From 506fc9d74cdb67af2eaea27662420ec07e32b2f3 Mon Sep 17 00:00:00 2001
From: Marius Balteanu <marius.balteanu@zitec.com>
Date: Tue, 5 Oct 2021 19:54:31 +0000
Subject: Tokenize search parameter in order to allow multiple search terms in:
 * the "contains" operator of text filters * in issue autocomplete
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Patch by Jens Krämer.

git-svn-id: http://svn.redmine.org/redmine/trunk@21238 e93f8b46-1217-0410-a6f0-8f06a7374b81
---
 lib/redmine/search.rb | 26 +++++++++++++++++---------
 1 file changed, 17 insertions(+), 9 deletions(-)

(limited to 'lib/redmine')

diff --git a/lib/redmine/search.rb b/lib/redmine/search.rb
index 3aeedbcd2..7eae79b5e 100644
--- a/lib/redmine/search.rb
+++ b/lib/redmine/search.rb
@@ -57,15 +57,7 @@ module Redmine
         @projects = projects
         @cache = options.delete(:cache)
         @options = options
-
-        # extract tokens from the question
-        # eg. hello "bye bye" => ["hello", "bye bye"]
-        @tokens = @question.scan(%r{((\s|^)"[^"]+"(\s|$)|\S+)}).collect {|m| m.first.gsub(%r{(^\s*"\s*|\s*"\s*$)}, '')}
-        # tokens must be at least 2 characters long
-        # but for Chinese characters (Chinese HANZI/Japanese KANJI), tokens can be one character
-        @tokens = @tokens.uniq.select {|w| w.length > 1 || w =~ /\p{Han}/}
-        # no more than 5 tokens to search for
-        @tokens.slice! 5..-1
+        @tokens = Tokenizer.new(@question).tokens
       end
 
       # Returns the total result count
@@ -135,6 +127,22 @@ module Redmine
       end
     end
 
+    class Tokenizer
+      def initialize(question)
+        @question = question.to_s
+      end
+
+      def tokens
+        # extract tokens from the question
+        # eg. hello "bye bye" => ["hello", "bye bye"]
+        tokens = @question.scan(%r{((\s|^)"[^"]+"(\s|$)|\S+)}).collect {|m| m.first.gsub(%r{(^\s*"\s*|\s*"\s*$)}, '')}
+        # tokens must be at least 2 characters long
+        # but for Chinese characters (Chinese HANZI/Japanese KANJI), tokens can be one character
+        # no more than 5 tokens to search for
+        tokens.uniq.select{|w| w.length > 1 || w =~ /\p{Han}/}.first 5
+      end
+    end
+
     module Controller
       def self.included(base)
         base.extend(ClassMethods)
-- 
cgit v1.2.3