* [PATCH 12/82] imap: support fetch for BODYSTRUCTURE and BODY
2020-06-10 7:03 7% [PATCH 00/82] public-inbox-imapd: read-only IMAP server Eric Wong
@ 2020-06-10 7:04 5% ` Eric Wong
0 siblings, 0 replies; 2+ results
From: Eric Wong @ 2020-06-10 7:04 UTC (permalink / raw)
To: meta
I'm not sure which clients use these, but it could be useful
down the line.
---
lib/PublicInbox/Eml.pm | 7 +--
lib/PublicInbox/IMAP.pm | 106 +++++++++++++++++++++++++++++++++++++++-
t/imapd.t | 16 +++++-
3 files changed, 123 insertions(+), 6 deletions(-)
diff --git a/lib/PublicInbox/Eml.pm b/lib/PublicInbox/Eml.pm
index 6f6874cd237..d2bd3915545 100644
--- a/lib/PublicInbox/Eml.pm
+++ b/lib/PublicInbox/Eml.pm
@@ -235,11 +235,11 @@ sub mp_descend ($$) {
# $arg - user-supplied arg (think pthread_create)
# $once - unref body scalar during iteration
sub each_part {
- my ($self, $cb, $arg, $once) = @_;
+ my ($self, $cb, $arg, $once, $all) = @_;
my $p = mp_descend($self, $once // 0) or
return $cb->([$self, 0, 0], $arg);
- $cb->([$self, 0, 0], $arg) if $self->{-call_cb}; # rare
+ $cb->([$self, 0, 0], $arg) if ($all || $self->{-call_cb}); # rare
$p = [ $p, 0 ];
my @s; # our virtual stack
@@ -255,7 +255,8 @@ sub each_part {
(my $nxt = mp_descend($sub, $nr))) {
push(@s, $p) if scalar @{$p->[0]};
$p = [ $nxt, @idx, 0 ];
- $cb->([$sub, $depth, @idx], $arg) if $sub->{-call_cb};
+ ($all || $sub->{-call_cb}) and
+ $cb->([$sub, $depth, @idx], $arg);
} else { # a leaf node
$cb->([$sub, $depth, @idx], $arg);
}
diff --git a/lib/PublicInbox/IMAP.pm b/lib/PublicInbox/IMAP.pm
index ca9a0ea7d42..6c5e0290925 100644
--- a/lib/PublicInbox/IMAP.pm
+++ b/lib/PublicInbox/IMAP.pm
@@ -18,6 +18,7 @@ use base qw(PublicInbox::DS);
use fields qw(imapd logged_in ibx long_cb -login_tag
-idle_tag -idle_max);
use PublicInbox::Eml;
+use PublicInbox::EmlContentFoo qw(parse_content_disposition);
use PublicInbox::DS qw(now);
use PublicInbox::Syscall qw(EPOLLIN EPOLLONESHOT);
use Text::ParseWords qw(parse_line);
@@ -248,6 +249,105 @@ sub eml_envelope ($) {
) . ')';
}
+sub _esc_hash ($) {
+ my ($hash) = @_;
+ if ($hash && scalar keys %$hash) {
+ $hash = [ %$hash ]; # flatten hash into 1-dimensional array
+ '(' . join(' ', map { _esc($_) } @$hash) . ')';
+ } else {
+ 'NIL';
+ }
+}
+
+sub body_disposition ($) {
+ my ($eml) = @_;
+ my $cd = $eml->header_raw('Content-Disposition') or return 'NIL';
+ $cd = parse_content_disposition($cd);
+ my $buf = '('._esc($cd->{type});
+ $buf .= ' ' . _esc_hash(delete $cd->{attributes});
+ $buf .= ')';
+}
+
+sub body_leaf ($$;$) {
+ my ($eml, $structure, $hold) = @_;
+ my $buf = '';
+ $eml->{is_submsg} and # parent was a message/(rfc822|news|global)
+ $buf .= eml_envelope($eml). ' ';
+ my $ct = $eml->ct;
+ $buf .= '('._esc($ct->{type}).' ';
+ $buf .= _esc($ct->{subtype});
+ $buf .= ' ' . _esc_hash(delete $ct->{attributes});
+ $buf .= ' ' . _esc($eml->header_raw('Content-ID'));
+ $buf .= ' ' . _esc($eml->header_raw('Content-Description'));
+ my $cte = $eml->header_raw('Content-Transfer-Encoding') // '7bit';
+ $buf .= ' ' . _esc($cte);
+ $buf .= ' ' . $eml->{imap_body_len};
+ $buf .= ' '.($eml->body_raw =~ tr/\n/\n/) if lc($ct->{type}) eq 'text';
+
+ # for message/(rfc822|global|news), $hold[0] should have envelope
+ $buf .= ' ' . (@$hold ? join('', @$hold) : 'NIL') if $hold;
+
+ if ($structure) {
+ $buf .= ' '._esc($eml->header_raw('Content-MD5'));
+ $buf .= ' '. body_disposition($eml);
+ $buf .= ' '._esc($eml->header_raw('Content-Language'));
+ $buf .= ' '._esc($eml->header_raw('Content-Location'));
+ }
+ $buf .= ')';
+}
+
+sub body_parent ($$$) {
+ my ($eml, $structure, $hold) = @_;
+ my $ct = $eml->ct;
+ my $type = lc($ct->{type});
+ if ($type eq 'multipart') {
+ my $buf = '(';
+ $buf .= @$hold ? join('', @$hold) : 'NIL';
+ $buf .= ' '._esc($ct->{subtype});
+ if ($structure) {
+ $buf .= ' '._esc_hash(delete $ct->{attributes});
+ $buf .= ' '.body_disposition($eml);
+ $buf .= ' '._esc($eml->header_raw('Content-Language'));
+ $buf .= ' '._esc($eml->header_raw('Content-Location'));
+ }
+ $buf .= ')';
+ @$hold = ($buf);
+ } else { # message/(rfc822|global|news)
+ @$hold = (body_leaf($eml, $structure, $hold));
+ }
+}
+
+# this is gross, but we need to process the parent part AFTER
+# the child parts are done
+sub bodystructure_prep {
+ my ($p, $q) = @_;
+ my ($eml, $depth) = @$p; # ignore idx
+ # set length here, as $eml->{bdy} gets deleted for message/rfc822
+ $eml->{imap_body_len} = length($eml->body_raw);
+ push @$q, $eml, $depth;
+}
+
+# for FETCH BODY and FETCH BODYSTRUCTURE
+sub fetch_body ($;$) {
+ my ($eml, $structure) = @_;
+ my @q;
+ $eml->each_part(\&bodystructure_prep, \@q, 0, 1);
+ my $cur_depth = 0;
+ my @hold;
+ do {
+ my ($part, $depth) = splice(@q, -2);
+ my $is_mp_parent = $depth == ($cur_depth - 1);
+ $cur_depth = $depth;
+
+ if ($is_mp_parent) {
+ body_parent($part, $structure, \@hold);
+ } else {
+ unshift @hold, body_leaf($part, $structure);
+ }
+ } while (@q);
+ join('', @hold);
+}
+
sub uid_fetch_cb { # called by git->cat_async
my ($bref, $oid, $type, $size, $fetch_m_arg) = @_;
my ($self, undef, $ibx, undef, undef, $msgs, $want) = @$fetch_m_arg;
@@ -286,7 +386,11 @@ sub uid_fetch_cb { # called by git->cat_async
$self->msg_more(" $f {".length($$bref)."}\r\n");
$self->msg_more($$bref);
}
- # TODO BODY/BODYSTRUCTURE, specific headers
+ $want->{BODYSTRUCTURE} and
+ $self->msg_more(' BODYSTRUCTURE '.fetch_body($eml, 1));
+ $want->{BODY} and
+ $self->msg_more(' BODY '.fetch_body($eml));
+
$self->msg_more(")\r\n");
}
diff --git a/t/imapd.t b/t/imapd.t
index c31ac12f941..31154bdf3e7 100644
--- a/t/imapd.t
+++ b/t/imapd.t
@@ -7,7 +7,7 @@ use Time::HiRes ();
use PublicInbox::TestCommon;
use PublicInbox::Config;
use PublicInbox::Spawn qw(which);
-require_mods(qw(DBD::SQLite Mail::IMAPClient));
+require_mods(qw(DBD::SQLite Mail::IMAPClient Mail::IMAPClient::BodyStructure));
my $level = '-Lbasic';
SKIP: {
@@ -190,6 +190,11 @@ for my $r ('1:*', '1') {
$ret = $mic->fetch_hash($r, 'FLAGS') or BAIL_OUT "FETCH $@";
is_deeply($ret->{1}->{FLAGS}, '', 'no flags');
+
+ my $bs = $mic->get_bodystructure($r) or BAIL_OUT("bodystructure: $@");
+ ok($bs, 'got a bodystructure');
+ is(lc($bs->bodytype), 'text', '->bodytype');
+ is(lc($bs->bodyenc), '8bit', '->bodyenc');
}
# Mail::IMAPClient ->compress creates cyclic reference:
@@ -217,10 +222,12 @@ $pi_config->each_inbox(sub {
my $ng = $ibx->{newsgroup};
my $mic = Mail::IMAPClient->new(%mic_opt);
ok($mic && $mic->login && $mic->IsAuthenticated, "authed $name");
+ my $uidnext = $mic->uidnext($ng); # we'll fetch BODYSTRUCTURE on this
+ ok($uidnext, 'got uidnext for later fetch');
is_deeply([$mic->has_capability('IDLE')], ['IDLE'], "IDLE capa $name");
ok(!$mic->idle, "IDLE fails w/o SELECT/EXAMINE $name");
ok($mic->examine($ng), "EXAMINE $ng succeeds");
- ok($mic->idle, "IDLE succeeds on $ng");
+ ok(my $idle_tag = $mic->idle, "IDLE succeeds on $ng");
open(my $fh, '<', 't/data/message_embed.eml') or BAIL_OUT("open: $!");
run_script(['-mda', '--no-precheck'], $env, { 0 => $fh }) or
@@ -280,6 +287,11 @@ $pi_config->each_inbox(sub {
ok(@res = $mic->idle_data(11), "IDLE succeeds on $ng after HUP");
is(grep(/\A\* [0-9] EXISTS\b/, @res), 1, 'got EXISTS message');
ok((Time::HiRes::time() - $t0) < 10, 'IDLE client notified');
+ ok($mic->done($idle_tag), 'IDLE DONE');
+ my $bs = $mic->get_bodystructure($uidnext);
+ ok($bs, 'BODYSTRUCTURE ok for deeply nested');
+ $ret = $mic->fetch_hash($uidnext, 'BODY') or BAIL_OUT "FETCH $@";
+ ok($ret->{$uidnext}->{BODY}, 'got something in BODY');
});
$td->kill;
^ permalink raw reply related [relevance 5%]
* [PATCH 00/82] public-inbox-imapd: read-only IMAP server
@ 2020-06-10 7:03 7% Eric Wong
2020-06-10 7:04 5% ` [PATCH 12/82] imap: support fetch for BODYSTRUCTURE and BODY Eric Wong
0 siblings, 1 reply; 2+ results
From: Eric Wong @ 2020-06-10 7:03 UTC (permalink / raw)
To: meta
So I finally wrote my first IMAP server! And I'm actually
fairly satisfied with how it's turning out to support a bunch
of other performance + scalability work I've wanted to do.
Some previous notes here:
https://public-inbox.org/meta/20200609113442.GA16856@dcvr/
I finally seem to have gotten it to play nicely with mutt header
caching, so it's fit for public consumption :)
imaps://news.public-inbox.org/INBOX.comp.mail.public-inbox.meta.0
You can use any username+password, and AUTH=ANONYMOUS also
works if your client does that.
It doesn't support UTF-7 (mailbox names) or advertise UTF-8
in CAPABILITIES, yet; I still have RFCs to read :P
And there's a bunch of new things which could use some
testing from non-mutt/mbsync/offlineimap users.
Maybe you'll find some client-side bugs like I did :P
v1 reindexing also gets a little bit of parallelism :)
Anyways, I'll probably be porting some of the scalability
and slow-storage work to older parts of the code before
fiddling with more IMAP extensions.
Eric Wong (82):
doc: add some IMAP standards
nntpd: restrict allowed newsgroup names
preliminary imap server implementation
inboxidle: new class to detect inbox changes
imap: support IDLE
msgmap: split ->max into its own method
imap: delay InboxIdle start, support refresh
imap: implement STATUS command
imap: use Text::ParseWords::parse_line to handle quoted words
imap: support LIST command
t/imapd: support FakeInotify and KQNotify
imap: support fetch for BODYSTRUCTURE and BODY
eml: each_part: single part $idx is 1
imap: allow fetch of partial of BODY[...] and headers
imap: always include `resp-text' in responses
imap: split out unit tests and benchmarks
imap: fix multi-message partial header fetches
imap: simplify partial fetch structure
imap: support sequence number FETCH
imap: do not include ".PEEK" in responses
imap: support the CLOSE command
imap: speed up HEADER.FIELDS[.NOT] range fetches
git: async: flatten the inflight array
git: do our own read buffering for cat-file
imap: use git-cat-file asynchronously
git: idle rbuf for async
imap: support LSUB command
imap: FETCH: support comma-delimited ranges
add imapd compression test
testcommon: tcp_(server|connect): BAIL_OUT on failure
*deflate: drop invalid comment about rbuf
imap: fix pipelining with async git
git: cat_async: provide requested OID + "missing" on missing blobs
git: move async_cat reference to PublicInbox::Git
git: async: automatic retry on alternates change
imapclient: wrapper for Mail::IMAPClient
xt: add imapd-validate and imapd-mbsync-oimap
imap: support out-of-bounds ranges
xt/perf-imap-list: time refresh_inboxlist
imap: case-insensitive mailbox name comparisons
imap: break giant inboxes into sub-inboxes of 50K messages
imap: start introducing iterative config reloading
imap: require ".$UID_MIN-$UID_END" suffix
imapd: ensure LIST is sorted alphabetically, for now
imap: omit $UID_END from mailbox name, use index
t/config.t: always compare against git bool behavior
xt/*: show some tunable parameters
imap: STATUS and LIST are case-insensitive, too
imap: EXAMINE/STATUS: return correct counts
imap: avoid uninitialized warnings on incomplete commands
imap: start parsing out queries for SQLite and Xapian
imap: SEARCH: clamp results to the 50K UID range
imap: allow UID range search on timestamps
over: get_art: use dbh->prepare_cached
search: index byte size of a message for IMAP search
search: index UID for IMAP search, too
imap: remove dummies from sequence number FETCH
imap: compile UID FETCH to opcodes
imap: UID FETCH: optimize for smsg-only case
imap: UID FETCH: optimize (UID FLAGS) harder
imap: IDLE: avoid extraneous wakeups, keep-alive
imap: 30 minute auto-logout timer
imap: split ->logged_in attribute into a separate class
searchidx: v1 (re)-index uses git asynchronously
index: account for CRLF conversion when storing bytes
imap: rely on smsg->{bytes} for RFC822.SIZE
imap: UID FETCH requires at least one data item
imap: LIST shows "INBOX" in all caps
imap: support 8000 octet lines
imap: reinstate some message sequence number support
imap: cleanup ->{uid_base} usage
imap: FETCH: more granular CRLF conversion
imap: further speed up HEADER.FIELDS FETCH requests
imap: FETCH: try to make fake MSNs sequentially
imap: STATUS/EXAMINE: rely on SQLite overview
imap: UID SEARCH: support multiple ranges
imap: wire up Xapian search, msn SEARCH and multiple ranges
imap: misc cleanups and notes
imapd: don't bother sorting LIST output
imap: drop non-UID SEARCH for now
over: uid_range: remove LIMIT
imap: FETCH: proper MSN => UID mapping for requests
Documentation/public-inbox-imapd.pod | 91 ++
Documentation/standards.perl | 10 +
MANIFEST | 18 +
lib/PublicInbox/Config.pm | 18 +
lib/PublicInbox/Daemon.pm | 24 +-
lib/PublicInbox/DummyInbox.pm | 22 +
lib/PublicInbox/Eml.pm | 9 +-
lib/PublicInbox/FakeInotify.pm | 59 ++
lib/PublicInbox/Git.pm | 163 +--
lib/PublicInbox/GitAsyncCat.pm | 51 +
lib/PublicInbox/IMAP.pm | 1397 ++++++++++++++++++++++++++
lib/PublicInbox/IMAPClient.pm | 119 +++
lib/PublicInbox/IMAPD.pm | 114 +++
lib/PublicInbox/IMAPdeflate.pm | 126 +++
lib/PublicInbox/Import.pm | 2 +-
lib/PublicInbox/In2Tie.pm | 17 +
lib/PublicInbox/Inbox.pm | 33 +-
lib/PublicInbox/InboxIdle.pm | 79 ++
lib/PublicInbox/KQNotify.pm | 66 ++
lib/PublicInbox/Lock.pm | 7 +
lib/PublicInbox/MsgIter.pm | 2 +-
lib/PublicInbox/Msgmap.pm | 20 +-
lib/PublicInbox/NNTPD.pm | 12 +-
lib/PublicInbox/NNTPdeflate.pm | 1 -
lib/PublicInbox/Over.pm | 50 +-
lib/PublicInbox/Search.pm | 32 +-
lib/PublicInbox/SearchIdx.pm | 89 +-
lib/PublicInbox/SearchIdxShard.pm | 11 +-
lib/PublicInbox/Smsg.pm | 8 +-
lib/PublicInbox/TestCommon.pm | 7 +-
lib/PublicInbox/V2Writable.pm | 10 +-
script/public-inbox-imapd | 14 +
t/config.t | 15 +-
t/eml.t | 2 +-
t/git.t | 40 +-
t/imap.t | 133 +++
t/imapd-tls.t | 204 ++++
t/imapd.t | 398 ++++++++
t/import.t | 5 +-
t/inbox_idle.t | 72 ++
t/nntpd.t | 5 +-
t/over.t | 3 +
t/search.t | 19 +
xt/cmp-msgstr.t | 1 -
xt/cmp-msgview.t | 1 -
xt/eml_check_limits.t | 6 +-
xt/git_async_cmp.t | 2 +-
xt/imapd-mbsync-oimap.t | 132 +++
xt/imapd-validate.t | 177 ++++
xt/mem-msgview.t | 1 +
xt/msgtime_cmp.t | 1 -
xt/perf-msgview.t | 1 -
52 files changed, 3718 insertions(+), 181 deletions(-)
create mode 100644 Documentation/public-inbox-imapd.pod
create mode 100644 lib/PublicInbox/DummyInbox.pm
create mode 100644 lib/PublicInbox/FakeInotify.pm
create mode 100644 lib/PublicInbox/GitAsyncCat.pm
create mode 100644 lib/PublicInbox/IMAP.pm
create mode 100644 lib/PublicInbox/IMAPClient.pm
create mode 100644 lib/PublicInbox/IMAPD.pm
create mode 100644 lib/PublicInbox/IMAPdeflate.pm
create mode 100644 lib/PublicInbox/In2Tie.pm
create mode 100644 lib/PublicInbox/InboxIdle.pm
create mode 100644 lib/PublicInbox/KQNotify.pm
create mode 100644 script/public-inbox-imapd
create mode 100644 t/imap.t
create mode 100644 t/imapd-tls.t
create mode 100644 t/imapd.t
create mode 100644 t/inbox_idle.t
create mode 100644 xt/imapd-mbsync-oimap.t
create mode 100644 xt/imapd-validate.t
^ permalink raw reply [relevance 7%]
Results 1-2 of 2 | reverse | options above
-- pct% links below jump to the message on this page, permalinks otherwise --
2020-06-10 7:03 7% [PATCH 00/82] public-inbox-imapd: read-only IMAP server Eric Wong
2020-06-10 7:04 5% ` [PATCH 12/82] imap: support fetch for BODYSTRUCTURE and BODY Eric Wong
Code repositories for project(s) associated with this public inbox
https://80x24.org/public-inbox.git
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).