voku / portable-utf8

src/voku/helper/UTF8.php

Spacing +75 added lines, -77 removed lines

@@ -855,7 +855,7 @@ 
   public static function add_bom_to_string($str)
   {
     if (self::string_has_bom($str) === false) {
-      $str = self::bom() . $str;
+      $str = self::bom().$str;
     }
 
     return $str;
@@ -980,10 +980,10 @@ 
         &&
         self::$SUPPORT['mbstring'] === false
     ) {
-      trigger_error('UTF8::chr() without mbstring cannot handle "' . $encoding . '" encoding', E_USER_WARNING);
+      trigger_error('UTF8::chr() without mbstring cannot handle "'.$encoding.'" encoding', E_USER_WARNING);
     }
 
-    $cacheKey = $code_point . $encoding;
+    $cacheKey = $code_point.$encoding;
     if (isset($CHAR_CACHE[$cacheKey]) === true) {
       return $CHAR_CACHE[$cacheKey];
     }
@@ -1008,16 +1008,16 @@ 
     if ($code_point <= 0x7F) {
       $str = self::chr_and_parse_int($code_point);
     } elseif ($code_point <= 0x7FF) {
-      $str = self::chr_and_parse_int(($code_point >> 6) + 0xC0) .
+      $str = self::chr_and_parse_int(($code_point >> 6) + 0xC0).
              self::chr_and_parse_int(($code_point & 0x3F) + 0x80);
     } elseif ($code_point <= 0xFFFF) {
-      $str = self::chr_and_parse_int(($code_point >> 12) + 0xE0) .
-             self::chr_and_parse_int((($code_point >> 6) & 0x3F) + 0x80) .
+      $str = self::chr_and_parse_int(($code_point >> 12) + 0xE0).
+             self::chr_and_parse_int((($code_point >> 6) & 0x3F) + 0x80).
              self::chr_and_parse_int(($code_point & 0x3F) + 0x80);
     } else {
-      $str = self::chr_and_parse_int(($code_point >> 18) + 0xF0) .
-             self::chr_and_parse_int((($code_point >> 12) & 0x3F) + 0x80) .
-             self::chr_and_parse_int((($code_point >> 6) & 0x3F) + 0x80) .
+      $str = self::chr_and_parse_int(($code_point >> 18) + 0xF0).
+             self::chr_and_parse_int((($code_point >> 12) & 0x3F) + 0x80).
+             self::chr_and_parse_int((($code_point >> 6) & 0x3F) + 0x80).
              self::chr_and_parse_int(($code_point & 0x3F) + 0x80);
     }
 
@@ -1077,7 +1077,7 @@ 
     }
 
     return array_map(
-        function ($data) {
+        function($data) {
           return self::strlen($data, '8BIT');
         },
         self::split($str)
@@ -1319,7 +1319,7 @@ 
       $flags = ENT_QUOTES;
     }
 
-    return self::html_entity_decode('&#' . $int . ';', $flags);
+    return self::html_entity_decode('&#'.$int.';', $flags);
   }
 
   /**
@@ -1397,7 +1397,7 @@ 
           &&
           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(
@@ -1606,7 +1606,7 @@ 
           ) {
             // Prevent leading combining chars
             // for NFC-safe concatenations.
-            $var = $leading_combining . $var;
+            $var = $leading_combining.$var;
           }
         }
 
@@ -2030,7 +2030,7 @@ 
    */
   private static function getData($file)
   {
-    $file = __DIR__ . '/data/' . $file . '.php';
+    $file = __DIR__.'/data/'.$file.'.php';
     if (file_exists($file)) {
       /** @noinspection PhpIncludeInspection */
       return require $file;
@@ -2175,7 +2175,7 @@ 
     return implode(
         '',
         array_map(
-            function ($data) use ($keepAsciiChars, $encoding) {
+            function($data) use ($keepAsciiChars, $encoding) {
               return self::single_chr_html_encode($data, $keepAsciiChars, $encoding);
             },
             self::split($str)
@@ -2296,7 +2296,7 @@ 
         &&
         self::$SUPPORT['mbstring'] === false
     ) {
-      trigger_error('UTF8::html_entity_decode() without mbstring cannot handle "' . $encoding . '" encoding', E_USER_WARNING);
+      trigger_error('UTF8::html_entity_decode() without mbstring cannot handle "'.$encoding.'" encoding', E_USER_WARNING);
     }
 
     do {
@@ -2304,7 +2304,7 @@ 
 
       $str = preg_replace_callback(
           "/&#\d{2,6};/",
-          function ($matches) use ($encoding) {
+          function($matches) use ($encoding) {
             $returnTmp = \mb_convert_encoding($matches[0], $encoding, 'HTML-ENTITIES');
 
             if ($returnTmp !== '"' && $returnTmp !== "'") {
@@ -2638,9 +2638,9 @@ 
     if ((int)$int === $int) {
       $hex = dechex($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 '';
@@ -3381,7 +3381,7 @@ 
         $cleanUtf8
     );
 
-    return $strPartOne . $strPartTwo;
+    return $strPartOne.$strPartTwo;
   }
 
   /**
@@ -3471,7 +3471,7 @@ 
       return preg_replace('/^[\pZ\pC]+/u', '', $str);
     }
 
-    return preg_replace('/^' . self::rxClass($chars) . '+/u', '', $str);
+    return preg_replace('/^'.self::rxClass($chars).'+/u', '', $str);
   }
 
   /**
@@ -4068,7 +4068,7 @@ 
     if (is_array($what) === true) {
       /** @noinspection ForeachSourceInspection */
       foreach ($what as $item) {
-        $str = preg_replace('/(' . preg_quote($item, '/') . ')+/', $item, $str);
+        $str = preg_replace('/('.preg_quote($item, '/').')+/', $item, $str);
       }
     }
 
@@ -4176,7 +4176,7 @@ 
       return preg_replace('/[\pZ\pC]+$/u', '', $str);
     }
 
-    return preg_replace('/' . self::rxClass($chars) . '+$/u', '', $str);
+    return preg_replace('/'.self::rxClass($chars).'+$/u', '', $str);
   }
 
   /**
@@ -4191,7 +4191,7 @@ 
   {
     static $RX_CLASSS_CACHE = array();
 
-    $cacheKey = $s . $class;
+    $cacheKey = $s.$class;
 
     if (isset($RX_CLASSS_CACHE[$cacheKey])) {
       return $RX_CLASSS_CACHE[$cacheKey];
@@ -4203,7 +4203,7 @@ 
     /** @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)) {
@@ -4214,13 +4214,13 @@ 
     }
 
     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).')';
     }
 
     $RX_CLASSS_CACHE[$cacheKey] = $return;
@@ -4238,7 +4238,7 @@ 
     }
 
     foreach (self::$SUPPORT as $utf8Support) {
-      echo $utf8Support . "\n<br>";
+      echo $utf8Support."\n<br>";
     }
   }
 
@@ -4271,7 +4271,7 @@ 
       $encoding = self::normalize_encoding($encoding, 'UTF-8');
     }
 
-    return '&#' . self::ord($char, $encoding) . ';';
+    return '&#'.self::ord($char, $encoding).';';
   }
 
   /**
@@ -4338,7 +4338,7 @@ 
         ) {
 
           if (($str[$i + 1] & "\xC0") === "\x80") {
-            $ret[] = $str[$i] . $str[$i + 1];
+            $ret[] = $str[$i].$str[$i + 1];
 
             $i++;
           }
@@ -4354,7 +4354,7 @@ 
               &&
               ($str[$i + 2] & "\xC0") === "\x80"
           ) {
-            $ret[] = $str[$i] . $str[$i + 1] . $str[$i + 2];
+            $ret[] = $str[$i].$str[$i + 1].$str[$i + 2];
 
             $i += 2;
           }
@@ -4372,7 +4372,7 @@ 
               &&
               ($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;
           }
@@ -4385,7 +4385,7 @@ 
       $ret = array_chunk($ret, $length);
 
       return array_map(
-          function ($item) {
+          function($item) {
             return implode('', $item);
           }, $ret
       );
@@ -4491,7 +4491,7 @@ 
     foreach (self::$ICONV_ENCODING 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;
       }
     }
@@ -4586,7 +4586,7 @@ 
       if ('' === $s .= '') {
         $s = '/^(?<=.)$/';
       } else {
-        $s = '/' . preg_quote($s, '/') . '/ui';
+        $s = '/'.preg_quote($s, '/').'/ui';
       }
     }
 
@@ -4644,7 +4644,7 @@ 
     }
 
     if (self::substr($str, $length - 1, 1) === ' ') {
-      return (string)self::substr($str, 0, $length - 1) . $strAddOn;
+      return (string)self::substr($str, 0, $length - 1).$strAddOn;
     }
 
     $str = (string)self::substr($str, 0, $length);
@@ -4653,9 +4653,9 @@ 
     $new_str = implode(' ', $array);
 
     if ($new_str === '') {
-      $str = (string)self::substr($str, 0, $length - 1) . $strAddOn;
+      $str = (string)self::substr($str, 0, $length - 1).$strAddOn;
     } else {
-      $str = $new_str . $strAddOn;
+      $str = $new_str.$strAddOn;
     }
 
     return $str;
@@ -4710,7 +4710,7 @@ 
           $pre = '';
       }
 
-      return $pre . $str . $post;
+      return $pre.$str.$post;
     }
 
     return $str;
@@ -4860,7 +4860,7 @@ 
     }
 
     /** @noinspection PhpInternalEntityUsedInspection */
-    preg_match_all('/' . self::GRAPHEME_CLUSTER_RX . '/u', $str, $a);
+    preg_match_all('/'.self::GRAPHEME_CLUSTER_RX.'/u', $str, $a);
     $a = $a[0];
 
     if ($len === 1) {
@@ -5096,7 +5096,7 @@ 
   public static function strcmp($str1, $str2)
   {
     /** @noinspection PhpUndefinedClassInspection */
-    return $str1 . '' === $str2 . '' ? 0 : strcmp(
+    return $str1.'' === $str2.'' ? 0 : strcmp(
         \Normalizer::normalize($str1, \Normalizer::NFD),
         \Normalizer::normalize($str2, \Normalizer::NFD)
     );
@@ -5131,7 +5131,7 @@ 
       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]);
     }
@@ -5342,7 +5342,7 @@ 
         &&
         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::$SUPPORT['mbstring'] === true) {
@@ -5363,7 +5363,7 @@ 
       return stristr($haystack, $needle, $before_needle);
     }
 
-    preg_match('/^(.*?)' . preg_quote($needle, '/') . '/usi', $haystack, $match);
+    preg_match('/^(.*?)'.preg_quote($needle, '/').'/usi', $haystack, $match);
 
     if (!isset($match[1])) {
       return false;
@@ -5438,7 +5438,7 @@ 
         &&
         self::$SUPPORT['iconv'] === false
     ) {
-      trigger_error('UTF8::strlen() without mbstring / iconv cannot handle "' . $encoding . '" encoding', E_USER_WARNING);
+      trigger_error('UTF8::strlen() without mbstring / iconv cannot handle "'.$encoding.'" encoding', E_USER_WARNING);
     }
 
     if (
@@ -5517,7 +5517,7 @@ 
    */
   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));
   }
 
   /**
@@ -5578,7 +5578,7 @@ 
       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]));
     }
 
@@ -5655,7 +5655,7 @@ 
         &&
         self::$SUPPORT['mbstring'] === false
     ) {
-      trigger_error('UTF8::strpos() without mbstring / iconv cannot handle "' . $encoding . '" encoding', E_USER_WARNING);
+      trigger_error('UTF8::strpos() without mbstring / iconv cannot handle "'.$encoding.'" encoding', E_USER_WARNING);
     }
 
     if (
@@ -5887,7 +5887,7 @@ 
         &&
         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::$SUPPORT['mbstring'] === true) {
@@ -5970,7 +5970,7 @@ 
         &&
         self::$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) {
@@ -6038,7 +6038,7 @@ 
       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;
   }
 
   /**
@@ -6084,7 +6084,7 @@ 
         &&
         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::$SUPPORT['mbstring'] === true) {
@@ -6101,7 +6101,7 @@ 
       return \grapheme_strstr($haystack, $needle, $before_needle);
     }
 
-    preg_match('/^(.*?)' . preg_quote($needle, '/') . '/us', $haystack, $match);
+    preg_match('/^(.*?)'.preg_quote($needle, '/').'/us', $haystack, $match);
 
     if (!isset($match[1])) {
       return false;
@@ -6208,9 +6208,9 @@ 
           Bootup::is_php('5.4') === true
       ) {
 
-        $langCode = $lang . '-Lower';
+        $langCode = $lang.'-Lower';
         if (!in_array($langCode, self::$SUPPORT['intl__transliterator_list_ids'], true)) {
-          trigger_error('UTF8::strtolower() without intl for special language: ' . $lang, E_USER_WARNING);
+          trigger_error('UTF8::strtolower() without intl for special language: '.$lang, E_USER_WARNING);
 
           $langCode = 'Any-Lower';
         }
@@ -6218,7 +6218,7 @@ 
         return transliterator_transliterate($langCode, $str);
       }
 
-      trigger_error('UTF8::strtolower() without intl + PHP >= 5.4 cannot handle the "lang"-parameter: ' . $lang, E_USER_WARNING);
+      trigger_error('UTF8::strtolower() without intl + PHP >= 5.4 cannot handle the "lang"-parameter: '.$lang, E_USER_WARNING);
     }
 
     return \mb_strtolower($str, $encoding);
@@ -6278,9 +6278,9 @@ 
           Bootup::is_php('5.4') === true
       ) {
 
-        $langCode = $lang . '-Upper';
+        $langCode = $lang.'-Upper';
         if (!in_array($langCode, self::$SUPPORT['intl__transliterator_list_ids'], true)) {
-          trigger_error('UTF8::strtoupper() without intl for special language: ' . $lang, E_USER_WARNING);
+          trigger_error('UTF8::strtoupper() without intl for special language: '.$lang, E_USER_WARNING);
 
           $langCode = 'Any-Upper';
         }
@@ -6288,7 +6288,7 @@ 
         return transliterator_transliterate($langCode, $str);
       }
 
-      trigger_error('UTF8::strtolower() without intl + PHP >= 5.4 cannot handle the "lang"-parameter: ' . $lang, E_USER_WARNING);
+      trigger_error('UTF8::strtolower() without intl + PHP >= 5.4 cannot handle the "lang"-parameter: '.$lang, E_USER_WARNING);
     }
 
     return \mb_strtoupper($str, $encoding);
@@ -6488,7 +6488,7 @@ 
         &&
         self::$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) {
@@ -6515,8 +6515,7 @@ 
 
     if (self::is_ascii($str)) {
       return ($length === null) ?
-          substr($str, $offset) :
-          substr($str, $offset, $length);
+          substr($str, $offset) : substr($str, $offset, $length);
     }
 
     // fallback via vanilla php
@@ -6651,14 +6650,14 @@ 
         &&
         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);
   }
@@ -6848,8 +6847,7 @@ 
 
     if (self::is_ascii($str)) {
       return ($length === null) ?
-          substr_replace($str, $replacement, $offset) :
-          substr_replace($str, $replacement, $offset, $length);
+          substr_replace($str, $replacement, $offset) : substr_replace($str, $replacement, $offset, $length);
     }
 
     preg_match_all('/./us', $str, $smatches);
@@ -6925,7 +6923,7 @@ 
 
     $strSwappedCase = preg_replace_callback(
         '/[\S]/u',
-        function ($match) use ($encoding) {
+        function($match) use ($encoding) {
           $marchToUpper = self::strtoupper($match[0], $encoding);
 
           if ($match[0] === $marchToUpper) {
@@ -7269,7 +7267,7 @@ 
           $c2 = $i + 1 >= $max ? "\x00" : $str[$i + 1];
 
           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
             $buf .= self::to_utf8_convert($c1);
@@ -7281,7 +7279,7 @@ 
           $c3 = $i + 2 >= $max ? "\x00" : $str[$i + 2];
 
           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
             $buf .= self::to_utf8_convert($c1);
@@ -7294,7 +7292,7 @@ 
           $c4 = $i + 3 >= $max ? "\x00" : $str[$i + 3];
 
           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
             $buf .= self::to_utf8_convert($c1);
@@ -7316,7 +7314,7 @@ 
     // 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
@@ -7345,7 +7343,7 @@ 
     } else {
       $cc1 = self::chr_and_parse_int($ordC1 / 64) | "\xC0";
       $cc2 = ($int & "\x3F") | "\x80";
-      $buf .= $cc1 . $cc2;
+      $buf .= $cc1.$cc2;
     }
 
     return $buf;
@@ -7408,7 +7406,7 @@ 
         $cleanUtf8
     );
 
-    return $strPartOne . $strPartTwo;
+    return $strPartOne.$strPartTwo;
   }
 
   /**
@@ -7453,7 +7451,7 @@ 
       $str = self::clean($str);
     }
 
-    $usePhpDefaultFunctions = !(bool)($charlist . implode('', $exceptions));
+    $usePhpDefaultFunctions = !(bool)($charlist.implode('', $exceptions));
 
     if (
         $usePhpDefaultFunctions === true
@@ -7940,7 +7938,7 @@ 
       return '';
     }
 
-    preg_match('/^\s*+(?:\S++\s*+){1,' . $limit . '}/u', $str, $matches);
+    preg_match('/^\s*+(?:\S++\s*+){1,'.$limit.'}/u', $str, $matches);
 
     if (
         !isset($matches[0])
@@ -7950,7 +7948,7 @@ 
       return $str;
     }
 
-    return self::rtrim($matches[0]) . $strAddOn;
+    return self::rtrim($matches[0]).$strAddOn;
   }
 
   /**
@@ -8018,7 +8016,7 @@ 
       $strReturn .= $break;
     }
 
-    return $strReturn . implode('', $chars);
+    return $strReturn.implode('', $chars);
   }
 
   /**