mirror of
https://github.com/phpbb/phpbb.git
synced 2025-07-12 04:36:32 +02:00
build
git-tools
phpBB
adm
assets
bin
cache
config
develop
add_permissions.php
adjust_avatars.php
adjust_bbcodes.php
adjust_magic_urls.php
adjust_sizes.php
adjust_smilies.php
adjust_uids.php
adjust_usernames.php
benchmark.php
blank.gif
blank.jpg
calc_email_hash.php
change_smiley_ref.php
check_flash_bbcodes.php
collect_cache_stats.sh
create_schema_files.php
create_search_index.php
create_variable_overview.php
export_events_for_wiki.php
fill.php
fix_files.sh
generate_utf_casefold.php
generate_utf_confusables.php
generate_utf_tables.php
imageset_to_css.php
lang_duplicates.php
merge_attachment_tables.php
merge_post_tables.php
mysql_upgrader.php
namespacify.php
nuke-db.php
regex.php
remove-php-end-tags.py
rename_interfaces.php
repair_bots.php
search_fill.php
set_permissions.sh
strip_icc_profiles.sh
unicode_testing.php
update_email_hash.php
utf_normalizer_test.php
docs
download
ext
files
images
includes
install
language
phpbb
store
styles
.htaccess
app.php
common.php
composer.json
composer.lock
cron.php
faq.php
feed.php
index.php
mcp.php
memberlist.php
posting.php
report.php
search.php
ucp.php
viewforum.php
viewonline.php
viewtopic.php
web.config
tests
travis
.gitignore
.travis.yml
README.md
composer.phar
phpunit.xml.dist
Closing tags converted using Oleg's script. remove-php-end-tags.py -a . Trailing newlines added using the following where $ext is file extension. find . -type f -name "*.$ext" -print | xargs printf "e %s\nw\n" | ed -s; Extensions: php, css, html, js, xml. PHPBB3-9556
119 lines
2.7 KiB
PHP
119 lines
2.7 KiB
PHP
<?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;
|
|
}
|