3 * Tests for UtfNormal::cleanUp() function.
5 * Copyright © 2004 Brion Vibber <brion@pobox.com>
6 * https://www.mediawiki.org/
8 * This program is free software; you can redistribute it and/or modify
9 * it under the terms of the GNU General Public License as published by
10 * the Free Software Foundation; either version 2 of the License, or
11 * (at your option) any later version.
13 * This program is distributed in the hope that it will be useful,
14 * but WITHOUT ANY WARRANTY; without even the implied warranty of
15 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
16 * GNU General Public License for more details.
18 * You should have received a copy of the GNU General Public License along
19 * with this program; if not, write to the Free Software Foundation, Inc.,
20 * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
21 * http://www.gnu.org/copyleft/gpl.html
27 * Additional tests for UtfNormal::cleanUp() function, inclusion
28 * regression checks for known problems.
34 * @todo covers tags, will be UtfNormal::cleanUp once the below is resolved
35 * @todo split me into test methods and providers per the below comment
37 * We ignore code coverage for this test suite until they are rewritten
38 * to use data providers (bug 46561).
41 class CleanUpTest
extends MediaWikiTestCase
{
43 public function testAscii() {
44 $text = 'This is plain ASCII text.';
45 $this->assertEquals( $text, UtfNormal
::cleanUp( $text ) );
49 public function testNull() {
50 $text = "a \x00 null";
51 $expect = "a \xef\xbf\xbd null";
54 bin2hex( UtfNormal
::cleanUp( $text ) ) );
58 public function testLatin() {
59 $text = "L'\xc3\xa9cole";
60 $this->assertEquals( $text, UtfNormal
::cleanUp( $text ) );
64 public function testLatinNormal() {
65 $text = "L'e\xcc\x81cole";
66 $expect = "L'\xc3\xa9cole";
67 $this->assertEquals( $expect, UtfNormal
::cleanUp( $text ) );
71 * This test is *very* expensive!
74 function XtestAllChars() {
75 $rep = UTF8_REPLACEMENT
;
76 for ( $i = 0x0; $i < UNICODE_MAX
; $i++
) {
77 $char = codepointToUtf8( $i );
78 $clean = UtfNormal
::cleanUp( $char );
79 $x = sprintf( "%04X", $i );
81 if ( $i %
0x1000 == 0 ) {
88 ( $i > 0x001f && $i < UNICODE_SURROGATE_FIRST
) ||
89 ( $i > UNICODE_SURROGATE_LAST
&& $i < 0xfffe ) ||
90 ( $i > 0xffff && $i <= UNICODE_MAX
)
92 if ( isset( UtfNormal
::$utfCanonicalComp[$char] )
93 ||
isset( UtfNormal
::$utfCanonicalDecomp[$char] )
95 $comp = UtfNormal
::NFC( $char );
99 "U+$x should be decomposed" );
104 "U+$x should be intact" );
107 $this->assertEquals( bin2hex( $rep ), bin2hex( $clean ), $x );
112 /** @todo document */
113 public function testAllBytes() {
114 $this->doTestBytes( '', '' );
115 $this->doTestBytes( 'x', '' );
116 $this->doTestBytes( '', 'x' );
117 $this->doTestBytes( 'x', 'x' );
120 /** @todo document */
121 function doTestBytes( $head, $tail ) {
122 for ( $i = 0x0; $i < 256; $i++
) {
123 $char = $head . chr( $i ) . $tail;
124 $clean = UtfNormal
::cleanUp( $char );
125 $x = sprintf( "%02X", $i );
130 ( $i > 0x001f && $i < 0x80 )
135 "ASCII byte $x should be intact" );
136 if ( $char != $clean ) {
140 $norm = $head . UTF8_REPLACEMENT
. $tail;
144 "Forbidden byte $x should be rejected" );
145 if ( $norm != $clean ) {
152 /** @todo document */
153 public function testDoubleBytes() {
154 $this->doTestDoubleBytes( '', '' );
155 $this->doTestDoubleBytes( 'x', '' );
156 $this->doTestDoubleBytes( '', 'x' );
157 $this->doTestDoubleBytes( 'x', 'x' );
163 function doTestDoubleBytes( $head, $tail ) {
164 for ( $first = 0xc0; $first < 0x100; $first +
= 2 ) {
165 for ( $second = 0x80; $second < 0x100; $second +
= 2 ) {
166 $char = $head . chr( $first ) . chr( $second ) . $tail;
167 $clean = UtfNormal
::cleanUp( $char );
168 $x = sprintf( "%02X,%02X", $first, $second );
169 if ( $first > 0xc1 &&
173 $norm = UtfNormal
::NFC( $char );
177 "Pair $x should be intact" );
178 if ( $norm != $clean ) {
181 } elseif ( $first > 0xfd ||
$second > 0xbf ) {
182 # fe and ff are not legal head bytes -- expect two replacement chars
183 $norm = $head . UTF8_REPLACEMENT
. UTF8_REPLACEMENT
. $tail;
187 "Forbidden pair $x should be rejected" );
188 if ( $norm != $clean ) {
192 $norm = $head . UTF8_REPLACEMENT
. $tail;
196 "Forbidden pair $x should be rejected" );
197 if ( $norm != $clean ) {
205 /** @todo document */
206 public function testTripleBytes() {
207 $this->doTestTripleBytes( '', '' );
208 $this->doTestTripleBytes( 'x', '' );
209 $this->doTestTripleBytes( '', 'x' );
210 $this->doTestTripleBytes( 'x', 'x' );
213 /** @todo document */
214 function doTestTripleBytes( $head, $tail ) {
215 for ( $first = 0xc0; $first < 0x100; $first +
= 2 ) {
216 for ( $second = 0x80; $second < 0x100; $second +
= 2 ) {
217 #for( $third = 0x80; $third < 0x100; $third++ ) {
218 for ( $third = 0x80; $third < 0x81; $third++
) {
219 $char = $head . chr( $first ) . chr( $second ) . chr( $third ) . $tail;
220 $clean = UtfNormal
::cleanUp( $char );
221 $x = sprintf( "%02X,%02X,%02X", $first, $second, $third );
223 if ( $first >= 0xe0 &&
228 if ( $first == 0xe0 && $second < 0xa0 ) {
230 bin2hex( $head . UTF8_REPLACEMENT
. $tail ),
232 "Overlong triplet $x should be rejected" );
233 } elseif ( $first == 0xed &&
234 ( chr( $first ) . chr( $second ) . chr( $third ) ) >= UTF8_SURROGATE_FIRST
237 bin2hex( $head . UTF8_REPLACEMENT
. $tail ),
239 "Surrogate triplet $x should be rejected" );
242 bin2hex( UtfNormal
::NFC( $char ) ),
244 "Triplet $x should be intact" );
246 } elseif ( $first > 0xc1 && $first < 0xe0 && $second < 0xc0 ) {
248 bin2hex( UtfNormal
::NFC( $head . chr( $first ) .
249 chr( $second ) ) . UTF8_REPLACEMENT
. $tail ),
251 "Valid 2-byte $x + broken tail" );
252 } elseif ( $second > 0xc1 && $second < 0xe0 && $third < 0xc0 ) {
254 bin2hex( $head . UTF8_REPLACEMENT
.
255 UtfNormal
::NFC( chr( $second ) . chr( $third ) . $tail ) ),
257 "Broken head + valid 2-byte $x" );
258 } elseif ( ( $first > 0xfd ||
$second > 0xfd ) &&
259 ( ( $second > 0xbf && $third > 0xbf ) ||
260 ( $second < 0xc0 && $third < 0xc0 ) ||
261 ( $second > 0xfd ) ||
264 # fe and ff are not legal head bytes -- expect three replacement chars
266 bin2hex( $head . UTF8_REPLACEMENT
. UTF8_REPLACEMENT
. UTF8_REPLACEMENT
. $tail ),
268 "Forbidden triplet $x should be rejected" );
269 } elseif ( $first > 0xc2 && $second < 0xc0 && $third < 0xc0 ) {
271 bin2hex( $head . UTF8_REPLACEMENT
. $tail ),
273 "Forbidden triplet $x should be rejected" );
276 bin2hex( $head . UTF8_REPLACEMENT
. UTF8_REPLACEMENT
. $tail ),
278 "Forbidden triplet $x should be rejected" );
285 /** @todo document */
286 public function testChunkRegression() {
287 # Check for regression against a chunking bug
288 $text = "\x46\x55\xb8" .
295 $expect = "\x46\x55\xef\xbf\xbd" .
305 bin2hex( UtfNormal
::cleanUp( $text ) ) );
308 /** @todo document */
309 public function testInterposeRegression() {
324 $expect = "\x4e\x30" .
340 bin2hex( UtfNormal
::cleanUp( $text ) ) );
343 /** @todo document */
344 public function testOverlongRegression() {
346 "\x1a" . # forbidden ascii
348 "\xc1\xa6" . # overlong sequence
350 "\x1c" . # forbidden ascii
365 bin2hex( UtfNormal
::cleanUp( $text ) ) );
368 /** @todo document */
369 public function testSurrogateRegression() {
370 $text = "\xed\xb4\x96" . # surrogate 0xDD16
374 $expect = "\xef\xbf\xbd" .
380 bin2hex( UtfNormal
::cleanUp( $text ) ) );
383 /** @todo document */
384 public function testBomRegression() {
385 $text = "\xef\xbf\xbe" . # U+FFFE, illegal char
389 $expect = "\xef\xbf\xbd" .
395 bin2hex( UtfNormal
::cleanUp( $text ) ) );
398 /** @todo document */
399 public function testForbiddenRegression() {
400 $text = "\xef\xbf\xbf"; # U+FFFF, illegal char
401 $expect = "\xef\xbf\xbd";
404 bin2hex( UtfNormal
::cleanUp( $text ) ) );
407 /** @todo document */
408 public function testHangulRegression() {
409 $text = "\xed\x9c\xaf" . # Hangul char
410 "\xe1\x87\x81"; # followed by another final jamo
411 $expect = $text; # Should *not* change.
414 bin2hex( UtfNormal
::cleanUp( $text ) ) );