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 28 #define( 'PRETTY_UTF8', true ); 31 function pretty($string)
33 return preg_replace_callback(
36 return sprintf(
"%02X", ord($hit[1]));
45 function pretty($string)
47 return trim(preg_replace_callback(
58 dl(
'php_utfnormal.so');
61 require_once
'include/Unicode/UtfNormal.php';
63 if (php_sapi_name() !=
'cli') {
64 die(
"Run me from the command line please.\n");
67 $in = fopen(
"NormalizationTest.txt",
"rt");
69 print
"Couldn't open NormalizationTest.txt -- can't run tests.\n";
70 print
"If necessary, manually download this file. It can be obtained at\n";
71 print
"http://www.unicode.org/Public/UNIDATA/NormalizationTest.txt";
82 while (
false !== ($line = fgets(
$in))) {
88 if (preg_match(
'/@Part([\d])/',
$data, $matches)) {
89 if ($matches[1] > 0) {
92 print
"Part {$matches[1]}: $comment";
96 $columns = array_map(
"hexSequenceToUtf8", explode(
";",
$data));
105 # print "FAILED: $comment"; 115 $in = fopen(
"UnicodeData.txt",
"rt");
117 print
"Can't open UnicodeData.txt for reading.\n";
118 print
"If necessary, fetch this file from the internet:\n";
119 print
"http://www.unicode.org/Public/UNIDATA/UnicodeData.txt\n";
122 print
"Now testing invariants...\n";
123 while (
false !== ($line = fgets(
$in))) {
124 $cols = explode(
';', $line);
128 # Can't check NULL with the ICU plugin, as null bytes fail in C land. 129 # Skip other control characters, as we strip them for XML safety. 130 # Surrogates are illegal on their own or in UTF-8, ignore. 150 print
"TEST SUCCEEDED!\n";
153 print
"TEST FAILED!\n";
164 print
"$success tests successful ($percSucc%)\n";
165 print
"$failure tests failed ($percFail%)\n\n";
182 if ($verbose && !
$result && !$reportFailure) {
191 #$result = ($a === $b); 192 $result = (strcmp($a, $b) == 0);
198 print
" $ok $form c$col '$aa' $eq '$bb'\n";
261 $result =
verbosify($char, $u->toNFD($char), 1,
'NFD', $reportFailure) && $result;
262 $result =
verbosify($char, $u->toNFKC($char), 1,
'NFKC', $reportFailure) && $result;
263 $result =
verbosify($char, $u->toNFKD($char), 1,
'NFKD', $reportFailure) && $result;
264 $result =
verbosify($char, $u->cleanUp($char), 1,
'cleanUp', $reportFailure) && $result;
266 if ($verbose && !$result && !$reportFailure) {
utf8ToCodepoint($char)
Determine the Unicode codepoint of a single-character UTF-8 sequence.
testNFD(&$u, $c, $comment, $verbose)
if((!isset($_SERVER['DOCUMENT_ROOT'])) OR(empty($_SERVER['DOCUMENT_ROOT']))) $_SERVER['DOCUMENT_ROOT']
const UTF8_SURROGATE_FIRST
testInvariant(&$u, $char, $desc, $reportFailure=false)
testNormals(&$u, $c, $comment, $reportFailure=false)
testNFKC(&$u, $c, $comment, $verbose)
testNFC(&$u, $c, $comment, $verbose)
verbosify($a, $b, $col, $form, $verbose)
if(isset($_POST['submit'])) $form
reportResults(&$total, &$success, &$failure)
Create styles array
The data for the language used.
testNFKD(&$u, $c, $comment, $verbose)
if(php_sapi_name() !='cli') $in
const UTF8_SURROGATE_LAST
codepointToUtf8($codepoint)
Return UTF-8 sequence for a given Unicode code point.
defined( 'APPLICATION_ENV')||define( 'APPLICATION_ENV'
testCleanUp(&$u, $c, $comment, $verbose)