More safely back up state

lib/Encoding/UTF8.php

@@ -6,7 +6,7 @@
 declare(strict_types=1);
 namespace MensBeam\Intl\Encoding;
 
-class UTF8  implements \Iterator {
+class UTF8 implements \Iterator {
     protected $string;
     protected $posByte = 0;
     protected $posChar = 0;
@@ -167,41 +167,35 @@ class UTF8  implements \Iterator {
     /** Retrieves the next $num characters from the string, without advancing the character pointer */
     public function peekChr(int $num = 1): string {
         $out = "";
-        $pC = $this->posChar;
-        $pB = $this->posByte;
+        $state = $this->stateSave();
         while ($num-- > 0 && ($b = $this->nextChr()) !== "") {
             $out .= $b;
         }
-        $this->posChar = $pC;
-        $this->posByte = $pB;
+        $this->stateApply($state);
         return $out;
     }
 
     /** Retrieves the next $num code points from the string, without advancing the character pointer */
     public function peekOrd(int $num = 1): array {
         $out = [];
-        $pC = $this->posChar;
-        $pB = $this->posByte;
+        $state = $this->stateSave();
         while ($num-- > 0 && ($b = $this->nextOrd()) !== false) {
             $out[] = $b;
         }
-        $this->posChar = $pC;
-        $this->posByte = $pB;
+        $this->stateApply($state);
         return $out;
     }
 
-    /** Calculates the length of the string in code points 
-     * 
+    /** Calculates the length of the string in code points
+     *
      * Note that this involves processing to the end of the string
     */
     public function len(): int {
         return $this->lenChar ?? (function() {
-            $pC = $this->posChar;
-            $pB = $this->posByte;
-            while ($this->nextChr() !== "");
+            $state = $this->stateSave();
+            while ($this->nextOrd() !== false);
             $this->lenChar = $this->posChar;
-            $this->posChar = $pC;
-            $this->posByte = $pB;
+            $this->stateApply($state);
             return $this->lenChar;
         })();
     }
@@ -228,6 +222,19 @@ class UTF8  implements \Iterator {
         }
     }
 
+    protected function stateSave(): array {
+        return [
+            'posChar' => $this->posChar,
+            'posByte' => $this->posByte,
+        ];
+    }
+
+    protected function stateApply(array $state) {
+        foreach($state as $key => $value) {
+            $this->$key = $value;
+        }
+    }
+
     /** Returns the UTF-8 encoding of $codePoint
      *
      * If $codePoint is less than 0 or greater than 1114111, an empty string is returned

tests/cases/Encoding/TestUTF8.php

@@ -9,7 +9,7 @@ namespace MensBeam\Intl\TestCase\Encoding;
 use MensBeam\Intl\Encoding\UTF8;
 
 class TestUTF8 extends \PHPUnit\Framework\TestCase {
-    
+
     /**
      * @covers MensBeam\Intl\Encoding\UTF8::chr
     */
@@ -23,7 +23,7 @@ class TestUTF8 extends \PHPUnit\Framework\TestCase {
         $this->assertSame("", UTF8::chr(\PHP_INT_MAX));
         $this->assertSame("", UTF8::chr(\PHP_INT_MIN));
     }
-    
+
     /**
      * @dataProvider provideStrings
      * @covers MensBeam\Intl\Encoding\UTF8::__construct
@@ -37,7 +37,7 @@ class TestUTF8 extends \PHPUnit\Framework\TestCase {
         }
         $this->assertEquals($exp, $out);
     }
-    
+
     /**
      * @dataProvider provideStrings
      * @covers MensBeam\Intl\Encoding\UTF8::__construct
@@ -54,7 +54,7 @@ class TestUTF8 extends \PHPUnit\Framework\TestCase {
         }
         $this->assertEquals($exp, $out);
     }
-    
+
     /**
      * @dataProvider provideStrings
      * @covers MensBeam\Intl\Encoding\UTF8::rewind
@@ -77,7 +77,7 @@ class TestUTF8 extends \PHPUnit\Framework\TestCase {
             $a++;
         }
     }
-    
+
     /**
      * @dataProvider provideStrings
      * @covers MensBeam\Intl\Encoding\UTF8::sync
@@ -93,7 +93,7 @@ class TestUTF8 extends \PHPUnit\Framework\TestCase {
             $this->assertSame(++$a, $s->posChr(), "Character position should be $a");
         }
     }
-    
+
     /**
      * @covers MensBeam\Intl\Encoding\UTF8::seek
      * @covers MensBeam\Intl\Encoding\UTF8::posChr
@@ -122,32 +122,32 @@ class TestUTF8 extends \PHPUnit\Framework\TestCase {
         $this->assertSame(1, $s->seek(-1));
         $this->assertSame(0, $s->posChr());
         $this->assertSame(0, $s->posByte());
-        
+
         $this->assertSame(0, $s->seek(1));
         $this->assertSame(1, $s->posChr());
         $this->assertSame(1, $s->posByte());
-        
+
         $this->assertSame(0, $s->seek(2));
         $this->assertSame(3, $s->posChr());
         $this->assertSame(6, $s->posByte());
-        
+
         $this->assertSame(0, $s->seek(4));
         $this->assertSame(7, $s->posChr());
         $this->assertSame(20, $s->posByte());
-        
+
         $this->assertSame(1, $s->seek(1));
         $this->assertSame(7, $s->posChr());
         $this->assertSame(20, $s->posByte());
-        
+
         $this->assertSame(0, $s->seek(-3));
         $this->assertSame(4, $s->posChr());
         $this->assertSame(10, $s->posByte());
-        
+
         $this->assertSame(6, $s->seek(-10));
         $this->assertSame(0, $s->posChr());
         $this->assertSame(0, $s->posByte());
     }
-    
+
     /**
      * @covers MensBeam\Intl\Encoding\UTF8::posChr
      * @covers MensBeam\Intl\Encoding\UTF8::posByte
@@ -177,7 +177,7 @@ class TestUTF8 extends \PHPUnit\Framework\TestCase {
         $this->assertSame(1, $s->posChr());
         $this->assertSame(1, $s->posByte());
     }
-    
+
     /**
      * @covers MensBeam\Intl\Encoding\UTF8::peekChr
     */
@@ -218,7 +218,7 @@ class TestUTF8 extends \PHPUnit\Framework\TestCase {
         $this->assertSame(5, $s->posChr());
         $this->assertSame(13, $s->posByte());
     }
-    
+
     /**
      * @covers MensBeam\Intl\Encoding\UTF8::peekOrd
     */
@@ -259,10 +259,12 @@ class TestUTF8 extends \PHPUnit\Framework\TestCase {
         $this->assertSame(5, $s->posChr());
         $this->assertSame(13, $s->posByte());
     }
-    
+
     /**
      * @dataProvider provideStrings
      * @covers MensBeam\Intl\Encoding\UTF8::len
+     * @covers MensBeam\Intl\Encoding\UTF8::stateSave
+     * @covers MensBeam\Intl\Encoding\UTF8::stateApply
     */
     public function testGetStringLength(string $input, array $points) {
         $s = new UTF8($input);