JavaScript: added support for Unicode-aware regexps

README.md

@@ -72,15 +72,36 @@ echo $builder->build(['☺', '☹']);
 
 ### UTF-8 input with JavaScript output
 
+For JavaScript regular expressions that do not use the `u` flag and need the higher codepoints to be split into surrogates.
+
 ```php
 $builder = new s9e\RegexpBuilder\Builder([
 	'input'  => 'Utf8ToSurrogates',
 	'output' => 'JavaScript'
 ]);
-echo $builder->build(['☺', '☹']);
+echo $builder->build(['☺', '☹']), "\n";
+echo $builder->build(['😁', '😂']);
+```
+```
+[\u2639\u263A]
+\uD83D[\uDE01\uDE02]
+```
+
+### UTF-8 input with Unicode-aware JavaScript output
+
+For JavaScript regular expressions that use the `u` flag introduced in ECMAScript 6.
+
+```php
+$builder = new s9e\RegexpBuilder\Builder([
+	'input'  => 'Utf8',
+	'output' => 'JavaScript'
+]);
+echo $builder->build(['☺', '☹']), "\n";
+echo $builder->build(['😁', '😂']);
 ```
 ```
 [\u2639\u263A]
+[\u{1F601}\u{1F602}]
 ```
 
 ### Custom delimiters

composer.json

@@ -1,6 +1,6 @@
 {
 	"name": "s9e/regexp-builder",
-	"version": "1.0.1",
+	"version": "1.1.0",
 	"type": "library",
 	"description": "Single-purpose library that generates regular expressions that match a list of literal strings.",
 	"homepage": "https://github.com/s9e/RegexpBuilder/",

src/Output/JavaScript.php

@@ -10,13 +10,13 @@
 class JavaScript extends PrintableAscii
 {
 	/** {@inheritdoc} */
-	protected $maxValue = 0xFFFF;
+	protected $maxValue = 0x10FFFF;
 
 	/**
 	* {@inheritdoc}
 	*/
 	protected function escapeUnicode($cp)
 	{
-		return sprintf('\\u%04X', $cp);
+		return sprintf(($cp > 0xFFFF) ? '\\u{%X}' : '\\u%04X', $cp);
 	}
 }

tests/Output/JavaScriptTest.php

@@ -22,7 +22,8 @@ public function getOutputTests()
 			[102, 'f'],
 			[0xC3, '\\xC3'],
 			[0x2026, '\\u2026'],
-			[0x1F600, new InvalidArgumentException('Value 128512 is out of bounds (0..65535)')]
+			[0x1F600, '\\u{1F600}'],
+			[0x110000, new InvalidArgumentException('Value 1114112 is out of bounds (0..1114111)')]
 		];
 	}
 }