* [PATCH 51/82] imap: start parsing out queries for SQLite and Xapian
2020-06-10 7:03 7% [PATCH 00/82] public-inbox-imapd: read-only IMAP server Eric Wong
@ 2020-06-10 7:04 7% ` Eric Wong
0 siblings, 0 replies; 2+ results
From: Eric Wong @ 2020-06-10 7:04 UTC (permalink / raw)
To: meta
None of the new cases are wired up, yet, but existing cases
still work.
---
lib/PublicInbox/IMAP.pm | 142 ++++++++++++++++++++++++++++++++++++++--
t/imap.t | 15 +++++
2 files changed, 150 insertions(+), 7 deletions(-)
diff --git a/lib/PublicInbox/IMAP.pm b/lib/PublicInbox/IMAP.pm
index 0452d6df937..b24dfcd70b5 100644
--- a/lib/PublicInbox/IMAP.pm
+++ b/lib/PublicInbox/IMAP.pm
@@ -24,6 +24,8 @@ use PublicInbox::Syscall qw(EPOLLIN EPOLLONESHOT);
use PublicInbox::GitAsyncCat;
use Text::ParseWords qw(parse_line);
use Errno qw(EAGAIN);
+use Time::Local qw(timegm);
+use POSIX qw(strftime);
my $Address;
for my $mod (qw(Email::Address::XS Mail::Address)) {
@@ -67,6 +69,10 @@ for my $att (keys %FETCH_ATT) {
my $valid_range = '[0-9]+|[0-9]+:[0-9]+|[0-9]+:\*';
$valid_range = qr/\A(?:$valid_range)(?:,(?:$valid_range))*\z/;
+my @MoY = qw(Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec);
+my %MoY;
+@MoY{@MoY} = (0..11);
+
sub greet ($) {
my ($self) = @_;
my $capa = capa($self);
@@ -787,6 +793,17 @@ sub cmd_fetch ($$$;@) {
} : $args; # error
}
+
+sub parse_date ($) { # 02-Oct-1993
+ my ($date_text) = @_;
+ my ($dd, $mon, $yyyy) = split(/-/, $_[0], 3);
+ defined($yyyy) or return;
+ my $mm = $MoY{$mon} // return;
+ $dd =~ /\A[0123]?[0-9]\z/ or return;
+ $yyyy =~ /\A[0-9]{4,}\z/ or return; # Y10K-compatible!
+ timegm(0, 0, 0, $dd, $mm, $yyyy);
+}
+
sub uid_search_all { # long_response
my ($self, $tag, $num) = @_;
my $uids = $self->{ibx}->mm->ids_after($num);
@@ -809,23 +826,134 @@ sub uid_search_uid_range { # long_response
}
}
+sub date_search {
+ my ($q, $k, $d) = @_;
+ my $sql = $q->{sql};
+
+ # Date: header
+ if ($k eq 'SENTON') {
+ my $end = $d + 86399; # no leap day...
+ my $da = strftime('%Y%m%d%H%M%S', gmtime($d));
+ my $db = strftime('%Y%m%d%H%M%S', gmtime($end));
+ $q->{xap} .= " dt:$da..$db";
+ $$sql .= " AND ds >= $d AND ds <= $end" if defined($sql);
+ } elsif ($k eq 'SENTBEFORE') {
+ $q->{xap} .= ' d:..'.strftime('%Y%m%d', gmtime($d));
+ $$sql .= " AND ds <= $d" if defined($sql);
+ } elsif ($k eq 'SENTSINCE') {
+ $q->{xap} .= ' d:'.strftime('%Y%m%d', gmtime($d)).'..';
+ $$sql .= " AND ds >= $d" if defined($sql);
+
+ # INTERNALDATE (Received)
+ } elsif ($k eq 'ON') {
+ my $end = $d + 86399; # no leap day...
+ $q->{xap} .= " ts:$d..$end";
+ $$sql .= " AND ts >= $d AND ts <= $end" if defined($sql);
+ } elsif ($k eq 'BEFORE') {
+ $q->{xap} .= " ts:..$d";
+ $$sql .= " AND ts <= $d" if defined($sql);
+ } elsif ($k eq 'SINCE') {
+ $q->{xap} .= " ts:$d..";
+ $$sql .= " AND ts >= $d" if defined($sql);
+ } else {
+ die "BUG: $k not recognized";
+ }
+}
+
+# IMAP to Xapian search key mapping
+my %I2X = (
+ SUBJECT => 's:',
+ BODY => 'b:',
+ FROM => 'f:',
+ TEXT => '', # n.b. does not include all headers
+ TO => 't:',
+ CC => 'c:',
+ # BCC => 'bcc:', # TODO
+ # KEYWORD # TODO ? dfpre,dfpost,...
+);
+
+sub parse_query {
+ my ($self, $rest) = @_;
+ if (uc($rest->[0]) eq 'CHARSET') {
+ shift @$rest;
+ defined(my $c = shift @$rest) or return 'BAD missing charset';
+ $c =~ /\A(?:UTF-8|US-ASCII)\z/ or return 'NO [BADCHARSET]';
+ }
+
+ my $sql = ''; # date conditions, {sql} deleted if Xapian is needed
+ my $q = { xap => '', sql => \$sql };
+ while (@$rest) {
+ my $k = uc(shift @$rest);
+ # default criteria
+ next if $k =~ /\A(?:ALL|RECENT|UNSEEN|NEW)\z/;
+ next if $k eq 'AND'; # the default, until we support OR
+ if ($k =~ $valid_range) { # sequence numbers == UIDs
+ push @{$q->{uid}}, $k;
+ } elsif ($k eq 'UID') {
+ $k = shift(@$rest) // '';
+ $k =~ $valid_range or return 'BAD UID range';
+ push @{$q->{uid}}, $k;
+ } elsif ($k =~ /\A(?:SENT)?(?:SINCE|ON|BEFORE)\z/) {
+ my $d = parse_date(shift(@$rest) // '');
+ defined $d or return "BAD $k date format";
+ date_search($q, $k, $d);
+ } elsif ($k =~ /\A(?:SMALLER|LARGER)\z/) {
+ delete $q->{sql}; # can't use over.sqlite3
+ my $bytes = shift(@$rest) // '';
+ $bytes =~ /\A[0-9]+\z/ or return "BAD $k not a number";
+ $q->{xap} .= ' bytes:' . ($k eq 'SMALLER' ?
+ '..'.(--$bytes) :
+ (++$bytes).'..');
+ } elsif (defined(my $xk = $I2X{$k})) {
+ delete $q->{sql}; # can't use over.sqlite3
+ my $arg = shift @$rest;
+ defined($arg) or return "BAD $k no arg";
+
+ # Xapian can't handle [*"] in probabilistic terms
+ $arg =~ tr/*"//d;
+ $q->{xap} .= qq[ $xk:"$arg"];
+ } else {
+ # TODO: parentheses, OR, NOT ...
+ return "BAD $k not supported (yet?)";
+ }
+ }
+
+ # favor using over.sqlite3 if possible, since Xapian is optional
+ if (exists $q->{sql}) {
+ delete($q->{xap});
+ delete($q->{sql}) if $sql eq '';
+ } elsif (!$self->{ibx}->search) {
+ return 'BAD Xapian not configured for mailbox';
+ }
+
+ if (my $uid = $q->{uid}) {
+ ((@$uid > 1) || $uid->[0] =~ /,/) and
+ return 'BAD multiple ranges not supported, yet';
+ ($q->{sql} // $q->{xap}) and
+ return 'BAD ranges and queries do not mix, yet';
+ $q->{uid} = join(',', @$uid); # TODO: multiple ranges
+ }
+ $q;
+}
+
sub cmd_uid_search ($$$;) {
- my ($self, $tag, $arg, @rest) = @_;
+ my ($self, $tag) = splice(@_, 0, 2);
my $ibx = $self->{ibx} or return "$tag BAD No mailbox selected\r\n";
- $arg = uc($arg);
- if ($arg eq 'ALL' && !@rest) {
+ my $q = parse_query($self, \@_);
+ return "$tag $q\r\n" if !ref($q);
+
+ if (!scalar(keys %$q)) {
$self->msg_more('* SEARCH');
my $num = 0;
long_response($self, \&uid_search_all, $tag, \$num);
- } elsif ($arg eq 'UID' && scalar(@rest) == 1) {
- if ($rest[0] =~ /\A([0-9]+):([0-9]+|\*)\z/s) {
+ } elsif (my $uid = $q->{uid}) {
+ if ($uid =~ /\A([0-9]+):([0-9]+|\*)\z/s) {
my ($beg, $end) = ($1, $2);
$end = $ibx->mm->max if $end eq '*';
$self->msg_more('* SEARCH');
long_response($self, \&uid_search_uid_range,
$tag, \$beg, $end);
- } elsif ($rest[0] =~ /\A[0-9]+\z/s) {
- my $uid = $rest[0];
+ } elsif ($uid =~ /\A[0-9]+\z/s) {
$uid = $ibx->over->get_art($uid) ? " $uid" : '';
"* SEARCH$uid\r\n$tag OK Search done\r\n";
} else {
diff --git a/t/imap.t b/t/imap.t
index af59ef69386..47e86ef42c7 100644
--- a/t/imap.t
+++ b/t/imap.t
@@ -9,6 +9,21 @@ use PublicInbox::IMAPD;
use PublicInbox::TestCommon;
require_mods(qw(DBD::SQLite));
require_git 2.6;
+use POSIX qw(strftime);
+
+{
+ my $parse_date = \&PublicInbox::IMAP::parse_date;
+ is(strftime('%Y-%m-%d', gmtime($parse_date->('02-Oct-1993'))),
+ '1993-10-02', 'parse_date works');
+ is(strftime('%Y-%m-%d', gmtime($parse_date->('2-Oct-1993'))),
+ '1993-10-02', 'parse_date works w/o leading zero');
+
+ is($parse_date->('2-10-1993'), undef, 'bad month');
+
+ # from what I can tell, RFC 3501 says nothing about date-month
+ # case-insensitivity, so be case-sensitive for now
+ is($parse_date->('02-oct-1993'), undef, 'case-sensitive month');
+}
my ($tmpdir, $for_destroy) = tmpdir();
my $cfgfile = "$tmpdir/config";
^ permalink raw reply related [relevance 7%]
* [PATCH 00/82] public-inbox-imapd: read-only IMAP server
@ 2020-06-10 7:03 7% Eric Wong
2020-06-10 7:04 7% ` [PATCH 51/82] imap: start parsing out queries for SQLite and Xapian 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 7% ` [PATCH 51/82] imap: start parsing out queries for SQLite and Xapian 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).