From 368fedd5c177795397ef49abdc404a7adb43a0da Mon Sep 17 00:00:00 2001
From: Petro Vashchuk <stalkernoid@gmail.com>
Date: Fri, 18 Jun 2021 10:43:14 +0300
Subject: [PATCH] Bug 28316: screen unquoted semicolons and all followup colons

Currently searches like: "book:", ":book" and "host-item:test:n"
cause internal server errors.

This patch adds additional regexes that remove the colons at the start
and end of the query, and another regex that screens all follow-up
colons that go after the first colon to avoid errors when searching for
"host-item:test:n".

To reproduce:
1) using ES, search for the book with title that contains
semicolon at the start or at the end of the line, separated with spaces,
this should cause internal server error.
2) try doing the same with something like "host-item:test:n", it should
result in error as well.
3) apply the patch.
4) repeat steps 1-2, ensure that it works now.

Signed-off-by: Victor Grousset/tuxayo <victor@tuxayo.net>
Signed-off-by: Alex Buckley <alexbuckley@catalyst.net.nz>
Signed-off-by: Martin Renvoize <martin.renvoize@ptfs-europe.com>
Signed-off-by: Martin Renvoize <martin.renvoize@ptfs-europe.com>

Signed-off-by: Jonathan Druart <jonathan.druart@bugs.koha-community.org>
Signed-off-by: Kyle M Hall <kyle@bywatersolutions.com>
(cherry picked from commit 5b4b14e493fef9f8f84060b6b5d83fbdcccfc65e)
Signed-off-by: Victor Grousset/tuxayo <victor@tuxayo.net>
---
 .../SearchEngine/Elasticsearch/QueryBuilder.pm | 18 ++++++++++++------
 1 file changed, 12 insertions(+), 6 deletions(-)

diff --git a/Koha/SearchEngine/Elasticsearch/QueryBuilder.pm b/Koha/SearchEngine/Elasticsearch/QueryBuilder.pm
index a894782c18..f12639edc4 100644
--- a/Koha/SearchEngine/Elasticsearch/QueryBuilder.pm
+++ b/Koha/SearchEngine/Elasticsearch/QueryBuilder.pm
@@ -938,14 +938,20 @@ sub _clean_search_term {
     if ($count % 2 == 1) {
         $term = $unquoted;
     }
-
-    # Remove unquoted colons that have whitespace on either side of them
-    $term =~ s/(:+)(\s+)$lookahead/$2/g;
-    $term =~ s/(\s+)(:+)$lookahead/$1/g;
-    $term =~ s/^://;
-
     $term = $self->_query_regex_escape_process($term);
 
+    # remove leading and trailing colons mixed with optional slashes and spaces
+    $term =~ s/^([\s\\]*:\s*)+//;
+    $term =~ s/([\s\\]*:\s*)+$//;
+    # remove unquoted colons that have whitespace on either side of them
+    $term =~ s/([\s\\]*:\s*)+(\s+)$lookahead/$2/g;
+    $term =~ s/(\s+)([\s\\]*:\s*)+$lookahead/$1/g;
+    # replace with spaces all repeated colons no matter how they surrounded with spaces and slashes
+    $term =~ s/([\s\\]*:\s*){2,}$lookahead/ /g;
+    # screen all followups for colons after first colon,
+    # and correctly ignore unevenly backslashed:
+    $term =~ s/((?<!\\)(?:[\\]{2})*:[^:\s]+(?<!\\)(?:[\\]{2})*)(?=:)/$1\\/g;
+
     return $term;
 }
 
-- 
2.39.5