require_once( 'PHPUnit.php' );
require_once( 'UtfNormal.php' );
+/**
+ * @package UtfNormal
+ */
class CleanUpTest extends PHPUnit_TestCase {
+ /**
+ * @param string $name ???
+ */
function CleanUpTest( $name ) {
$this->PHPUnit_TestCase( $name );
}
+ /** @todo document */
function setUp() {
}
-
+
+ /** @todo document */
function tearDown() {
}
-
+
+ /** @todo document */
function testAscii() {
$text = 'This is plain ASCII text.';
$this->assertEquals( $text, UtfNormal::cleanUp( $text ) );
}
-
+
+ /** @todo document */
function testNull() {
$text = "a \x00 null";
$expect = "a \xef\xbf\xbd null";
bin2hex( $expect ),
bin2hex( UtfNormal::cleanUp( $text ) ) );
}
-
+
+ /** @todo document */
function testLatin() {
$text = "L'\xc3\xa9cole";
$this->assertEquals( $text, UtfNormal::cleanUp( $text ) );
}
-
+
+ /** @todo document */
function testLatinNormal() {
$text = "L'e\xcc\x81cole";
$expect = "L'\xc3\xa9cole";
$this->assertEquals( $expect, UtfNormal::cleanUp( $text ) );
}
-
- # This test is *very* expensive!
+
+ /**
+ * This test is *very* expensive!
+ * @todo document
+ */
function XtestAllChars() {
$rep = UTF8_REPLACEMENT;
global $utfCanonicalComp, $utfCanonicalDecomp;
}
}
}
-
+
+ /** @todo document */
function testAllBytes() {
$this->doTestBytes( '', '' );
$this->doTestBytes( 'x', '' );
$this->doTestBytes( '', 'x' );
$this->doTestBytes( 'x', 'x' );
}
-
+
+ /** @todo document */
function doTestBytes( $head, $tail ) {
for( $i = 0x0; $i < 256; $i++ ) {
$char = $head . chr( $i ) . $tail;
}
}
}
-
+
+ /** @todo document */
function testDoubleBytes() {
$this->doTestDoubleBytes( '', '' );
$this->doTestDoubleBytes( 'x', '' );
$this->doTestDoubleBytes( '', 'x' );
$this->doTestDoubleBytes( 'x', 'x' );
}
-
+
+ /**
+ * @todo document
+ */
function doTestDoubleBytes( $head, $tail ) {
for( $first = 0xc0; $first < 0x100; $first++ ) {
for( $second = 0x80; $second < 0x100; $second++ ) {
}
}
+ /** @todo document */
function testTripleBytes() {
$this->doTestTripleBytes( '', '' );
$this->doTestTripleBytes( 'x', '' );
$this->doTestTripleBytes( '', 'x' );
$this->doTestTripleBytes( 'x', 'x' );
}
-
+
+ /** @todo document */
function doTestTripleBytes( $head, $tail ) {
for( $first = 0xc0; $first < 0x100; $first++ ) {
for( $second = 0x80; $second < 0x100; $second++ ) {
}
}
}
-
+
+ /** @todo document */
function testChunkRegression() {
# Check for regression against a chunking bug
$text = "\x46\x55\xb8" .
bin2hex( UtfNormal::cleanUp( $text ) ) );
}
+ /** @todo document */
function testInterposeRegression() {
$text = "\x4e\x30" .
"\xb1" . # bad tail
bin2hex( $expect ),
bin2hex( UtfNormal::cleanUp( $text ) ) );
}
-
+
+ /** @todo document */
function testOverlongRegression() {
$text = "\x67" .
"\x1a" . # forbidden ascii
bin2hex( $expect ),
bin2hex( UtfNormal::cleanUp( $text ) ) );
}
-
+
+ /** @todo document */
function testSurrogateRegression() {
$text = "\xed\xb4\x96" . # surrogate 0xDD16
"\x83" . # bad tail
bin2hex( $expect ),
bin2hex( UtfNormal::cleanUp( $text ) ) );
}
-
+
+ /** @todo document */
function testBomRegression() {
$text = "\xef\xbf\xbe" . # U+FFFE, illegal char
"\xb2" . # bad tail
bin2hex( UtfNormal::cleanUp( $text ) ) );
}
+ /** @todo document */
function testForbiddenRegression() {
$text = "\xef\xbf\xbf"; # U+FFFF, illegal char
$expect = "\xef\xbf\xbd";
bin2hex( $expect ),
bin2hex( UtfNormal::cleanUp( $text ) ) );
}
-
+
+ /** @todo document */
function testHangulRegression() {
$text = "\xed\x9c\xaf" . # Hangul char
"\xe1\x87\x81"; # followed by another final jamo