#!/usr/bin/perl -w # Copyright (C) 2016-2018 all contributors # License: AGPL-3.0+ use strict; use warnings; use Getopt::Long qw/:config gnu_getopt no_ignore_case auto_abbrev/; use PublicInbox::MIME; use PublicInbox::Inbox; use PublicInbox::V2Writable; use PublicInbox::Import; use PublicInbox::MDA; my $usage = "usage: $0 NAME EMAIL DIR \$dry_run, 'V|version=i' => \$version, 'F|format=s' => \$variant, ); GetOptions(%opts) or die $usage; if ($variant ne 'mboxrd' && $variant ne 'mboxo') { die "Unsupported mbox variant: $variant\n"; } my $name = shift or die $usage; # git my $email = shift or die $usage; # git@vger.kernel.org my $mainrepo = shift or die $usage; # /path/to/v2/repo my $ibx = { mainrepo => $mainrepo, name => $name, version => $version, -primary_address => $email, }; $ibx = PublicInbox::Inbox->new($ibx); my $im; unless ($dry_run) { if ($version >= 2) { $im = PublicInbox::V2Writable->new($ibx, 1); } else { system(qw(git init --bare -q), $mainrepo); my $git = PublicInbox::Git->new($mainrepo); $im = PublicInbox::Import->new($git, $name, $email, $ibx); } } binmode STDIN; my $msg = ''; use PublicInbox::Filter::Vger; my $vger = PublicInbox::Filter::Vger->new; sub do_add ($$) { my ($im, $msg) = @_; $$msg =~ s/(\r?\n)+\z/$1/s; my $mime = PublicInbox::MIME->new($msg); if ($variant eq 'mboxrd') { $$msg =~ s/^>(>*From )/$1/sm; } elsif ($variant eq 'mboxo') { $$msg =~ s/^>From /From /sm; } $mime = $vger->scrub($mime); return unless $im; $mime->header_set($_) foreach @PublicInbox::MDA::BAD_HEADERS; $im->add($mime) or warn "duplicate: ", $mime->header_obj->header_raw('Message-ID'), "\n"; } # asctime: From example@example.com Fri Jun 23 02:56:55 2000 my $from_strict = qr/^From \S+ +\S+ \S+ +\S+ [^:]+:[^:]+:[^:]+ [^:]+/; my $prev = undef; while (defined(my $l = )) { if ($l =~ /$from_strict/o) { if (!defined($prev) || $prev =~ /^\r?$/) { do_add($im, \$msg) if $msg; $msg = ''; $prev = $l; next; } warn "W[$.] $l\n"; } $prev = $l; $msg .= $l; } do_add($im, \$msg) if $msg; $im->done if $im;