/**
* Tests the static entities_to_utf8 method
* @return void
*/
public function test_entities_to_utf8()
{
$str = "Žluťoučký koníček©"&<>§«";
$this->assertSame("Žluťoučký koníček©\"&<>§«", textlib::entities_to_utf8($str));
}
function _unhtmlentities($string)
{
return textlib::entities_to_utf8($string);
// Moodle hack
$string = preg_replace('~&#x([0-9a-f]+);~ei', 'chr(hexdec("\\1"))', $string);
$string = preg_replace('~&#([0-9]+);~e', 'chr(\\1)', $string);
$trans_tbl = get_html_translation_table(HTML_ENTITIES);
$trans_tbl = array_flip($trans_tbl);
return strtr($string, $trans_tbl);
}
/**
* A lot of imported files contain unwanted entities.
* This method tries to clean up all known problems.
* @param string str string to correct
* @return string the corrected string
*/
public function cleaninput($str)
{
$html_code_list = array("'" => "'", "’" => "'", "“" => "\"", "”" => "\"", "–" => "-", "—" => "-");
$str = strtr($str, $html_code_list);
// Use textlib entities_to_utf8 function to convert only numerical entities.
$str = textlib::entities_to_utf8($str, false);
return $str;
}
public function test_entities_to_utf8()
{
$str = "Žluťoučký koníček";
$this->assertIdentical(textlib::entities_to_utf8($str), "Žluťoučký koníček");
}
protected function readquestion($lines) {
global $OUTPUT;
$text = implode(' ', $lines);
$text = str_replace(array('\t','\n','\r'), array('','',''), $text);
$startpos = strpos($text, '<question type');
$endpos = strpos($text, '</question>');
if ($startpos === false || $endpos === false) {
return false;
}
preg_match("/<question type=[\"\']([^\"\']+)[\"\']>/i", $text, $matches);
$type = strtolower($matches[1]); // multichoice or multianswerchoice
$questiontext = textlib::entities_to_utf8($this->stringbetween($text, '<text>', '</text>'));
$questionhint = textlib::entities_to_utf8($this->stringbetween($text, '<hint>', '</hint>'));
$questionaward = $this->stringbetween($text, '<award>', '</award>');
$optionlist = $this->stringbetween($text, '<answer>', '</answer>');
$optionlist = explode('<option', $optionlist);
$n = 0;
$optionscorrect = array();
$optionstext = array();
if ($type == 'multichoice') {
foreach ($optionlist as $option) {
if (trim($option) === '') {
continue;
}
$correct = $this->stringbetween($option, ' correct="', '">');
$answer = $this->stringbetween($option, '">', '</option>');
$optionscorrect[$n] = $correct;
$optionstext[$n] = textlib::entities_to_utf8($answer);
++$n;
}
} else if ($type == 'multianswerchoice') {
$numcorrect = 0;
$totalaward = 0;
$optionsaward = array();
foreach ($optionlist as $option) {
if (trim($option) === '') {
continue;
}
preg_match("/correct=\"([^\"]*)\"/i", $option, $correctmatch);
preg_match("/award=\"([^\"]*)\"/i", $option, $awardmatch);
$correct = $correctmatch[1];
$award = $awardmatch[1];
if ($correct == 'yes') {
$totalaward += $award;
++$numcorrect;
}
$answer = $this->stringbetween($option, '">', '</option>');
$optionscorrect[$n] = $correct;
$optionstext[$n] = textlib::entities_to_utf8($answer);
$optionsaward[$n] = $award;
++$n;
}
} else {
echo $OUTPUT->notification(get_string('unknownorunhandledtype', 'question', $type));
}
$question = $this->defaultquestion();
$question->qtype = 'multichoice';
$question->name = $this->create_default_question_name($questiontext, get_string('questionname', 'question'));
$this->add_blank_combined_feedback($question);
$question->questiontext = $questiontext;
$question->questiontextformat = FORMAT_HTML;
$question->single = ($type == 'multichoice') ? 1 : 0;
$question->fraction = array();
$question->answer = array();
for ($n = 0; $n < count($optionstext); ++$n) {
if ($optionstext[$n]) {
if (!isset($numcorrect)) {
// Single answer.
if ($optionscorrect[$n] == 'yes') {
$fraction = (int) $questionaward;
} else {
$fraction = 0;
}
} else {
// Multiple answers.
if ($optionscorrect[$n] == 'yes') {
$fraction = $optionsaward[$n] / $totalaward;
} else {
$fraction = -$optionsaward[$n] / count($optionstext);
}
}
$question->fraction[] = $fraction;
$question->answer[] = array('text' => $optionstext[$n], 'format' => FORMAT_HTML);
$question->feedback[] = array('text' => '', 'format' => FORMAT_HTML); // No feedback in this type.
}
}
return $question;
}
/**
* Given text in a variety of format codings, this function returns
* the text as plain text suitable for plain email.
*
* @uses FORMAT_MOODLE
* @uses FORMAT_HTML
* @uses FORMAT_PLAIN
* @uses FORMAT_WIKI
* @uses FORMAT_MARKDOWN
* @param string $text The text to be formatted. This is raw text originally from user input.
* @param int $format Identifier of the text format to be used
* [FORMAT_MOODLE, FORMAT_HTML, FORMAT_PLAIN, FORMAT_WIKI, FORMAT_MARKDOWN]
* @return string
*/
function format_text_email($text, $format)
{
switch ($format) {
case FORMAT_PLAIN:
return $text;
break;
case FORMAT_WIKI:
// there should not be any of these any more!
$text = wikify_links($text);
return textlib::entities_to_utf8(strip_tags($text), true);
break;
case FORMAT_HTML:
return html_to_text($text);
break;
case FORMAT_MOODLE:
case FORMAT_MARKDOWN:
default:
$text = wikify_links($text);
return textlib::entities_to_utf8(strip_tags($text), true);
break;
}
}
function test_obfuscate_text()
{
$text = 'Žluťoučký koníček 32131';
$obfuscated = obfuscate_text($text);
$this->assertNotSame($text, $obfuscated);
$back = textlib::entities_to_utf8($obfuscated, true);
$this->assertSame($text, $back);
}
/**
* Simplifies a string according to indexing rules.
*/
function tokenise_simplify($text, $overlap_cjk, $join_numbers)
{
// Decode entities to UTF-8
$text = textlib::entities_to_utf8($text, true);
// Lowercase
$text = textlib::strtolower($text);
// Simple CJK handling
if ($overlap_cjk) {
$text = preg_replace_callback('/[' . PREG_CLASS_CJK . ']+/u', 'tokenise_expand_cjk', $text);
}
// To improve searching for numerical data such as dates, IP addresses
// or version numbers, we consider a group of numerical characters
// separated only by punctuation characters to be one piece.
// This also means that searching for e.g. '20/03/1984' also returns
// results with '20-03-1984' in them.
// Readable regexp: ([number]+)[punctuation]+(?=[number])
if ($join_numbers) {
$text = preg_replace('/([' . PREG_CLASS_NUMBERS . ']+)[' . PREG_CLASS_PUNCTUATION . ']+(?=[' . PREG_CLASS_NUMBERS . '])/u', '\\1', $text);
} else {
// Keep all the detected numbers+punctuation in a safe place in order to restore them later
preg_match_all('/[' . PREG_CLASS_NUMBERS . ']+[' . PREG_CLASS_PUNCTUATION . PREG_CLASS_NUMBERS . ']+/u', $text, $foundseqs);
$storedseqs = array();
foreach (array_unique($foundseqs[0]) as $ntkey => $value) {
$prefix = (string) (count($storedseqs) + 1);
$storedseqs[START_DELIM . $prefix . CENTER_DELIM . $ntkey . END_DELIM] = $value;
}
if (!empty($storedseqs)) {
$text = str_replace($storedseqs, array_keys($storedseqs), $text);
}
}
// The dot, underscore and dash are simply removed. This allows meaningful
// search behaviour with acronyms and URLs.
$text = preg_replace('/[._-]+/', '', $text);
// With the exception of the rules above, we consider all punctuation,
// marks, spacers, etc, to be a word boundary.
$text = preg_replace('/[' . PREG_CLASS_SEARCH_EXCLUDE . ']+/u', ' ', $text);
// Restore, if not joining numbers, recover the original strings
if (!$join_numbers) {
if (!empty($storedseqs)) {
$text = str_replace(array_keys($storedseqs), $storedseqs, $text);
}
}
return $text;
}
