2 # Copyright (C) 2004 Brion Vibber <brion@pobox.com>
3 # http://www.mediawiki.org/
5 # This program is free software; you can redistribute it and/or modify
6 # it under the terms of the GNU General Public License as published by
7 # the Free Software Foundation; either version 2 of the License, or
8 # (at your option) any later version.
10 # This program is distributed in the hope that it will be useful,
11 # but WITHOUT ANY WARRANTY; without even the implied warranty of
12 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
13 # GNU General Public License for more details.
15 # You should have received a copy of the GNU General Public License along
16 # with this program; if not, write to the Free Software Foundation, Inc.,
17 # 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
18 # http://www.gnu.org/copyleft/gpl.html
21 if( php_sapi_name() != 'cli' ) {
22 die( "Run me from the command line please.\n" );
26 if( isset( $_SERVER['argv'] ) && in_array( '--icu', $_SERVER['argv'] ) ) {
27 dl( 'php_utfnormal.so' );
30 #ini_set( 'memory_limit', '40M' );
32 require_once 'PHPUnit/Framework.php';
33 require_once 'PHPUnit/TextUI/TestRunner.php';
35 require_once 'UtfNormal.php';
38 * Additional tests for UtfNormal::cleanUp() function, inclusion
39 * regression checks for known problems.
45 class CleanUpTest
extends PHPUnit_Framework_TestCase
{
55 function testAscii() {
56 $text = 'This is plain ASCII text.';
57 $this->assertEquals( $text, UtfNormal
::cleanUp( $text ) );
62 $text = "a \x00 null";
63 $expect = "a \xef\xbf\xbd null";
66 bin2hex( UtfNormal
::cleanUp( $text ) ) );
70 function testLatin() {
71 $text = "L'\xc3\xa9cole";
72 $this->assertEquals( $text, UtfNormal
::cleanUp( $text ) );
76 function testLatinNormal() {
77 $text = "L'e\xcc\x81cole";
78 $expect = "L'\xc3\xa9cole";
79 $this->assertEquals( $expect, UtfNormal
::cleanUp( $text ) );
83 * This test is *very* expensive!
86 function XtestAllChars() {
87 $rep = UTF8_REPLACEMENT
;
88 for( $i = 0x0; $i < UNICODE_MAX
; $i++
) {
89 $char = codepointToUtf8( $i );
90 $clean = UtfNormal
::cleanUp( $char );
91 $x = sprintf( "%04X", $i );
92 if( $i %
0x1000 == 0 ) echo "U+$x\n";
96 ($i > 0x001f && $i < UNICODE_SURROGATE_FIRST
) ||
97 ($i > UNICODE_SURROGATE_LAST
&& $i < 0xfffe ) ||
98 ($i > 0xffff && $i <= UNICODE_MAX
) ) {
99 if( isset( UtfNormal
::$utfCanonicalComp[$char] ) ||
isset( UtfNormal
::$utfCanonicalDecomp[$char] ) ) {
100 $comp = UtfNormal
::NFC( $char );
104 "U+$x should be decomposed" );
109 "U+$x should be intact" );
112 $this->assertEquals( bin2hex( $rep ), bin2hex( $clean ), $x );
117 /** @todo document */
118 function testAllBytes() {
119 $this->doTestBytes( '', '' );
120 $this->doTestBytes( 'x', '' );
121 $this->doTestBytes( '', 'x' );
122 $this->doTestBytes( 'x', 'x' );
125 /** @todo document */
126 function doTestBytes( $head, $tail ) {
127 for( $i = 0x0; $i < 256; $i++
) {
128 $char = $head . chr( $i ) . $tail;
129 $clean = UtfNormal
::cleanUp( $char );
130 $x = sprintf( "%02X", $i );
134 ($i > 0x001f && $i < 0x80) ) {
138 "ASCII byte $x should be intact" );
139 if( $char != $clean ) return;
141 $norm = $head . UTF8_REPLACEMENT
. $tail;
145 "Forbidden byte $x should be rejected" );
146 if( $norm != $clean ) return;
151 /** @todo document */
152 function testDoubleBytes() {
153 $this->doTestDoubleBytes( '', '' );
154 $this->doTestDoubleBytes( 'x', '' );
155 $this->doTestDoubleBytes( '', 'x' );
156 $this->doTestDoubleBytes( 'x', 'x' );
162 function doTestDoubleBytes( $head, $tail ) {
163 for( $first = 0xc0; $first < 0x100; $first++
) {
164 for( $second = 0x80; $second < 0x100; $second++
) {
165 $char = $head . chr( $first ) . chr( $second ) . $tail;
166 $clean = UtfNormal
::cleanUp( $char );
167 $x = sprintf( "%02X,%02X", $first, $second );
171 $norm = UtfNormal
::NFC( $char );
175 "Pair $x should be intact" );
176 if( $norm != $clean ) return;
177 } elseif( $first > 0xfd ||
$second > 0xbf ) {
178 # fe and ff are not legal head bytes -- expect two replacement chars
179 $norm = $head . UTF8_REPLACEMENT
. UTF8_REPLACEMENT
. $tail;
183 "Forbidden pair $x should be rejected" );
184 if( $norm != $clean ) return;
186 $norm = $head . UTF8_REPLACEMENT
. $tail;
190 "Forbidden pair $x should be rejected" );
191 if( $norm != $clean ) return;
197 /** @todo document */
198 function testTripleBytes() {
199 $this->doTestTripleBytes( '', '' );
200 $this->doTestTripleBytes( 'x', '' );
201 $this->doTestTripleBytes( '', 'x' );
202 $this->doTestTripleBytes( 'x', 'x' );
205 /** @todo document */
206 function doTestTripleBytes( $head, $tail ) {
207 for( $first = 0xc0; $first < 0x100; $first++
) {
208 for( $second = 0x80; $second < 0x100; $second++
) {
209 #for( $third = 0x80; $third < 0x100; $third++ ) {
210 for( $third = 0x80; $third < 0x81; $third++
) {
211 $char = $head . chr( $first ) . chr( $second ) . chr( $third ) . $tail;
212 $clean = UtfNormal
::cleanUp( $char );
213 $x = sprintf( "%02X,%02X,%02X", $first, $second, $third );
214 if( $first >= 0xe0 &&
218 if( $first == 0xe0 && $second < 0xa0 ) {
220 bin2hex( $head . UTF8_REPLACEMENT
. $tail ),
222 "Overlong triplet $x should be rejected" );
223 } elseif( $first == 0xed &&
224 ( chr( $first ) . chr( $second ) . chr( $third )) >= UTF8_SURROGATE_FIRST
) {
226 bin2hex( $head . UTF8_REPLACEMENT
. $tail ),
228 "Surrogate triplet $x should be rejected" );
231 bin2hex( UtfNormal
::NFC( $char ) ),
233 "Triplet $x should be intact" );
235 } elseif( $first > 0xc1 && $first < 0xe0 && $second < 0xc0 ) {
237 bin2hex( UtfNormal
::NFC( $head . chr( $first ) . chr( $second ) ) . UTF8_REPLACEMENT
. $tail ),
239 "Valid 2-byte $x + broken tail" );
240 } elseif( $second > 0xc1 && $second < 0xe0 && $third < 0xc0 ) {
242 bin2hex( $head . UTF8_REPLACEMENT
. UtfNormal
::NFC( chr( $second ) . chr( $third ) . $tail ) ),
244 "Broken head + valid 2-byte $x" );
245 } elseif( ( $first > 0xfd ||
$second > 0xfd ) &&
246 ( ( $second > 0xbf && $third > 0xbf ) ||
247 ( $second < 0xc0 && $third < 0xc0 ) ||
248 ( $second > 0xfd ) ||
249 ( $third > 0xfd ) ) ) {
250 # fe and ff are not legal head bytes -- expect three replacement chars
252 bin2hex( $head . UTF8_REPLACEMENT
. UTF8_REPLACEMENT
. UTF8_REPLACEMENT
. $tail ),
254 "Forbidden triplet $x should be rejected" );
255 } elseif( $first > 0xc2 && $second < 0xc0 && $third < 0xc0 ) {
257 bin2hex( $head . UTF8_REPLACEMENT
. $tail ),
259 "Forbidden triplet $x should be rejected" );
262 bin2hex( $head . UTF8_REPLACEMENT
. UTF8_REPLACEMENT
. $tail ),
264 "Forbidden triplet $x should be rejected" );
271 /** @todo document */
272 function testChunkRegression() {
273 # Check for regression against a chunking bug
274 $text = "\x46\x55\xb8" .
281 $expect = "\x46\x55\xef\xbf\xbd" .
291 bin2hex( UtfNormal
::cleanUp( $text ) ) );
294 /** @todo document */
295 function testInterposeRegression() {
310 $expect = "\x4e\x30" .
326 bin2hex( UtfNormal
::cleanUp( $text ) ) );
329 /** @todo document */
330 function testOverlongRegression() {
332 "\x1a" . # forbidden ascii
334 "\xc1\xa6" . # overlong sequence
336 "\x1c" . # forbidden ascii
351 bin2hex( UtfNormal
::cleanUp( $text ) ) );
354 /** @todo document */
355 function testSurrogateRegression() {
356 $text = "\xed\xb4\x96" . # surrogate 0xDD16
360 $expect = "\xef\xbf\xbd" .
366 bin2hex( UtfNormal
::cleanUp( $text ) ) );
369 /** @todo document */
370 function testBomRegression() {
371 $text = "\xef\xbf\xbe" . # U+FFFE, illegal char
375 $expect = "\xef\xbf\xbd" .
381 bin2hex( UtfNormal
::cleanUp( $text ) ) );
384 /** @todo document */
385 function testForbiddenRegression() {
386 $text = "\xef\xbf\xbf"; # U+FFFF, illegal char
387 $expect = "\xef\xbf\xbd";
390 bin2hex( UtfNormal
::cleanUp( $text ) ) );
393 /** @todo document */
394 function testHangulRegression() {
395 $text = "\xed\x9c\xaf" . # Hangul char
396 "\xe1\x87\x81"; # followed by another final jamo
397 $expect = $text; # Should *not* change.
400 bin2hex( UtfNormal
::cleanUp( $text ) ) );
405 $suite = new PHPUnit_Framework_TestSuite( 'CleanUpTest' );
406 $result = PHPUnit_TextUI_TestRunner
::run( $suite );
408 if( !$result->wasSuccessful() ) {