2# Copyright (C) 2004 Brion Vibber <brion@pobox.com> 
    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. 
   28#define( 'PRETTY_UTF8', true ); 
   30if (defined(
'PRETTY_UTF8')) {
 
   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');
 
   61require_once 
'include/Unicode/UtfNormal.php';
 
   63if (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";
 
   82while (
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";
 
  123while (
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";
 
  191    #$result = ($a === $b); 
  192    $result = (strcmp($a, $b) == 0);
 
  198        print "  $ok $form c$col '$aa' $eq '$bb'\n";
 
verbosify($a, $b, $col, $form, $verbose)
if(php_sapi_name() !='cli') $in
testNFC(&$u, $c, $comment, $verbose)
testNormals(&$u, $c, $comment, $reportFailure=false)
testCleanUp(&$u, $c, $comment, $verbose)
testNFKC(&$u, $c, $comment, $verbose)
testNFD(&$u, $c, $comment, $verbose)
testNFKD(&$u, $c, $comment, $verbose)
testInvariant(&$u, $char, $desc, $reportFailure=false)
reportResults(&$total, &$success, &$failure)
codepointToUtf8($codepoint)
Return UTF-8 sequence for a given Unicode code point.
utf8ToCodepoint($char)
Determine the Unicode codepoint of a single-character UTF-8 sequence.
const UTF8_SURROGATE_FIRST
const UTF8_SURROGATE_LAST
An exception for terminatinating execution or to throw for unit testing.
if(isset($_POST['submit'])) $form
if((!isset($_SERVER['DOCUMENT_ROOT'])) OR(empty($_SERVER['DOCUMENT_ROOT']))) $_SERVER['DOCUMENT_ROOT']