voku / portable-utf8

src/voku/helper/UTF8.php

Doc Comments +4 added lines, -4 removed lines

@@ -2668,7 +2668,7 @@ 
   /**
    * Check if the input is binary... (is look like a hack).
    *
-   * @param mixed $input
+   * @param string $input
    *
    * @return bool
    */
@@ -5027,7 +5027,7 @@ 
    * @param string  $encoding  [optional] <p>Set the charset for e.g. "\mb_" function.</p>
    * @param boolean $cleanUtf8 [optional] <p>Clean non UTF-8 chars from the string.</p>
    *
-   * @return int|false <p>
+   * @return string <p>
    *                   The numeric position of the first occurrence of needle in the haystack string.<br />
    *                   If needle is not found it returns false.
    *                   </p>
@@ -5303,7 +5303,7 @@ 
    * @link http://php.net/manual/en/function.mb-strrpos.php
    *
    * @param string     $haystack  <p>The string being checked, for the last occurrence of needle</p>
-   * @param string|int $needle    <p>The string to find in haystack.<br />Or a code point as int.</p>
+   * @param string $needle    <p>The string to find in haystack.<br />Or a code point as int.</p>
    * @param int        $offset    [optional] <p>May be specified to begin searching an arbitrary number of characters
    *                              into the string. Negative values will stop searching at an arbitrary point prior to
    *                              the end of the string.
@@ -6388,7 +6388,7 @@ 
    * 2) when any of these: àáâãäåæçèéêëìíîï  are followed by TWO chars from group B,
    * 3) when any of these: ðñòó  are followed by THREE chars from group B.
    *
-   * @param string|string[] $str                    <p>Any string or array.</p>
+   * @param string $str                    <p>Any string or array.</p>
    * @param bool            $decodeHtmlEntityToUtf8 <p>Set to true, if you need to decode html-entities.</p>
    *
    * @return string|string[] <p>The UTF-8 encoded string.</p>

Spacing +68 added lines, -68 removed lines

@@ -839,7 +839,7 @@ 
   public static function add_bom_to_string($str)
   {
     if (self::string_has_bom($str) === false) {
-      $str = self::bom() . $str;
+      $str = self::bom().$str;
     }
 
     return $str;
@@ -939,7 +939,7 @@ 
 
     // use static cache, if there is no support for "IntlChar"
     static $cache = array();
-    $cacheKey = $code_point . $encoding;
+    $cacheKey = $code_point.$encoding;
     if (isset($cache[$cacheKey]) === true) {
       return $cache[$cacheKey];
     }
@@ -947,16 +947,16 @@ 
     if (0x80 > $code_point %= 0x200000) {
       $str = chr($code_point);
     } elseif (0x800 > $code_point) {
-      $str = chr(0xC0 | $code_point >> 6) .
+      $str = chr(0xC0 | $code_point >> 6).
              chr(0x80 | $code_point & 0x3F);
     } elseif (0x10000 > $code_point) {
-      $str = chr(0xE0 | $code_point >> 12) .
-             chr(0x80 | $code_point >> 6 & 0x3F) .
+      $str = chr(0xE0 | $code_point >> 12).
+             chr(0x80 | $code_point >> 6 & 0x3F).
              chr(0x80 | $code_point & 0x3F);
     } else {
-      $str = chr(0xF0 | $code_point >> 18) .
-             chr(0x80 | $code_point >> 12 & 0x3F) .
-             chr(0x80 | $code_point >> 6 & 0x3F) .
+      $str = chr(0xF0 | $code_point >> 18).
+             chr(0x80 | $code_point >> 12 & 0x3F).
+             chr(0x80 | $code_point >> 6 & 0x3F).
              chr(0x80 | $code_point & 0x3F);
     }
 
@@ -1216,7 +1216,7 @@ 
   public static function decimal_to_chr($code)
   {
     return \mb_convert_encoding(
-        '&#x' . dechex($code) . ';',
+        '&#x'.dechex($code).';',
         'UTF-8',
         'HTML-ENTITIES'
     );
@@ -1296,7 +1296,7 @@ 
           &&
           self::$support['mbstring'] === false
       ) {
-        trigger_error('UTF8::encode() without mbstring cannot handle "' . $encoding . '" encoding', E_USER_WARNING);
+        trigger_error('UTF8::encode() without mbstring cannot handle "'.$encoding.'" encoding', E_USER_WARNING);
       }
 
       $strEncoded = \mb_convert_encoding(
@@ -1496,7 +1496,7 @@ 
           ) {
             // Prevent leading combining chars
             // for NFC-safe concatenations.
-            $var = $leading_combining . $var;
+            $var = $leading_combining.$var;
           }
         }
         break;
@@ -1916,7 +1916,7 @@ 
    */
   private static function getData($file)
   {
-    $file = __DIR__ . '/data/' . $file . '.php';
+    $file = __DIR__.'/data/'.$file.'.php';
     if (file_exists($file)) {
       /** @noinspection PhpIncludeInspection */
       return require $file;
@@ -2021,7 +2021,7 @@ 
     return implode(
         '',
         array_map(
-            function ($data) use ($keepAsciiChars, $encoding) {
+            function($data) use ($keepAsciiChars, $encoding) {
               return UTF8::single_chr_html_encode($data, $keepAsciiChars, $encoding);
             },
             self::split($str)
@@ -2140,7 +2140,7 @@ 
 
       $str = preg_replace_callback(
           "/&#\d{2,6};/",
-          function ($matches) use ($encoding) {
+          function($matches) use ($encoding) {
             $returnTmp = \mb_convert_encoding($matches[0], $encoding, 'HTML-ENTITIES');
 
             if ($returnTmp !== '"' && $returnTmp !== "'") {
@@ -2449,9 +2449,9 @@ 
     if (ctype_digit((string)$int)) {
       $hex = dechex((int)$int);
 
-      $hex = (strlen($hex) < 4 ? substr('0000' . $hex, -4) : $hex);
+      $hex = (strlen($hex) < 4 ? substr('0000'.$hex, -4) : $hex);
 
-      return $pfix . $hex;
+      return $pfix.$hex;
     }
 
     return '';
@@ -3155,7 +3155,7 @@ 
    */
   public static function lcfirst($str)
   {
-    return self::strtolower(self::substr($str, 0, 1)) . self::substr($str, 1);
+    return self::strtolower(self::substr($str, 0, 1)).self::substr($str, 1);
   }
 
   /**
@@ -3179,7 +3179,7 @@ 
       return preg_replace('/^[\pZ\pC]+/u', '', $str);
     }
 
-    return preg_replace('/^' . self::rxClass($chars) . '+/u', '', $str);
+    return preg_replace('/^'.self::rxClass($chars).'+/u', '', $str);
   }
 
   /**
@@ -3680,7 +3680,7 @@ 
     if (is_array($what)) {
       /** @noinspection ForeachSourceInspection */
       foreach ($what as $item) {
-        $str = preg_replace('/(' . preg_quote($item, '/') . ')+/', $item, $str);
+        $str = preg_replace('/('.preg_quote($item, '/').')+/', $item, $str);
       }
     }
 
@@ -3765,7 +3765,7 @@ 
       return preg_replace('/[\pZ\pC]+$/u', '', $str);
     }
 
-    return preg_replace('/' . self::rxClass($chars) . '+$/u', '', $str);
+    return preg_replace('/'.self::rxClass($chars).'+$/u', '', $str);
   }
 
   /**
@@ -3780,7 +3780,7 @@ 
   {
     static $rxClassCache = array();
 
-    $cacheKey = $s . $class;
+    $cacheKey = $s.$class;
 
     if (isset($rxClassCache[$cacheKey])) {
       return $rxClassCache[$cacheKey];
@@ -3792,7 +3792,7 @@ 
     /** @noinspection SuspiciousLoopInspection */
     foreach (self::str_split($s) as $s) {
       if ('-' === $s) {
-        $class[0] = '-' . $class[0];
+        $class[0] = '-'.$class[0];
       } elseif (!isset($s[2])) {
         $class[0] .= preg_quote($s, '/');
       } elseif (1 === self::strlen($s)) {
@@ -3803,13 +3803,13 @@ 
     }
 
     if ($class[0]) {
-      $class[0] = '[' . $class[0] . ']';
+      $class[0] = '['.$class[0].']';
     }
 
     if (1 === count($class)) {
       $return = $class[0];
     } else {
-      $return = '(?:' . implode('|', $class) . ')';
+      $return = '(?:'.implode('|', $class).')';
     }
 
     $rxClassCache[$cacheKey] = $return;
@@ -3827,7 +3827,7 @@ 
     }
 
     foreach (self::$support as $utf8Support) {
-      echo $utf8Support . "\n<br>";
+      echo $utf8Support."\n<br>";
     }
   }
 
@@ -3861,7 +3861,7 @@ 
       $encoding = self::normalize_encoding($encoding);
     }
 
-    return '&#' . self::ord($char, $encoding) . ';';
+    return '&#'.self::ord($char, $encoding).';';
   }
 
   /**
@@ -3913,19 +3913,19 @@ 
           $ret[] = $str[$i];
         } elseif ((($str[$i] & "\xE0") === "\xC0") && isset($str[$i + 1])) {
           if (($str[$i + 1] & "\xC0") === "\x80") {
-            $ret[] = $str[$i] . $str[$i + 1];
+            $ret[] = $str[$i].$str[$i + 1];
 
             $i++;
           }
         } elseif ((($str[$i] & "\xF0") === "\xE0") && isset($str[$i + 2])) {
           if ((($str[$i + 1] & "\xC0") === "\x80") && (($str[$i + 2] & "\xC0") === "\x80")) {
-            $ret[] = $str[$i] . $str[$i + 1] . $str[$i + 2];
+            $ret[] = $str[$i].$str[$i + 1].$str[$i + 2];
 
             $i += 2;
           }
         } elseif ((($str[$i] & "\xF8") === "\xF0") && isset($str[$i + 3])) {
           if ((($str[$i + 1] & "\xC0") === "\x80") && (($str[$i + 2] & "\xC0") === "\x80") && (($str[$i + 3] & "\xC0") === "\x80")) {
-            $ret[] = $str[$i] . $str[$i + 1] . $str[$i + 2] . $str[$i + 3];
+            $ret[] = $str[$i].$str[$i + 1].$str[$i + 2].$str[$i + 3];
 
             $i += 3;
           }
@@ -3937,7 +3937,7 @@ 
       $ret = array_chunk($ret, $length);
 
       return array_map(
-          function ($item) {
+          function($item) {
             return implode('', $item);
           }, $ret
       );
@@ -4036,7 +4036,7 @@ 
     foreach (self::$iconvEncoding as $encodingTmp) {
       # INFO: //IGNORE and //TRANSLIT still throw notice
       /** @noinspection PhpUsageOfSilenceOperatorInspection */
-      if (md5(@\iconv($encodingTmp, $encodingTmp . '//IGNORE', $str)) === $md5) {
+      if (md5(@\iconv($encodingTmp, $encodingTmp.'//IGNORE', $str)) === $md5) {
         return $encodingTmp;
       }
     }
@@ -4126,7 +4126,7 @@ 
       if ('' === $s .= '') {
         $s = '/^(?<=.)$/';
       } else {
-        $s = '/' . preg_quote($s, '/') . '/ui';
+        $s = '/'.preg_quote($s, '/').'/ui';
       }
     }
 
@@ -4184,7 +4184,7 @@ 
     }
 
     if (self::substr($str, $length - 1, 1) === ' ') {
-      return self::substr($str, 0, $length - 1) . $strAddOn;
+      return self::substr($str, 0, $length - 1).$strAddOn;
     }
 
     $str = self::substr($str, 0, $length);
@@ -4193,9 +4193,9 @@ 
     $new_str = implode(' ', $array);
 
     if ($new_str === '') {
-      $str = self::substr($str, 0, $length - 1) . $strAddOn;
+      $str = self::substr($str, 0, $length - 1).$strAddOn;
     } else {
-      $str = $new_str . $strAddOn;
+      $str = $new_str.$strAddOn;
     }
 
     return $str;
@@ -4250,7 +4250,7 @@ 
           $pre = '';
       }
 
-      return $pre . $str . $post;
+      return $pre.$str.$post;
     }
 
     return $str;
@@ -4380,7 +4380,7 @@ 
     }
 
     /** @noinspection PhpInternalEntityUsedInspection */
-    preg_match_all('/' . Grapheme::GRAPHEME_CLUSTER_RX . '/u', $str, $a);
+    preg_match_all('/'.Grapheme::GRAPHEME_CLUSTER_RX.'/u', $str, $a);
     $a = $a[0];
 
     if ($len === 1) {
@@ -4574,7 +4574,7 @@ 
   public static function strcmp($str1, $str2)
   {
     /** @noinspection PhpUndefinedClassInspection */
-    return $str1 . '' === $str2 . '' ? 0 : strcmp(
+    return $str1.'' === $str2.'' ? 0 : strcmp(
         \Normalizer::normalize($str1, \Normalizer::NFD),
         \Normalizer::normalize($str2, \Normalizer::NFD)
     );
@@ -4605,7 +4605,7 @@ 
       return null;
     }
 
-    if (preg_match('/^(.*?)' . self::rxClass($charList) . '/us', $str, $length)) {
+    if (preg_match('/^(.*?)'.self::rxClass($charList).'/us', $str, $length)) {
       /** @noinspection OffsetOperationsInspection */
       return self::strlen($length[1]);
     }
@@ -4810,7 +4810,7 @@ 
         &&
         self::$support['mbstring'] === false
     ) {
-      trigger_error('UTF8::stristr() without mbstring cannot handle "' . $encoding . '" encoding', E_USER_WARNING);
+      trigger_error('UTF8::stristr() without mbstring cannot handle "'.$encoding.'" encoding', E_USER_WARNING);
     }
 
     if (self::$support['mbstring'] === true) {
@@ -4821,7 +4821,7 @@ 
       return \grapheme_stristr($haystack, $needle, $before_needle);
     }
 
-    preg_match('/^(.*?)' . preg_quote($needle, '/') . '/usi', $haystack, $match);
+    preg_match('/^(.*?)'.preg_quote($needle, '/').'/usi', $haystack, $match);
 
     if (!isset($match[1])) {
       return false;
@@ -4883,7 +4883,7 @@ 
         &&
         self::$support['mbstring'] === false
     ) {
-      trigger_error('UTF8::strlen() without mbstring cannot handle "' . $encoding . '" encoding', E_USER_WARNING);
+      trigger_error('UTF8::strlen() without mbstring cannot handle "'.$encoding.'" encoding', E_USER_WARNING);
     }
 
     if (self::$support['mbstring'] === true) {
@@ -4948,7 +4948,7 @@ 
    */
   public static function strnatcmp($str1, $str2)
   {
-    return $str1 . '' === $str2 . '' ? 0 : strnatcmp(self::strtonatfold($str1), self::strtonatfold($str2));
+    return $str1.'' === $str2.'' ? 0 : strnatcmp(self::strtonatfold($str1), self::strtonatfold($str2));
   }
 
   /**
@@ -5009,7 +5009,7 @@ 
       return false;
     }
 
-    if (preg_match('/' . self::rxClass($char_list) . '/us', $haystack, $m)) {
+    if (preg_match('/'.self::rxClass($char_list).'/us', $haystack, $m)) {
       return substr($haystack, strpos($haystack, $m[0]));
     } else {
       return false;
@@ -5076,7 +5076,7 @@ 
         &&
         self::$support['mbstring'] === false
     ) {
-      trigger_error('UTF8::strpos() without mbstring cannot handle "' . $encoding . '" encoding', E_USER_WARNING);
+      trigger_error('UTF8::strpos() without mbstring cannot handle "'.$encoding.'" encoding', E_USER_WARNING);
     }
 
     if (self::$support['mbstring'] === true) {
@@ -5278,7 +5278,7 @@ 
         &&
         self::$support['mbstring'] === false
     ) {
-      trigger_error('UTF8::strripos() without mbstring cannot handle "' . $encoding . '" encoding', E_USER_WARNING);
+      trigger_error('UTF8::strripos() without mbstring cannot handle "'.$encoding.'" encoding', E_USER_WARNING);
     }
 
     if (self::$support['mbstring'] === true) {
@@ -5359,7 +5359,7 @@ 
         &&
         self::$support['mbstring'] === false
     ) {
-      trigger_error('UTF8::strrpos() without mbstring cannot handle "' . $encoding . '" encoding', E_USER_WARNING);
+      trigger_error('UTF8::strrpos() without mbstring cannot handle "'.$encoding.'" encoding', E_USER_WARNING);
     }
 
     if (self::$support['mbstring'] === true) {
@@ -5419,7 +5419,7 @@ 
       return 0;
     }
 
-    return preg_match('/^' . self::rxClass($mask) . '+/u', $str, $str) ? self::strlen($str[0]) : 0;
+    return preg_match('/^'.self::rxClass($mask).'+/u', $str, $str) ? self::strlen($str[0]) : 0;
   }
 
   /**
@@ -5465,7 +5465,7 @@ 
         &&
         self::$support['mbstring'] === false
     ) {
-      trigger_error('UTF8::strstr() without mbstring cannot handle "' . $encoding . '" encoding', E_USER_WARNING);
+      trigger_error('UTF8::strstr() without mbstring cannot handle "'.$encoding.'" encoding', E_USER_WARNING);
     }
 
     if (self::$support['mbstring'] === true) {
@@ -5482,7 +5482,7 @@ 
       }
     }
 
-    preg_match('/^(.*?)' . preg_quote($needle, '/') . '/us', $haystack, $match);
+    preg_match('/^(.*?)'.preg_quote($needle, '/').'/us', $haystack, $match);
 
     if (!isset($match[1])) {
       return false;
@@ -5748,7 +5748,7 @@ 
         &&
         self::$support['mbstring'] === false
     ) {
-      trigger_error('UTF8::substr() without mbstring cannot handle "' . $encoding . '" encoding', E_USER_WARNING);
+      trigger_error('UTF8::substr() without mbstring cannot handle "'.$encoding.'" encoding', E_USER_WARNING);
     }
 
     if (self::$support['mbstring'] === true) {
@@ -5861,14 +5861,14 @@ 
         &&
         self::$support['mbstring'] === false
     ) {
-      trigger_error('UTF8::substr_count() without mbstring cannot handle "' . $encoding . '" encoding', E_USER_WARNING);
+      trigger_error('UTF8::substr_count() without mbstring cannot handle "'.$encoding.'" encoding', E_USER_WARNING);
     }
 
     if (self::$support['mbstring'] === true) {
       return \mb_substr_count($haystack, $needle, $encoding);
     }
 
-    preg_match_all('/' . preg_quote($needle, '/') . '/us', $haystack, $matches, PREG_SET_ORDER);
+    preg_match_all('/'.preg_quote($needle, '/').'/us', $haystack, $matches, PREG_SET_ORDER);
 
     return count($matches);
   }
@@ -6115,7 +6115,7 @@ 
 
     $strSwappedCase = preg_replace_callback(
         '/[\S]/u',
-        function ($match) use ($encoding) {
+        function($match) use ($encoding) {
           $marchToUpper = UTF8::strtoupper($match[0], $encoding);
 
           if ($match[0] === $marchToUpper) {
@@ -6305,7 +6305,7 @@ 
 
       $bank = $ord >> 8;
       if (!array_key_exists($bank, (array)$UTF8_TO_ASCII)) {
-        $bankfile = __DIR__ . '/data/' . sprintf('x%02x', $bank) . '.php';
+        $bankfile = __DIR__.'/data/'.sprintf('x%02x', $bank).'.php';
         if (file_exists($bankfile)) {
           /** @noinspection PhpIncludeInspection */
           require $bankfile;
@@ -6427,40 +6427,40 @@ 
         if ($c1 >= "\xc0" & $c1 <= "\xdf") { // looks like 2 bytes UTF8
 
           if ($c2 >= "\x80" && $c2 <= "\xbf") { // yeah, almost sure it's UTF8 already
-            $buf .= $c1 . $c2;
+            $buf .= $c1.$c2;
             $i++;
           } else { // not valid UTF8 - convert it
             $cc1 = (chr(ord($c1) / 64) | "\xc0");
             $cc2 = ($c1 & "\x3f") | "\x80";
-            $buf .= $cc1 . $cc2;
+            $buf .= $cc1.$cc2;
           }
 
         } elseif ($c1 >= "\xe0" & $c1 <= "\xef") { // looks like 3 bytes UTF8
 
           if ($c2 >= "\x80" && $c2 <= "\xbf" && $c3 >= "\x80" && $c3 <= "\xbf") { // yeah, almost sure it's UTF8 already
-            $buf .= $c1 . $c2 . $c3;
+            $buf .= $c1.$c2.$c3;
             $i += 2;
           } else { // not valid UTF8 - convert it
             $cc1 = (chr(ord($c1) / 64) | "\xc0");
             $cc2 = ($c1 & "\x3f") | "\x80";
-            $buf .= $cc1 . $cc2;
+            $buf .= $cc1.$cc2;
           }
 
         } elseif ($c1 >= "\xf0" & $c1 <= "\xf7") { // looks like 4 bytes UTF8
 
           if ($c2 >= "\x80" && $c2 <= "\xbf" && $c3 >= "\x80" && $c3 <= "\xbf" && $c4 >= "\x80" && $c4 <= "\xbf") { // yeah, almost sure it's UTF8 already
-            $buf .= $c1 . $c2 . $c3 . $c4;
+            $buf .= $c1.$c2.$c3.$c4;
             $i += 3;
           } else { // not valid UTF8 - convert it
             $cc1 = (chr(ord($c1) / 64) | "\xc0");
             $cc2 = ($c1 & "\x3f") | "\x80";
-            $buf .= $cc1 . $cc2;
+            $buf .= $cc1.$cc2;
           }
 
         } else { // doesn't look like UTF8, but should be converted
           $cc1 = (chr(ord($c1) / 64) | "\xc0");
           $cc2 = (($c1 & "\x3f") | "\x80");
-          $buf .= $cc1 . $cc2;
+          $buf .= $cc1.$cc2;
         }
 
       } elseif (($c1 & "\xc0") === "\x80") { // needs conversion
@@ -6471,7 +6471,7 @@ 
         } else {
           $cc1 = (chr($ordC1 / 64) | "\xc0");
           $cc2 = (($c1 & "\x3f") | "\x80");
-          $buf .= $cc1 . $cc2;
+          $buf .= $cc1.$cc2;
         }
 
       } else { // it doesn't need conversion
@@ -6482,7 +6482,7 @@ 
     // decode unicode escape sequences
     $buf = preg_replace_callback(
         '/\\\\u([0-9a-f]{4})/i',
-        function ($match) {
+        function($match) {
           return \mb_convert_encoding(pack('H*', $match[1]), 'UTF-8', 'UCS-2BE');
         },
         $buf
@@ -6536,7 +6536,7 @@ 
    */
   public static function ucfirst($str, $encoding = 'UTF-8', $cleanUtf8 = false)
   {
-    return self::strtoupper(self::substr($str, 0, 1, $encoding, $cleanUtf8), $encoding, $cleanUtf8) . self::substr($str, 1, null, $encoding, $cleanUtf8);
+    return self::strtoupper(self::substr($str, 0, 1, $encoding, $cleanUtf8), $encoding, $cleanUtf8).self::substr($str, 1, null, $encoding, $cleanUtf8);
   }
 
   /**
@@ -7013,7 +7013,7 @@ 
       return '';
     }
 
-    preg_match('/^\s*+(?:\S++\s*+){1,' . $words . '}/u', $str, $matches);
+    preg_match('/^\s*+(?:\S++\s*+){1,'.$words.'}/u', $str, $matches);
 
     if (
         !isset($matches[0])
@@ -7023,7 +7023,7 @@ 
       return $str;
     }
 
-    return self::rtrim($matches[0]) . $strAddOn;
+    return self::rtrim($matches[0]).$strAddOn;
   }
 
   /**
@@ -7091,7 +7091,7 @@ 
       $strReturn .= $break;
     }
 
-    return $strReturn . implode('', $chars);
+    return $strReturn.implode('', $chars);
   }
 
   /**