chamilo
/
chamilo-lms
mirror of https://github.com/chamilo/chamilo-lms/tree/1.11.x
2
0
Fork 0
Code Issues Projects Releases Wiki Activity

merge

Browse Source
skala
rvelasquez 16 years ago
parent 26d33a85b0 51a649cd96
commit eb7e83c301
3 changed files with 353 additions and 174 deletions
Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL
Show Stats Download Patch File Download Diff File
  1. 2
      main/inc/lib/add_course.lib.inc.php
  2. 372
      main/inc/lib/multibyte_string_functions.lib.php
  3. 95
      main/inc/lib/multibyte_string_functions_internal.lib.php

2
main/inc/lib/add_course.lib.inc.php
Unescape View File

@ -64,7 +64,7 @@ function generate_course_code($course_title, $encoding = null)
if (empty($encoding)) {
$encoding = api_get_system_encoding();
}
return substr(preg_replace('/[^A-Z0-9]/', '', strtoupper(api_transliterate($course_title, $encoding))), 0, 20);
return substr(preg_replace('/[^A-Z0-9]/', '', strtoupper(api_transliterate($course_title, 'X', $encoding))), 0, 20);
}

372
main/inc/lib/multibyte_string_functions.lib.php
Unescape View File

@ -410,29 +410,37 @@ function api_str_ireplace($search, $replace, $subject, & $count = null, $encodin
* @link http://php.net/str_split
*/
function api_str_split($string, $split_length = 1, $encoding = null) {
if ($split_length < 1) {
return false;
}
if (empty($encoding)) {
$encoding = api_mb_internal_encoding();
}
if (empty($string)) {
return array();
}
if ($split_length < 1) {
return false;
}
if (_api_is_single_byte_encoding($encoding)) {
return str_split($string, $split_length);
}
$result = array();
if (api_mb_supports($encoding)) {
for ($i = 0, $length = @mb_strlen($string, $encoding); $i < $length; $i += $split_length) {
$result[] = @mb_substr($string, $i, $split_length, $encoding);
if (api_is_encoding_supported($encoding)) {
$len = api_strlen($string);
if ($len <= $split_length) {
return array($string);
}
if (!api_is_utf8($encoding)) {
$string = api_utf8_encode($string, $encoding);
}
elseif (api_iconv_supports($encoding) || api_is_utf8($encoding)) {
for ($i = 0, $length = api_strlen($string, $encoding); $i < $length; $i += $split_length) {
$result[] = api_substr($string, $i, $split_length, $encoding);
if (preg_match_all('/.{'.$split_length.'}|[^\x00]{1,'.$split_length.'}$/us', $string, $result) === false) {
return array();
}
} else {
return str_split($string, $split_length);
if (!api_is_utf8($encoding)) {
global $_api_encoding;
$_api_encoding = $encoding;
$result = _api_array_utf8_decode($result[0]);
}
return $result;
return $result[0];
}
return str_split($string, $split_length);
}
/**
@ -454,11 +462,11 @@ function api_stripos($haystack, $needle, $offset = 0, $encoding = null) {
if (api_mb_supports($encoding)) {
return @mb_stripos($haystack, $needle, $offset, $encoding);
}
elseif (MBSTRING_INSTALLED && (api_iconv_supports($encoding) || _api_convert_encoding_supports($encoding))) {
return api_utf8_decode(@mb_stripos(api_utf8_encode($haystack, $encoding), api_utf8_encode($needle, $encoding), $offset, 'UTF-8'), $encoding);
elseif (api_is_encoding_supported($encoding)) {
if (MBSTRING_INSTALLED) {
return @mb_stripos(api_utf8_encode($haystack, $encoding), api_utf8_encode($needle, $encoding), $offset, 'UTF-8');
}
elseif (api_iconv_supports($encoding) || _api_convert_encoding_supports($encoding)) {
api_strpos(api_strtolower($haystack, $encoding), api_strtolower($needle, $encoding), $offset, $encoding);
return api_strpos(api_strtolower($haystack, $encoding), api_strtolower($needle, $encoding), $offset, $encoding);
}
return stripos($haystack, $needle, $offset);
}
@ -466,28 +474,54 @@ function api_stripos($haystack, $needle, $offset = 0, $encoding = null) {
/**
* Finds first occurrence of a string within another, case insensitive.
* @param string $haystack The string from which to get the first occurrence.
* @param string @needle The string to be found.
* @param bool $part (optional) Determines which portion of $haystack this function returns. The default value is FALSE.
* @param mixed $needle The string to be found.
* @param bool $before_needle (optional) Determines which portion of $haystack this function returns. The default value is FALSE.
* @param string $encoding (optional) The used internally by this function character encoding. If it is omitted, the platform character set will be used by default.
* @return mixed Returns the portion of $haystack, or FALSE if $needle is not found.
* Notes:
* If $part is set to TRUE, the function returns all of $haystack from the beginning to the first occurrence of $needle.
* If $part is set to FALSE, the function returns all of $haystack from the first occurrence of $needle to the end.
* If $needle is not a string, it is converted to an integer and applied as the ordinal value (codepoint if the encoding is UTF-8) of a character.
* If $before_needle is set to TRUE, the function returns all of $haystack from the beginning to the first occurrence of $needle.
* If $before_needle is set to FALSE, the function returns all of $haystack from the first occurrence of $needle to the end.
* This function is aimed at replacing the functions stristr() and mb_stristr() for human-language strings.
* @link http://php.net/manual/en/function.stristr
* @link http://php.net/manual/en/function.mb-stristr
*/
function api_stristr($haystack, $needle, $part = false, $encoding = null) {
function api_stristr($haystack, $needle, $before_needle = false, $encoding = null) {
if (empty($encoding)) {
$encoding = api_mb_internal_encoding();
}
if (!is_string($needle)) {
$needle = (int)$needle;
if (api_is_utf8($encoding)) {
$needle = _api_utf8_chr($needle);
} else {
$needle = chr($needle);
}
}
if (api_mb_supports($encoding)) {
return @mb_stristr($haystack, $needle, $part, $encoding);
return @mb_stristr($haystack, $needle, $before_needle, $encoding);
}
elseif (MBSTRING_INSTALLED && (api_iconv_supports($encoding) || _api_convert_encoding_supports($encoding))) {
return api_utf8_decode(@mb_stristr(api_utf8_encode($haystack, $encoding), api_utf8_encode($needle, $encoding), $part, 'UTF-8'));
elseif (api_is_encoding_supported($encoding)) {
if (MBSTRING_INSTALLED) {
$result = @mb_stristr(api_utf8_encode($haystack, $encoding), api_utf8_encode($needle, $encoding), $before_needle, 'UTF-8');
if ($result === false) {
return false;
}
return api_utf8_decode($result, $encoding);
}
$result = api_strstr(api_strtolower($haystack, $encoding), api_strtolower($needle, $encoding), $before_needle, $encoding);
if ($result === false) {
return false;
}
return stristr($haystack, $needle, $part);
if ($before_needle) {
return api_substr($haystack, 0, api_strlen($result, $encoding), $encoding);
}
return api_substr($haystack, api_strlen($haystack, $encoding) - api_strlen($result, $encoding), null, $encoding);
}
if (PHP_VERSION < 5.3) {
return stristr($haystack, $needle);
}
return stristr($haystack, $needle, $before_needle);
}
/**
@ -545,10 +579,10 @@ function api_strpos($haystack, $needle, $offset = 0, $encoding = null) {
elseif (api_mb_supports($encoding)) {
return @mb_strpos($haystack, $needle, $offset, $encoding);
}
elseif (MBSTRING_INSTALLED && (api_iconv_supports($encoding) || _api_convert_encoding_supports($encoding))) {
return api_utf8_decode(@mb_strpos(api_utf8_encode($haystack, $encoding), api_utf8_encode($needle, $encoding), $offset, 'UTF-8'), $encoding);
elseif (api_is_encoding_supported($encoding)) {
if (MBSTRING_INSTALLED) {
return @mb_strpos(api_utf8_encode($haystack, $encoding), api_utf8_encode($needle, $encoding), $offset, 'UTF-8');
}
elseif (api_iconv_supports($encoding) || _api_convert_encoding_supports($encoding)) {
if (!api_is_utf8($encoding)) {
$haystack = api_utf8_encode($haystack, $encoding);
$needle = api_utf8_encode($needle, $encoding);
@ -559,45 +593,71 @@ function api_strpos($haystack, $needle, $offset = 0, $encoding = null) {
return api_strlen($haystack[0]);
}
return false;
} else {
}
$haystack = api_substr($haystack, $offset);
if (($pos = api_strpos($haystack, $needle)) !== false ) {
return $pos + $offset;
}
return false;
}
}
return strpos($haystack, $needle, $offset);
}
/**
* Finds the last occurrence of a character in a string.
* @param string $haystack The string from which to get the last occurrence.
* @param string $needle The string which first character is to be found.
* @param bool $part (optional) Determines which portion of $haystack this function returns. The default value is FALSE.
* @param mixed $needle The string which first character is to be found.
* @param bool $before_needle (optional) Determines which portion of $haystack this function returns. The default value is FALSE.
* @param string $encoding (optional) The used internally by this function character encoding. If it is omitted, the platform character set will be used by default.
* @return mixed Returns the portion of $haystack, or FALSE if the first character from $needle is not found.
* Notes:
* If $part is set to TRUE, the function returns all of $haystack from the beginning to the first occurrence.
* If $part is set to FALSE, the function returns all of $haystack from the first occurrence to the end.
* If $needle is not a string, it is converted to an integer and applied as the ordinal value (codepoint if the encoding is UTF-8) of a character.
* If $before_needle is set to TRUE, the function returns all of $haystack from the beginning to the first occurrence.
* If $before_needle is set to FALSE, the function returns all of $haystack from the first occurrence to the end.
* This function is aimed at replacing the functions strrchr() and mb_strrchr() for human-language strings.
* @link http://php.net/manual/en/function.strrchr
* @link http://php.net/manual/en/function.mb-strrchr
*/
function api_strrchr($haystack, $needle, $part = false, $encoding = null) {
function api_strrchr($haystack, $needle, $before_needle = false, $encoding = null) {
if (empty($encoding)) {
$encoding = api_mb_internal_encoding();
}
if (!is_string($needle)) {
$needle = (int)$needle;
if (api_is_utf8($encoding)) {
$needle = _api_utf8_chr($needle);
} else {
$needle = chr($needle);
}
}
if (_api_is_single_byte_encoding($encoding)) {
if (!$before_needle) {
return strrchr($haystack, $needle);
}
$result = strrchr($haystack, $needle);
if ($result === false) {
return false;
}
return api_substr($haystack, 0, api_strlen($haystack, $encoding) - api_strlen($result, $encoding), $encoding);
}
elseif (api_mb_supports($encoding)) {
return @mb_strrchr($haystack, $needle, $part, $encoding);
return @mb_strrchr($haystack, $needle, $before_needle, $encoding);
}
elseif (MBSTRING_INSTALLED && (api_iconv_supports($encoding) || _api_convert_encoding_supports($encoding))) {
return api_utf8_decode(@mb_strrchr(api_utf8_encode($haystack, $encoding), api_utf8_encode($needle, $encoding), $part, 'UTF-8'), $encoding);
elseif (MBSTRING_INSTALLED && api_is_encoding_supported($encoding)) {
$result = @mb_strrchr(api_utf8_encode($haystack, $encoding), api_utf8_encode($needle, $encoding), $before_needle, 'UTF-8');
if ($result === false) {
return false;
}
return api_utf8_decode($result, $encoding);
}
if (!$before_needle) {
return strrchr($haystack, $needle);
}
$result = strrchr($haystack, $needle);
if ($result === false) {
return false;
}
return api_substr($haystack, 0, api_strlen($haystack, $encoding) - api_strlen($result, $encoding), $encoding);
}
/**
@ -609,17 +669,19 @@ function api_strrchr($haystack, $needle, $part = false, $encoding = null) {
* @link http://php.net/manual/en/function.strrev
*/
function api_strrev($string, $encoding = null) {
if (empty($encoding)) {
$encoding = api_mb_internal_encoding();
}
if (empty($string)) {
return '';
}
if (empty($encoding)) {
$encoding = api_mb_internal_encoding();
if (_api_is_single_byte_encoding($encoding)) {
return strrev($string);
}
$result = '';
for ($i = api_strlen($string, $encoding) - 1; $i > -1; $i--) {
$result .= api_substr($string, $i, 1, $encoding);
if (api_is_encoding_supported($encoding)) {
return implode(array_reverse(api_str_split($string, 1, $encoding)));
}
return $result;
return strrev($string);
}
/**
@ -638,11 +700,49 @@ function api_strrpos($haystack, $needle, $offset = 0, $encoding = null) {
if (empty($encoding)) {
$encoding = api_mb_internal_encoding();
}
if (_api_is_single_byte_encoding($encoding)) {
return strrpos($haystack, $needle, $offset);
}
if (api_mb_supports($encoding)) {
return @mb_strrpos($haystack, $needle, $offset, $encoding);
}
elseif (MBSTRING_INSTALLED && api_iconv_supports($encoding)) {
return api_utf8_decode(@mb_strrpos(api_utf8_encode($haystack, $encoding), api_utf8_encode($needle, $encoding), $offset, 'UTF-8'), $encoding);
elseif (api_is_encoding_supported($encoding)) {
if (MBSTRING_INSTALLED) {
return @mb_strrpos(api_utf8_encode($haystack, $encoding), api_utf8_encode($needle, $encoding), $offset, 'UTF-8');
}
// This branch (this fragment of code) is an adaptation from the CakePHP(tm) Project, http://www.cakefoundation.org
if (!api_is_utf8($encoding)) {
$haystack = api_utf8_encode($haystack, $encoding);
$needle = api_utf8_encode($needle, $encoding);
}
$found = false;
$haystack = _api_utf8_to_unicode($haystack);
$haystack_count = count($haystack);
$matches = array_count_values($haystack);
$needle = _api_utf8_to_unicode($needle);
$needle_count = count($needle);
$position = $offset;
while (($found === false) && ($position < $haystack_count)) {
if (isset($needle[0]) && $needle[0] === $haystack[$position]) {
for ($i = 1; $i < $needle_count; $i++) {
if ($needle[$i] !== $haystack[$position + $i]) {
if ($needle[$i] === $haystack[($position + $i) -1]) {
$position--;
$found = true;
continue;
}
}
}
if (!$offset && isset($matches[$needle[0]]) && $matches[$needle[0]] > 1) {
$matches[$needle[0]] = $matches[$needle[0]] - 1;
} elseif ($i === $needle_count) {
$found = true;
$position--;
}
}
$position++;
}
return ($found) ? $position : false;
}
return strrpos($haystack, $needle, $offset);
}
@ -650,31 +750,67 @@ function api_strrpos($haystack, $needle, $offset = 0, $encoding = null) {
/**
* Finds first occurrence of a string within another.
* @param string $haystack The string from which to get the first occurrence.
* @param string @needle The string to be found.
* @param bool $part (optional) Determines which portion of $haystack this function returns. The default value is FALSE.
* @param mixed $needle The string to be found.
* @param bool $before_needle (optional) Determines which portion of $haystack this function returns. The default value is FALSE.
* @param string $encoding (optional) The used internally by this function character encoding. If it is omitted, the platform character set will be used by default.
* @return mixed Returns the portion of $haystack, or FALSE if $needle is not found.
* Notes:
* If $part is set to TRUE, the function returns all of $haystack from the beginning to the first occurrence of $needle.
* If $part is set to FALSE, the function returns all of $haystack from the first occurrence of $needle to the end.
* If $needle is not a string, it is converted to an integer and applied as the ordinal value (codepoint if the encoding is UTF-8) of a character.
* If $before_needle is set to TRUE, the function returns all of $haystack from the beginning to the first occurrence of $needle.
* If $before_needle is set to FALSE, the function returns all of $haystack from the first occurrence of $needle to the end.
* This function is aimed at replacing the functions strstr() and mb_strstr() for human-language strings.
* @link http://php.net/manual/en/function.strstr
* @link http://php.net/manual/en/function.mb-strstr
*/
function api_strstr($haystack, $needle, $part = false, $encoding = null) {
function api_strstr($haystack, $needle, $before_needle = false, $encoding = null) {
if (empty($encoding)) {
$encoding = api_mb_internal_encoding();
}
if (!is_string($needle)) {
$needle = (int)$needle;
if (api_is_utf8($encoding)) {
$needle = _api_utf8_chr($needle);
} else {
$needle = chr($needle);
}
}
if (_api_is_single_byte_encoding($encoding)) {
return strstr($haystack, $needle, $part);
// Adding the missing parameter $before_needle to the original function strstr(), PHP_VERSION < 5.3
if (!$before_needle) {
return strstr($haystack, $needle);
}
if (PHP_VERSION < 5.3) {
$result = explode($needle, $haystack, 2);
if ($result === false || count($result) < 2) {
return false;
}
return $result[0];
}
return strstr($haystack, $needle, $before_needle);
}
if (api_mb_supports($encoding)) {
return @mb_strstr($haystack, $needle, $part, $encoding);
return @mb_strstr($haystack, $needle, $before_needle, $encoding);
}
elseif (MBSTRING_INSTALLED && api_is_encoding_supported($encoding)) {
$result = @mb_strstr(api_utf8_encode($haystack, $encoding), api_utf8_encode($needle, $encoding), $before_needle, 'UTF-8');
if ($result !== false) {
return api_utf8_decode($result, $encoding);
} else {
return false;
}
elseif (MBSTRING_INSTALLED && api_iconv_supports($encoding)) {
return api_utf8_decode(@mb_strstr(api_utf8_encode($haystack, $encoding), api_utf8_encode($needle, $encoding), $part, 'UTF-8'), $encoding);
}
return strstr($haystack, $needle, $part);
// Adding the missing parameter $before_needle to the original function strstr(), PHP_VERSION < 5.3
if (!$before_needle) {
return strstr($haystack, $needle);
}
if (PHP_VERSION < 5.3) {
$result = explode($needle, $haystack, 2);
if ($result === false || count($result) < 2) {
return false;
}
return $result[0];
}
return strstr($haystack, $needle, $before_needle);
}
/**
@ -693,14 +829,14 @@ function api_strtolower($string, $encoding = null) {
if (api_mb_supports($encoding)) {
return @mb_strtolower($string, $encoding);
}
elseif (MBSTRING_INSTALLED && api_iconv_supports($encoding)) {
elseif (api_is_encoding_supported($encoding)) {
if (MBSTRING_INSTALLED) {
return api_utf8_decode(@mb_strtolower(api_utf8_encode($string, $encoding), 'UTF-8'), $encoding);
}
elseif (api_iconv_supports($encoding) || _api_convert_encoding_supports($encoding)) {
// This branch (this fragment of code) is an adaptation from the CakePHP(tm) Project, http://www.cakefoundation.org
if (!api_is_utf8($encoding)) {
$string = api_utf8_encode($string, $encoding);
}
// This branch (this fragment of code) is an adaptation from the CakePHP(tm) Project, http://www.cakefoundation.org
$codepoints = _api_utf8_to_unicode($string);
$length = count($codepoints);
$matched = false;
@ -757,14 +893,14 @@ function api_strtoupper($string, $encoding = null) {
if (api_mb_supports($encoding)) {
return @mb_strtoupper($string, $encoding);
}
elseif (MBSTRING_INSTALLED && api_iconv_supports($encoding)) {
elseif (api_is_encoding_supported($encoding)) {
if (MBSTRING_INSTALLED) {
return api_utf8_decode(@mb_strtoupper(api_utf8_encode($string, $encoding), 'UTF-8'), $encoding);
}
elseif (api_iconv_supports($encoding) || _api_convert_encoding_supports($encoding)) {
// This branch (this fragment of code) is an adaptation from the CakePHP(tm) Project, http://www.cakefoundation.org
if (!api_is_utf8($encoding)) {
$string = api_utf8_encode($string, $encoding);
}
// This branch (this fragment of code) is an adaptation from the CakePHP(tm) Project, http://www.cakefoundation.org
$codepoints = _api_utf8_to_unicode($string);
$length = count($codepoints);
$matched = false;
@ -917,14 +1053,20 @@ function api_substr($string, $start, $length = null, $encoding = null) {
if (is_null($length)) {
$length = api_strlen($string, $encoding);
}
if (_api_is_single_byte_encoding($encoding)) {
return substr($string, $start, $length);
}
if (api_mb_supports($encoding)) {
return @mb_substr($string, $start, $length, $encoding);
}
elseif (MBSTRING_INSTALLED && api_iconv_supports($encoding)) {
elseif (api_is_encoding_supported($encoding)) {
if (MBSTRING_INSTALLED) {
return api_utf8_decode(@mb_substr(api_utf8_encode($string, $encoding), $start, $length, 'UTF-8'), $encoding);
}
elseif (api_is_utf8($encoding)) {
// The following branch of code is from the Drupal CMS, see the function drupal_substr().
if (!api_is_utf8($encoding)) {
$string = api_utf8_encode($string, $encoding);
}
$strlen = api_byte_count($string);
// Find the starting byte offset
$bytes = 0;
@ -985,7 +1127,11 @@ function api_substr($string, $start, $length = null, $encoding = null) {
}
}
$iend = $bytes;
return substr($string, $istart, max(0, $iend - $istart + 1));
$string = substr($string, $istart, max(0, $iend - $istart + 1));
if (!api_is_utf8($encoding)) {
$string = api_utf8_decode($string, $encoding);
}
return $string;
}
return substr($string, $start, $length);
}
@ -1013,16 +1159,29 @@ function api_substr_replace($string, $replacement, $start, $length = null, $enco
if (empty($encoding)) {
$encoding = api_mb_internal_encoding();
}
if ($length == null) {
return api_substr($string, 0, $start, $encoding) . $replacement;
} else {
if (api_is_encoding_supported($encoding) && !_api_is_single_byte_encoding($encoding)) {
$string_length = api_strlen($string, $encoding);
if ($start < 0) {
$start = max(0, $string_length + $start);
}
else if ($start > $string_length) {
$start = $string_length;
}
if ($length < 0) {
$length = api_strlen($string, $encoding) - $start + $length;
$length = max(0, $string_length - $start + $length);
}
return
api_substr($string, 0, $start, $encoding) . $replacement .
api_substr($string, $start + $length, api_strlen($string, $encoding), $encoding);
else if (is_null($length) || ($length > $string_length)) {
$length = $string_length;
}
if (($start + $length) > $string_length) {
$length = $string_length - $start;
}
return api_substr($string, 0, $start, $encoding) . $replacement . api_substr($string, $start + $length, $string_length - $start - $length, $encoding);
}
if (is_null($length)) {
return substr_replace($string, $replacement, $start);
}
return substr_replace($string, $replacement, $start, $length);
}
/**
@ -1091,12 +1250,14 @@ function api_ereg($pattern, $string, & $regs = null) {
}
}
elseif (MBSTRING_INSTALLED && api_iconv_supports($encoding)) {
global $_api_encoding;
$_api_encoding = $encoding;
api_mb_regex_encoding('UTF-8');
if ($count < 3) {
$result = @mb_ereg(api_utf8_encode($pattern, $encoding), api_utf8_encode($string, $encoding));
} else {
$result = @mb_ereg(api_utf8_encode($pattern, $encoding), api_utf8_encode($string, $encoding), $regs);
$regs = _api_array_utf8_decode($regs, $encoding);
$regs = _api_array_utf8_decode($regs);
}
api_mb_regex_encoding($encoding);
return $result;
@ -1172,13 +1333,14 @@ function api_eregi($pattern, $string, & $regs = null) {
}
}
elseif (MBSTRING_INSTALLED && api_iconv_supports($encoding)) {
global $_api_encoding;
$_api_encoding = $encoding;
api_mb_regex_encoding('UTF-8');
if ($count < 3) {
$result = @mb_eregi(api_utf8_encode($pattern, $encoding), api_utf8_encode($string, $encoding));
} else {
$result = @mb_eregi(api_utf8_encode($pattern, $encoding), api_utf8_encode($string, $encoding), $regs);
$regs = _api_array_utf8_decode($regs, $encoding);
$regs = _api_array_utf8_decode($regs);
}
api_mb_regex_encoding($encoding);
return $result;
@ -1367,13 +1529,15 @@ function api_split($pattern, $string, $limit = null) {
}
}
elseif (MBSTRING_INSTALLED && api_iconv_supports($encoding)) {
global $_api_encoding;
$_api_encoding = $encoding;
api_mb_regex_encoding('UTF-8');
if (is_null($limit)) {
$result = @mb_split(api_utf8_encode($pattern, $encoding), api_utf8_encode($string, $encoding));
} else {
$result = @mb_split(api_utf8_encode($pattern, $encoding), api_utf8_encode($string, $encoding), $limit);
}
$result = _api_array_utf8_decode($result, $encoding);
$result = _api_array_utf8_decode($result);
api_mb_regex_encoding($encoding);
return $result;
} else {
@ -1916,7 +2080,7 @@ function api_rsort(&$array, $sort_flag = SORT_REGULAR, $language = null, $encodi
* '&#1060;&#1105;&#1076;&#1086;&#1088; '.
* '&#1052;&#1080;&#1093;&#1072;&#1081;&#1083;&#1086;&#1074;&#1080;&#1095; '.
* '&#1044;&#1086;&#1089;&#1090;&#1086;&#1077;&#1074;&#1082;&#1080;&#1081;',
* ENT_QUOTES, 'UTF-8'), 'UTF-8');
* ENT_QUOTES, 'UTF-8'), 'X', 'UTF-8');
* The output should be: Fyodor Mihaylovich Dostoevkiy
*
* @param string $string The input string.
@ -2194,24 +2358,34 @@ yoruba: ISO-8859-15, WINDOWS-1252, ISO-8859-1;
/**
* This function unifies the encoding identificators, so they could be compared.
* @param string $encoding The specified encoding.
* @param string/array $encoding The specified encoding.
* @return string Returns the encoding identificator modified in suitable for comparison way.
*/
function api_refine_encoding_id($encoding) {
if (is_array($encoding)){
return array_map('strtoupper', $encoding);
}
return strtoupper($encoding);
}
/**
* This function checks whether two $encoding are equal (same, equvalent).
* @param string $encoding1 The first encoding
* @param string $encoding2 The second encoding
* @param string/array $encoding1 The first encoding
* @param string/array $encoding2 The second encoding
* @return bool Returns TRUE if the encodings are equal, FALSE otherwise.
*/
function api_equal_encodings($encoding1, $encoding2) {
// We have to deal with aliases. This function alone does not solve
// the problem entirely. And there is no time for this kind of research.
// At the momemnt, the quick proposition could be:
return strcmp(api_refine_encoding_id($encoding1), api_refine_encoding_id($encoding2)) == 0 ? true : false;
$is_array_encoding1 = is_array($encoding1);
$is_array_encoding2 = is_array($encoding2);
$encoding1 = api_refine_encoding_id($encoding1);
$encoding2 = api_refine_encoding_id($encoding2);
if (!$is_array_encoding1 && !$is_array_encoding2) {
return $encoding1 == $encoding2;
}
if ($is_array_encoding2) {
return in_array($encoding1, $encoding2);
}
return in_array($encoding2, $encoding1);
}
/**
@ -2222,27 +2396,33 @@ function api_equal_encodings($encoding1, $encoding2) {
function api_is_utf8($encoding) {
static $result = array();
if (!isset($result[$encoding])) {
$result[$encoding] = api_equal_encodings($encoding, 'UTF-8');
$result[$encoding] = api_equal_encodings($encoding, array('UTF-8', 'CP65001', 'WINDOWS-65001'));
}
return $result[$encoding];
}
/**
* This function checks whether a given encoding represents (is an alias of) ISO Latin 1 character set.
* @param string $encoding The tested encoding.
* @param string/array $encoding The tested encoding.
* @return bool Returns TRUE if the given encoding id means Latin 1 character set, otherwise returns false.
*/
function api_is_latin1($encoding, $strict = false) {
static $latin1_encodings = array('ISO-8859-1', 'ISO8859-1', 'CP819', 'LATIN1');
static $latin1_encodings_like = array(
static $latin1 = array();
static $latin1_strict = array();
if ($strict) {
if (!isset($latin1_strict[$encoding])) {
$latin1_strict[$encoding] = api_equal_encodings($encoding, array('ISO-8859-1', 'ISO8859-1', 'CP819', 'LATIN1'));
}
return $latin1_strict[$encoding];
}
if (!isset($latin1[$encoding])) {
$latin1[$encoding] = api_equal_encodings($encoding, array(
'ISO-8859-1', 'ISO8859-1', 'CP819', 'LATIN1',
'ISO-8859-15', 'ISO8859-15', 'CP923', 'LATIN0', 'LATIN-9',
'WINDOWS-1252', 'CP1252', 'WIN-1252', 'WIN1252'
);
if ($strict) {
return in_array(api_refine_encoding_id($encoding), $latin1_encodings);
));
}
return in_array(api_refine_encoding_id($encoding), $latin1_encodings_like);
return $latin1[$encoding];
}
/**
@ -2461,7 +2641,11 @@ function api_iconv_set_encoding($type, $encoding = null) {
* @return bool Returns TRUE when the specified encoding is supported, FALSE othewise.
*/
function api_is_encoding_supported($encoding) {
return api_mb_supports($encoding) || api_iconv_supports($encoding) || _api_convert_encoding_supports($encoding);
static $supported = array();
if (!isset($supported[$encoding])) {
$supported[$encoding] = api_mb_supports($encoding) || api_iconv_supports($encoding) || _api_convert_encoding_supports($encoding);
}
return $supported[$encoding];
}
/**

95
main/inc/lib/multibyte_string_functions_internal.lib.php
Unescape View File

@ -10,6 +10,10 @@
* ==============================================================================
*/
// Global variables used by some callback functions.
$_api_encoding = null;
$_api_collator = null;
/**
* ----------------------------------------------------------------------------
@ -21,7 +25,6 @@
function _api_convert_encoding($string, $to_encoding, $from_encoding) {
static $character_map = array();
static $utf8_like = array('UTF-8', 'US-ASCII');
static $unknown = 63; // '?'
if (empty($string)) {
return $string;
}
@ -56,7 +59,7 @@ function _api_convert_encoding($string, $to_encoding, $from_encoding) {
if (isset($character_map[$from]['local'][$ord])) {
$codepoints[] = $character_map[$from]['local'][$ord];
} else {
$codepoints[] = $unknown;
$codepoints[] = 0xFFFD; // U+FFFD REPLACEMENT CHARACTER is the general substitute character in the Unicode Standard.
}
} else {
$codepoints[] = $ord;
@ -66,13 +69,12 @@ function _api_convert_encoding($string, $to_encoding, $from_encoding) {
$codepoints = _api_utf8_to_unicode($string);
}
if ($to != 'UTF-8') {
$unknown_char = chr($unknown);
foreach ($codepoints as $i => &$codepoint) {
if ($codepoint > 127) {
if (isset($character_map[$from]['local'][$codepoint])) {
$codepoint = chr($character_map[$from]['local'][$codepoint]);
} else {
$codepoint = $unknown_char;
$codepoint = '?'; // Unknown character.
}
} else {
$codepoint = chr($codepoint);
@ -138,16 +140,12 @@ function &_api_parse_character_map($name) {
* output can be > 0xFFFF. Occurrances of the BOM are ignored. Surrogates
* are not allowed.
* @param string $string The UTF-8 encoded string.
* @param string $unknown (optional) A US-ASCII character to represent invalid bytes.
* @return array Returns an array of unicode code points.
* @author Henri Sivonen, mailto:hsivonen@iki.fi
* @link http://hsivonen.iki.fi/php-utf8/
* @author Ivan Tcholakov, 2009, modifications for the Dokeos LMS.
*/
function _api_utf8_to_unicode($string, $unknown = '?') {
if (!empty($unknown)) {
$unknown = ord($unknown[0]);
}
function _api_utf8_to_unicode($string) {
$state = 0; // cached expected number of octets after the current octet
// until the beginning of the next UTF8 character sequence
$codepoint = 0; // cached Unicode character
@ -204,9 +202,7 @@ function _api_utf8_to_unicode($string, $unknown = '?') {
$state = 0;
$codepoint = 0;
$bytes = 1;
if (!empty($unknown)) {
$result[] = $unknown;
}
$result[] = 0xFFFD; // U+FFFD REPLACEMENT CHARACTER is the general substitute character in the Unicode Standard.
continue ;
}
} else {
@ -234,9 +230,7 @@ function _api_utf8_to_unicode($string, $unknown = '?') {
$state = 0;
$codepoint = 0;
$bytes = 1;
if (!empty($unknown)) {
$result[] = $unknown;
}
$result[] = 0xFFFD;
continue ;
}
if (0xFEFF != $codepoint) {
@ -254,9 +248,7 @@ function _api_utf8_to_unicode($string, $unknown = '?') {
$state = 0;
$codepoint = 0;
$bytes = 1;
if (!empty($unknown)) {
$result[] = $unknown;
}
$result[] = 0xFFFD;
}
}
}
@ -264,33 +256,28 @@ function _api_utf8_to_unicode($string, $unknown = '?') {
}
/**
* Takes an array of ints representing the Unicode characters and returns
* a UTF-8 string. Astral planes are supported ie. the ints in the
* input can be > 0xFFFF. Occurrances of the BOM are ignored. Surrogates
* are not allowed.
* @param array $array An array of unicode code points representing a string.
* @param string $unknown (optional) A US-ASCII character to represent invalid bytes.
* Takes an array of ints representing the Unicode characters and returns a UTF-8 string.
* @param array $codepoints An array of unicode code points representing a string.
* @return string Returns a UTF-8 string constructed using the given code points.
* @author Henri Sivonen, mailto:hsivonen@iki.fi
* @link http://hsivonen.iki.fi/php-utf8/
* @author Ivan Tcholakov, 2009, modifications for the Dokeos LMS.
* @see _api_utf8_from_unicodepoint()
*/
function _api_utf8_from_unicode($array, $unknown = '?') {
foreach ($array as $i => &$codepoint) {
$codepoint = _api_utf8_from_unicodepoint($codepoint, $unknown);
}
return implode($array);
function _api_utf8_from_unicode($codepoints) {
return implode(array_map('_api_utf8_chr', $codepoints));
}
/**
* Takes an integer value and returns its correspondent representing the Unicode character.
* Takes an integer value (codepoint) and returns its correspondent representing the Unicode character.
* Astral planes are supported, ie the intger input can be > 0xFFFF. Occurrances of the BOM are ignored.
* Surrogates are not allowed.
* @param array $array An array of unicode code points representing a string
* @param string $unknown (optional) A US-ASCII character to represent invalid bytes.
* @return string Returns the corresponding UTF-8 character.
* @author Henri Sivonen, mailto:hsivonen@iki.fi
* @link http://hsivonen.iki.fi/php-utf8/
* @author Ivan Tcholakov, 2009, modifications for the Dokeos LMS.
* @see _api_utf8_from_unicode()
* This is a UTF-8 aware version of the function chr().
* @link http://php.net/manual/en/function.chr.php
*/
function _api_utf8_from_unicodepoint($codepoint, $unknown = '?') {
function _api_utf8_chr($codepoint) {
// ASCII range (including control chars)
if ( ($codepoint >= 0) && ($codepoint <= 0x007f) ) {
$result = chr($codepoint);
@ -304,7 +291,7 @@ function _api_utf8_from_unicodepoint($codepoint, $unknown = '?') {
// Test for illegal surrogates
} else if ($codepoint >= 0xD800 && $codepoint <= 0xDFFF) {
// found a surrogate
$result = $unknown;
$result = _api_utf8_chr(0xFFFD); // U+FFFD REPLACEMENT CHARACTER is the general substitute character in the Unicode Standard.
// 3 byte sequence
} else if ($codepoint <= 0xffff) {
$result = chr(0xe0 | ($codepoint >> 12)) . chr(0x80 | (($codepoint >> 6) & 0x003f)) . chr(0x80 | ($codepoint & 0x003f));
@ -313,11 +300,27 @@ function _api_utf8_from_unicodepoint($codepoint, $unknown = '?') {
$result = chr(0xf0 | ($codepoint >> 18)) . chr(0x80 | (($codepoint >> 12) & 0x3f)) . chr(0x80 | (($codepoint >> 6) & 0x3f)) . chr(0x80 | ($codepoint & 0x3f));
} else {
// out of range
$result = $unknown;
$result = _api_utf8_chr(0xFFFD);
}
return $result;
}
/**
* Takes the first UTF-8 character in a string and returns its codepoint (integer).
* @param string $utf8_character The UTF-8 encoded character.
* @return int Returns: the codepoint; or 0xFFFD (unknown character) when the input string is empty.
* This is a UTF-8 aware version of the function ord().
* @link http://php.net/manual/en/function.ord.php
* Note about a difference with the original funtion ord(): ord('') returns 0.
*/
function _api_utf8_ord($utf8_character) {
if (empty($utf8_character)) {
return 0xFFFD;
}
$codepoints = _api_utf8_to_unicode($utf8_character);
return $codepoints[0];
}
/**
* ----------------------------------------------------------------------------
@ -329,7 +332,6 @@ function _api_utf8_from_unicodepoint($codepoint, $unknown = '?') {
function _api_utf8_get_letter_case_properties($codepoint, $type = 'lower') {
static $config = array();
static $range = array();
if (!isset($range[$codepoint])) {
if ($codepoint > 128 && $codepoint < 256) {
$range[$codepoint] = '0080_00ff'; // Latin-1 Supplement
@ -368,7 +370,6 @@ function _api_utf8_get_letter_case_properties($codepoint, $type = 'lower') {
} else {
$range[$codepoint] = false;
}
if ($range[$codepoint] === false) {
return null;
}
@ -379,14 +380,11 @@ function _api_utf8_get_letter_case_properties($codepoint, $type = 'lower') {
}
}
}
if ($range[$codepoint] === false || !isset($config[$range[$codepoint]])) {
return null;
}
$result = array();
$count = count($config[$range[$codepoint]]);
for ($i = 0; $i < $count; $i++) {
if ($type === 'lower' && $config[$range[$codepoint]][$i][$type][0] === $codepoint) {
$result[] = $config[$range[$codepoint]][$i];
@ -406,12 +404,13 @@ function _api_utf8_get_letter_case_properties($codepoint, $type = 'lower') {
// This (callback) function convers from UTF-8 to other encoding.
// It works with arrays of strings too.
function _api_array_utf8_decode($variable, $encoding) {
function _api_array_utf8_decode($variable) {
global $_api_encoding;
if (is_array($variable)) {
return array_map('_api_array_utf8_decode', $variable, $encoding);
return array_map('_api_array_utf8_decode', $variable);
}
if (is_string($var)) {
return api_utf8_decode($variable, $encoding);
return api_utf8_decode($variable, $_api_encoding);
}
return $variable;
}
@ -451,10 +450,6 @@ function _api_get_alpha_numerical_collator($language = null) {
return $collator[$language];
}
// Global variables used by the sorting functions.
$_api_collator = null;
$_api_encoding = null;
// A string comparison function that serves sorting functions.
function _api_cmp($string1, $string2) {
global $_api_collator, $_api_encoding;

Write Preview
Loading…
Cancel
Save