X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=t%2Fsearch.t;h=13210ff5a4af56e518490fe282c18bc2e8f08af4;hb=4eee5af6011cc8cdefb66c9729952c7eff5c0b0b;hp=3754717da338f7cee583d6e477b4bd7ffb0be5de;hpb=4a2e89007cb7b62151cb1869e49b27ebacfc27eb;p=public-inbox.git diff --git a/t/search.t b/t/search.t index 3754717d..13210ff5 100644 --- a/t/search.t +++ b/t/search.t @@ -1,4 +1,4 @@ -# Copyright (C) 2015-2020 all contributors +# Copyright (C) 2015-2021 all contributors # License: AGPL-3.0+ use strict; use warnings; @@ -9,6 +9,7 @@ require PublicInbox::SearchIdx; require PublicInbox::Inbox; require PublicInbox::InboxWritable; use PublicInbox::Eml; +use POSIX qw(strftime); my ($tmpdir, $for_destroy) = tmpdir(); my $git_dir = "$tmpdir/a.git"; my $ibx = PublicInbox::Inbox->new({ inboxdir => $git_dir }); @@ -60,7 +61,7 @@ sub oct_is ($$$) { } { - my $crlf_adjust = \&PublicInbox::SearchIdx::crlf_adjust; + my $crlf_adjust = \&PublicInbox::Smsg::crlf_adjust; is($crlf_adjust->("hi\r\nworld\r\n"), 0, 'no adjustment needed'); is($crlf_adjust->("hi\nworld\n"), 2, 'LF-only counts two CR'); is($crlf_adjust->("hi\r\nworld\n"), 1, 'CRLF/LF-mix 1 counts 1 CR'); @@ -532,6 +533,130 @@ $ibx->with_umask(sub { is($query->('s:"mail header experiments"')->[0]->{mid}, '20200418222508.GA13918@dcvr', 'Subject search reaches inside message/rfc822'); + + $doc_id = $rw->add_message(eml_load('t/data/binary.patch')); + $rw->commit_txn_lazy; + $ibx->search->reopen; + my $res = $query->('HcmV'); + is_deeply($res, [], 'no results against trailer'); + $res = $query->('IcmZPo000310RR91'); + is_deeply($res, [], 'no results against 1-byte binary patch'); + $res = $query->('"GIT binary patch"'); + is(scalar(@$res), 1, 'got binary result from "GIT binary patch"'); + is($res->[0]->{mid}, 'binary-patch-test@example', 'msgid for binary'); + my $s = $query->('"literal 1"'); + is_deeply($s, $res, 'got binary result from exact literal size'); + $s = $query->('"literal 2"'); + is_deeply($s, [], 'no results for wrong size'); }); +SKIP: { + my ($s, $g) = ($ibx->search, $ibx->git); + my $q = $s->query_argv_to_string($g, ["quoted phrase"]); + is($q, q["quoted phrase"], 'quoted phrase'); + $q = $s->query_argv_to_string($g, ['s:pa ce']); + is($q, q[s:"pa ce"], 'space with prefix'); + $q = $s->query_argv_to_string($g, ["\(s:pa ce", "AND", "foo\)"]); + is($q, q[(s:"pa ce" AND foo)], 'space AND foo'); + + local $ENV{TZ} = 'UTC'; + my $now = strftime('%H:%M:%S', gmtime(time)); + if ($now =~ /\A23:(?:59|60)/ || $now =~ /\A00:00:0[01]\z/) { + skip 'too close to midnight, time is tricky', 6; + } + $q = $s->query_argv_to_string($g, [qw(d:20101002 blah)]); + is($q, 'd:20101002..20101003 blah', 'YYYYMMDD expanded to range'); + $q = $s->query_argv_to_string($g, [qw(d:2010-10-02)]); + is($q, 'd:20101002..20101003', 'YYYY-MM-DD expanded to range'); + $q = $s->query_argv_to_string($g, [qw(rt:2010-10-02.. yy)]); + $q =~ /\Art:(\d+)\.\. yy/ or fail("rt: expansion failed: $q"); + is(strftime('%Y-%m-%d', gmtime($1//0)), '2010-10-02', 'rt: beg expand'); + $q = $s->query_argv_to_string($g, [qw(rt:..2010-10-02 zz)]); + $q =~ /\Art:\.\.(\d+) zz/ or fail("rt: expansion failed: $q"); + is(strftime('%Y-%m-%d', gmtime($1//0)), '2010-10-02', 'rt: end expand'); + $q = $s->query_argv_to_string($g, [qw(something dt:2010-10-02..)]); + like($q, qr/\Asomething dt:20101002\d{6}\.\./, 'dt: expansion'); + $q = $s->query_argv_to_string($g, [qw(x dt:yesterday.. y)]); + my $exp = strftime('%Y%m%d', gmtime(time - 86400)); + like($q, qr/x dt:$exp[0-9]{6}\.\. y/, '"yesterday" handled'); + $q = $s->query_argv_to_string($g, [qw(x dt:20101002054123)]); + is($q, 'x dt:20101002054123..20101003054123', 'single dt: expanded'); + $q = $s->query_argv_to_string($g, [qw(x dt:2010-10-02T05:41:23Z)]); + is($q, 'x dt:20101002054123..20101003054123', 'ISO8601 dt: expanded'); + $q = $s->query_argv_to_string($g, [qw(rt:1970..1971)]); + $q =~ /\Art:(\d+)\.\.(\d+)\z/ or fail "YYYY rt: expansion: $q"; + my ($beg, $end) = ($1, $2); + is(strftime('%Y', gmtime($beg)), 1970, 'rt: starts at 1970'); + is(strftime('%Y', gmtime($end)), 1971, 'rt: ends at 1971'); + $q = $s->query_argv_to_string($g, [qw(rt:1970-01-01)]); + $q =~ /\Art:(\d+)\.\.(\d+)\z/ or fail "YYYY-MM-DD rt: expansion: $q"; + ($beg, $end) = ($1, $2); + is(strftime('%Y-%m-%d', gmtime($beg)), '1970-01-01', + 'rt: date-only w/o range'); + is(strftime('%Y-%m-%d', gmtime($end)), '1970-01-02', + 'rt: date-only auto-end'); + $q = $s->query_argv_to_string($g, [qw{OR (rt:1993-10-02)}]); + like($q, qr/\AOR \(rt:749\d{6}\.\.749\d{6}\)\z/, + 'trailing parentheses preserved'); + + my $qs = qq[f:bob rt:1993-10-02..2010-10-02]; + $s->query_approxidate($g, $qs); + like($qs, qr/\Af:bob rt:749\d{6}\.\.128\d{7}\z/, + 'no phrases, no problem'); + + my $orig = $qs = qq[f:bob "d:1993-10-02..2010-10-02"]; + $s->query_approxidate($g, $qs); + is($qs, $orig, 'phrase preserved'); + + $orig = $qs = qq[f:bob "d:1993-10-02..2010-10-02 "] . + qq["dt:1993-10-02..2010-10-02 " \x{201c}]; + $s->query_approxidate($g, $qs); + is($qs, $orig, 'phrase preserved even with escaped ""'); + + $orig = $qs = qq[f:bob "hello world" d:1993-10-02..2010-10-02]; + $s->query_approxidate($g, $qs); + is($qs, qq[f:bob "hello world" d:19931002..20101002], + 'post-phrase date corrected'); + + # Xapian uses "" to escape " inside phrases, we don't explictly + # handle that, but are able to pass the result through unchanged + for my $pair (["\x{201c}", "\x{201d}"], ['"', '"']) { + my ($x, $y) = @$pair; + $orig = $qs = qq[${x}hello d:1993-10-02.."" world$y]; + $s->query_approxidate($g, $qs); + is($qs, $orig, 'phrases unchanged \x'.ord($x).'-\x'.ord($y)); + + $s->query_approxidate($g, my $tmp = "$qs d:..2010-10-02"); + is($tmp, "$orig d:..20101002", + 'two phrases did not throw off date parsing'); + + $orig = $qs = qq[${x}hello d:1993-10-02..$y$x world$y]; + $s->query_approxidate($g, $qs); + is($qs, $orig, 'phrases unchanged \x'.ord($x).'-\x'.ord($y)); + + $s->query_approxidate($g, $tmp = "$qs d:..2010-10-02"); + is($tmp, "$orig d:..20101002", + 'two phrases did not throw off date parsing'); + } + + my $x_days_ago = strftime('%Y%m%d', gmtime(time - (5 * 86400))); + $orig = $qs = qq[broken d:5.days.ago..]; + $s->query_approxidate($g, $qs); + like($qs, qr/\Abroken dt:$x_days_ago[0-9]{6}\.\./, + 'date.phrase.with.dots'); + + $orig = $qs = 'd:20101002..now'; + $s->query_approxidate($g, $qs); + like($qs, qr/\Adt:20101002000000\.\.[0-9]{14}\z/, + 'approxidate on range-end only'); + + $ENV{TEST_EXPENSIVE} or + skip 'TEST_EXPENSIVE not set for argv overflow check', 1; + my @w; + local $SIG{__WARN__} = sub { push @w, @_ }; # for pure Perl version + my @fail = map { 'd:1993-10-02..2010-10-02' } (1..(4096 * 32)); + eval { $s->query_argv_to_string($g, \@fail) }; + ok($@, 'exception raised'); +} + done_testing();