Merge branch 'AnrDaemon-fix-issue-549-v3' into support/3.1

CHANGELOG.md

@@ -6,6 +6,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+### Fixed
+- Fixed problems with smarty_mb_str_replace [#549](https://github.com/smarty-php/smarty/issues/549)
+
 ## [3.1.45] - 2022-05-17
 
 ### Security

libs/plugins/shared.mb_str_replace.php

@@ -44,9 +44,43 @@ function smarty_mb_str_replace($search, $replace, $subject, &$count = 0)
                 }
             }
         } else {
+            $mb_reg_charset = mb_regex_encoding();
+            // Check if mbstring regex is using UTF-8
+            $reg_is_unicode = !strcasecmp($mb_reg_charset, "UTF-8");
+            if(!$reg_is_unicode) {
+                // ...and set to UTF-8 if not
+                mb_regex_encoding("UTF-8");
+            }
+
+            // See if charset used by Smarty is matching one used by regex...
+            $current_charset = mb_regex_encoding();
+            $convert_result = (bool)strcasecmp(Smarty::$_CHARSET, $current_charset);
+            if($convert_result) {
+                // ...convert to it if not.
+                $subject = mb_convert_encoding($subject, $current_charset, Smarty::$_CHARSET);
+                $search = mb_convert_encoding($search, $current_charset, Smarty::$_CHARSET);
+                $replace = mb_convert_encoding($replace, $current_charset, Smarty::$_CHARSET);
+            }
+
             $parts = mb_split(preg_quote($search), $subject);
+            // If original regex encoding was not unicode...
+            if(!$reg_is_unicode) {
+                // ...restore original regex encoding to avoid breaking the system.
+                mb_regex_encoding($mb_reg_charset);
+            }
+            if($parts === false) {
+                // This exception is thrown if call to mb_split failed.
+                // Usually it happens, when $search or $replace are not valid for given mb_regex_encoding().
+                // There may be other cases for it to fail, please file an issue if you find a reproducible one.
+                throw new SmartyException("Source string is not a valid $current_charset sequence (probably)");
+            }
+
             $count = count($parts) - 1;
             $subject = implode($replace, $parts);
+            // Convert results back to charset used by Smarty, if needed.
+            if($convert_result) {
+                $subject = mb_convert_encoding($subject, Smarty::$_CHARSET, $current_charset);
+            }
         }
         return $subject;
     }

tests/UnitTests/TemplateSource/_Issues/549/MbSplitEncodingIssue549Test.php

@@ -0,0 +1,77 @@
+<?php
+/**
+ * Smarty PHPunit tests - issue #549 regression tests
+ *
+ * @package PHPunit
+ * @author  Andrey Repin <anrdaemon@yandex.ru>
+ */
+
+/**
+ * class for compiler tests
+ *
+ * @runTestsInSeparateProcess
+ * @preserveGlobalState    disabled
+ * @backupStaticAttributes enabled
+ *
+ * mb_split breaks if Smarty encoding is not the same as mbstring regex encoding.
+ */
+class MbSplitEncodingIssue549Test extends PHPUnit_Smarty
+{
+    /** @var string Saved Smarty charset */
+    private $charset;
+
+    /** @var array Source data for tests, hexed to protect from accidental reencoding */
+    private $data = array(
+        "subject" => '4772c3bc6e6577616c64', // "Grünewald"
+        "pattern" => '77616c64', // "wald"
+        "replacement" => '7374c3bc726d', // "stürm"
+        "result" => '4772c3bc6e657374c3bc726d', // "Grünestürm"
+    );
+
+    public function setUp()
+    {
+        if(!\Smarty::$_MBSTRING)
+        {
+            return $this->markTestSkipped("mbstring extension is not in use by Smarty");
+        }
+
+        $this->charset = \Smarty::$_CHARSET;
+        $this->setUpSmarty(dirname(__FILE__));
+    }
+
+    public function tearDown()
+    {
+        \Smarty::$_CHARSET = $this->charset ?: \Smarty::$_CHARSET;
+        $this->cleanDirs();
+    }
+
+    /** Provider for testReplaceModifier
+     */
+    public function encodingPairsProvider()
+    {
+        return array(
+            "with non-UNICODE src/non-UNICODE regex (PHP < 5.6 default)" => array("Windows-1252", "EUC-JP"),
+            "with UTF-8 src/non-UNICODE regex (PHP < 5.6 default)" => array("UTF-8", "EUC-JP"),
+            "with UTF-8 src/UTF-8 regex (PHP >= 5.6)" => array("UTF-8", "UTF-8"),
+            "with non-UNICODE src/UTF-8 regex" => array("Windows-1252", "UTF-8"),
+        );
+    }
+
+    /** Test behavior of `replace` modifier with different source and regex encodings
+     *
+     * @dataProvider encodingPairsProvider
+     */
+    public function testReplaceModifier($mb_int_encoding, $mb_regex_encoding)
+    {
+        $data = $this->data;
+        \array_walk($data, function(&$value, $key) use($mb_int_encoding) {
+            $value = \mb_convert_encoding(pack("H*", $value), $mb_int_encoding, "UTF-8");
+        });
+        \extract($data, \EXTR_SKIP);
+
+        \mb_regex_encoding($mb_regex_encoding);
+        \Smarty::$_CHARSET = $mb_int_encoding;
+        $this->assertEquals($result, $this->smarty->fetch("string:{\"$subject\"|replace:\"$pattern\":\"$replacement\"}"));
+    }
+
+}

tests/UnitTests/TemplateSource/_Issues/549/cache/.gitignore

@@ -0,0 +1,2 @@
+# Ignore anything in here, but keep this directory
+*

tests/UnitTests/TemplateSource/_Issues/549/templates_c/.gitignore

@@ -0,0 +1,2 @@
+# Ignore anything in here, but keep this directory
+*