/**
* Creates LaTeX representation of the given document node.
*
* This method is useful when parts of the rendered document should be
* presented as the LaTeX source for processing (validating and rendering)
* by external tools, i.e. MathJaX, mathTeX or mimeTeX.
*
* @param PhpLatex_Node|array $node
* @return string
*/
public static function toLatex($node)
{
if ($node instanceof PhpLatex_Node) {
switch ($node->getType()) {
case PhpLatex_Parser::TYPE_SPECIAL:
if ($node->value === '_' || $node->value === '^') {
return $node->value . self::toLatex($node->getChildren());
}
return $node->value;
case PhpLatex_Parser::TYPE_TEXT:
// make sure text is properly escaped
$source = PhpLatex_Utils::escape($node->value);
return $source;
case PhpLatex_Parser::TYPE_GROUP:
$source = $node->optional ? '[{' : '{';
$source .= self::toLatex($node->getChildren());
$source .= $node->optional ? '}]' : '}';
return $source;
case PhpLatex_Parser::TYPE_VERBATIM:
return $node->value;
case PhpLatex_Parser::TYPE_MATH:
$source = self::toLatex($node->getChildren());
if ($node->inline) {
return '\\(' . $source . '\\)';
} else {
return '\\[' . $source . '\\]';
}
case PhpLatex_Parser::TYPE_COMMAND:
if ($node->value === '\\string') {
$value = $node->value;
foreach ($node->getChildren() as $child) {
$value .= self::toLatex($child);
}
return $value;
}
if ($node->symbol || $node->hasChildren()) {
return $node->value . self::toLatex($node->getChildren());
}
// control word, add space that was removed after
return $node->value . ' ';
case PhpLatex_Parser::TYPE_ENVIRON:
return "\\begin{" . $node->value . "}\n" . self::toLatex($node->getChildren()) . "\\end{" . $node->value . "}\n";
case PhpLatex_Parser::TYPE_DOCUMENT:
return self::toLatex($node->getChildren());
}
} elseif (is_array($node)) {
// render node list and concatenate results
$latex = '';
foreach ($node as $child) {
$latex .= self::toLatex($child);
}
return $latex;
}
}
public static function getTextValue(DOMText $node)
{
$value = str_replace(array("\r\n", "\r"), "\n", $node->wholeText);
$value = PhpLatex_Utils::escape($value);
// replace UTF-8 characters with their counterparts if encoding is not UTF-8,
// otherwise remove invalid UTF-8 characters
if (in_array(self::$_outputEncoding, array('UTF-8', 'UTF8'), true)) {
// regex taken from http://stackoverflow.com/questions/1401317/remove-non-utf8-characters-from-string
$regex = '
/
(
(?: [\\x00-\\x7F] # single-byte sequences 0xxxxxxx
| [\\xC0-\\xDF][\\x80-\\xBF] # double-byte sequences 110xxxxx 10xxxxxx
| [\\xE0-\\xEF][\\x80-\\xBF]{2} # triple-byte sequences 1110xxxx 10xxxxxx * 2
| [\\xF0-\\xF7][\\x80-\\xBF]{3} # quadruple-byte sequence 11110xxx 10xxxxxx * 3
){1,100} # ...one or more times
)
| . # anything else
/x';
$value = preg_replace($regex, '$1', $value);
} else {
$value = PhpLatex_Utils::escapeUtf8($value);
}
return $value;
}
