user/dev discussion of public-inbox itself
 help / color / mirror / code / Atom feed
From: Eric Wong <e@yhbt.net>
To: meta@public-inbox.org
Subject: [PATCH 12/82] imap: support fetch for BODYSTRUCTURE and BODY
Date: Wed, 10 Jun 2020 07:04:09 +0000	[thread overview]
Message-ID: <20200610070519.18252-13-e@yhbt.net> (raw)
In-Reply-To: <20200610070519.18252-1-e@yhbt.net>

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;

  parent reply	other threads:[~2020-06-10  7:05 UTC|newest]

Thread overview: 84+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-06-10  7:03 [PATCH 00/82] public-inbox-imapd: read-only IMAP server Eric Wong
2020-06-10  7:03 ` [PATCH 01/82] doc: add some IMAP standards Eric Wong
2020-06-10  7:03 ` [PATCH 02/82] nntpd: restrict allowed newsgroup names Eric Wong
2020-06-10  7:04 ` [PATCH 03/82] preliminary imap server implementation Eric Wong
2020-06-10  7:04 ` [PATCH 04/82] inboxidle: new class to detect inbox changes Eric Wong
2020-06-10  7:04 ` [PATCH 05/82] imap: support IDLE Eric Wong
2020-06-10  7:04 ` [PATCH 06/82] msgmap: split ->max into its own method Eric Wong
2020-06-10  7:04 ` [PATCH 07/82] imap: delay InboxIdle start, support refresh Eric Wong
2020-06-10  7:04 ` [PATCH 08/82] imap: implement STATUS command Eric Wong
2020-06-10  7:04 ` [PATCH 09/82] imap: use Text::ParseWords::parse_line to handle quoted words Eric Wong
2020-06-10  7:04 ` [PATCH 10/82] imap: support LIST command Eric Wong
2020-06-10  7:04 ` [PATCH 11/82] t/imapd: support FakeInotify and KQNotify Eric Wong
2020-06-10  7:04 ` Eric Wong [this message]
2020-06-10  7:04 ` [PATCH 13/82] eml: each_part: single part $idx is 1 Eric Wong
2020-06-10  7:04 ` [PATCH 14/82] imap: allow fetch of partial of BODY[...] and headers Eric Wong
2020-06-10  7:04 ` [PATCH 15/82] imap: always include `resp-text' in responses Eric Wong
2020-06-10  7:04 ` [PATCH 16/82] imap: split out unit tests and benchmarks Eric Wong
2020-06-10  7:04 ` [PATCH 17/82] imap: fix multi-message partial header fetches Eric Wong
2020-06-10  7:04 ` [PATCH 18/82] imap: simplify partial fetch structure Eric Wong
2020-06-10  7:04 ` [PATCH 19/82] imap: support sequence number FETCH Eric Wong
2020-06-10  7:04 ` [PATCH 20/82] imap: do not include ".PEEK" in responses Eric Wong
2020-06-10  7:04 ` [PATCH 21/82] imap: support the CLOSE command Eric Wong
2020-06-10  7:04 ` [PATCH 22/82] imap: speed up HEADER.FIELDS[.NOT] range fetches Eric Wong
2020-06-10  7:04 ` [PATCH 23/82] git: async: flatten the inflight array Eric Wong
2020-06-10  7:04 ` [PATCH 24/82] git: do our own read buffering for cat-file Eric Wong
2020-06-10  7:04 ` [PATCH 25/82] imap: use git-cat-file asynchronously Eric Wong
2020-06-10  7:04 ` [PATCH 26/82] git: idle rbuf for async Eric Wong
2020-06-10  7:04 ` [PATCH 27/82] imap: support LSUB command Eric Wong
2020-06-10  7:04 ` [PATCH 28/82] imap: FETCH: support comma-delimited ranges Eric Wong
2020-06-10  7:04 ` [PATCH 29/82] add imapd compression test Eric Wong
2020-06-10  7:04 ` [PATCH 30/82] testcommon: tcp_(server|connect): BAIL_OUT on failure Eric Wong
2020-06-10  7:04 ` [PATCH 31/82] *deflate: drop invalid comment about rbuf Eric Wong
2020-06-10  7:04 ` [PATCH 32/82] imap: fix pipelining with async git Eric Wong
2020-06-10  7:04 ` [PATCH 33/82] git: cat_async: provide requested OID + "missing" on missing blobs Eric Wong
2020-06-10  7:04 ` [PATCH 34/82] git: move async_cat reference to PublicInbox::Git Eric Wong
2020-06-10  7:04 ` [PATCH 35/82] git: async: automatic retry on alternates change Eric Wong
2020-06-10  7:04 ` [PATCH 36/82] imapclient: wrapper for Mail::IMAPClient Eric Wong
2020-06-10  7:04 ` [PATCH 37/82] xt: add imapd-validate and imapd-mbsync-oimap Eric Wong
2020-06-10  7:04 ` [PATCH 38/82] imap: support out-of-bounds ranges Eric Wong
2020-06-10  7:04 ` [PATCH 39/82] xt/perf-imap-list: time refresh_inboxlist Eric Wong
2020-06-10  7:04 ` [PATCH 40/82] imap: case-insensitive mailbox name comparisons Eric Wong
2020-06-10  7:04 ` [PATCH 41/82] imap: break giant inboxes into sub-inboxes of 50K messages Eric Wong
2020-06-10  7:04 ` [PATCH 42/82] imap: start doing iterative config reloading Eric Wong
2020-06-10  7:04 ` [PATCH 43/82] imap: require ".$UID_MIN-$UID_END" suffix Eric Wong
2020-06-10  7:04 ` [PATCH 44/82] imapd: ensure LIST is sorted alphabetically, for now Eric Wong
2020-06-10  7:04 ` [PATCH 45/82] imap: omit $UID_END from mailbox name, use index Eric Wong
2020-06-10  7:04 ` [PATCH 46/82] t/config.t: always compare against git bool behavior Eric Wong
2020-06-10  7:04 ` [PATCH 47/82] xt/*: show some tunable parameters Eric Wong
2020-06-10  7:04 ` [PATCH 48/82] imap: STATUS and LIST are case-insensitive, too Eric Wong
2020-06-10  7:04 ` [PATCH 49/82] imap: EXAMINE/STATUS: return correct counts Eric Wong
2020-06-10  7:04 ` [PATCH 50/82] imap: avoid uninitialized warnings on incomplete commands Eric Wong
2020-06-10  7:04 ` [PATCH 51/82] imap: start parsing out queries for SQLite and Xapian Eric Wong
2020-06-10  7:04 ` [PATCH 52/82] imap: SEARCH: clamp results to the 50K UID range Eric Wong
2020-06-10  7:04 ` [PATCH 53/82] imap: allow UID range search on timestamps Eric Wong
2020-06-10  7:04 ` [PATCH 54/82] over: get_art: use dbh->prepare_cached Eric Wong
2020-06-10  7:04 ` [PATCH 55/82] search: index byte size of a message for IMAP search Eric Wong
2020-06-10  7:04 ` [PATCH 56/82] search: index UID for IMAP search, too Eric Wong
2020-06-10  7:04 ` [PATCH 57/82] imap: remove dummies from sequence number FETCH Eric Wong
2020-06-10  7:04 ` [PATCH 58/82] imap: compile UID FETCH to opcodes Eric Wong
2020-06-10  7:04 ` [PATCH 59/82] imap: UID FETCH: optimize for smsg-only case Eric Wong
2020-06-10  7:04 ` [PATCH 60/82] imap: UID FETCH: optimize (UID FLAGS) harder Eric Wong
2020-06-10  7:04 ` [PATCH 61/82] imap: IDLE: avoid extraneous wakeups, keep-alive Eric Wong
2020-06-10  7:04 ` [PATCH 62/82] imap: 30 minute auto-logout timer Eric Wong
2020-06-10  7:05 ` [PATCH 63/82] imap: split ->logged_in attribute into a separate class Eric Wong
2020-06-10  7:05 ` [PATCH 64/82] searchidx: v1 (re)-index uses git asynchronously Eric Wong
2020-06-10  7:05 ` [PATCH 65/82] index: account for CRLF conversion when storing bytes Eric Wong
2020-06-10  7:05 ` [PATCH 66/82] imap: rely on smsg->{bytes} for RFC822.SIZE Eric Wong
2020-06-10  7:05 ` [PATCH 67/82] imap: UID FETCH requires at least one data item Eric Wong
2020-06-10  7:05 ` [PATCH 68/82] imap: LIST shows "INBOX" in all caps Eric Wong
2020-06-10  7:05 ` [PATCH 69/82] imap: support 8000 octet lines Eric Wong
2020-06-10  7:05 ` [PATCH 70/82] imap: reinstate some message sequence number support Eric Wong
2020-06-10  7:05 ` [PATCH 71/82] imap: cleanup ->{uid_base} usage Eric Wong
2020-06-10  7:05 ` [PATCH 72/82] imap: FETCH: more granular CRLF conversion Eric Wong
2020-06-10  7:05 ` [PATCH 73/82] imap: further speed up HEADER.FIELDS FETCH requests Eric Wong
2020-06-10  7:05 ` [PATCH 74/82] imap: FETCH: try to make fake MSNs sequentially Eric Wong
2020-06-10  7:05 ` [PATCH 75/82] imap: STATUS/EXAMINE: rely on SQLite overview Eric Wong
2020-06-10  7:05 ` [PATCH 76/82] imap: UID SEARCH: support multiple ranges Eric Wong
2020-06-10  7:05 ` [PATCH 77/82] imap: wire up Xapian, MSN SEARCH and multi sequence-sets Eric Wong
2020-06-10  7:05 ` [PATCH 78/82] imap: misc cleanups and notes Eric Wong
2020-06-10  7:05 ` [PATCH 79/82] imapd: don't bother sorting LIST output Eric Wong
2020-06-10  7:05 ` [PATCH 80/82] imap: remove non-UID SEARCH for now Eric Wong
2020-06-10  7:05 ` [PATCH 81/82] over: uid_range: remove LIMIT Eric Wong
2020-06-10  7:05 ` [PATCH 82/82] imap: FETCH: proper MSN => UID mapping for requests Eric Wong
2020-06-12 23:49 ` [PATCH 83/82] imap: introduce memory-efficient uo2m mapping Eric Wong

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

  List information: https://public-inbox.org/README

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200610070519.18252-13-e@yhbt.net \
    --to=e@yhbt.net \
    --cc=meta@public-inbox.org \
    --subject='Re: [PATCH 12/82] imap: support fetch for BODYSTRUCTURE and BODY' \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

Code repositories for project(s) associated with this 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).