makary/phpbb
1
0
Fork 0
mirror of https://github.com/phpbb/phpbb.git synced 2025-06-29 14:48:53 +00:00
Code Issues Projects Releases Packages Wiki Activity

let's remove 350+ impossible entries

Browse source 
git-svn-id: file:///svn/phpbb/trunk@7908 89ea8834-ac86-4346-8a33-228a782c2dd0
This commit is contained in:
David M 2007-07-19 20:38:08 +00:00
parent e9b908174c
commit 870991c060
2 changed files with 18 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

18
phpBB/develop/generate_utf_confusables.php
View file

@ -30,15 +30,22 @@ $phpEx = substr(strrchr(__FILE__, '.'), 1);
echo "Checking for required files\n"; echo "Checking for required files\n";
download('http://unicode.org/reports/tr39/data/confusables.txt'); download('http://unicode.org/reports/tr39/data/confusables.txt');
download('http://unicode.org/Public/UNIDATA/CaseFolding.txt');
echo "\n"; echo "\n";
/** /**
* Load the CaseFolding table * Load the confusables table
*/ */
echo "Loading confusables\n"; echo "Loading confusables\n";
$unidata = file_get_contents('confusables.txt'); $unidata = file_get_contents('confusables.txt');
/**
* Load the CaseFolding table
*/
echo "Loading CaseFolding\n";
$casefolds = file_get_contents('CaseFolding.txt');
function utf8_chr($cp) function utf8_chr($cp)
{ {
@ -61,6 +68,7 @@ function utf8_chr($cp)
} }
preg_match_all('/^([0-9A-F]+) ;\s((?:[0-9A-F]+ )*);.*?$/im', $unidata, $array, PREG_SET_ORDER); preg_match_all('/^([0-9A-F]+) ;\s((?:[0-9A-F]+ )*);.*?$/im', $unidata, $array, PREG_SET_ORDER);
preg_match_all('/^([0-9A-F]+); ([CFS]); ([0-9A-F]+(?: [0-9A-F]+)*);/im', $casefolds, $casefold_array);
// some that we defined ourselves // some that we defined ourselves
$uniarray = array( $uniarray = array(
@ -136,6 +144,14 @@ foreach ($array as $value)
$temp_hold = str_replace(utf8_chr(0x0031), utf8_chr(0x006C), $temp_hold); $temp_hold = str_replace(utf8_chr(0x0031), utf8_chr(0x006C), $temp_hold);
} }
} }
// uppercased chars that were folded do not exist in this universe,
// no amount of normalization could ever "trick" this into not working
if (in_array($value[1], $casefold_array[1]))
{
continue;
}
$uniarray[utf8_chr(hexdec((string)$value[1]))] = $temp_hold; $uniarray[utf8_chr(hexdec((string)$value[1]))] = $temp_hold;
} }

2
phpBB/includes/utf/data/confusables.php
View file

File diff suppressed because one or more lines are too long