unofficial mirror of meta@public-inbox.org
 help / color / mirror / Atom feed
From: Eric Wong <e@yhbt.net>
To: meta@public-inbox.org
Subject: [PATCH 51/82] imap: start parsing out queries for SQLite and Xapian
Date: Wed, 10 Jun 2020 07:04:48 +0000	[thread overview]
Message-ID: <20200610070519.18252-52-e@yhbt.net> (raw)
In-Reply-To: <20200610070519.18252-1-e@yhbt.net>

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";

  parent reply	other threads:[~2020-06-10  7:07 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 ` [PATCH 12/82] imap: support fetch for BODYSTRUCTURE and BODY Eric Wong
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 ` Eric Wong [this message]
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=20200610070519.18252-52-e@yhbt.net \
    --to=e@yhbt.net \
    --cc=meta@public-inbox.org \
    /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
Be sure your reply has a Subject: header at the top and a blank line before the message body.
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).