package PublicInbox::NetReader;
use strict;
use v5.10.1;
-use parent qw(Exporter);
+use parent qw(Exporter PublicInbox::IPC);
+use PublicInbox::Eml;
+
+our %IMAPflags2kw = map {; "\\\u$_" => $_ } qw(seen answered flagged draft);
# TODO: trim this down, this is huge
our @EXPORT = qw(uri_new uri_scheme uri_section
- mic_for nn_new nn_for
- imap_url nntp_url
+ nn_new nn_for
+ imap_uri nntp_url
cfg_bool cfg_intvl imap_common_init
);
sub auth_anon_cb { '' }; # for Mail::IMAPClient::Authcallback
+# mic_for may prompt the user and store auth info, prepares mic_get
sub mic_for { # mic = Mail::IMAPClient
- my ($self, $url, $mic_args) = @_;
+ my ($self, $url, $mic_args, $lei) = @_;
require PublicInbox::URIimap;
my $uri = PublicInbox::URIimap->new($url);
require PublicInbox::GitCredential;
}
if ($cred) {
$cred->check_netrc unless defined $cred->{password};
- $cred->fill; # may prompt user here
+ $cred->fill($lei); # may prompt user here
$mic->User($mic_arg->{User} = $cred->{username});
$mic->Password($mic_arg->{Password} = $cred->{password});
} else { # AUTH=ANONYMOUS
$mic->Authmechanism($mic_arg->{Authmechanism} = 'ANONYMOUS');
- $mic->Authcallback($mic_arg->{Authcallback} = \&auth_anon_cb);
+ $mic_arg->{Authcallback} = 'auth_anon_cb';
+ $mic->Authcallback(\&auth_anon_cb);
}
+ my $err;
if ($mic->login && $mic->IsAuthenticated) {
# success! keep IMAPClient->new arg in case we get disconnected
$self->{mic_arg}->{uri_section($uri)} = $mic_arg;
} else {
- warn "E: <$url> LOGIN: $@\n";
+ $err = "E: <$url> LOGIN: $@\n";
+ if ($cred && defined($cred->{password})) {
+ $err =~ s/\Q$cred->{password}\E/*******/g;
+ }
$mic = undef;
}
$cred->run($mic ? 'approve' : 'reject') if $cred;
+ if ($err) {
+ $lei ? $lei->fail($err) : warn($err);
+ }
$mic;
}
$nn;
}
-sub nn_for ($$$) { # nn = Net::NNTP
- my ($self, $url, $nn_args) = @_;
+sub nn_for ($$$;$) { # nn = Net::NNTP
+ my ($self, $url, $nn_args, $lei) = @_;
my $uri = uri_new($url);
my $sec = uri_section($uri);
my $nntp_opt = $self->{nntp_opt}->{$sec} //= {};
my $nn = nn_new($nn_arg, $nntp_opt, $url);
if ($cred) {
- $cred->fill; # may prompt user here
+ $cred->fill($lei); # may prompt user here
if ($nn->authinfo($u, $p)) {
push @{$nntp_opt->{-postconn}}, [ 'authinfo', $u, $p ];
} else {
$nn;
}
-sub imap_url {
+sub imap_uri {
my ($url) = @_;
require PublicInbox::URIimap;
my $uri = PublicInbox::URIimap->new($url);
- $uri ? $uri->canonical->as_string : undef;
+ $uri ? $uri->canonical : undef;
}
my %IS_NNTP = (news => 1, snews => 1, nntp => 1);
}
# flesh out common IMAP-specific data structures
-sub imap_common_init ($) {
- my ($self) = @_;
+sub imap_common_init ($;$) {
+ my ($self, $lei) = @_;
+ $self->{quiet} = 1 if $lei && $lei->{opt}->{quiet};
eval { require PublicInbox::IMAPClient } or
die "Mail::IMAPClient is required for IMAP:\n$@\n";
eval { require PublicInbox::IMAPTracker } or
die "DBD::SQLite is required for IMAP\n:$@\n";
require PublicInbox::URIimap;
- my $cfg = $self->{pi_cfg};
+ my $cfg = $self->{pi_cfg} // $lei->_lei_cfg;
my $mic_args = {}; # scheme://authority => Mail:IMAPClient arg
- for my $url (@{$self->{imap_order}}) {
- my $uri = PublicInbox::URIimap->new($url);
+ for my $uri (@{$self->{imap_order}}) {
my $sec = uri_section($uri);
for my $k (qw(Starttls Debug Compress)) {
- my $bool = cfg_bool($cfg, "imap.$k", $url) // next;
+ my $bool = cfg_bool($cfg, "imap.$k", $$uri) // next;
$mic_args->{$sec}->{$k} = $bool;
}
- my $to = cfg_intvl($cfg, 'imap.timeout', $url);
+ my $to = cfg_intvl($cfg, 'imap.timeout', $$uri);
$mic_args->{$sec}->{Timeout} = $to if $to;
for my $k (qw(pollInterval idleInterval)) {
- $to = cfg_intvl($cfg, "imap.$k", $url) // next;
+ $to = cfg_intvl($cfg, "imap.$k", $$uri) // next;
$self->{imap_opt}->{$sec}->{$k} = $to;
}
my $k = 'imap.fetchBatchSize';
- my $bs = $cfg->urlmatch($k, $url) // next;
+ my $bs = $cfg->urlmatch($k, $$uri) // next;
if ($bs =~ /\A([0-9]+)\z/) {
$self->{imap_opt}->{$sec}->{batch_size} = $bs;
} else {
# make sure we can connect and cache the credentials in memory
$self->{mic_arg} = {}; # schema://authority => IMAPClient->new args
my $mics = {}; # schema://authority => IMAPClient obj
- for my $url (@{$self->{imap_order}}) {
- my $uri = PublicInbox::URIimap->new($url);
- $mics->{uri_section($uri)} //= mic_for($self, $url, $mic_args);
+ for my $uri (@{$self->{imap_order}}) {
+ my $sec = uri_section($uri);
+ $mics->{$sec} //= mic_for($self, "$sec/", $mic_args, $lei);
+ next unless $self->isa('PublicInbox::NetWriter');
+ my $dst = $uri->mailbox // next;
+ my $mic = $mics->{$sec};
+ next if $mic->exists($dst); # already exists
+ $mic->create($dst) or die "CREATE $dst failed <$uri>: $@";
}
$mics;
}
+sub add_url {
+ my ($self, $arg) = @_;
+ if (my $uri = imap_uri($arg)) {
+ push @{$self->{imap_order}}, $uri;
+ } else {
+ push @{$self->{unsupported_url}}, $arg;
+ }
+}
+
+sub errors {
+ my ($self) = @_;
+ if (my $u = $self->{unsupported_url}) {
+ return "Unsupported URL(s): @$u";
+ }
+ if ($self->{imap_order}) {
+ eval { require PublicInbox::IMAPClient } or
+ die "Mail::IMAPClient is required for IMAP:\n$@\n";
+ }
+ undef;
+}
+
+sub _imap_do_msg ($$$$$) {
+ my ($self, $uri, $uid, $raw, $flags) = @_;
+ # our target audience expects LF-only, save storage
+ $$raw =~ s/\r\n/\n/sg;
+ my $kw = [];
+ for my $f (split(/ /, $flags)) {
+ my $k = $IMAPflags2kw{$f} // next; # TODO: X-Label?
+ push @$kw, $k;
+ }
+ my ($eml_cb, @args) = @{$self->{eml_each}};
+ $eml_cb->($uri, $uid, $kw, PublicInbox::Eml->new($raw), @args);
+}
+
+sub _imap_fetch_all ($$$) {
+ my ($self, $mic, $uri) = @_;
+ my $sec = uri_section($uri);
+ my $mbx = $uri->mailbox;
+ $mic->Clear(1); # trim results history
+ $mic->examine($mbx) or return "E: EXAMINE $mbx ($sec) failed: $!";
+ my ($r_uidval, $r_uidnext);
+ for ($mic->Results) {
+ /^\* OK \[UIDVALIDITY ([0-9]+)\].*/ and $r_uidval = $1;
+ /^\* OK \[UIDNEXT ([0-9]+)\].*/ and $r_uidnext = $1;
+ last if $r_uidval && $r_uidnext;
+ }
+ $r_uidval //= $mic->uidvalidity($mbx) //
+ return "E: $uri cannot get UIDVALIDITY";
+ $r_uidnext //= $mic->uidnext($mbx) //
+ return "E: $uri cannot get UIDNEXT";
+ my $itrk = $self->{incremental} ?
+ PublicInbox::IMAPTracker->new($$uri) : 0;
+ my ($l_uidval, $l_uid) = $itrk ? $itrk->get_last : ();
+ $l_uidval //= $r_uidval; # first time
+ $l_uid //= 0;
+ if ($l_uidval != $r_uidval) {
+ return "E: $uri UIDVALIDITY mismatch\n".
+ "E: local=$l_uidval != remote=$r_uidval";
+ }
+ my $r_uid = $r_uidnext - 1;
+ if ($l_uid > $r_uid) {
+ return "E: $uri local UID exceeds remote ($l_uid > $r_uid)\n".
+ "E: $uri strangely, UIDVALIDLITY matches ($l_uidval)\n";
+ }
+ return if $l_uid >= $r_uid; # nothing to do
+ $l_uid ||= 1;
+ my ($mod, $shard) = @{$self->{shard_info} // []};
+ unless ($self->{quiet}) {
+ my $m = $mod ? " [(UID % $mod) == $shard]" : '';
+ warn "# $uri fetching UID $l_uid:$r_uid$m\n";
+ }
+ $mic->Uid(1); # the default, we hope
+ my $bs = $self->{imap_opt}->{$sec}->{batch_size} // 1;
+ my $req = $mic->imap4rev1 ? 'BODY.PEEK[]' : 'RFC822.PEEK';
+ my $key = $req;
+ $key =~ s/\.PEEK//;
+ my ($uids, $batch);
+ my $err;
+ do {
+ # I wish "UID FETCH $START:*" could work, but:
+ # 1) servers do not need to return results in any order
+ # 2) Mail::IMAPClient doesn't offer a streaming API
+ $uids = $mic->search("UID $l_uid:*") or
+ return "E: $uri UID SEARCH $l_uid:* error: $!";
+ return if scalar(@$uids) == 0;
+
+ # RFC 3501 doesn't seem to indicate order of UID SEARCH
+ # responses, so sort it ourselves. Order matters so
+ # IMAPTracker can store the newest UID.
+ @$uids = sort { $a <=> $b } @$uids;
+
+ # Did we actually get new messages?
+ return if $uids->[0] < $l_uid;
+
+ $l_uid = $uids->[-1] + 1; # for next search
+ my $last_uid;
+ my $n = $self->{max_batch};
+
+ @$uids = grep { ($_ % $mod) == $shard } @$uids if $mod;
+ while (scalar @$uids) {
+ my @batch = splice(@$uids, 0, $bs);
+ $batch = join(',', @batch);
+ local $0 = "UID:$batch $mbx $sec";
+ my $r = $mic->fetch_hash($batch, $req, 'FLAGS');
+ unless ($r) { # network error?
+ $err = "E: $uri UID FETCH $batch error: $!";
+ last;
+ }
+ for my $uid (@batch) {
+ # messages get deleted, so holes appear
+ my $per_uid = delete $r->{$uid} // next;
+ my $raw = delete($per_uid->{$key}) // next;
+ _imap_do_msg($self, $uri, $uid, \$raw,
+ $per_uid->{FLAGS});
+ $last_uid = $uid;
+ last if $self->{quit};
+ }
+ last if $self->{quit};
+ }
+ $itrk->update_last($r_uidval, $last_uid) if $itrk;
+ } until ($err || $self->{quit});
+ $err;
+}
+
+# uses cached auth info prepared by mic_for
+sub mic_get {
+ my ($self, $uri) = @_;
+ my $sec = uri_section($uri);
+ # see if caller saved result of imap_common_init
+ my $cached = $self->{mics_cached};
+ if ($cached) {
+ my $mic = $cached->{$sec};
+ return $mic if $mic && $mic->IsConnected;
+ delete $cached->{$sec};
+ }
+ my $mic_arg = $self->{mic_arg}->{$sec} or
+ die "BUG: no Mail::IMAPClient->new arg for $sec";
+ if (defined(my $cb_name = $mic_arg->{Authcallback})) {
+ if (ref($cb_name) ne 'CODE') {
+ $mic_arg->{Authcallback} = $self->can($cb_name);
+ }
+ }
+ my $mic = PublicInbox::IMAPClient->new(%$mic_arg);
+ $cached //= {}; # invalid placeholder if no cache enabled
+ $mic && $mic->IsConnected ? ($cached->{$sec} = $mic) : undef;
+}
+
+sub imap_each {
+ my ($self, $url, $eml_cb, @args) = @_;
+ my $uri = ref($url) ? $url : PublicInbox::URIimap->new($url);
+ my $sec = uri_section($uri);
+ local $0 = $uri->mailbox." $sec";
+ my $mic = mic_get($self, $uri);
+ my $err;
+ if ($mic) {
+ local $self->{eml_each} = [ $eml_cb, @args ];
+ $err = _imap_fetch_all($self, $mic, $uri);
+ } else {
+ $err = "E: not connected: $!";
+ }
+ warn $err if $err;
+ $mic;
+}
+
+sub new { bless {}, shift };
+
1;