mb_str_replace () ... ist langsam. Alternativen?

Question

Ich möchte sicher, dass einige String-Ersatz machen, das ich renne sind Multi-Byte-sicher. Ich habe ein paar mb_str_replace Funktionen rund um das Netz gefunden, aber sie sind langsam. Ich spreche 20% zu erhöhen, nachdem vielleicht 500-900 Bytes durchquert.

Alle Empfehlungen? Ich denke über die Verwendung von preg_replace wie es nativer ist und kompiliert in so dass es schneller sein könnte. Irgendwelche Gedanken würden geschätzt.

Answer 1

Wie gesagt

Answer 2

Als Codierung ist eine echte Herausforderung, wenn es Eingaben von überall (UTF-8 oder andere), ziehe ich nur multibyte sichere Funktionen. Für str_replace, ich bin mit dieser einen die schnell genug ist.

if (!function_exists('mb_str_replace'))
{
   function mb_str_replace($search, $replace, $subject, &$count = 0)
   {
      if (!is_array($subject))
      {
         $searches = is_array($search) ? array_values($search) : array($search);
         $replacements = is_array($replace) ? array_values($replace) : array($replace);
         $replacements = array_pad($replacements, count($searches), '');
         foreach ($searches as $key => $search)
         {
            $parts = mb_split(preg_quote($search), $subject);
            $count += count($parts) - 1;
            $subject = implode($replacements[$key], $parts);
         }
      }
      else
      {
         foreach ($subject as $key => $value)
         {
            $subject[$key] = mb_str_replace($search, $replace, $value, $count);
         }
      }
      return $subject;
   }
}

Hier ist meine Implementierung basiert weg Alain Antwort :

/**
 * Replace all occurrences of the search string with the replacement string. Multibyte safe.
 *
 * @param string|array $search The value being searched for, otherwise known as the needle. An array may be used to designate multiple needles.
 * @param string|array $replace The replacement value that replaces found search values. An array may be used to designate multiple replacements.
 * @param string|array $subject The string or array being searched and replaced on, otherwise known as the haystack.
 *                              If subject is an array, then the search and replace is performed with every entry of subject, and the return value is an array as well.
 * @param string $encoding The encoding parameter is the character encoding. If it is omitted, the internal character encoding value will be used.
 * @param int $count If passed, this will be set to the number of replacements performed.
 * @return array|string
 */
public static function mbReplace($search, $replace, $subject, $encoding = 'auto', &$count=0) {
    if(!is_array($subject)) {
        $searches = is_array($search) ? array_values($search) : [$search];
        $replacements = is_array($replace) ? array_values($replace) : [$replace];
        $replacements = array_pad($replacements, count($searches), '');
        foreach($searches as $key => $search) {
            $replace = $replacements[$key];
            $search_len = mb_strlen($search, $encoding);

            $sb = [];
            while(($offset = mb_strpos($subject, $search, 0, $encoding)) !== false) {
                $sb[] = mb_substr($subject, 0, $offset, $encoding);
                $subject = mb_substr($subject, $offset + $search_len, null, $encoding);
                ++$count;
            }
            $sb[] = $subject;
            $subject = implode($replace, $sb);
        }
    } else {
        foreach($subject as $key => $value) {
            $subject[$key] = self::mbReplace($search, $replace, $value, $encoding, $count);
        }
    }
    return $subject;
}

Seine keine Zeichencodierung akzeptieren, obwohl ich nehme an, Sie es über mb_regex_encoding .

Meine Einheit Prüfungen bestehen:

function testMbReplace() {
    $this->assertSame('bbb',Str::mbReplace('a','b','aaa','auto',$count1));
    $this->assertSame(3,$count1);
    $this->assertSame('ccc',Str::mbReplace(['a','b'],['b','c'],'aaa','auto',$count2));
    $this->assertSame(6,$count2);
    $this->assertSame("\xbf\x5c\x27",Str::mbReplace("\x27","\x5c\x27","\xbf\x27",'iso-8859-1'));
    $this->assertSame("\xbf\x27",Str::mbReplace("\x27","\x5c\x27","\xbf\x27",'gbk'));
}

Am besten bewerteten Hinweis auf http://php.net/manual/en /ref.mbstring.php#109937 sagt str_replace Werke für Multibyte-Strings.

Answer 3

Als Codierung ist eine echte Herausforderung, wenn es Eingaben von überall (UTF-8 oder andere), ziehe ich nur multibyte sichere Funktionen. Für str_replace, ich bin mit dieser einen die schnell genug ist.

if (!function_exists('mb_str_replace'))
{
   function mb_str_replace($search, $replace, $subject, &$count = 0)
   {
      if (!is_array($subject))
      {
         $searches = is_array($search) ? array_values($search) : array($search);
         $replacements = is_array($replace) ? array_values($replace) : array($replace);
         $replacements = array_pad($replacements, count($searches), '');
         foreach ($searches as $key => $search)
         {
            $parts = mb_split(preg_quote($search), $subject);
            $count += count($parts) - 1;
            $subject = implode($replacements[$key], $parts);
         }
      }
      else
      {
         foreach ($subject as $key => $value)
         {
            $subject[$key] = mb_str_replace($search, $replace, $value, $count);
         }
      }
      return $subject;
   }
}

Answer 4

Hier ist meine Implementierung basiert weg Alain Antwort :

/**
 * Replace all occurrences of the search string with the replacement string. Multibyte safe.
 *
 * @param string|array $search The value being searched for, otherwise known as the needle. An array may be used to designate multiple needles.
 * @param string|array $replace The replacement value that replaces found search values. An array may be used to designate multiple replacements.
 * @param string|array $subject The string or array being searched and replaced on, otherwise known as the haystack.
 *                              If subject is an array, then the search and replace is performed with every entry of subject, and the return value is an array as well.
 * @param string $encoding The encoding parameter is the character encoding. If it is omitted, the internal character encoding value will be used.
 * @param int $count If passed, this will be set to the number of replacements performed.
 * @return array|string
 */
public static function mbReplace($search, $replace, $subject, $encoding = 'auto', &$count=0) {
    if(!is_array($subject)) {
        $searches = is_array($search) ? array_values($search) : [$search];
        $replacements = is_array($replace) ? array_values($replace) : [$replace];
        $replacements = array_pad($replacements, count($searches), '');
        foreach($searches as $key => $search) {
            $replace = $replacements[$key];
            $search_len = mb_strlen($search, $encoding);

            $sb = [];
            while(($offset = mb_strpos($subject, $search, 0, $encoding)) !== false) {
                $sb[] = mb_substr($subject, 0, $offset, $encoding);
                $subject = mb_substr($subject, $offset + $search_len, null, $encoding);
                ++$count;
            }
            $sb[] = $subject;
            $subject = implode($replace, $sb);
        }
    } else {
        foreach($subject as $key => $value) {
            $subject[$key] = self::mbReplace($search, $replace, $value, $encoding, $count);
        }
    }
    return $subject;
}

Seine keine Zeichencodierung akzeptieren, obwohl ich nehme an, Sie es über mb_regex_encoding .

Meine Einheit Prüfungen bestehen:

function testMbReplace() {
    $this->assertSame('bbb',Str::mbReplace('a','b','aaa','auto',$count1));
    $this->assertSame(3,$count1);
    $this->assertSame('ccc',Str::mbReplace(['a','b'],['b','c'],'aaa','auto',$count2));
    $this->assertSame(6,$count2);
    $this->assertSame("\xbf\x5c\x27",Str::mbReplace("\x27","\x5c\x27","\xbf\x27",'iso-8859-1'));
    $this->assertSame("\xbf\x27",Str::mbReplace("\x27","\x5c\x27","\xbf\x27",'gbk'));
}

Answer 5

Am besten bewerteten Hinweis auf http://php.net/manual/en /ref.mbstring.php#109937 sagt str_replace Werke für Multibyte-Strings.