/**
* Format a string data.
*
* @param string $str A string.
*
* @return string
*/
protected function formatString($str)
{
if (extension_loaded('mbstring')) {
$originalStr = $str;
$str = mb_convert_case($str, MB_CASE_TITLE, 'UTF-8');
// Correct for MB_TITLE_CASE's insistence on uppercasing letters
// immediately preceded by numerals, eg: 1st -> 1St
$originalEncoding = mb_regex_encoding();
mb_regex_encoding('UTF-8');
// matches an upper case letter character immediately preceded by a numeral
mb_ereg_search_init($str, '[0-9]\\p{Lu}');
while ($match = mb_ereg_search_pos()) {
$charPos = $match[0] + 1;
// Only swap it back to lowercase if it was lowercase to begin with
if (mb_ereg_match('\\p{Ll}', $originalStr[$charPos])) {
$str[$charPos] = mb_strtolower($str[$charPos]);
}
}
mb_regex_encoding($originalEncoding);
} else {
$str = $this->lowerize($str);
$str = ucwords($str);
}
$str = str_replace('-', '- ', $str);
$str = str_replace('- ', '-', $str);
return $str;
}
function test_search($test_enc, $str, $look_for, $opt, $in_enc = 'EUC-JP')
{
mb_regex_encoding($test_enc);
$str = mb_convert_encoding($str, $test_enc, $in_enc);
$look_for = mb_convert_encoding($look_for, $test_enc, $in_enc);
mb_ereg_search_init($str, $look_for, $opt);
while (mb_ereg_search_pos()) {
$regs = mb_ereg_search_getregs();
array_shift($regs);
printf("(%s) (%d) %s\n", $test_enc, mb_ereg_search_getpos(), mb_convert_encoding(is_array($regs) ? implode('-', $regs) : '', $in_enc, $test_enc));
}
}
/**
* A cross between mb_split and preg_split, adding the preg_split flags
* to mb_split.
* @param string $pattern
* @param string $string
* @param int $limit
* @param int $flags
* @return array
*/
private static function mbSplit($pattern, $string, $limit = -1, $flags = 0)
{
$strlen = strlen($string);
// bytes!
mb_ereg_search_init($string);
$lengths = array();
$position = 0;
while (($array = mb_ereg_search_pos($pattern, '')) !== false) {
// capture split
$lengths[] = array($array[0] - $position, false, null);
// move position
$position = $array[0] + $array[1];
// capture delimiter
$regs = mb_ereg_search_getregs();
$lengths[] = array($array[1], true, isset($regs[1]) && $regs[1]);
// Continue on?
if ($position >= $strlen) {
break;
}
}
// Add last bit, if not ending with split
$lengths[] = array($strlen - $position, false, null);
// Substrings
$parts = array();
$position = 0;
$count = 1;
foreach ($lengths as $length) {
$is_delimiter = $length[1];
$is_captured = $length[2];
if ($limit > 0 && !$is_delimiter && ($length[0] || ~$flags & PREG_SPLIT_NO_EMPTY) && ++$count > $limit) {
if ($length[0] > 0 || ~$flags & PREG_SPLIT_NO_EMPTY) {
$parts[] = $flags & PREG_SPLIT_OFFSET_CAPTURE ? array(mb_strcut($string, $position), $position) : mb_strcut($string, $position);
}
break;
} elseif ((!$is_delimiter || $flags & PREG_SPLIT_DELIM_CAPTURE && $is_captured) && ($length[0] || ~$flags & PREG_SPLIT_NO_EMPTY)) {
$parts[] = $flags & PREG_SPLIT_OFFSET_CAPTURE ? array(mb_strcut($string, $position, $length[0]), $position) : mb_strcut($string, $position, $length[0]);
}
$position += $length[0];
}
return $parts;
}
* NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
* DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
* THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
* THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/
$lang = $_REQUEST["lang"];
$xml = new SimpleXMLElement(file_get_contents("php://input"));
$spell = pspell_new($lang, "", "", "utf-8", PSPELL_NORMAL);
$suggestions = array();
$offset = 0;
mb_regex_encoding("UTF-8");
foreach (mb_split("\n", $xml->text) as $line) {
$len = mb_strlen($line, "UTF-8");
mb_ereg_search_init($line, "\\w+");
while (($wpos = mb_ereg_search_pos()) != FALSE) {
$word = mb_substr($line, $wpos[0], $wpos[1]);
if (!pspell_check($spell, $word)) {
$woffset = mb_strlen(mb_substr($line, 0, $wpos[0]), "UTF-8");
$wlen = mb_strlen($word, "UTF-8");
array_push($suggestions, array($offset + $woffset, $wlen, pspell_suggest($spell, $word)));
}
}
$offset += $len + 1;
}
$xml = new SimpleXMLElement("<spellresponse/>");
$xml->addAttribute("error", count($suggestions) ? "1" : "0");
foreach ($suggestions as $s) {
$c = $xml->addChild("c", join("\t", $s[2]));
$c->addAttribute("o", $s[0]);
$c->addAttribute("l", $s[1]);
$reg = "\\w+";
mb_regex_encoding("UTF-8");
mb_ereg_search_init($str, $reg);
$r = mb_ereg_search();
$r = mb_ereg_search_getregs();
// get first result
var_dump($r == array("PrÜÝ" . "fung"));
$str = "PrÜÝ" . "fung abc pÜ";
$reg = "\\w+";
mb_regex_encoding("UTF-8");
mb_ereg_search_init($str, $reg);
$r = mb_ereg_search();
$r = mb_ereg_search_getregs();
// get first result
var_dump($r == array("PrÜÝ" . "fung"));
var_dump(mb_ereg_search_pos());
$str = "PrÜÝ" . "fung abc pÜ";
$reg = "\\w+";
mb_regex_encoding("UTF-8");
mb_ereg_search_init($str, $reg);
$r = mb_ereg_search();
$r = mb_ereg_search_getregs();
// get first result
var_dump($r === array("PrÜÝ" . "fung"));
$r = mb_ereg_search_regs();
// get next result
var_dump($r);
$str = "PrÜÝ" . "fung abc pÜ";
$reg = "\\w+";
mb_regex_encoding("UTF-8");
mb_ereg_search_init($str, $reg);
if (isset($_POST['submit']) && isset($_POST['page']) && $_POST['page'] == $i) {
echo "selected";
}
echo ">" . $names[$i] . "</option>";
}
echo "</select>\n\t\t\t<input type='submit' name='submit' value='Edit'></form>";
//if there is a GET variable make a POST variable
if (isset($_GET['page'])) {
$_POST['page'] = $_GET['page'];
$_POST['submit'] = "submit";
}
//when they select which page, this is the form to edit it
if (isset($_POST['submit']) && isset($_POST['page'])) {
$page = $names[$_POST['page']];
$menu = $menu_names[$_POST['page']];
//read the file
$myFile = "../pages/{$menu}/{$page}.php";
$fh = fopen($myFile, "r");
$theData = fread($fh, filesize($myFile));
fclose($fh);
//search it for the div tag
mb_ereg_search_init($theData, "<div class='info'>");
$arro = mb_ereg_search_pos("<div class='info'>");
mb_ereg_search_init($theData, "</div>");
$arroc = mb_ereg_search_pos("</div>");
echo "<form action='change_page.php' method='POST'>\n\t\t\t\t<textarea rows='15' cols='40' name='body'>";
//get the substring between the tags and get rid of the whitespace before and after
echo trim(strip_tags(substr($theData, $arro[0] + $arro[1], $arroc[0] - ($arro[0] + $arro[1]))));
echo "</textarea>\n\t\t\t\t<input type='hidden' name='x' value='{$x[$_POST['page']]}'>\n\t\t\t\t<input type='hidden' name='y' value='{$y[$_POST['page']]}'>\n\t\t\t\t<input type='hidden' name='z' value='{$z[$_POST['page']]}'>\n\t\t\t\t<input type='hidden' name='name' value='{$page}'>\n\t\t\t\t<input type='hidden' name='html' value='n'>\n\t\t\t\t<input type='hidden' name='nav' value='n'>\n\t\t\t\t<input type='submit' name='submit' value='Save'>\n\t\t\t\t</form>";
}
include "../includes/layout/b2.php";
function wrsqz_extractTextFromMathML($formula, $encoded=true){
//Algorythm: We scan the mathML tag by tag.
//If a tag is one of the allowed (math, mrow) we save it at the stack
//and continue with the next.
//If the tag is not allowed (mfenced, mfrac,...) we skip all mathML until its
//closure (</mfenced>, </mfrac>)
//If the tag is <mtext> we rearange the formula
//If a tag is a closure of allowed tag, we pop it from the stack.
//rapid return if nothing to do.
if(strpos($formula,'mtext')===false) return $formula;
//initializations
$opentag = $encoded ? '«' : '<';
$closetag = $encoded ? '»' : '>';
//tags where an <mtext> can live inside.
$allowedtags = array('math', 'mrow');
$pattern = $opentag.'([^'.$opentag.$closetag.']*)'.$closetag; //regexp that matches a single tag label
mb_ereg_search_init($formula, $pattern);
$stack = array(); //stack of opened tags
$omittedcontent=false; //there is math content before the current point?
$lasttag=null; //last tag of the stack
$length = strlen($formula);
$beginformula = strpos($formula, $opentag); //position of the first character of the last formula (in bytes).
$pos=array(0,0);
//CAUTION: If you change this function, be very carefull with multibyte
// and non-multibyte functions.
while(($pos[0]+$pos[1])<$length){
$pos = mb_ereg_search_pos($pattern);
if($pos[0]+$pos[1] < $length){
//this will be always true but the last iteration
mb_ereg_search_setpos($pos[0]+$pos[1]);
}
$tag = substr($formula, $pos[0],$pos[1]);
$trimmedTag = mb_substr($tag,1,-1);
//skip autoclosed tags
if(mb_substr($trimmedTag,-1) == '/'){
continue;
}
//discard attributes
if(($spacepos = mb_strpos($trimmedTag,' '))!==false){
$trimmedTag=mb_substr($trimmedTag,0,$spacepos);
}
if(in_array($trimmedTag,$allowedtags)){
//allowed tag
$stack[]=array($trimmedTag,$tag);
$lasttag = $trimmedTag;
}else if($trimmedTag == '/'.$lasttag){
//close allowed tag
array_pop($stack);
$lasttag = end($stack);
$lasttag = $lasttag[0];
//discard empty formulas
if(empty($stack) && !$omittedcontent){
$formula1 = substr($formula, 0, $beginformula);
if($pos[0]+$pos[1]<$length){
//this isn't the end.
$formula2 = substr($formula, $pos[0]+$pos[1]);
$formula = $formula1 . $formula2;
$length = strlen($formula);
mb_ereg_search_init($formula, $pattern);
mb_ereg_search_setpos($beginformula);
}else{
//this is the last iteration. $length and mb_ereg_search
//string and position will be wrong, but it doesn't matter.
$formula = $formula1;
}
}
}else if($trimmedTag == 'mtext'){
$pos2 = mb_ereg_search_pos($opentag.'/mtext'.$closetag);
$text = substr($formula, $pos[0]+$pos[1], $pos2[0]-($pos[0]+$pos[1]));
//Decode some chars in text
if($encoded) $text=wrsqz_mathmlDecode($text);
$text = str_replace('·','·',$text);
$text = str_replace(''',''',$text);
$formula1 = substr($formula, 0, $pos[0]); //until <mtext>
$formula2 = substr($formula, $pos2[0]+$pos2[1]); //from </mtext>
if($omittedcontent){
//we have a non-empty formula before the text so we must close it
//compute the tail (close tags) of the formula before the text
//and the head (open tags) of the formula after the text.
$copystack = $stack; //copy stack
$tail1 = '';
$head2 = '';
while($stacktag = array_pop($copystack)){
$tail1.= $opentag.'/'.$stacktag[0].$closetag;
$head2 = $stacktag[1] . $head2;
}
$formula1 = $formula1 . $tail1;
$formula2 = $head2 . $formula2;
//update $formula
$formula = $formula1 . $text . $formula2;
$beginformula = $pos[0]+strlen($tail1)+strlen($text);
$position = $beginformula+strlen($head2);
}else{
//we have an empty formula before the text so we must skip it.
$head = substr($formula1, 0, $beginformula); //all before the empty formula
$formula1 = substr($formula1, $beginformula);
$formula = $head . $text . $formula1 . $formula2;
$beginformula += strlen($text);
$position = $beginformula +strlen($formula1);
}
//update parameters with the new formula.
$length = strlen($formula);
$omittedcontent = false;
mb_ereg_search_init($formula, $pattern);
mb_ereg_search_setpos($position);
}else{
//not allowed tag: go to its closure and remember that we omitted content
$pos = mb_ereg_search_pos($opentag.'/'.$trimmedTag.$closetag);
if($pos === false){
return $formula; //this is an error in XML (unclosed tag);
}
$omittedcontent=true;
mb_ereg_search_setpos($pos[0]+$pos[1]);
}
}
return $formula;
}
/**
* Finds the substring of the $string that has at most $length letters with the $suffix appended (if needed)
* Allows for custom $delimiter and $suffix.
* Uses mb_ereg_* functions that have less complexity than the explode and foreach functions used in other subString function.
* @param string $string
* @param int $length
* @param string $delimiter
* @param string $suffix
* @return string
*/
public static function subStringCustom($string, $length, $delimiter = ' ', $suffix = '...')
{
mb_internal_encoding(mb_detect_encoding($string));
//Detect current string encoding
if (mb_strlen($string) <= $length) {
//String is already shorter than the length, return the string
return $string;
}
$length -= mb_strlen($suffix);
//We subtract the suffix's length from our goal
//We find matches of $delimiter that have at most the $length characters before it
$pattern = '.{0,' . $length . '}' . $delimiter;
mb_ereg_search_init($string, $pattern);
$latestMatchPosition = mb_ereg_search_pos();
return mb_substr($string, 0, end($latestMatchPosition) - 1) . $suffix;
//Append suffix and return result
}
<?php
mb_regex_encoding('iso-8859-1');
$test_str = 'I�t�rn�ti�n�liz�ti�n';
if (mb_ereg_search_init($test_str)) {
$val = mb_ereg_search_pos("n�ti�n");
var_dump($val);
} else {
var_dump("false");
}
