From dd98584c8572b85afbd68ff98423605df9b18822 Mon Sep 17 00:00:00 2001
From: Ere Maijala <ere.maijala@helsinki.fi>
Date: Thu, 31 Jan 2019 13:43:00 +0200
Subject: [PATCH] Bug 22228: Escape lone colons and make sure term is balanced
MIME-Version: 1.0
Content-Type: text/plain; charset=utf8
Content-Transfer-Encoding: 8bit

Escapes unquoted colons that have whitespace on either side. Removed unbalanced quotes.

Test plan:

1. Make sure the test case described in the bug works
2. Make sure tests pass:
  prove t/Koha/SearchEngine/Elasticsearch/QueryBuilder.t

Signed-off-by: Björn Nylén <bjorn.nylen(at)ub.lu.se>

Signed-off-by: Josef Moravec <josef.moravec@gmail.com>

Signed-off-by: Nick Clemens <nick@bywatersolutions.com>
---
 .../Elasticsearch/QueryBuilder.pm             | 15 +++++++
 .../SearchEngine/Elasticsearch/QueryBuilder.t | 41 ++++++++++++++++++-
 2 files changed, 54 insertions(+), 2 deletions(-)

diff --git a/Koha/SearchEngine/Elasticsearch/QueryBuilder.pm b/Koha/SearchEngine/Elasticsearch/QueryBuilder.pm
index c65a4b56dd..252416cbf8 100644
--- a/Koha/SearchEngine/Elasticsearch/QueryBuilder.pm
+++ b/Koha/SearchEngine/Elasticsearch/QueryBuilder.pm
@@ -803,11 +803,26 @@ to ensure those parts are correct.
 sub _clean_search_term {
     my ( $self, $term ) = @_;
 
+    # Lookahead for checking if we are inside quotes
+    my $lookahead = '(?=(?:[^\"]*+\"[^\"]*+\")*+[^\"]*+$)';
+
     # Some hardcoded searches (like with authorities) produce things like
     # 'an=123', when it ought to be 'an:123' for our purposes.
     $term =~ s/=/:/g;
+
     $term = $self->_convert_index_strings_freeform($term);
     $term =~ s/[{}]/"/g;
+
+    # Remove unbalanced quotes
+    my $unquoted = $term;
+    my $count = ($unquoted =~ tr/"/ /);
+    if ($count % 2 == 1) {
+        $term = $unquoted;
+    }
+
+    # Remove unquoted colons that have whitespace on either side of them
+    $term =~ s/(\:[:\s]+|[:\s]+:)$lookahead//g;
+
     return $term;
 }
 
diff --git a/t/Koha/SearchEngine/Elasticsearch/QueryBuilder.t b/t/Koha/SearchEngine/Elasticsearch/QueryBuilder.t
index 1c7f73e3f5..4a901a4e84 100644
--- a/t/Koha/SearchEngine/Elasticsearch/QueryBuilder.t
+++ b/t/Koha/SearchEngine/Elasticsearch/QueryBuilder.t
@@ -17,7 +17,7 @@
 
 use Modern::Perl;
 
-use Test::More tests => 2;
+use Test::More tests => 3;
 
 use Koha::SearchEngine::Elasticsearch::QueryBuilder;
 
@@ -83,4 +83,41 @@ subtest '_split_query() tests' => sub {
     is_deeply(\@res, \@exp, 'quoted search terms surrounded by spaces correctly');
 };
 
-1;
\ No newline at end of file
+subtest '_clean_search_term() tests' => sub {
+    plan tests => 10;
+
+    my $qb;
+    ok(
+        $qb = Koha::SearchEngine::Elasticsearch::QueryBuilder->new({ 'index' => $Koha::SearchEngine::Elasticsearch::BIBLIOS_INDEX }),
+        'Creating a new QueryBuilder object'
+    );
+
+    my $res = $qb->_clean_search_term('an=123');
+    is($res, 'an:123', 'equals sign replaced with colon');
+
+    $res = $qb->_clean_search_term('"balanced quotes"');
+    is($res, '"balanced quotes"', 'balanced quotes returned correctly');
+
+    $res = $qb->_clean_search_term('unbalanced quotes"');
+    is($res, 'unbalanced quotes ', 'unbalanced quotes removed');
+
+    $res = $qb->_clean_search_term('"unbalanced "quotes"');
+    is($res, ' unbalanced  quotes ', 'unbalanced quotes removed');
+
+    $res = $qb->_clean_search_term('test : query');
+    is($res, 'test query', 'dangling colon removed');
+
+    $res = $qb->_clean_search_term('test :: query');
+    is($res, 'test query', 'dangling double colon removed');
+
+    $res = $qb->_clean_search_term('test "another : query"');
+    is($res, 'test "another : query"', 'quoted dangling colon not removed');
+
+    $res = $qb->_clean_search_term('test {another part}');
+    is($res, 'test "another part"', 'curly brackets replaced correctly');
+
+    $res = $qb->_clean_search_term('test {another part');
+    is($res, 'test  another part', 'unbalanced curly brackets replaced correctly');
+};
+
+1;
-- 
2.39.5