[+]: optimized "UTF8::str_detect_encoding()"

[*]: added more API doc

API.md

@@ -539,12 +539,71 @@ Create an array containing a range of UTF-8 characters.
 UTF8::range('κ', 'ζ'); // array('κ', 'ι', 'θ', 'η', 'ζ',)
 ```
 
-##### remove_bom(mixed $var1, mixed $var2) : array
+##### remove_bom(string $str) : string
 
 Remove the BOM from UTF-8 / UTF-16 / UTF-32 strings.
 
 ```php
 UTF8::remove_bom("\xEF\xBB\xBFΜπορώ να"); // 'Μπορώ να'
 ```
 
+##### remove_duplicates(string $str, string|array $what = ' ') : string
+
+Removes duplicate occurrences of a string in another string.
+
+```php
+UTF8::remove_duplicates('öäü-κόσμεκόσμε-äöü', 'κόσμε'); // 'öäü-κόσμε-äöü'
+```
+
+##### remove_invisible_characters(string $str, bool $url_encoded = true, string $replacement = '') : string
+
+Remove invisible characters from a string.
+
+```php
+UTF8::remove_duplicates("κόσ\0με"); // 'κόσμε'
+```
+
+##### replace_diamond_question_mark(string $str, string $unknown = '?') : string
+
+Replace the diamond question mark (�) with the replacement.
+
+```php
+UTF8::replace_diamond_question_mark('中文空白�'); // '中文空白'
+```
+
+##### rtrim(string $str = '', string $chars = INF) : string
+
+Strip whitespace or other characters from end of a UTF-8 string.
+
+```php
+UTF8::rtrim('-ABC-中文空白-  '); // '-ABC-中文空白-'
+```
+
+##### single_chr_html_encode(string $char, bool $keepAsciiChars = false) : string
+
+Converts a UTF-8 character to HTML Numbered Entity like "{".
+
+```php
+UTF8::single_chr_html_encode('κ'); // 'κ'
+```
+
+##### split(string $str, int $length = 1, bool $cleanUtf8 = false) : array
+
+Convert a string to an array of Unicode characters.
+
+```php
+UTF8::split('中文空白'); // array('中', '文', '空', '白')
+```
+
+##### str_detect_encoding(string $str, int $length = 1, bool $cleanUtf8 = false) : array
+
+Optimized "\mb_detect_encoding()"-function -> with support for UTF-16 and UTF-32.
+
+```php
+UTF8::str_detect_encoding('中文空白'); // array('中', '文', '空', '白')
+```
+
+
+
+
 ... TODO

src/voku/helper/UTF8.php

@@ -4317,10 +4317,9 @@ public static function remove_duplicates($str, $what = ' ')
   }
 
   /**
-   * Remove Invisible Characters
+   * Remove invisible characters from a string.
    *
-   * This prevents sandwiching null characters
-   * between ascii characters, like Java\0script.
+   * e.g.: This prevents sandwiching null characters between ascii characters, like Java\0script.
    *
    * copy&past from https://github.com/bcit-ci/CodeIgniter/blob/develop/system/core/Common.php
    *
@@ -4352,7 +4351,7 @@ public static function remove_invisible_characters($str, $url_encoded = true, $r
   }
 
   /**
-   * replace diamond question mark (�)
+   * Replace the diamond question mark (�) with the replacement.
    *
    * @param string $str
    * @param string $unknown
@@ -4612,14 +4611,14 @@ public static function str_detect_encoding($str)
     // INFO: UTF-16, UTF-32, UCS2 and UCS4, encoding detection will fail always with "\mb_detect_encoding()"
 
     $detectOrder = array(
-        'windows-1251',
-        'ISO-8859-1',
-        'ASCII',
-        'UTF-8',
+        'ISO-8859-1', 'ISO-8859-2', 'ISO-8859-3', 'ISO-8859-4', 'ISO-8859-5',
+        'ISO-8859-6', 'ISO-8859-7', 'ISO-8859-8', 'ISO-8859-9', 'ISO-8859-10',
+        'ISO-8859-13', 'ISO-8859-14', 'ISO-8859-15', 'ISO-8859-16',
+        'WINDOWS-1251', 'WINDOWS-1252', 'WINDOWS-1254',
+        'ISO-2022-JP', 'JIS', 'EUC-JP',
     );
 
     self::checkForSupport();
-
     $encoding = \mb_detect_encoding($str, $detectOrder, true);
     if ($encoding) {
       return $encoding;

tests/Utf8GlobalTest.php

@@ -489,7 +489,7 @@ public function testEncode()
     $tests = array(
         '  -ABC-中文空白-  ' => '  -ABC-????-  ',
         '      - ÖÄÜ- '  => '      - ÖÄÜ- ',
-        'öäü'            => '???',
+        'öäü'            => 'öäü',
         ''               => '',
         'abc'            => 'abc',
         'Berbée'         => 'Berbée',
@@ -1528,7 +1528,7 @@ public function testNormalizeWhitespace()
         " foo\t foo "                                                                         => ' foo	 foo ',
     );
 
-    for ($i = 0; $i < 2; $i++) {
+    for ($i = 0; $i < 2; $i++) { // keep this loop for simple performance tests
       foreach ($tests as $before => $after) {
         self::assertSame($after, UTF8::normalize_whitespace($before));
       }
@@ -1857,9 +1857,17 @@ public function testStrDetectEncoding()
         01                              => 'ASCII', // ASCII
     );
 
-    foreach ($tests as $before => $after) {
-      self::assertSame($after, UTF8::str_detect_encoding($before), 'value: ' . $before);
+    for ($i = 0; $i <= 2; $i++) { // keep this loop for simple performance tests
+      foreach ($tests as $before => $after) {
+        self::assertSame($after, UTF8::str_detect_encoding($before), 'value: ' . $before);
+      }
     }
+
+    $testString = file_get_contents(__DIR__ . '/fixtures/latin.txt');
+    self::assertContains('ISO-8859-1', UTF8::str_detect_encoding($testString));
+
+    $testString = file_get_contents(__DIR__ . '/fixtures/iso-8859-7.txt');
+    self::assertContains('ISO-8859-1', UTF8::str_detect_encoding($testString)); // ?
   }
 
   public function testStrLimit()
@@ -2095,7 +2103,7 @@ public function testStripTags()
 
   public function testStripos()
   {
-    for ($i = 0; $i <= 5; $i++) {
+    for ($i = 0; $i <= 2; $i++) { // keep this loop for simple performance tests
       self::assertSame(3, UTF8::stripos('DÉJÀ', 'à'));
       self::assertSame(1, UTF8::stripos('aςσb', 'ΣΣ'));
       self::assertSame(16, UTF8::stripos('der Straße nach Paris', 'Paris'));
@@ -2210,7 +2218,7 @@ public function testStrpbrk()
 
   public function testStrpos()
   {
-    for ($i = 0; $i <= 3; $i++) { // keep this loop for simple performance tests
+    for ($i = 0; $i <= 2; $i++) { // keep this loop for simple performance tests
 
       // php compatible tests
 
@@ -2993,7 +3001,7 @@ public function testToUtf8_v3()
    */
   public function testTrim($input, $output)
   {
-    for ($i = 0; $i <= 10; $i++) {
+    for ($i = 0; $i <= 2; $i++) { // keep this loop for simple performance tests
       self::assertSame($output, UTF8::trim($input));
     }
   }