#!/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 Date::Parse qw/str2time/; use Email::MIME; $Email::MIME::ContentType::STRICT_PARAMS = 0; # user input is imperfect use PublicInbox::Git; use PublicInbox::Import; my $usage = "usage: $0 NAME EMAIL \$dry_run ); GetOptions(%opts) or die $usage; chomp(my $git_dir = `git rev-parse --git-dir`); my $git = PublicInbox::Git->new($git_dir); my $name = shift or die $usage; # git my $email = shift or die $usage; # git@vger.kernel.org my $im = $dry_run ? undef : PublicInbox::Import->new($git, $name, $email); 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; $msg = Email::MIME->new($$msg); $msg = $vger->scrub($msg); my $hdr = $msg->header_obj; my $date = $hdr->header_raw('Date'); if ($date) { eval { str2time($date) }; if ($@) { warn "bad Date: $date in ", $hdr->header_raw('Message-ID'), ": $@\n"; } } else { warn "missing Date: $date in ", $hdr->header_raw('Message-ID'), ": $@\n"; my $n = 0; foreach my $r ($hdr->header_raw('Received')) { warn "$n Received: $r\n"; } warn(('-' x 72), "\n"); } return unless $im; $im->add($msg) or warn "duplicate: ", $hdr->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;