- Patch #768040 by jhodgdon, janusman, codycraven: truncate_utf8() only works for latin languages and drupal_substr() had a bug.

2 files changed, 121 insertions, 65 deletions

diff --git a/modules/search/search.module b/modules/search/search.module
index 4eeb670e2..c7dee7e4e 100644
--- a/modules/search/search.module
+++ b/modules/search/search.module
@@ -7,68 +7,6 @@
  */
 
 /**
- * Matches Unicode character classes to exclude from the search index.
- *
- * @see http://unicode.org/glossary
- *
- * Characters with the following General_category (gc) property values are
- * excluded from the search index. Also, they are used as word boundaries.
- * While this does not fully conform to the  Word Boundaries algorithm
- * described in http://unicode.org/reports/tr29, as PCRE does not contain the
- * Word_Break property table, this simpler algorithm has to do.
- * - Cc, Cf, Cn, Co, Cs: Other.
- * - Pc, Pd, Pe, Pf, Pi, Po, Ps: Punctuation.
- * - Sc, Sk, Sm, So: Symbols.
- * - Zl, Zp, Zs: Separators.
- *
- * Consequently, the index only contains characters with the following
- * General_category (gc) property values:
- * - Ll, Lm, Lo, Lt, Lu: Letters.
- * - Mc, Me, Mn: Combining Marks.
- * - Nd, Nl, No: Numbers.
- *
- * Note that the PCRE property matcher is not used because we wanted to be
- * compatible with Unicode 5.2.0 regardless of the PCRE version used (and any
- * bugs in PCRE property tables).
- */
-define('PREG_CLASS_SEARCH_EXCLUDE',
-  '\x{0}-\x{2F}\x{3A}-\x{40}\x{5B}-\x{60}\x{7B}-\x{A9}\x{AB}-\x{B1}\x{B4}' .
-  '\x{B6}-\x{B8}\x{BB}\x{BF}\x{D7}\x{F7}\x{2C2}-\x{2C5}\x{2D2}-\x{2DF}' .
-  '\x{2E5}-\x{2EB}\x{2ED}\x{2EF}-\x{2FF}\x{375}\x{37E}-\x{385}\x{387}\x{3F6}' .
-  '\x{482}\x{55A}-\x{55F}\x{589}-\x{58A}\x{5BE}\x{5C0}\x{5C3}\x{5C6}' .
-  '\x{5F3}-\x{60F}\x{61B}-\x{61F}\x{66A}-\x{66D}\x{6D4}\x{6DD}\x{6E9}' .
-  '\x{6FD}-\x{6FE}\x{700}-\x{70F}\x{7F6}-\x{7F9}\x{830}-\x{83E}' .
-  '\x{964}-\x{965}\x{970}\x{9F2}-\x{9F3}\x{9FA}-\x{9FB}\x{AF1}\x{B70}' .
-  '\x{BF3}-\x{BFA}\x{C7F}\x{CF1}-\x{CF2}\x{D79}\x{DF4}\x{E3F}\x{E4F}' .
-  '\x{E5A}-\x{E5B}\x{F01}-\x{F17}\x{F1A}-\x{F1F}\x{F34}\x{F36}\x{F38}' .
-  '\x{F3A}-\x{F3D}\x{F85}\x{FBE}-\x{FC5}\x{FC7}-\x{FD8}\x{104A}-\x{104F}' .
-  '\x{109E}-\x{109F}\x{10FB}\x{1360}-\x{1368}\x{1390}-\x{1399}\x{1400}' .
-  '\x{166D}-\x{166E}\x{1680}\x{169B}-\x{169C}\x{16EB}-\x{16ED}' .
-  '\x{1735}-\x{1736}\x{17B4}-\x{17B5}\x{17D4}-\x{17D6}\x{17D8}-\x{17DB}' .
-  '\x{1800}-\x{180A}\x{180E}\x{1940}-\x{1945}\x{19DE}-\x{19FF}' .
-  '\x{1A1E}-\x{1A1F}\x{1AA0}-\x{1AA6}\x{1AA8}-\x{1AAD}\x{1B5A}-\x{1B6A}' .
-  '\x{1B74}-\x{1B7C}\x{1C3B}-\x{1C3F}\x{1C7E}-\x{1C7F}\x{1CD3}\x{1FBD}' .
-  '\x{1FBF}-\x{1FC1}\x{1FCD}-\x{1FCF}\x{1FDD}-\x{1FDF}\x{1FED}-\x{1FEF}' .
-  '\x{1FFD}-\x{206F}\x{207A}-\x{207E}\x{208A}-\x{208E}\x{20A0}-\x{20B8}' .
-  '\x{2100}-\x{2101}\x{2103}-\x{2106}\x{2108}-\x{2109}\x{2114}' .
-  '\x{2116}-\x{2118}\x{211E}-\x{2123}\x{2125}\x{2127}\x{2129}\x{212E}' .
-  '\x{213A}-\x{213B}\x{2140}-\x{2144}\x{214A}-\x{214D}\x{214F}' .
-  '\x{2190}-\x{244A}\x{249C}-\x{24E9}\x{2500}-\x{2775}\x{2794}-\x{2B59}' .
-  '\x{2CE5}-\x{2CEA}\x{2CF9}-\x{2CFC}\x{2CFE}-\x{2CFF}\x{2E00}-\x{2E2E}' .
-  '\x{2E30}-\x{3004}\x{3008}-\x{3020}\x{3030}\x{3036}-\x{3037}' .
-  '\x{303D}-\x{303F}\x{309B}-\x{309C}\x{30A0}\x{30FB}\x{3190}-\x{3191}' .
-  '\x{3196}-\x{319F}\x{31C0}-\x{31E3}\x{3200}-\x{321E}\x{322A}-\x{3250}' .
-  '\x{3260}-\x{327F}\x{328A}-\x{32B0}\x{32C0}-\x{33FF}\x{4DC0}-\x{4DFF}' .
-  '\x{A490}-\x{A4C6}\x{A4FE}-\x{A4FF}\x{A60D}-\x{A60F}\x{A673}\x{A67E}' .
-  '\x{A6F2}-\x{A716}\x{A720}-\x{A721}\x{A789}-\x{A78A}\x{A828}-\x{A82B}' .
-  '\x{A836}-\x{A839}\x{A874}-\x{A877}\x{A8CE}-\x{A8CF}\x{A8F8}-\x{A8FA}' .
-  '\x{A92E}-\x{A92F}\x{A95F}\x{A9C1}-\x{A9CD}\x{A9DE}-\x{A9DF}' .
-  '\x{AA5C}-\x{AA5F}\x{AA77}-\x{AA79}\x{AADE}-\x{AADF}\x{ABEB}' .
-  '\x{D800}-\x{F8FF}\x{FB29}\x{FD3E}-\x{FD3F}\x{FDFC}-\x{FDFD}' .
-  '\x{FE10}-\x{FE19}\x{FE30}-\x{FE6B}\x{FEFF}-\x{FF0F}\x{FF1A}-\x{FF20}' .
-  '\x{FF3B}-\x{FF40}\x{FF5B}-\x{FF65}\x{FFE0}-\x{FFFD}');
-
-/**
  * Matches all 'N' Unicode character classes (numbers)
  */
 define('PREG_CLASS_NUMBERS',
@@ -454,7 +392,7 @@ function search_simplify($text) {
 
   // With the exception of the rules above, we consider all punctuation,
   // marks, spacers, etc, to be a word boundary.
-  $text = preg_replace('/[' . PREG_CLASS_SEARCH_EXCLUDE . ']+/u', ' ', $text);
+  $text = preg_replace('/[' . PREG_CLASS_UNICODE_WORD_BOUNDARY . ']+/u', ' ', $text);
 
   return $text;
 }
@@ -1075,7 +1013,7 @@ function search_data($keys = NULL, $type = 'node') {
  */
 function search_excerpt($keys, $text) {
   // We highlight around non-indexable or CJK characters.
-  $boundary = '(?:(?<=[' . PREG_CLASS_SEARCH_EXCLUDE . PREG_CLASS_CJK . '])|(?=[' . PREG_CLASS_SEARCH_EXCLUDE . PREG_CLASS_CJK . ']))';
+  $boundary = '(?:(?<=[' . PREG_CLASS_UNICODE_WORD_BOUNDARY . PREG_CLASS_CJK . '])|(?=[' . PREG_CLASS_UNICODE_WORD_BOUNDARY . PREG_CLASS_CJK . ']))';
 
   // Extract positive keywords and phrases
   preg_match_all('/ ("([^"]+)"|(?!OR)([^" ]+))/', ' ' . $keys, $matches);
diff --git a/modules/simpletest/tests/unicode.test b/modules/simpletest/tests/unicode.test
index 07551ee69..cdae50955 100644
--- a/modules/simpletest/tests/unicode.test
+++ b/modules/simpletest/tests/unicode.test
@@ -48,6 +48,7 @@ class UnicodeUnitTest extends DrupalWebTestCase {
     $this->helperTestUcFirst();
     $this->helperTestStrLen();
     $this->helperTestSubStr();
+    $this->helperTestTruncate();
   }
 
   /**
@@ -67,6 +68,7 @@ class UnicodeUnitTest extends DrupalWebTestCase {
     $this->helperTestUcFirst();
     $this->helperTestStrLen();
     $this->helperTestSubStr();
+    $this->helperTestTruncate();
   }
 
   function helperTestStrToLower() {
@@ -127,10 +129,18 @@ class UnicodeUnitTest extends DrupalWebTestCase {
   function helperTestSubStr() {
     $testcase = array(
       //     012345678901234567890123
+      array('frànçAIS is über-åwesome', 0, 0,
+            ''),
       array('frànçAIS is über-åwesome', 0, 1,
             'f'),
       array('frànçAIS is über-åwesome', 0, 8,
             'frànçAIS'),
+      array('frànçAIS is über-åwesome', 0, 23,
+            'frànçAIS is über-åwesom'),
+      array('frànçAIS is über-åwesome', 0, 24,
+            'frànçAIS is über-åwesome'),
+      array('frànçAIS is über-åwesome', 0, 25,
+            'frànçAIS is über-åwesome'),
       array('frànçAIS is über-åwesome', 0, 100,
             'frànçAIS is über-åwesome'),
       array('frànçAIS is über-åwesome', 4, 4,
@@ -141,16 +151,38 @@ class UnicodeUnitTest extends DrupalWebTestCase {
             ''),
       array('frànçAIS is über-åwesome', -4, 2,
                                 'so'),
+      array('frànçAIS is über-åwesome', -4, 3,
+                                'som'),
+      array('frànçAIS is über-åwesome', -4, 4,
+                                'some'),
+      array('frànçAIS is über-åwesome', -4, 5,
+                                'some'),
       array('frànçAIS is über-åwesome', -7, 10,
                              'åwesome'),
       array('frànçAIS is über-åwesome', 5, -10,
                  'AIS is üb'),
+      array('frànçAIS is über-åwesome', 0, -10,
+            'frànçAIS is üb'),
+      array('frànçAIS is über-åwesome', 0, -1,
+        'frànçAIS is über-åwesom'),
+      array('frànçAIS is über-åwesome', -7, -2,
+                             'åweso'),
+      array('frànçAIS is über-åwesome', -7, -6,
+                             'å'),
+      array('frànçAIS is über-åwesome', -7, -7,
+                             ''),
+      array('frànçAIS is über-åwesome', -7, -8,
+                             ''),
+      array('...', 0, 2, '..'),
+      array('以呂波耳・ほへとち。リヌルヲ。', 1, 3,
+              '呂波耳'),
 
     );
 
     foreach ($testcase as $test) {
       list($input, $start, $length, $output) = $test;
-      $this->assertEqual(drupal_substr($input, $start, $length), $output, t('%input substring-ed at offset %offset for %length characters is %output', array('%input' => $input, '%offset' => $start, '%length' => $length, '%output' => $output)));
+      $result = drupal_substr($input, $start, $length);
+      $this->assertEqual($result, $output, t('%input substring at offset %offset for %length characters is %output (got %result)', array('%input' => $input, '%offset' => $start, '%length' => $length, '%output' => $output, '%result' => $result)));
     }
   }
 
@@ -215,4 +247,90 @@ class UnicodeUnitTest extends DrupalWebTestCase {
       $this->assertIdentical(decode_entities($input, $exclude), $output, t('Make sure the decoded entity of %input, excluding %excludes, is %output', array('%input' => $input, '%excludes' => implode(',', $exclude), '%output' => $output)));
     }
   }
+
+  /**
+   * Tests truncate_utf8().
+   */
+  function helperTestTruncate() {
+    // Each case is an array with input string, length to truncate to, and
+    // expected return value.
+
+    // Test non-wordsafe, non-ellipsis cases.
+    $non_wordsafe_non_ellipsis_cases = array(
+      array('frànçAIS is über-åwesome', 24, 'frànçAIS is über-åwesome'),
+      array('frànçAIS is über-åwesome', 23, 'frànçAIS is über-åwesom'),
+      array('frànçAIS is über-åwesome', 17, 'frànçAIS is über-'),
+      array('以呂波耳・ほへとち。リヌルヲ。', 6, '以呂波耳・ほ'),
+    );
+    $this->runTruncateTests($non_wordsafe_non_ellipsis_cases, FALSE, FALSE);
+
+    // Test non-wordsafe, ellipsis cases.
+    $non_wordsafe_ellipsis_cases = array(
+      array('frànçAIS is über-åwesome', 24, 'frànçAIS is über-åwesome'),
+      array('frànçAIS is über-åwesome', 23, 'frànçAIS is über-åwe...'),
+      array('frànçAIS is über-åwesome', 17, 'frànçAIS is üb...'),
+    );
+    $this->runTruncateTests($non_wordsafe_ellipsis_cases, FALSE, TRUE);
+
+    // Test wordsafe, ellipsis cases.
+    $wordsafe_ellipsis_cases = array(
+      array('123', 1, '.'),
+      array('123', 2, '..'),
+      array('123', 3, '123'),
+      array('1234', 3, '...'),
+      array('1234567890', 10, '1234567890'),
+      array('12345678901', 10, '1234567...'),
+      array('12345678901', 11, '12345678901'),
+      array('123456789012', 11, '12345678...'),
+      array('12345 7890', 10, '12345 7890'),
+      array('12345 7890', 9, '12345...'),
+      array('123 567 90', 10, '123 567 90'),
+      array('123 567 901', 10, '123 567...'),
+      array('Stop. Hammertime.', 17, 'Stop. Hammertime.'),
+      array('Stop. Hammertime.', 16, 'Stop....'),
+      array('frànçAIS is über-åwesome', 24, 'frànçAIS is über-åwesome'),
+      array('frànçAIS is über-åwesome', 23, 'frànçAIS is über...'),
+      array('frànçAIS is über-åwesome', 17, 'frànçAIS is...'),
+      array('¿Dónde está el niño?', 20, '¿Dónde está el niño?'),
+      array('¿Dónde está el niño?', 19, '¿Dónde está el...'),
+      array('¿Dónde está el niño?', 15, '¿Dónde está...'),
+      array('¿Dónde está el niño?', 10, '¿Dónde...'),
+      array('Help! Help! Help!', 17, 'Help! Help! Help!'),
+      array('Help! Help! Help!', 16, 'Help! Help!...'),
+      array('Help! Help! Help!', 15, 'Help! Help!...'),
+      array('Help! Help! Help!', 14, 'Help! Help!...'),
+      array('Help! Help! Help!', 13, 'Help! Help...'),
+      array('Help! Help! Help!', 12, 'Help!...'),
+      array('Help! Help! Help!', 11, 'Help!...'),
+      array('Help! Help! Help!', 10, 'Help!...'),
+      array('Help! Help! Help!', 9, 'Help!...'),
+      array('Help! Help! Help!', 8, 'Help!...'),
+      array('Help! Help! Help!', 7, 'Help...'),
+      array('Help! Help! Help!', 6, 'Hel...'),
+      array('Help! Help! Help!', 5, 'He...'),
+    );
+    $this->runTruncateTests($wordsafe_ellipsis_cases, TRUE, TRUE);
+  }
+
+  /**
+   * Runs test cases for helperTestTruncate().
+   *
+   * Runs each test case through truncate_utf8() and compares the output
+   * to the expected output.
+   *
+   * @param $cases
+   *   Cases array. Each case is an array with the input string, length to
+   *   truncate to, and expected output.
+   * @param $wordsafe
+   *   TRUE to use word-safe truncation, FALSE to not use word-safe truncation.
+   * @param $ellipsis
+   *   TRUE to append ... if the input is truncated, FALSE to not append ....
+   */
+  function runTruncateTests($cases, $wordsafe, $ellipsis) {
+    foreach ($cases as $case) {
+      list($input, $max_length, $expected) = $case;
+      $output = truncate_utf8($input, $max_length, $wordsafe, $ellipsis);
+      $this->assertEqual($output, $expected, t('%input truncate to %length characters with %wordsafe, %ellipsis is %expected (got %output)', array('%input' => $input, '%length' => $max_length, '%output' => $output, '%expected' => $expected, '%wordsafe' => ($wordsafe ? 'word-safe' : 'not word-safe'), '%ellipsis' => ($ellipsis ? 'ellipsis' : 'not ellipsis'))));
+    }
+  }
 }