($junk); + +Removes a message from the repository. On success, it returns +a ':'-prefixed numeric code representing the git-fast-import +mark and the original messages as an Email::MIME object. +If the message could not be found, the code is "MISSING" +and the original message is undef. If there is a mismatch where +the "Message-ID" is matched but the subject and body do not match, +the returned code is "MISMATCH" and the conflicting message +is returned as orig. + +=head2 done + +Finalizes the L and unlocks the repository. +Calling this is required to finalize changes to a repository. + +=head1 SEE ALSO + +L + +=head1 CONTACT + +All feedback welcome via plain-text mail to L + +The mail archives are hosted at L + +=head1 COPYRIGHT + +Copyright (C) 2016 all contributors L + +License: AGPL-3.0+ L + +=cut