mirror of
https://github.com/phpbb/phpbb.git
synced 2025-06-29 06:38:52 +00:00
- search result extract shouldn't end in the middle of a multibyte character [Bug #11863]
- missing localisation for an imageset shouldn't create lots of "imageset refreshed" log messages [Bug #12027] - explain that themes which need parsing cannot be stored on the filesystem [Bug #11134] - normalize usernames (we really need to make sure we normalize everything) - improved utf8_clean_string, more complete list of homographs and NFKC normalization, also the resulting string is now trimmed - corrected searching subforums explanation [Bug #12209] git-svn-id: file:///svn/phpbb/trunk@7890 89ea8834-ac86-4346-8a33-228a782c2dd0
This commit is contained in:
Nils Adermann
parent
f27fa04b8c
commit
909e195a9b
14 changed files with 406 additions and 182 deletions
211
phpBB/develop/generate_utf_confusables.php
Normal file
211
phpBB/develop/generate_utf_confusables.php
Normal file
|
|
@ -0,0 +1,211 @@
|
|||
<?php
|
||||
/**
|
||||
*
|
||||
* @package phpBB3
|
||||
* @version $Id$
|
||||
* @copyright (c) 2005 phpBB Group
|
||||
* @license http://opensource.org/licenses/gpl-license.php GNU Public License
|
||||
*
|
||||
*/
|
||||
|
||||
if (php_sapi_name() != 'cli')
|
||||
{
|
||||
die("This program must be run from the command line.\n");
|
||||
}
|
||||
|
||||
//
|
||||
// Security message:
|
||||
//
|
||||
// This script is potentially dangerous.
|
||||
// Remove or comment the next line (die(".... ) to enable this script.
|
||||
// Do NOT FORGET to either remove this script or disable it after you have used it.
|
||||
//
|
||||
die("Please read the first lines of this script for instructions on how to enable it");
|
||||
|
||||
set_time_limit(0);
|
||||
|
||||
define('IN_PHPBB', true);
|
||||
$phpbb_root_path = '../';
|
||||
$phpEx = substr(strrchr(__FILE__, '.'), 1);
|
||||
|
||||
echo "Checking for required files\n";
|
||||
download('http://unicode.org/reports/tr39/data/confusables.txt');
|
||||
echo "\n";
|
||||
|
||||
|
||||
/**
|
||||
* Load the CaseFolding table
|
||||
*/
|
||||
echo "Loading confusables\n";
|
||||
$unidata = file_get_contents('confusables.txt');
|
||||
|
||||
|
||||
function utf8_chr($cp)
|
||||
{
|
||||
if ($cp > 0xFFFF)
|
||||
{
|
||||
return chr(0xF0 | ($cp >> 18)) . chr(0x80 | (($cp >> 12) & 0x3F)) . chr(0x80 | (($cp >> 6) & 0x3F)) . chr(0x80 | ($cp & 0x3F));
|
||||
}
|
||||
else if ($cp > 0x7FF)
|
||||
{
|
||||
return chr(0xE0 | ($cp >> 12)) . chr(0x80 | (($cp >> 6) & 0x3F)) . chr(0x80 | ($cp & 0x3F));
|
||||
}
|
||||
else if ($cp > 0x7F)
|
||||
{
|
||||
return chr(0xC0 | ($cp >> 6)) . chr(0x80 | ($cp & 0x3F));
|
||||
}
|
||||
else
|
||||
{
|
||||
return chr($cp);
|
||||
}
|
||||
}
|
||||
|
||||
preg_match_all('/^([0-9A-F]+) ;\s((?:[0-9A-F]+ )*);/im', $unidata, $array, PREG_SET_ORDER);
|
||||
|
||||
// some that we defined ourselves
|
||||
$uniarray = array(
|
||||
"\xC2\xA1" => "\x69", // EXCLAMATION MARK, INVERTED => LATIN SMALL LETTER I
|
||||
"\xC7\x83" => "\x21", // LATIN LETTER RETROFLEX CLICK => EXCLAMATION MARK
|
||||
"\xCE\xB1" => "\x61", // GREEK SMALL LETTER ALPHA => LATIN SMALL LETTER A
|
||||
"\xE1\x9A\x80" => "\x20", // OGHAM SPACE MARK
|
||||
|
||||
"\xC2\xAD" => '', // HYPHEN, SOFT => empty string
|
||||
"\xDB\x9D" => '', // ARABIC END OF AYAH
|
||||
"\xDC\x8F" => '', // SYRIAC ABBREVIATION MARK
|
||||
"\xE1\xA0\x86" => '', // MONGOLIAN TODO SOFT HYPHEN
|
||||
"\xE1\xA0\x8E" => '', // MONGOLIAN VOWEL SEPARATOR
|
||||
"\xE2\x80\x8B" => '', // ZERO WIDTH SPACE
|
||||
"\xE2\x80\x8C" => '', // ZERO WIDTH NON-JOINER
|
||||
"\xE2\x80\x8D" => '', // ZERO WIDTH JOINER
|
||||
"\xE2\x80\xA8" => '', // LINE SEPARATOR
|
||||
"\xE2\x80\xA9" => '', // PARAGRAPH SEPARATOR
|
||||
"\xE2\x81\xA0" => '', // WORD JOINER
|
||||
"\xE2\x81\xA1" => '', // FUNCTION APPLICATION
|
||||
"\xE2\x81\xA2" => '', // INVISIBLE TIMES
|
||||
"\xE2\x81\xA3" => '', // INVISIBLE SEPARATOR
|
||||
"\xE2\x81\xAA" => '', // [CONTROL CHARACTERS]
|
||||
"\xE2\x81\xAB" => '', // [CONTROL CHARACTERS]
|
||||
"\xE2\x81\xAC" => '', // [CONTROL CHARACTERS]
|
||||
"\xE2\x81\xAD" => '', // [CONTROL CHARACTERS]
|
||||
"\xE2\x81\xAE" => '', // [CONTROL CHARACTERS]
|
||||
"\xE2\x81\xAF" => '', // [CONTROL CHARACTERS]
|
||||
"\xEF\xBB\xBF" => '', // ZERO WIDTH NO-BREAK SPACE
|
||||
"\xEF\xBF\xB9" => '', // [CONTROL CHARACTERS]
|
||||
"\xEF\xBF\xBA" => '', // [CONTROL CHARACTERS]
|
||||
"\xEF\xBF\xBB" => '', // [CONTROL CHARACTERS]
|
||||
"\xEF\xBF\xBC" => '', // [CONTROL CHARACTERS]
|
||||
"\xF0\x9D\x85\xB3" => '', // [MUSICAL CONTROL CHARACTERS]
|
||||
"\xF0\x9D\x85\xB4" => '', // [MUSICAL CONTROL CHARACTERS]
|
||||
"\xF0\x9D\x85\xB5" => '', // [MUSICAL CONTROL CHARACTERS]
|
||||
"\xF0\x9D\x85\xB6" => '', // [MUSICAL CONTROL CHARACTERS]
|
||||
"\xF0\x9D\x85\xB7" => '', // [MUSICAL CONTROL CHARACTERS]
|
||||
"\xF0\x9D\x85\xB8" => '', // [MUSICAL CONTROL CHARACTERS]
|
||||
"\xF0\x9D\x85\xB9" => '', // [MUSICAL CONTROL CHARACTERS]
|
||||
"\xF0\x9D\x85\xBA" => '', // [MUSICAL CONTROL CHARACTERS]
|
||||
);
|
||||
|
||||
$copy = $uniarray;
|
||||
|
||||
foreach ($array as $value)
|
||||
{
|
||||
if (isset($copy[utf8_chr(hexdec((string)$value[1]))]))
|
||||
{
|
||||
$num = '';
|
||||
$string = utf8_chr(hexdec((string)$value[1]));
|
||||
for ($i = 0; $i < strlen($string); $i++)
|
||||
{
|
||||
$num .= '\x' . str_pad(base_convert(ord($string[$i]), 10, 16), 2, '0', STR_PAD_LEFT);
|
||||
}
|
||||
echo $num . "\n";
|
||||
if ($uniarray[$string] != implode(array_map('utf8_chr', array_map('hexdec', explode(' ', trim($value[2]))))))
|
||||
{
|
||||
echo " --> $string\n";
|
||||
echo " --> " . implode(array_map('utf8_chr', array_map('hexdec', explode(' ', trim($value[2]))))) . "\n";
|
||||
}
|
||||
}
|
||||
$uniarray[utf8_chr(hexdec((string)$value[1]))] = implode(array_map('utf8_chr', array_map('hexdec', explode(' ', trim($value[2])))));
|
||||
}
|
||||
|
||||
echo "Writing to confusables.$phpEx\n";
|
||||
|
||||
$fp = fopen($phpbb_root_path . 'includes/utf/data/confusables.' . $phpEx, 'wb');
|
||||
fwrite($fp, '<?php return ' . my_var_export($uniarray) . ';');
|
||||
fclose($fp);
|
||||
|
||||
/**
|
||||
* Return a parsable string representation of a variable
|
||||
*
|
||||
* This is function is limited to array/strings/integers
|
||||
*
|
||||
* @param mixed $var Variable
|
||||
* @return string PHP code representing the variable
|
||||
*/
|
||||
function my_var_export($var)
|
||||
{
|
||||
if (is_array($var))
|
||||
{
|
||||
$lines = array();
|
||||
|
||||
foreach ($var as $k => $v)
|
||||
{
|
||||
$lines[] = my_var_export($k) . '=>' . my_var_export($v);
|
||||
}
|
||||
|
||||
return 'array(' . implode(',', $lines) . ')';
|
||||
}
|
||||
else if (is_string($var))
|
||||
{
|
||||
return "'" . str_replace(array('\\', "'"), array('\\\\', "\\'"), $var) . "'";
|
||||
}
|
||||
else
|
||||
{
|
||||
return $var;
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Download a file to the develop/ dir
|
||||
*
|
||||
* @param string $url URL of the file to download
|
||||
* @return void
|
||||
*/
|
||||
function download($url)
|
||||
{
|
||||
global $phpbb_root_path;
|
||||
|
||||
if (file_exists($phpbb_root_path . 'develop/' . basename($url)))
|
||||
{
|
||||
return;
|
||||
}
|
||||
|
||||
echo 'Downloading from ', $url, ' ';
|
||||
|
||||
if (!$fpr = fopen($url, 'rb'))
|
||||
{
|
||||
die("Can't download from $url\nPlease download it yourself and put it in the develop/ dir, kthxbai");
|
||||
}
|
||||
|
||||
if (!$fpw = fopen($phpbb_root_path . 'develop/' . basename($url), 'wb'))
|
||||
{
|
||||
die("Can't open develop/" . basename($url) . " for output... please check your permissions or something");
|
||||
}
|
||||
|
||||
$i = 0;
|
||||
$chunk = 32768;
|
||||
$done = '';
|
||||
|
||||
while (!feof($fpr))
|
||||
{
|
||||
$i += fwrite($fpw, fread($fpr, $chunk));
|
||||
echo str_repeat("\x08", strlen($done));
|
||||
|
||||
$done = ($i >> 10) . ' KiB';
|
||||
echo $done;
|
||||
}
|
||||
fclose($fpr);
|
||||
fclose($fpw);
|
||||
|
||||
echo "\n";
|
||||
}
|
||||
|
||||
?>
|
||||
120
phpBB/develop/unicode_testing.php
Normal file
120
phpBB/develop/unicode_testing.php
Normal file
|
|
@ -0,0 +1,120 @@
|
|||
<?php
|
||||
//
|
||||
// This file provides some useful functions for debugging the unicode/UTF-8 library
|
||||
// It requires utf_tools.php to be loaded
|
||||
//
|
||||
die("Please read the first lines of this script for instructions on how to enable it");
|
||||
|
||||
if (!headers_sent())
|
||||
{
|
||||
header('Content-type: text/html; charset=UTF-8');
|
||||
}
|
||||
|
||||
/**
|
||||
* Converts unicode escape sequences (\u0123) into UTF-8 characters
|
||||
*
|
||||
* @param string A unicode sequence
|
||||
* @return string UTF-8 representation of the given unicode sequence
|
||||
*/
|
||||
function unicode_to_utf8($string)
|
||||
{
|
||||
$utf8 = '';
|
||||
$chars = array();
|
||||
for ($i = 0; $i < strlen($string); $i++)
|
||||
{
|
||||
if (isset($string[$i + 5]) && substr($string, $i, 2) == '\\u' && ctype_xdigit(substr($string, $i + 2, 4)))
|
||||
{
|
||||
$utf8 .= utf8_from_unicode(array(base_convert(substr($string, $i + 2, 4), 16, 10)));
|
||||
$i += 5;
|
||||
}
|
||||
else
|
||||
{
|
||||
$utf8 .= $string[$i];
|
||||
}
|
||||
}
|
||||
return $utf8;
|
||||
}
|
||||
|
||||
/**
|
||||
* Takes an array of ints representing the Unicode characters and returns
|
||||
* a UTF-8 string.
|
||||
*
|
||||
* @param array $array array of unicode code points representing a string
|
||||
* @return string UTF-8 character string
|
||||
*/
|
||||
function utf8_from_unicode($array)
|
||||
{
|
||||
$str = '';
|
||||
foreach ($array as $value)
|
||||
{
|
||||
$str .= utf8_chr($value);
|
||||
}
|
||||
return $str;
|
||||
}
|
||||
|
||||
/**
|
||||
* Converts a UTF-8 string to unicode code points
|
||||
*
|
||||
* @param string $text UTF-8 string
|
||||
* @return string Unicode code points
|
||||
*/
|
||||
function utf8_to_unicode($text)
|
||||
{
|
||||
return preg_replace_callback(
|
||||
'#[\\xC2-\\xF4][\\x80-\\xBF]?[\\x80-\\xBF]?[\\x80-\\xBF]#',
|
||||
'utf8_to_unicode_callback',
|
||||
preg_replace_callback(
|
||||
'#[\\x00-\\x7f]#',
|
||||
'utf8_to_unicode_callback',
|
||||
$text
|
||||
)
|
||||
);
|
||||
}
|
||||
|
||||
/**
|
||||
* Takes a UTF-8 char and replaces it with its unicode escape sequence. Attention, $m is an array
|
||||
*
|
||||
* @param array $m 0-based numerically indexed array passed by preg_replace_callback()
|
||||
* @return string A unicode escape sequence
|
||||
*/
|
||||
function utf8_to_unicode_callback($m)
|
||||
{
|
||||
return '\u' . str_pad(base_convert(utf8_ord($m[0]), 10, 16), 4, '0', STR_PAD_LEFT) . '';
|
||||
}
|
||||
|
||||
/**
|
||||
* A wrapper function for the normalizer which takes care of including the class if required and modifies the passed strings
|
||||
* to be in NFKC
|
||||
*
|
||||
* @param mixed $strings a string or an array of strings to normalize
|
||||
* @return mixed the normalized content, preserving array keys if array given.
|
||||
*/
|
||||
function utf8_normalize_nfkc($strings)
|
||||
{
|
||||
if (empty($strings))
|
||||
{
|
||||
return $strings;
|
||||
}
|
||||
|
||||
if (!class_exists('utf_normalizer'))
|
||||
{
|
||||
global $phpbb_root_path, $phpEx;
|
||||
include($phpbb_root_path . 'includes/utf/utf_normalizer.' . $phpEx);
|
||||
}
|
||||
|
||||
if (!is_array($strings))
|
||||
{
|
||||
utf_normalizer::nfkc($strings);
|
||||
}
|
||||
else if (is_array($strings))
|
||||
{
|
||||
foreach ($strings as $key => $string)
|
||||
{
|
||||
utf_normalizer::nfkc($strings[$key]);
|
||||
}
|
||||
}
|
||||
|
||||
return $strings;
|
||||
}
|
||||
|
||||
?>
|
||||
|
|
@ -242,7 +242,11 @@ p a {
|
|||
<li>[Fix] Do not display return to search link in prosilver if search is not allowed (Bug #11393)</li>
|
||||
<li>[Fix] Use global url validation for img bbcode tag (Bug #11935)</li>
|
||||
<li>[Fix] Added proper unicode support to style names (Bug #12165)</li>
|
||||
|
||||
<li>[Fix] Search result extract should not end in the middle of a multibyte character (Bug #11863)</li>
|
||||
<li>[Fix] Missing localisation for an imageset no longer triggers a lot of "imageset refreshed" log messages (Bug #12027)</li>
|
||||
<li>[Fix] Explain that themes which need parsing cannot be stored on the filesystem (Bug #11134)</li>
|
||||
<li>[Fix] Normalize usernames</li>
|
||||
<li>[Change] Improved utf8_clean_string with a more complete list of homographs and NFKC normalization</li>
|
||||
|
||||
</ul>
|
||||
|
||||
|
|
|
|||
|
|
@ -2051,6 +2051,18 @@ parse_css_file = {PARSE_CSS_FILE}
|
|||
$error[] = $user->lang['EDIT_' . strtoupper($mode) . '_STORED_DB'];
|
||||
$store_db = 1;
|
||||
}
|
||||
|
||||
// themes which have to be parsed have to go into db
|
||||
if ($mode == 'theme')
|
||||
{
|
||||
$cfg = parse_cfg_file("{$phpbb_root_path}styles/" . $style_row["{$mode}_path"] . "/theme/theme.cfg");
|
||||
|
||||
if (isset($cfg['parse_css_file']) && $cfg['parse_css_file'])
|
||||
{
|
||||
$error[] = $user->lang['EDIT_THEME_STORE_PARSED'];
|
||||
$store_db = 1;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if (!sizeof($error))
|
||||
|
|
|
|||
|
|
@ -2394,7 +2394,7 @@ function get_context($text, $words, $length = 400)
|
|||
{
|
||||
if (preg_match('#(?:[^\w]|^)(' . $word . ')(?:[^\w]|$)#i', $text, $match))
|
||||
{
|
||||
$pos = strpos($text, $match[1]);
|
||||
$pos = utf8_strpos($text, $match[1]);
|
||||
if ($pos !== false)
|
||||
{
|
||||
$word_indizes[] = $pos;
|
||||
|
|
@ -2417,21 +2417,21 @@ function get_context($text, $words, $length = 400)
|
|||
$final_text_index = -1;
|
||||
|
||||
// cycle through every character in the original text
|
||||
for ($i = $word_indizes[$word], $n = strlen($text); $i < $n; $i++)
|
||||
for ($i = $word_indizes[$word], $n = utf8_strlen($text); $i < $n; $i++)
|
||||
{
|
||||
// if the current position is the start of one of the words then append $sequence_length characters to the final text
|
||||
if (isset($word_indizes[$word]) && ($i == $word_indizes[$word]))
|
||||
{
|
||||
if ($final_text_index < $i - $sequence_length - 1)
|
||||
{
|
||||
$final_text .= '... ' . preg_replace('#^([^ ]*)#', '', substr($text, $i - $sequence_length, $sequence_length));
|
||||
$final_text .= '... ' . preg_replace('#^([^ ]*)#', '', utf8_substr($text, $i - $sequence_length, $sequence_length));
|
||||
}
|
||||
else
|
||||
{
|
||||
// if the final text is already nearer to the current word than $sequence_length we only append the text
|
||||
// from its current index on and distribute the unused length to all other sequenes
|
||||
$sequence_length += (int) (($final_text_index - $i + $sequence_length + 1) / (2 * $wordnum));
|
||||
$final_text .= substr($text, $final_text_index + 1, $i - $final_text_index - 1);
|
||||
$final_text .= utf8_substr($text, $final_text_index + 1, $i - $final_text_index - 1);
|
||||
}
|
||||
$final_text_index = $i - 1;
|
||||
|
||||
|
|
@ -2443,17 +2443,17 @@ function get_context($text, $words, $length = 400)
|
|||
if ($j > 0)
|
||||
{
|
||||
// add the character to the final text and increment the sequence counter
|
||||
$final_text .= $text[$i];
|
||||
$final_text .= utf8_substr($text, $i, 1);
|
||||
$final_text_index++;
|
||||
$j++;
|
||||
|
||||
// if this is a whitespace then check whether we are done with this sequence
|
||||
if ($text[$i] == ' ')
|
||||
if (utf8_substr($text, $i, 1) == ' ')
|
||||
{
|
||||
// only check whether we have to exit the context generation completely if we haven't already reached the end anyway
|
||||
if ($i + 4 < $n)
|
||||
{
|
||||
if (($j > $sequence_length && $word >= $wordnum) || strlen($final_text) > $length)
|
||||
if (($j > $sequence_length && $word >= $wordnum) || utf8_strlen($final_text) > $length)
|
||||
{
|
||||
$final_text .= ' ...';
|
||||
break;
|
||||
|
|
@ -2479,7 +2479,7 @@ function get_context($text, $words, $length = 400)
|
|||
|
||||
if (!sizeof($words) || !sizeof($word_indizes))
|
||||
{
|
||||
return (strlen($text) >= $length + 3) ? substr($text, 0, $length) . '...' : $text;
|
||||
return (utf8_strlen($text) >= $length + 3) ? utf8_substr($text, 0, $length) . '...' : $text;
|
||||
}
|
||||
}
|
||||
|
||||
|
|
|
|||
|
|
@ -1465,13 +1465,19 @@ class user extends session
|
|||
}
|
||||
}
|
||||
|
||||
if (sizeof($sql_ary))
|
||||
{
|
||||
$db->sql_multi_insert(STYLES_IMAGESET_DATA_TABLE, $sql_ary);
|
||||
|
||||
$db->sql_transaction('commit');
|
||||
|
||||
$cache->destroy('sql', STYLES_IMAGESET_DATA_TABLE);
|
||||
|
||||
add_log('admin', 'LOG_IMAGESET_REFRESHED', $this->theme['imageset_name'], $this->img_lang);
|
||||
add_log('admin', 'LOG_IMAGESET_LANG_REFRESHED', $this->theme['imageset_name'], $this->img_lang);
|
||||
}
|
||||
else
|
||||
{
|
||||
$db->sql_transaction('commit');
|
||||
add_log('admin', 'LOG_IMAGESET_LANG_MISSING', $this->theme['imageset_name'], $this->img_lang);
|
||||
}
|
||||
}
|
||||
|
||||
// If this function got called from the error handler we are finished here.
|
||||
|
|
|
|||
|
|
@ -36,7 +36,7 @@ class ucp_profile
|
|||
case 'reg_details':
|
||||
|
||||
$data = array(
|
||||
'username' => request_var('username', $user->data['username'], true),
|
||||
'username' => utf8_normalize_nfc(request_var('username', $user->data['username'], true)),
|
||||
'email' => strtolower(request_var('email', $user->data['user_email'])),
|
||||
'email_confirm' => strtolower(request_var('email_confirm', '')),
|
||||
'new_password' => request_var('new_password', '', true),
|
||||
|
|
|
|||
|
|
@ -142,7 +142,7 @@ class ucp_register
|
|||
}
|
||||
|
||||
$data = array(
|
||||
'username' => request_var('username', '', true),
|
||||
'username' => utf8_normalize_nfc(request_var('username', '', true)),
|
||||
'new_password' => request_var('new_password', '', true),
|
||||
'password_confirm' => request_var('password_confirm', '', true),
|
||||
'email' => strtolower(request_var('email', '')),
|
||||
|
|
|
|||
1
phpBB/includes/utf/data/confusables.php
Normal file
1
phpBB/includes/utf/data/confusables.php
Normal file
File diff suppressed because one or more lines are too long
|
|
@ -1847,155 +1847,23 @@ function utf8_normalize_nfc($strings)
|
|||
* @return string Cleaned up version of the input string
|
||||
*/
|
||||
function utf8_clean_string($text)
|
||||
{
|
||||
$text = utf8_case_fold($text);
|
||||
|
||||
if (!class_exists('utf_normalizer'))
|
||||
{
|
||||
global $phpbb_root_path, $phpEx;
|
||||
include($phpbb_root_path . 'includes/utf/utf_normalizer.' . $phpEx);
|
||||
|
||||
static $homographs = array();
|
||||
if (empty($homographs))
|
||||
{
|
||||
$homographs = include($phpbb_root_path . 'includes/utf/data/confusables.' . $phpEx);
|
||||
}
|
||||
|
||||
utf_normalizer::nfc($text);
|
||||
|
||||
static $homographs = array(
|
||||
"\xC2\xA1" => "\x69", // EXCLAMATION MARK, INVERTED => LATIN SMALL LETTER I
|
||||
"\xC2\xAD" => '', // HYPHEN, SOFT => empty string
|
||||
"\xC4\x90" => "\xC3\x90", // LATIN CAPITAL LETTER D WITH STROKE => LATIN CAPITAL LETTER ETH
|
||||
"\xC7\x83" => "\x21", // LATIN LETTER RETROFLEX CLICK => EXCLAMATION MARK
|
||||
"\xC9\x85" => "\xCE\x9B", // LATIN CAPITAL LETTER TURNED V => GREEK CAPITAL LETTER LAMDA
|
||||
"\xC9\x99" => "\xC7\x9D", // LATIN SMALL LETTER SCHWA => LATIN SMALL LETTER TURNED E
|
||||
"\xCA\x99" => "\xD0\xB2", // LATIN LETTER SMALL CAPITAL B => CYRILLIC SMALL LETTER VE
|
||||
"\xCA\x9C" => "\xD0\xBD", // LATIN LETTER SMALL CAPITAL H => CYRILLIC SMALL LETTER EN
|
||||
"\xCE\x91" => "\x41", // GREEK CAPITAL LETTER ALPHA => LATIN CAPITAL LETTER A
|
||||
"\xCE\x92" => "\x42", // GREEK CAPITAL LETTER BETA => LATIN CAPITAL LETTER B
|
||||
"\xCE\x95" => "\x45", // GREEK CAPITAL LETTER EPSILON => LATIN CAPITAL LETTER E
|
||||
"\xCE\x96" => "\x5A", // GREEK CAPITAL LETTER ZETA => LATIN CAPITAL LETTER Z
|
||||
"\xCE\x97" => "\x48", // GREEK CAPITAL LETTER ETA => LATIN CAPITAL LETTER H
|
||||
"\xCE\x99" => "\x49", // GREEK CAPITAL LETTER IOTA => LATIN CAPITAL LETTER I
|
||||
"\xCE\x9A" => "\x4B", // GREEK CAPITAL LETTER KAPPA => LATIN CAPITAL LETTER K
|
||||
"\xCE\x9C" => "\x4D", // GREEK CAPITAL LETTER MU => LATIN CAPITAL LETTER M
|
||||
"\xCE\x9D" => "\x4E", // GREEK CAPITAL LETTER NU => LATIN CAPITAL LETTER N
|
||||
"\xCE\x9F" => "\x4F", // GREEK CAPITAL LETTER OMICRON => LATIN CAPITAL LETTER O
|
||||
"\xCE\xA1" => "\x50", // GREEK CAPITAL LETTER RHO => LATIN CAPITAL LETTER P
|
||||
"\xCE\xA3" => "\xC6\xA9", // GREEK CAPITAL LETTER SIGMA => LATIN CAPITAL LETTER ESH
|
||||
"\xCE\xA4" => "\x54", // GREEK CAPITAL LETTER TAU => LATIN CAPITAL LETTER T
|
||||
"\xCE\xA5" => "\x59", // GREEK CAPITAL LETTER UPSILON => LATIN CAPITAL LETTER Y
|
||||
"\xCE\xA7" => "\x58", // GREEK CAPITAL LETTER CHI => LATIN CAPITAL LETTER X
|
||||
"\xCE\xB1" => "\x61", // GREEK SMALL LETTER ALPHA => LATIN SMALL LETTER A
|
||||
"\xCE\xB5" => "\xC9\x9B", // GREEK SMALL LETTER EPSILON => LATIN SMALL LETTER OPEN E
|
||||
"\xCE\xB9" => "\xC9\xA9", // GREEK SMALL LETTER IOTA => LATIN SMALL LETTER IOTA
|
||||
"\xCE\xBF" => "\x6F", // GREEK SMALL LETTER OMICRON => LATIN SMALL LETTER O
|
||||
"\xCF\xB3" => "\x6A", // GREEK LETTER YOT => LATIN SMALL LETTER J
|
||||
"\xD0\x85" => "\x53", // CYRILLIC CAPITAL LETTER DZE => LATIN CAPITAL LETTER S
|
||||
"\xD0\x88" => "\x4A", // CYRILLIC CAPITAL LETTER JE => LATIN CAPITAL LETTER J
|
||||
"\xD0\x91" => "\xC6\x82", // CYRILLIC CAPITAL LETTER BE => LATIN CAPITAL LETTER B WITH TOPBAR
|
||||
"\xD0\x93" => "\xCE\x93", // CYRILLIC CAPITAL LETTER GHE => GREEK CAPITAL LETTER GAMMA
|
||||
"\xD0\x9F" => "\xCE\xA0", // CYRILLIC CAPITAL LETTER PE => GREEK CAPITAL LETTER PI
|
||||
"\xD0\xA1" => "\x43", // CYRILLIC CAPITAL LETTER ES => LATIN CAPITAL LETTER C
|
||||
"\xD0\xB0" => "\x61", // CYRILLIC SMALL LETTER A => LATIN SMALL LETTER A
|
||||
"\xD0\xB5" => "\x65", // CYRILLIC SMALL LETTER IE => LATIN SMALL LETTER E
|
||||
"\xD0\xBA" => "\xC4\xB8", // CYRILLIC SMALL LETTER KA => LATIN SMALL LETTER KRA
|
||||
"\xD0\xBE" => "\x6F", // CYRILLIC SMALL LETTER O => LATIN SMALL LETTER O
|
||||
"\xD1\x80" => "\x70", // CYRILLIC SMALL LETTER ER => LATIN SMALL LETTER P
|
||||
"\xD1\x81" => "\x63", // CYRILLIC SMALL LETTER ES => LATIN SMALL LETTER C
|
||||
"\xD1\x83" => "\x79", // CYRILLIC SMALL LETTER U => LATIN SMALL LETTER Y
|
||||
"\xD1\x85" => "\x78", // CYRILLIC SMALL LETTER HA => LATIN SMALL LETTER X
|
||||
"\xD1\x95" => "\x73", // CYRILLIC SMALL LETTER DZE => LATIN SMALL LETTER S
|
||||
"\xD1\x96" => "\x69", // CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I => LATIN SMALL LETTER I
|
||||
"\xD1\x98" => "\x6A", // CYRILLIC SMALL LETTER JE => LATIN SMALL LETTER J
|
||||
"\xD2\xBB" => "\x68", // CYRILLIC SMALL LETTER SHHA => LATIN SMALL LETTER H
|
||||
"\xD3\x8F" => "\xC9\xAA", // CYRILLIC SMALL LETTER PALOCHKA => LATIN LETTER SMALL CAPITAL I
|
||||
"\xD3\x94" => "\xC3\x86", // CYRILLIC CAPITAL LIGATURE A IE => LATIN CAPITAL LETTER AE
|
||||
"\xD3\x95" => "\xC3\xA6", // CYRILLIC SMALL LIGATURE A IE => LATIN SMALL LETTER AE
|
||||
"\xD3\x98" => "\xC6\x8E", // CYRILLIC CAPITAL LETTER SCHWA => LATIN CAPITAL LETTER REVERSED E
|
||||
"\xD3\x99" => "\xC7\x9D", // CYRILLIC SMALL LETTER SCHWA => LATIN SMALL LETTER TURNED E
|
||||
"\xD3\xA1" => "\xCA\x92", // CYRILLIC SMALL LETTER ABKHASIAN DZE => LATIN SMALL LETTER EZH
|
||||
"\xD3\xA8" => "\xC6\x9F", // CYRILLIC CAPITAL LETTER BARRED O => LATIN CAPITAL LETTER O WITH MIDDLE TILDE
|
||||
"\xD3\xA9" => "\xC9\xB5", // CYRILLIC SMALL LETTER BARRED O => LATIN SMALL LETTER BARRED O
|
||||
"\xD4\x81" => "\x64", // CYRILLIC SMALL LETTER KOMI DE => LATIN SMALL LETTER D
|
||||
"\xE1\x81\x80" => "\xE1\x80\x9D", // MYANMAR DIGIT ZERO => MYANMAR LETTER WA
|
||||
"\xE1\x9E\xA3" => "\xE1\x9E\xA2", // KHMER INDEPENDENT VOWEL QAQ => KHMER LETTER QA
|
||||
"\xE1\xA1\x95" => "\xE1\xA0\xB5", // MONGOLIAN LETTER TODO YA => MONGOLIAN LETTER JA
|
||||
"\xE1\xA7\x90" => "\xE1\xA6\x9E", // NEW TAI LUE DIGIT ZERO => NEW TAI LUE LETTER LOW VA
|
||||
"\xE1\xAD\x92" => "\xE1\xAC\x8D", // BALINESE DIGIT TWO => BALINESE LETTER LA LENGA
|
||||
"\xE1\xAD\x93" => "\xE1\xAC\x91", // BALINESE DIGIT THREE => BALINESE LETTER OKARA
|
||||
"\xE1\xAD\x98" => "\xE1\xAC\xA8", // BALINESE DIGIT EIGHT => BALINESE LETTER PA KAPAL
|
||||
"\xE1\xAD\x9C" => "\xE1\xAD\x90", // BALINESE WINDU => BALINESE DIGIT ZERO
|
||||
"\xE1\xB4\x8D" => "\xD0\xBC", // LATIN LETTER SMALL CAPITAL M => CYRILLIC SMALL LETTER EM
|
||||
"\xE1\xB4\x9B" => "\xD1\x82", // LATIN LETTER SMALL CAPITAL T => CYRILLIC SMALL LETTER TE
|
||||
"\xE1\xB4\xA6" => "\xD0\xB3", // GREEK LETTER SMALL CAPITAL GAMMA => CYRILLIC SMALL LETTER GHE
|
||||
"\xE1\xB4\xA8" => "\xD0\xBF", // GREEK LETTER SMALL CAPITAL PI => CYRILLIC SMALL LETTER PE
|
||||
"\xE1\xB4\xA9" => "\xE1\xB4\x98", // GREEK LETTER SMALL CAPITAL RHO => LATIN LETTER SMALL CAPITAL P
|
||||
"\xE1\xB4\xAB" => "\xD0\xBB", // CYRILLIC LETTER SMALL CAPITAL EL => CYRILLIC SMALL LETTER EL
|
||||
"\xE2\x8D\xB3" => "\xC9\xA9", // APL FUNCTIONAL SYMBOL IOTA => LATIN SMALL LETTER IOTA
|
||||
"\xE2\x8D\xB4" => "\xCF\x81", // APL FUNCTIONAL SYMBOL RHO => GREEK SMALL LETTER RHO
|
||||
"\xE2\x8D\xB5" => "\xCF\x89", // APL FUNCTIONAL SYMBOL OMEGA => GREEK SMALL LETTER OMEGA
|
||||
"\xE2\x8D\xBA" => "\xCE\xB1", // APL FUNCTIONAL SYMBOL ALPHA => GREEK SMALL LETTER ALPHA
|
||||
"\xE2\xB1\xA7" => "\xD2\xA2", // LATIN CAPITAL LETTER H WITH DESCENDER => CYRILLIC CAPITAL LETTER EN WITH DESCENDER
|
||||
"\xE2\xB1\xA9" => "\xD2\x9A", // LATIN CAPITAL LETTER K WITH DESCENDER => CYRILLIC CAPITAL LETTER KA WITH DESCENDER
|
||||
"\xF0\x90\x8F\x91" => "\xF0\x90\x8E\x82", // OLD PERSIAN NUMBER ONE => UGARITIC LETTER GAMLA
|
||||
"\xF0\x90\x8F\x93" => "\xF0\x90\x8E\x93", // OLD PERSIAN NUMBER TEN => UGARITIC LETTER AIN
|
||||
"\xF0\x90\x92\xA0" => "\xF0\x90\x92\x86", // OSMANYA DIGIT ZERO => OSMANYA LETTER DEEL
|
||||
"\xF0\x92\x80\xB8" => "\xF0\x90\x8E\x9A", // CUNEIFORM SIGN ASH => UGARITIC LETTER TO
|
||||
|
||||
"\xC2\xA0" => "\x20", // NO-BREAK SPACE
|
||||
"\xE1\x9A\x80" => "\x20", // OGHAM SPACE MARK
|
||||
"\xE2\x80\x80" => "\x20", // EN QUAD
|
||||
"\xE2\x80\x81" => "\x20", // EM QUAD
|
||||
"\xE2\x80\x82" => "\x20", // EN SPACE
|
||||
"\xE2\x80\x83" => "\x20", // EM SPACE
|
||||
"\xE2\x80\x84" => "\x20", // THREE-PER-EM SPACE
|
||||
"\xE2\x80\x85" => "\x20", // FOUR-PER-EM SPACE
|
||||
"\xE2\x80\x86" => "\x20", // SIX-PER-EM SPACE
|
||||
"\xE2\x80\x87" => "\x20", // FIGURE SPACE
|
||||
"\xE2\x80\x88" => "\x20", // PUNCTUATION SPACE
|
||||
"\xE2\x80\x89" => "\x20", // THIN SPACE
|
||||
"\xE2\x80\x8A" => "\x20", // HAIR SPACE
|
||||
"\xE2\x80\xAF" => "\x20", // NARROW NO-BREAK SPACE
|
||||
"\xE2\x81\x9F" => "\x20", // MEDIUM MATHEMATICAL SPACE
|
||||
"\xE3\x80\x80" => "\x20", // IDEOGRAPHIC SPACE
|
||||
|
||||
"\xDB\x9D" => '', // ARABIC END OF AYAH
|
||||
"\xDC\x8F" => '', // SYRIAC ABBREVIATION MARK
|
||||
"\xE1\xA0\x86" => '', // MONGOLIAN TODO SOFT HYPHEN
|
||||
"\xE1\xA0\x8E" => '', // MONGOLIAN VOWEL SEPARATOR
|
||||
"\xE2\x80\x8B" => '', // ZERO WIDTH SPACE
|
||||
"\xE2\x80\x8C" => '', // ZERO WIDTH NON-JOINER
|
||||
"\xE2\x80\x8D" => '', // ZERO WIDTH JOINER
|
||||
"\xE2\x80\xA8" => '', // LINE SEPARATOR
|
||||
"\xE2\x80\xA9" => '', // PARAGRAPH SEPARATOR
|
||||
"\xE2\x81\xA0" => '', // WORD JOINER
|
||||
"\xE2\x81\xA1" => '', // FUNCTION APPLICATION
|
||||
"\xE2\x81\xA2" => '', // INVISIBLE TIMES
|
||||
"\xE2\x81\xA3" => '', // INVISIBLE SEPARATOR
|
||||
"\xE2\x81\xAA" => '', // [CONTROL CHARACTERS]
|
||||
"\xE2\x81\xAB" => '', // [CONTROL CHARACTERS]
|
||||
"\xE2\x81\xAC" => '', // [CONTROL CHARACTERS]
|
||||
"\xE2\x81\xAD" => '', // [CONTROL CHARACTERS]
|
||||
"\xE2\x81\xAE" => '', // [CONTROL CHARACTERS]
|
||||
"\xE2\x81\xAF" => '', // [CONTROL CHARACTERS]
|
||||
"\xEF\xBB\xBF" => '', // ZERO WIDTH NO-BREAK SPACE
|
||||
"\xEF\xBF\xB9" => '', // [CONTROL CHARACTERS]
|
||||
"\xEF\xBF\xBA" => '', // [CONTROL CHARACTERS]
|
||||
"\xEF\xBF\xBB" => '', // [CONTROL CHARACTERS]
|
||||
"\xEF\xBF\xBC" => '', // [CONTROL CHARACTERS]
|
||||
"\xF0\x9D\x85\xB3" => '', // [MUSICAL CONTROL CHARACTERS]
|
||||
"\xF0\x9D\x85\xB4" => '', // [MUSICAL CONTROL CHARACTERS]
|
||||
"\xF0\x9D\x85\xB5" => '', // [MUSICAL CONTROL CHARACTERS]
|
||||
"\xF0\x9D\x85\xB6" => '', // [MUSICAL CONTROL CHARACTERS]
|
||||
"\xF0\x9D\x85\xB7" => '', // [MUSICAL CONTROL CHARACTERS]
|
||||
"\xF0\x9D\x85\xB8" => '', // [MUSICAL CONTROL CHARACTERS]
|
||||
"\xF0\x9D\x85\xB9" => '', // [MUSICAL CONTROL CHARACTERS]
|
||||
"\xF0\x9D\x85\xBA" => '', // [MUSICAL CONTROL CHARACTERS]
|
||||
);
|
||||
|
||||
$text = utf8_case_fold_nfkc($text);
|
||||
$text = strtr($text, $homographs);
|
||||
|
||||
// Other control characters
|
||||
$text = preg_replace('#(?:[\x00-\x1F\x7F]+|(?:\xC2[\x80-\x9F])+)#', '', $text);
|
||||
|
||||
return $text;
|
||||
// we can use trim here as all the other space characters should have been turned
|
||||
// into normal ASCII spaces by now
|
||||
return trim($text);
|
||||
}
|
||||
|
||||
/**
|
||||
|
|
|
|||
1
phpBB/install/data/confusables.php
Normal file
1
phpBB/install/data/confusables.php
Normal file
File diff suppressed because one or more lines are too long
|
|
@ -523,6 +523,7 @@ $lang = array_merge($lang, array(
|
|||
'LOG_IMAGESET_EDIT_DETAILS' => '<strong>Edited imageset details</strong><br />» %s',
|
||||
'LOG_IMAGESET_EDIT' => '<strong>Edited imageset</strong><br />» %s',
|
||||
'LOG_IMAGESET_EXPORT' => '<strong>Exported imageset</strong><br />» %s',
|
||||
'LOG_IMAGESET_LANG_MISSING' => '<strong>Imageset misses “%2$s” localisation</strong><br />» %1$s',
|
||||
'LOG_IMAGESET_LANG_REFRESHED' => '<strong>Refreshed “%2$s” localisation of imageset</strong><br />» %1$s',
|
||||
'LOG_IMAGESET_REFRESHED' => '<strong>Refreshed imageset</strong><br />» %s',
|
||||
|
||||
|
|
|
|||
|
|
@ -73,7 +73,7 @@ $lang = array_merge($lang, array(
|
|||
'SEARCH_AUTHOR_EXPLAIN' => 'Use * as a wildcard for partial matches.',
|
||||
'SEARCH_FIRST_POST' => 'First post of topics only',
|
||||
'SEARCH_FORUMS' => 'Search in forums',
|
||||
'SEARCH_FORUMS_EXPLAIN' => 'Select the forum or forums you wish to search in. For speed all subforums can be searched by selecting the parent and setting enable search subforums below.',
|
||||
'SEARCH_FORUMS_EXPLAIN' => 'Select the forum or forums you wish to search in. Subforums are searched automatically if you do not disable “search subforums“ below.',
|
||||
'SEARCH_IN_RESULTS' => 'Search these results',
|
||||
'SEARCH_KEYWORDS_EXPLAIN' => 'Place <strong>+</strong> in front of a word which must be found and <strong>-</strong> in front of a word which must not be found. Put a list of words separated by <strong>|</strong> into brackets if only one of the words must be found. Use * as a wildcard for partial matches.',
|
||||
'SEARCH_MSG_ONLY' => 'Message text only',
|
||||
|
|
|
|||
|
|
@ -44,7 +44,7 @@ $sort_days = request_var('st', 0);
|
|||
$sort_key = request_var('sk', 't');
|
||||
$sort_dir = request_var('sd', 'd');
|
||||
|
||||
$return_chars = request_var('ch', ($topic_id) ? -1 : 200);
|
||||
$return_chars = request_var('ch', ($topic_id) ? -1 : 300);
|
||||
$search_forum = request_var('fid', array(0));
|
||||
|
||||
// Is user able to search? Has search been disabled?
|
||||
|
|
@ -476,7 +476,7 @@ if ($keywords || $author || $author_id || $search_id || $submit)
|
|||
$u_search .= ($u_search_forum) ? '&fid%5B%5D=' . $u_search_forum : '';
|
||||
$u_search .= (!$search_child) ? '&sc=0' : '';
|
||||
$u_search .= ($search_fields != 'all') ? '&sf=' . $search_fields : '';
|
||||
$u_search .= ($return_chars != 200) ? '&ch=' . $return_chars : '';
|
||||
$u_search .= ($return_chars != 300) ? '&ch=' . $return_chars : '';
|
||||
|
||||
$template->assign_vars(array(
|
||||
'SEARCH_TITLE' => $l_search_title,
|
||||
|
|
@ -1009,7 +1009,7 @@ $s_characters .= '<option value="50">50</option>';
|
|||
|
||||
for ($i = 100; $i <= 1000 ; $i += 100)
|
||||
{
|
||||
$selected = ($i == 200) ? ' selected="selected"' : '';
|
||||
$selected = ($i == 300) ? ' selected="selected"' : '';
|
||||
$s_characters .= '<option value="' . $i . '"' . $selected . '>' . $i . '</option>';
|
||||
}
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue