Verzeichnisstruktur phpBB-3.0.0
- Veröffentlicht
- 12.12.2007
So funktioniert es
|
|
Auf das letzte Element klicken. Dies geht jeweils ein Schritt zurück |
Auf das Icon klicken, dies öffnet das Verzeichnis. Nochmal klicken schließt das Verzeichnis. |
|
|
(Beispiel Datei-Icons)
|
Auf das Icon klicken um den Quellcode anzuzeigen |
new_normalizer.php
001 <?php
002 /**
003 *
004 * @package install
005 * @version $Id$
006 * @copyright (c) 2007 phpBB Group
007 * @license http://opensource.org/licenses/gpl-license.php GNU Public License
008 *
009 */
010
011 /**
012 * @ignore
013 */
014 if (!defined('IN_PHPBB'))
015 {
016 exit;
017 }
018
019 /**
020 * A wrapper function for the normalizer which takes care of including the class if required and modifies the passed strings
021 * to be in NFC (Normalization Form Composition).
022 *
023 * @param mixed $strings a string or an array of strings to normalize
024 * @return mixed the normalized content, preserving array keys if array given.
025 */
026 function utf8_new_normalize_nfc($strings)
027 {
028 if (empty($strings))
029 {
030 return $strings;
031 }
032
033 if (!is_array($strings))
034 {
035 utf_new_normalizer::nfc($strings);
036 }
037 else if (is_array($strings))
038 {
039 foreach ($strings as $key => $string)
040 {
041 if (is_array($string))
042 {
043 foreach ($string as $_key => $_string)
044 {
045 utf_new_normalizer::nfc($strings[$key][$_key]);
046 }
047 }
048 else
049 {
050 utf_new_normalizer::nfc($strings[$key]);
051 }
052 }
053 }
054
055 return $strings;
056 }
057
058 class utf_new_normalizer
059 {
060 /**
061 * Validate, cleanup and normalize a string
062 *
063 * The ultimate convenience function! Clean up invalid UTF-8 sequences,
064 * and convert to Normal Form C, canonical composition.
065 *
066 * @param string &$str The dirty string
067 * @return string The same string, all shiny and cleaned-up
068 */
069 function cleanup(&$str)
070 {
071 // The string below is the list of all autorized characters, sorted by frequency in latin text
072 $pos = strspn($str, "\x20\x65\x69\x61\x73\x6E\x74\x72\x6F\x6C\x75\x64\x5D\x5B\x63\x6D\x70\x27\x0A\x67\x7C\x68\x76\x2E\x66\x62\x2C\x3A\x3D\x2D\x71\x31\x30\x43\x32\x2A\x79\x78\x29\x28\x4C\x39\x41\x53\x2F\x50\x22\x45\x6A\x4D\x49\x6B\x33\x3E\x35\x54\x3C\x44\x34\x7D\x42\x7B\x38\x46\x77\x52\x36\x37\x55\x47\x4E\x3B\x4A\x7A\x56\x23\x48\x4F\x57\x5F\x26\x21\x4B\x3F\x58\x51\x25\x59\x5C\x09\x5A\x2B\x7E\x5E\x24\x40\x60\x7F\x0D");
073 $len = strlen($str);
074
075 if ($pos == $len)
076 {
077 // ASCII strings with no special chars return immediately
078 return;
079 }
080
081 // Note: we do not check for $GLOBALS['utf_canonical_decomp']. It is assumed they are always loaded together
082 if (!isset($GLOBALS['utf_nfc_qc']))
083 {
084 global $phpbb_root_path, $phpEx;
085 include($phpbb_root_path . 'includes/utf/data/utf_nfc_qc.' . $phpEx);
086 }
087
088 if (!isset($GLOBALS['utf_canonical_decomp']))
089 {
090 global $phpbb_root_path, $phpEx;
091 include($phpbb_root_path . 'includes/utf/data/utf_canonical_decomp.' . $phpEx);
092 }
093
094 // Replace any byte in the range 0x00..0x1F, except for \r, \n and \t
095 // We replace those characters with a 0xFF byte, which is illegal in UTF-8 and will in turn be replaced with a UTF replacement char
096 $str = strtr(
097 $str,
098 "\x00\x01\x02\x03\x04\x05\x06\x07\x08\x0B\x0C\x0E\x0F\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1A\x1B\x1C\x1D\x1E\x1F",
099 "\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF"
100 );
101
102 $str = utf_new_normalizer::recompose($str, $pos, $len, $GLOBALS['utf_nfc_qc'], $GLOBALS['utf_canonical_decomp']);
103 }
104
105 /**
106 * Validate and normalize a UTF string to NFC
107 *
108 * @param string &$str Unchecked UTF string
109 * @return string The string, validated and in normal form
110 */
111 function nfc(&$str)
112 {
113 $pos = strspn($str, UTF8_ASCII_RANGE);
114 $len = strlen($str);
115
116 if ($pos == $len)
117 {
118 // ASCII strings return immediately
119 return;
120 }
121
122 if (!isset($GLOBALS['utf_nfc_qc']))
123 {
124 global $phpbb_root_path, $phpEx;
125 include($phpbb_root_path . 'includes/utf/data/utf_nfc_qc.' . $phpEx);
126 }
127
128 if (!isset($GLOBALS['utf_canonical_decomp']))
129 {
130 global $phpbb_root_path, $phpEx;
131 include($phpbb_root_path . 'includes/utf/data/utf_canonical_decomp.' . $phpEx);
132 }
133
134 $str = utf_new_normalizer::recompose($str, $pos, $len, $GLOBALS['utf_nfc_qc'], $GLOBALS['utf_canonical_decomp']);
135 }
136
137 /**
138 * Validate and normalize a UTF string to NFKC
139 *
140 * @param string &$str Unchecked UTF string
141 * @return string The string, validated and in normal form
142 */
143 function nfkc(&$str)
144 {
145 $pos = strspn($str, UTF8_ASCII_RANGE);
146 $len = strlen($str);
147
148 if ($pos == $len)
149 {
150 // ASCII strings return immediately
151 return;
152 }
153
154 if (!isset($GLOBALS['utf_nfkc_qc']))
155 {
156 global $phpbb_root_path, $phpEx;
157 include($phpbb_root_path . 'includes/utf/data/utf_nfkc_qc.' . $phpEx);
158 }
159
160 if (!isset($GLOBALS['utf_compatibility_decomp']))
161 {
162 global $phpbb_root_path, $phpEx;
163 include($phpbb_root_path . 'includes/utf/data/utf_compatibility_decomp.' . $phpEx);
164 }
165
166 $str = utf_new_normalizer::recompose($str, $pos, $len, $GLOBALS['utf_nfkc_qc'], $GLOBALS['utf_compatibility_decomp']);
167 }
168
169 /**
170 * Recompose a UTF string
171 *
172 * @param string $str Unchecked UTF string
173 * @param integer $pos Position of the first UTF char (in bytes)
174 * @param integer $len Length of the string (in bytes)
175 * @param array &$qc Quick-check array, passed by reference but never modified
176 * @param array &$decomp_map Decomposition mapping, passed by reference but never modified
177 * @return string The string, validated and recomposed
178 *
179 * @access private
180 */
181 function recompose($str, $pos, $len, &$qc, &$decomp_map)
182 {
183 global $utf_canonical_comp;
184
185 // Load the canonical composition table
186 if (!isset($utf_canonical_comp))
187 {
188 global $phpbb_root_path, $phpEx;
189 include($phpbb_root_path . 'includes/utf/data/utf_canonical_comp.' . $phpEx);
190 }
191
192 return utf_normalizer::recompose($str, $pos, $len, $qc, $decomp_map);
193 }
194 }
195
196 ?>