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

Issue #306 - The multibute string library: Logic upgrades, optimizations for speed.

Browse Source
skala
Ivan Tcholakov 16 years ago
parent a29e18b691
commit 51a649cd96
2 changed files with 239 additions and 107 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. 331
      main/inc/lib/multibyte_string_functions.lib.php
  2. 15
      main/inc/lib/multibyte_string_functions_internal.lib.php

331
main/inc/lib/multibyte_string_functions.lib.php
Unescape View File

@ -410,29 +410,37 @@ function api_str_ireplace($search, $replace, $subject, & $count = null, $encodin
* @link http://php.net/str_split * @link http://php.net/str_split
*/ */
function api_str_split($string, $split_length = 1, $encoding = null) { function api_str_split($string, $split_length = 1, $encoding = null) {
if ($split_length < 1) {
return false;
}
if (empty($encoding)) { if (empty($encoding)) {
$encoding = api_mb_internal_encoding(); $encoding = api_mb_internal_encoding();
} }
if (empty($string)) {
return array();
}
if ($split_length < 1) {
return false;
}
if (_api_is_single_byte_encoding($encoding)) { if (_api_is_single_byte_encoding($encoding)) {
return str_split($string, $split_length); return str_split($string, $split_length);
} }
$result = array(); if (api_is_encoding_supported($encoding)) {
if (api_mb_supports($encoding)) { $len = api_strlen($string);
for ($i = 0, $length = @mb_strlen($string, $encoding); $i < $length; $i += $split_length) { if ($len <= $split_length) {
$result[] = @mb_substr($string, $i, $split_length, $encoding); return array($string);
} }
} if (!api_is_utf8($encoding)) {
elseif (api_is_encoding_supported($encoding)) { $string = api_utf8_encode($string, $encoding);
for ($i = 0, $length = api_strlen($string, $encoding); $i < $length; $i += $split_length) {
$result[] = api_substr($string, $i, $split_length, $encoding);
} }
} else { if (preg_match_all('/.{'.$split_length.'}|[^\x00]{1,'.$split_length.'}$/us', $string, $result) === false) {
return str_split($string, $split_length); return array();
}
if (!api_is_utf8($encoding)) {
global $_api_encoding;
$_api_encoding = $encoding;
$result = _api_array_utf8_decode($result[0]);
}
return $result[0];
} }
return $result; return str_split($string, $split_length);
} }
/** /**
@ -456,22 +464,22 @@ function api_stripos($haystack, $needle, $offset = 0, $encoding = null) {
} }
elseif (api_is_encoding_supported($encoding)) { elseif (api_is_encoding_supported($encoding)) {
if (MBSTRING_INSTALLED) { if (MBSTRING_INSTALLED) {
return api_utf8_decode(@mb_stripos(api_utf8_encode($haystack, $encoding), api_utf8_encode($needle, $encoding), $offset, 'UTF-8'), $encoding); return @mb_stripos(api_utf8_encode($haystack, $encoding), api_utf8_encode($needle, $encoding), $offset, 'UTF-8');
} else {
return api_strpos(api_strtolower($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, $offset); return stripos($haystack, $needle, $offset);
} }
/** /**
* Finds first occurrence of a string within another, case insensitive. * Finds first occurrence of a string within another, case insensitive.
* @param string $haystack The string from which to get the first occurrence. * @param string $haystack The string from which to get the first occurrence.
* @param string @needle The string to be found. * @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 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. * @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. * @return mixed Returns the portion of $haystack, or FALSE if $needle is not found.
* Notes: * Notes:
* 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 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. * If $before_needle is set to FALSE, the function returns all of $haystack from the first occurrence of $needle to the end.
* This function is aimed at replacing the functions stristr() and mb_stristr() for human-language strings. * This function is aimed at replacing the functions stristr() and mb_stristr() for human-language strings.
@ -482,13 +490,25 @@ function api_stristr($haystack, $needle, $before_needle = false, $encoding = nul
if (empty($encoding)) { if (empty($encoding)) {
$encoding = api_mb_internal_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($encoding)) { if (api_mb_supports($encoding)) {
return @mb_stristr($haystack, $needle, $before_needle, $encoding); return @mb_stristr($haystack, $needle, $before_needle, $encoding);
} }
elseif (MBSTRING_INSTALLED && api_is_encoding_supported($encoding)) {
return api_utf8_decode(@mb_stristr(api_utf8_encode($haystack, $encoding), api_utf8_encode($needle, $encoding), $before_needle, 'UTF-8'));
}
elseif (api_is_encoding_supported($encoding)) { 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); $result = api_strstr(api_strtolower($haystack, $encoding), api_strtolower($needle, $encoding), $before_needle, $encoding);
if ($result === false) { if ($result === false) {
return false; return false;
@ -559,10 +579,10 @@ function api_strpos($haystack, $needle, $offset = 0, $encoding = null) {
elseif (api_mb_supports($encoding)) { elseif (api_mb_supports($encoding)) {
return @mb_strpos($haystack, $needle, $offset, $encoding); return @mb_strpos($haystack, $needle, $offset, $encoding);
} }
elseif (MBSTRING_INSTALLED && (api_iconv_supports($encoding) || _api_convert_encoding_supports($encoding))) { elseif (api_is_encoding_supported($encoding)) {
return api_utf8_decode(@mb_strpos(api_utf8_encode($haystack, $encoding), api_utf8_encode($needle, $encoding), $offset, 'UTF-8'), $encoding); if (MBSTRING_INSTALLED) {
} return @mb_strpos(api_utf8_encode($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)) { if (!api_is_utf8($encoding)) {
$haystack = api_utf8_encode($haystack, $encoding); $haystack = api_utf8_encode($haystack, $encoding);
$needle = api_utf8_encode($needle, $encoding); $needle = api_utf8_encode($needle, $encoding);
@ -573,25 +593,25 @@ function api_strpos($haystack, $needle, $offset = 0, $encoding = null) {
return api_strlen($haystack[0]); return api_strlen($haystack[0]);
} }
return false; return false;
} else {
$haystack = api_substr($haystack, $offset);
if (($pos = api_strpos($haystack, $needle)) !== false ) {
return $pos + $offset;
}
return false;
} }
$haystack = api_substr($haystack, $offset);
if (($pos = api_strpos($haystack, $needle)) !== false ) {
return $pos + $offset;
}
return false;
} }
return strpos($haystack, $needle, $offset); return strpos($haystack, $needle, $offset);
} }
/** /**
* Finds the last occurrence of a character in a string. * Finds the last occurrence of a character in a string.
* @param string $haystack The string from which to get the last occurrence. * @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 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 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. * @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. * @return mixed Returns the portion of $haystack, or FALSE if the first character from $needle is not found.
* Notes: * Notes:
* 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 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. * If $before_needle is set to FALSE, the function returns all of $haystack from the first occurrence to the end.
* This function is aimed at replacing the functions strrchr() and mb_strrchr() for human-language strings. * This function is aimed at replacing the functions strrchr() and mb_strrchr() for human-language strings.
@ -602,16 +622,42 @@ function api_strrchr($haystack, $needle, $before_needle = false, $encoding = nul
if (empty($encoding)) { if (empty($encoding)) {
$encoding = api_mb_internal_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($encoding)) { if (_api_is_single_byte_encoding($encoding)) {
return strrchr($haystack, $needle); if (!$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)) { elseif (api_mb_supports($encoding)) {
return @mb_strrchr($haystack, $needle, $before_needle, $encoding); return @mb_strrchr($haystack, $needle, $before_needle, $encoding);
} }
elseif (MBSTRING_INSTALLED && (api_iconv_supports($encoding) || _api_convert_encoding_supports($encoding))) { elseif (MBSTRING_INSTALLED && api_is_encoding_supported($encoding)) {
return api_utf8_decode(@mb_strrchr(api_utf8_encode($haystack, $encoding), api_utf8_encode($needle, $encoding), $before_needle, 'UTF-8'), $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 strrchr($haystack, $needle); return api_substr($haystack, 0, api_strlen($haystack, $encoding) - api_strlen($result, $encoding), $encoding);
} }
/** /**
@ -623,17 +669,19 @@ function api_strrchr($haystack, $needle, $before_needle = false, $encoding = nul
* @link http://php.net/manual/en/function.strrev * @link http://php.net/manual/en/function.strrev
*/ */
function api_strrev($string, $encoding = null) { function api_strrev($string, $encoding = null) {
if (empty($encoding)) {
$encoding = api_mb_internal_encoding();
}
if (empty($string)) { if (empty($string)) {
return ''; return '';
} }
if (empty($encoding)) { if (_api_is_single_byte_encoding($encoding)) {
$encoding = api_mb_internal_encoding(); return strrev($string);
} }
$result = ''; if (api_is_encoding_supported($encoding)) {
for ($i = api_strlen($string, $encoding) - 1; $i > -1; $i--) { return implode(array_reverse(api_str_split($string, 1, $encoding)));
$result .= api_substr($string, $i, 1, $encoding);
} }
return $result; return strrev($string);
} }
/** /**
@ -652,23 +700,62 @@ function api_strrpos($haystack, $needle, $offset = 0, $encoding = null) {
if (empty($encoding)) { if (empty($encoding)) {
$encoding = api_mb_internal_encoding(); $encoding = api_mb_internal_encoding();
} }
if (_api_is_single_byte_encoding($encoding)) {
return strrpos($haystack, $needle, $offset);
}
if (api_mb_supports($encoding)) { if (api_mb_supports($encoding)) {
return @mb_strrpos($haystack, $needle, $offset, $encoding); return @mb_strrpos($haystack, $needle, $offset, $encoding);
} }
elseif (MBSTRING_INSTALLED && api_iconv_supports($encoding)) { elseif (api_is_encoding_supported($encoding)) {
return api_utf8_decode(@mb_strrpos(api_utf8_encode($haystack, $encoding), api_utf8_encode($needle, $encoding), $offset, 'UTF-8'), $encoding); if (MBSTRING_INSTALLED) {
return @mb_strrpos(api_utf8_encode($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, $offset); return strrpos($haystack, $needle, $offset);
} }
/** /**
* Finds first occurrence of a string within another. * Finds first occurrence of a string within another.
* @param string $haystack The string from which to get the first occurrence. * @param string $haystack The string from which to get the first occurrence.
* @param string @needle The string to be found. * @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 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. * @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. * @return mixed Returns the portion of $haystack, or FALSE if $needle is not found.
* Notes: * Notes:
* 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 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. * If $before_needle is set to FALSE, the function returns all of $haystack from the first occurrence of $needle to the end.
* This function is aimed at replacing the functions strstr() and mb_strstr() for human-language strings. * This function is aimed at replacing the functions strstr() and mb_strstr() for human-language strings.
@ -742,14 +829,14 @@ function api_strtolower($string, $encoding = null) {
if (api_mb_supports($encoding)) { if (api_mb_supports($encoding)) {
return @mb_strtolower($string, $encoding); return @mb_strtolower($string, $encoding);
} }
elseif (MBSTRING_INSTALLED && api_iconv_supports($encoding)) { elseif (api_is_encoding_supported($encoding)) {
return api_utf8_decode(@mb_strtolower(api_utf8_encode($string, $encoding), 'UTF-8'), $encoding); if (MBSTRING_INSTALLED) {
} return api_utf8_decode(@mb_strtolower(api_utf8_encode($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)) { if (!api_is_utf8($encoding)) {
$string = api_utf8_encode($string, $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); $codepoints = _api_utf8_to_unicode($string);
$length = count($codepoints); $length = count($codepoints);
$matched = false; $matched = false;
@ -806,14 +893,14 @@ function api_strtoupper($string, $encoding = null) {
if (api_mb_supports($encoding)) { if (api_mb_supports($encoding)) {
return @mb_strtoupper($string, $encoding); return @mb_strtoupper($string, $encoding);
} }
elseif (MBSTRING_INSTALLED && api_iconv_supports($encoding)) { elseif (api_is_encoding_supported($encoding)) {
return api_utf8_decode(@mb_strtoupper(api_utf8_encode($string, $encoding), 'UTF-8'), $encoding); if (MBSTRING_INSTALLED) {
} return api_utf8_decode(@mb_strtoupper(api_utf8_encode($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)) { if (!api_is_utf8($encoding)) {
$string = api_utf8_encode($string, $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); $codepoints = _api_utf8_to_unicode($string);
$length = count($codepoints); $length = count($codepoints);
$matched = false; $matched = false;
@ -966,14 +1053,20 @@ function api_substr($string, $start, $length = null, $encoding = null) {
if (is_null($length)) { if (is_null($length)) {
$length = api_strlen($string, $encoding); $length = api_strlen($string, $encoding);
} }
if (_api_is_single_byte_encoding($encoding)) {
return substr($string, $start, $length);
}
if (api_mb_supports($encoding)) { if (api_mb_supports($encoding)) {
return @mb_substr($string, $start, $length, $encoding); return @mb_substr($string, $start, $length, $encoding);
} }
elseif (MBSTRING_INSTALLED && api_iconv_supports($encoding)) { elseif (api_is_encoding_supported($encoding)) {
return api_utf8_decode(@mb_substr(api_utf8_encode($string, $encoding), $start, $length, 'UTF-8'), $encoding); if (MBSTRING_INSTALLED) {
} return api_utf8_decode(@mb_substr(api_utf8_encode($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(). // 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); $strlen = api_byte_count($string);
// Find the starting byte offset // Find the starting byte offset
$bytes = 0; $bytes = 0;
@ -1034,7 +1127,11 @@ function api_substr($string, $start, $length = null, $encoding = null) {
} }
} }
$iend = $bytes; $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, $length); return substr($string, $start, $length);
} }
@ -1062,16 +1159,29 @@ function api_substr_replace($string, $replacement, $start, $length = null, $enco
if (empty($encoding)) { if (empty($encoding)) {
$encoding = api_mb_internal_encoding(); $encoding = api_mb_internal_encoding();
} }
if ($length == null) { if (api_is_encoding_supported($encoding) && !_api_is_single_byte_encoding($encoding)) {
return api_substr($string, 0, $start, $encoding) . $replacement; $string_length = api_strlen($string, $encoding);
} else { if ($start < 0) {
$start = max(0, $string_length + $start);
}
else if ($start > $string_length) {
$start = $string_length;
}
if ($length < 0) { if ($length < 0) {
$length = api_strlen($string, $encoding) - $start + $length; $length = max(0, $string_length - $start + $length);
} }
return else if (is_null($length) || ($length > $string_length)) {
api_substr($string, 0, $start, $encoding) . $replacement . $length = $string_length;
api_substr($string, $start + $length, api_strlen($string, $encoding), $encoding); }
if (($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, $length);
} }
/** /**
@ -1140,12 +1250,14 @@ function api_ereg($pattern, $string, & $regs = null) {
} }
} }
elseif (MBSTRING_INSTALLED && api_iconv_supports($encoding)) { elseif (MBSTRING_INSTALLED && api_iconv_supports($encoding)) {
global $_api_encoding;
$_api_encoding = $encoding;
api_mb_regex_encoding('UTF-8'); api_mb_regex_encoding('UTF-8');
if ($count < 3) { if ($count < 3) {
$result = @mb_ereg(api_utf8_encode($pattern, $encoding), api_utf8_encode($string, $encoding)); $result = @mb_ereg(api_utf8_encode($pattern, $encoding), api_utf8_encode($string, $encoding));
} else { } else {
$result = @mb_ereg(api_utf8_encode($pattern, $encoding), api_utf8_encode($string, $encoding), $regs); $result = @mb_ereg(api_utf8_encode($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($encoding); api_mb_regex_encoding($encoding);
return $result; return $result;
@ -1221,13 +1333,14 @@ function api_eregi($pattern, $string, & $regs = null) {
} }
} }
elseif (MBSTRING_INSTALLED && api_iconv_supports($encoding)) { elseif (MBSTRING_INSTALLED && api_iconv_supports($encoding)) {
global $_api_encoding;
$_api_encoding = $encoding;
api_mb_regex_encoding('UTF-8'); api_mb_regex_encoding('UTF-8');
if ($count < 3) { if ($count < 3) {
$result = @mb_eregi(api_utf8_encode($pattern, $encoding), api_utf8_encode($string, $encoding)); $result = @mb_eregi(api_utf8_encode($pattern, $encoding), api_utf8_encode($string, $encoding));
} else { } else {
$result = @mb_eregi(api_utf8_encode($pattern, $encoding), api_utf8_encode($string, $encoding), $regs); $result = @mb_eregi(api_utf8_encode($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($encoding); api_mb_regex_encoding($encoding);
return $result; return $result;
@ -1416,13 +1529,15 @@ function api_split($pattern, $string, $limit = null) {
} }
} }
elseif (MBSTRING_INSTALLED && api_iconv_supports($encoding)) { elseif (MBSTRING_INSTALLED && api_iconv_supports($encoding)) {
global $_api_encoding;
$_api_encoding = $encoding;
api_mb_regex_encoding('UTF-8'); api_mb_regex_encoding('UTF-8');
if (is_null($limit)) { if (is_null($limit)) {
$result = @mb_split(api_utf8_encode($pattern, $encoding), api_utf8_encode($string, $encoding)); $result = @mb_split(api_utf8_encode($pattern, $encoding), api_utf8_encode($string, $encoding));
} else { } else {
$result = @mb_split(api_utf8_encode($pattern, $encoding), api_utf8_encode($string, $encoding), $limit); $result = @mb_split(api_utf8_encode($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($encoding); api_mb_regex_encoding($encoding);
return $result; return $result;
} else { } else {
@ -2243,24 +2358,34 @@ yoruba: ISO-8859-15, WINDOWS-1252, ISO-8859-1;
/** /**
* This function unifies the encoding identificators, so they could be compared. * This function unifies the encoding identificators, so they could be compared.
* @param string $encoding The specified encoding. * @param string/array $encoding The specified encoding.
* @return string Returns the encoding identificator modified in suitable for comparison way. * @return string Returns the encoding identificator modified in suitable for comparison way.
*/ */
function api_refine_encoding_id($encoding) { function api_refine_encoding_id($encoding) {
if (is_array($encoding)){
return array_map('strtoupper', $encoding);
}
return strtoupper($encoding); return strtoupper($encoding);
} }
/** /**
* This function checks whether two $encoding are equal (same, equvalent). * This function checks whether two $encoding are equal (same, equvalent).
* @param string $encoding1 The first encoding * @param string/array $encoding1 The first encoding
* @param string $encoding2 The second encoding * @param string/array $encoding2 The second encoding
* @return bool Returns TRUE if the encodings are equal, FALSE otherwise. * @return bool Returns TRUE if the encodings are equal, FALSE otherwise.
*/ */
function api_equal_encodings($encoding1, $encoding2) { function api_equal_encodings($encoding1, $encoding2) {
// We have to deal with aliases. This function alone does not solve $is_array_encoding1 = is_array($encoding1);
// the problem entirely. And there is no time for this kind of research. $is_array_encoding2 = is_array($encoding2);
// At the momemnt, the quick proposition could be: $encoding1 = api_refine_encoding_id($encoding1);
return strcmp(api_refine_encoding_id($encoding1), api_refine_encoding_id($encoding2)) == 0 ? true : false; $encoding2 = api_refine_encoding_id($encoding2);
if (!$is_array_encoding1 && !$is_array_encoding2) {
return $encoding1 == $encoding2;
}
if ($is_array_encoding2) {
return in_array($encoding1, $encoding2);
}
return in_array($encoding2, $encoding1);
} }
/** /**
@ -2271,27 +2396,33 @@ function api_equal_encodings($encoding1, $encoding2) {
function api_is_utf8($encoding) { function api_is_utf8($encoding) {
static $result = array(); static $result = array();
if (!isset($result[$encoding])) { if (!isset($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]; return $result[$encoding];
} }
/** /**
* This function checks whether a given encoding represents (is an alias of) ISO Latin 1 character set. * 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 $encoding The tested encoding.
* @return bool Returns TRUE if the given encoding id means Latin 1 character set, otherwise returns false. * @return bool Returns TRUE if the given encoding id means Latin 1 character set, otherwise returns false.
*/ */
function api_is_latin1($encoding, $strict = false) { function api_is_latin1($encoding, $strict = false) {
static $latin1_encodings = array('ISO-8859-1', 'ISO8859-1', 'CP819', 'LATIN1'); static $latin1 = array();
static $latin1_encodings_like = array( static $latin1_strict = array();
'ISO-8859-1', 'ISO8859-1', 'CP819', 'LATIN1',
'ISO-8859-15', 'ISO8859-15', 'CP923', 'LATIN0', 'LATIN-9',
'WINDOWS-1252', 'CP1252', 'WIN-1252', 'WIN1252'
);
if ($strict) { if ($strict) {
return in_array(api_refine_encoding_id($encoding), $latin1_encodings); if (!isset($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($encoding, array(
'ISO-8859-1', 'ISO8859-1', 'CP819', 'LATIN1',
'ISO-8859-15', 'ISO8859-15', 'CP923', 'LATIN0', 'LATIN-9',
'WINDOWS-1252', 'CP1252', 'WIN-1252', 'WIN1252'
));
} }
return in_array(api_refine_encoding_id($encoding), $latin1_encodings_like); return $latin1[$encoding];
} }
/** /**

15
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;
$_api_collator = null;
/** /**
* ---------------------------------------------------------------------------- * ----------------------------------------------------------------------------
@ -400,12 +404,13 @@ function _api_utf8_get_letter_case_properties($codepoint, $type = 'lower') {
// This (callback) function convers from UTF-8 to other encoding. // This (callback) function convers from UTF-8 to other encoding.
// It works with arrays of strings too. // It works with arrays of strings too.
function _api_array_utf8_decode($variable, $encoding) { function _api_array_utf8_decode($variable) {
global $_api_encoding;
if (is_array($variable)) { 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)) { if (is_string($var)) {
return api_utf8_decode($variable, $encoding); return api_utf8_decode($variable, $_api_encoding);
} }
return $variable; return $variable;
} }
@ -445,10 +450,6 @@ function _api_get_alpha_numerical_collator($language = null) {
return $collator[$language]; return $collator[$language];
} }
// Global variables used by the sorting functions.
$_api_collator = null;
$_api_encoding = null;
// A string comparison function that serves sorting functions. // A string comparison function that serves sorting functions.
function _api_cmp($string1, $string2) { function _api_cmp($string1, $string2) {
global $_api_collator, $_api_encoding; global $_api_collator, $_api_encoding;

Write Preview
Loading…
Cancel
Save