<?php
+# Copyright (C) 2004 Brion Vibber <brion@pobox.com>
+# http://www.mediawiki.org/
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License along
+# with this program; if not, write to the Free Software Foundation, Inc.,
+# 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
+# http://www.gnu.org/copyleft/gpl.html
+
+
+if( php_sapi_name() != 'cli' ) {
+ die( "Run me from the command line please.\n" );
+}
+
/** */
if( isset( $_SERVER['argv'] ) && in_array( '--icu', $_SERVER['argv'] ) ) {
dl( 'php_utfnormal.so' );
#ini_set( 'memory_limit', '40M' );
-require_once( 'PHPUnit.php' );
-require_once( 'UtfNormal.php' );
+require_once 'PHPUnit/Framework.php';
+require_once 'PHPUnit/TextUI/TestRunner.php';
-class CleanUpTest extends PHPUnit_TestCase {
- function CleanUpTest( $name ) {
- $this->PHPUnit_TestCase( $name );
- }
+require_once 'UtfNormal.php';
+/**
+ * Additional tests for UtfNormal::cleanUp() function, inclusion
+ * regression checks for known problems.
+ * Requires PHPUnit.
+ *
+ * @ingroup UtfNormal
+ * @private
+ */
+class CleanUpTest extends PHPUnit_Framework_TestCase {
+ /** @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, $utfCanonicalDecomp;
"U+$x should be decomposed" );
} else {
$this->assertEquals(
- bin2hex( $char ),
+ bin2hex( $char ),
bin2hex( $clean ),
"U+$x should be intact" );
}
}
}
}
-
+
+ /** @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;
$i == 0x000d ||
($i > 0x001f && $i < 0x80) ) {
$this->assertEquals(
- bin2hex( $char ),
+ bin2hex( $char ),
bin2hex( $clean ),
"ASCII byte $x should be intact" );
if( $char != $clean ) return;
}
}
}
-
+
+ /** @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++ ) {
$second < 0xc0 ) {
$norm = UtfNormal::NFC( $char );
$this->assertEquals(
- bin2hex( $norm ),
+ bin2hex( $norm ),
bin2hex( $clean ),
"Pair $x should be intact" );
if( $norm != $clean ) return;
}
}
+ /** @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++ ) {
$third < 0xc0 ) {
if( $first == 0xe0 && $second < 0xa0 ) {
$this->assertEquals(
- bin2hex( $head . UTF8_REPLACEMENT . $tail ),
+ bin2hex( $head . UTF8_REPLACEMENT . $tail ),
bin2hex( $clean ),
"Overlong triplet $x should be rejected" );
- } elseif( $first == 0xed &&
+ } elseif( $first == 0xed &&
( chr( $first ) . chr( $second ) . chr( $third )) >= UTF8_SURROGATE_FIRST ) {
$this->assertEquals(
- bin2hex( $head . UTF8_REPLACEMENT . $tail ),
+ bin2hex( $head . UTF8_REPLACEMENT . $tail ),
bin2hex( $clean ),
"Surrogate triplet $x should be rejected" );
} else {
$this->assertEquals(
- bin2hex( UtfNormal::NFC( $char ) ),
+ bin2hex( UtfNormal::NFC( $char ) ),
bin2hex( $clean ),
"Triplet $x should be intact" );
}
bin2hex( $head . UTF8_REPLACEMENT . UTF8_REPLACEMENT . UTF8_REPLACEMENT . $tail ),
bin2hex( $clean ),
"Forbidden triplet $x should be rejected" );
- } elseif( $second < 0xc0 && $second < 0xc0 ) {
+ } elseif( $first > 0xc2 && $second < 0xc0 && $third < 0xc0 ) {
$this->assertEquals(
bin2hex( $head . UTF8_REPLACEMENT . $tail ),
bin2hex( $clean ),
}
}
}
-
+
+ /** @todo document */
function testChunkRegression() {
# Check for regression against a chunking bug
$text = "\x46\x55\xb8" .
- "\xdc\x96" .
+ "\xdc\x96" .
"\xee" .
"\xe7" .
"\x44" .
"\xaa" .
"\x2f\x25";
$expect = "\x46\x55\xef\xbf\xbd" .
- "\xdc\x96" .
+ "\xdc\x96" .
"\xef\xbf\xbd" .
"\xef\xbf\xbd" .
"\x44" .
bin2hex( UtfNormal::cleanUp( $text ) ) );
}
+ /** @todo document */
function testInterposeRegression() {
$text = "\x4e\x30" .
"\xb1" . # bad tail
"\xad" . # bad tail
"\x7d" .
"\xd9\x95";
-
+
$expect = "\x4e\x30" .
"\xef\xbf\xbd" .
"\x3a" .
"\xef\xbf\xbd" .
"\x7d" .
"\xd9\x95";
-
+
+ $this->assertEquals(
+ bin2hex( $expect ),
+ bin2hex( UtfNormal::cleanUp( $text ) ) );
+ }
+
+ /** @todo document */
+ function testOverlongRegression() {
+ $text = "\x67" .
+ "\x1a" . # forbidden ascii
+ "\xea" . # bad head
+ "\xc1\xa6" . # overlong sequence
+ "\xad" . # bad tail
+ "\x1c" . # forbidden ascii
+ "\xb0" . # bad tail
+ "\x3c" .
+ "\x9e"; # bad tail
+ $expect = "\x67" .
+ "\xef\xbf\xbd" .
+ "\xef\xbf\xbd" .
+ "\xef\xbf\xbd" .
+ "\xef\xbf\xbd" .
+ "\xef\xbf\xbd" .
+ "\xef\xbf\xbd" .
+ "\x3c" .
+ "\xef\xbf\xbd";
+ $this->assertEquals(
+ bin2hex( $expect ),
+ bin2hex( UtfNormal::cleanUp( $text ) ) );
+ }
+
+ /** @todo document */
+ function testSurrogateRegression() {
+ $text = "\xed\xb4\x96" . # surrogate 0xDD16
+ "\x83" . # bad tail
+ "\xb4" . # bad tail
+ "\xac"; # bad head
+ $expect = "\xef\xbf\xbd" .
+ "\xef\xbf\xbd" .
+ "\xef\xbf\xbd" .
+ "\xef\xbf\xbd";
+ $this->assertEquals(
+ bin2hex( $expect ),
+ bin2hex( UtfNormal::cleanUp( $text ) ) );
+ }
+
+ /** @todo document */
+ function testBomRegression() {
+ $text = "\xef\xbf\xbe" . # U+FFFE, illegal char
+ "\xb2" . # bad tail
+ "\xef" . # bad head
+ "\x59";
+ $expect = "\xef\xbf\xbd" .
+ "\xef\xbf\xbd" .
+ "\xef\xbf\xbd" .
+ "\x59";
+ $this->assertEquals(
+ bin2hex( $expect ),
+ bin2hex( UtfNormal::cleanUp( $text ) ) );
+ }
+
+ /** @todo document */
+ function testForbiddenRegression() {
+ $text = "\xef\xbf\xbf"; # U+FFFF, illegal char
+ $expect = "\xef\xbf\xbd";
+ $this->assertEquals(
+ bin2hex( $expect ),
+ bin2hex( UtfNormal::cleanUp( $text ) ) );
+ }
+
+ /** @todo document */
+ function testHangulRegression() {
+ $text = "\xed\x9c\xaf" . # Hangul char
+ "\xe1\x87\x81"; # followed by another final jamo
+ $expect = $text; # Should *not* change.
$this->assertEquals(
bin2hex( $expect ),
bin2hex( UtfNormal::cleanUp( $text ) ) );
}
-$suite =& new PHPUnit_TestSuite( 'CleanUpTest' );
-$result = PHPUnit::run( $suite );
-echo $result->toString();
+$suite = new PHPUnit_Framework_TestSuite( 'CleanUpTest' );
+$result = PHPUnit_TextUI_TestRunner::run( $suite );
-?>
\ No newline at end of file
+if( !$result->wasSuccessful() ) {
+ exit( -1 );
+}
+exit( 0 );