- Patch #493770 by Garrett Albright, tobiasb: search incorrectly splits some katakana words.

2 files changed, 37 insertions, 5 deletions

diff --git a/modules/search/search.module b/modules/search/search.module
index 632073d24..e83c78549 100644
--- a/modules/search/search.module
+++ b/modules/search/search.module
@@ -42,11 +42,11 @@ define('PREG_CLASS_SEARCH_EXCLUDE',
 '\x{2108}\x{2109}\x{2114}\x{2116}-\x{2118}\x{211e}-\x{2123}\x{2125}\x{2127}' .
 '\x{2129}\x{212e}\x{2132}\x{213a}\x{213b}\x{2140}-\x{2144}\x{214a}-\x{2b13}' .
 '\x{2ce5}-\x{2cff}\x{2d6f}\x{2e00}-\x{3005}\x{3007}-\x{303b}\x{303d}-\x{303f}' .
-'\x{3099}-\x{309e}\x{30a0}\x{30fb}-\x{30fe}\x{3190}-\x{319f}\x{31c0}-\x{31cf}' .
-'\x{3200}-\x{33ff}\x{4dc0}-\x{4dff}\x{a015}\x{a490}-\x{a716}\x{a802}\x{a806}' .
-'\x{a80b}\x{a823}-\x{a82b}\x{d800}-\x{f8ff}\x{fb1e}\x{fb29}\x{fd3e}\x{fd3f}' .
-'\x{fdfc}-\x{fe6b}\x{feff}-\x{ff0f}\x{ff1a}-\x{ff20}\x{ff3b}-\x{ff40}\x{ff5b}-' .
-'\x{ff65}\x{ff70}\x{ff9e}\x{ff9f}\x{ffe0}-\x{fffd}');
+'\x{3099}-\x{309e}\x{30a0}\x{30fb}\x{30fd}\x{30fe}\x{3190}-\x{319f}\x{31c0}-' .
+'\x{31cf}\x{3200}-\x{33ff}\x{4dc0}-\x{4dff}\x{a015}\x{a490}-\x{a716}\x{a802}' .
+'\x{a806}\x{a80b}\x{a823}-\x{a82b}\x{d800}-\x{f8ff}\x{fb1e}\x{fb29}\x{fd3e}' .
+'\x{fd3f}\x{fdfc}-\x{fe6b}\x{feff}-\x{ff0f}\x{ff1a}-\x{ff20}\x{ff3b}-\x{ff40}' .
+'\x{ff5b}-\x{ff65}\x{ff70}\x{ff9e}\x{ff9f}\x{ffe0}-\x{fffd}');
 
 /**
  * Matches all 'N' Unicode character classes (numbers)
diff --git a/modules/search/search.test b/modules/search/search.test
index 035b7645d..11137c441 100644
--- a/modules/search/search.test
+++ b/modules/search/search.test
@@ -5,6 +5,7 @@
 // Here we test with _test_ and _test2_ as the type.
 define('SEARCH_TYPE', '_test_');
 define('SEARCH_TYPE_2', '_test2_');
+define('SEARCH_TYPE_JPN', '_test3_');
 
 class SearchMatchTestCase extends DrupalWebTestCase {
   public static function getInfo() {
@@ -42,6 +43,14 @@ class SearchMatchTestCase extends DrupalWebTestCase {
     for ($i = 1; $i <= 5; ++$i) {
       search_index($i + 7, SEARCH_TYPE_2, $this->getText2($i));
     }
+    // No getText builder function for Japanese text; just a simple array.
+    foreach (array(
+      13 => '以呂波耳・ほへとち。リヌルヲ。',
+      14 => 'ドルーパルが大好きよ！',
+      15 => 'コーヒーとケーキ',
+    ) as $i => $jpn) {
+      search_index($i, SEARCH_TYPE_JPN, $jpn);
+    }
     search_update_totals();
   }
 
@@ -162,6 +171,29 @@ class SearchMatchTestCase extends DrupalWebTestCase {
       $this->_testQueryMatching($query, $set, $results);
       $this->_testQueryScores($query, $set, $results);
     }
+    
+    // These queries are run against the third index type, SEARCH_TYPE_JPN.
+    $queries = array(
+      // Simple AND queries.
+      '呂波耳' => array(13),
+      '以呂波耳' => array(13),
+      'ほへと　ヌルヲ' => array(13),
+      'とちリ' => array(),
+      'ドルーパル' => array(14),
+      'パルが大' => array(14),
+      'コーヒー' => array(15),
+      'ヒーキ' => array(),
+    );
+    foreach ($queries as $query => $results) {
+      $result = db_select('search_index', 'i')
+        ->extend('SearchQuery')
+        ->searchExpression($query, SEARCH_TYPE_JPN)
+        ->execute();
+
+      $set = $result ? $result->fetchAll() : array();
+      $this->_testQueryMatching($query, $set, $results);
+      $this->_testQueryScores($query, $set, $results);
+    }      
   }
 
   /**