public function parseString(PHPTAL_Dom_DocumentBuilder $builder, $src, $filename = '<string>')
{
try {
$builder->setEncoding($this->input_encoding);
$this->_file = $filename;
$this->_line = 1;
$state = self::ST_ROOT;
$mark = 0;
$len = strlen($src);
$quoteStyle = '"';
$tagname = "";
$attribute = "";
$attributes = array();
$customDoctype = false;
$builder->setSource($this->_file, $this->_line);
$builder->onDocumentStart();
$i = 0;
// remove BOM (UTF-8 byte order mark)...
if (substr($src, 0, 3) === self::BOM_STR) {
$i = 3;
}
for (; $i < $len; $i++) {
$c = $src[$i];
// Change to substr($src, $i, 1); if you want to use mb_string.func_overload
if ($c === "\n") {
$builder->setSource($this->_file, ++$this->_line);
}
switch ($state) {
case self::ST_ROOT:
if ($c === '<') {
$mark = $i;
// mark tag start
$state = self::ST_LT;
} elseif (!self::isWhiteChar($c)) {
$this->raiseError("Characters found before beginning of the document! (wrap document in < tal:block > to avoid this error)");
}
break;
case self::ST_TEXT:
if ($c === '<') {
if ($mark != $i) {
$builder->onElementData($this->sanitizeEscapedText($this->checkEncoding(substr($src, $mark, $i - $mark))));
}
$mark = $i;
$state = self::ST_LT;
}
break;
case self::ST_LT:
if ($c === '/') {
$mark = $i + 1;
$state = self::ST_TAG_CLOSE;
} elseif ($c === '?' and strtolower(substr($src, $i, 5)) === '?xml ') {
$state = self::ST_XMLDEC;
} elseif ($c === '?') {
$state = self::ST_PREPROC;
} elseif ($c === '!' and substr($src, $i, 3) === '!--') {
$state = self::ST_COMMENT;
} elseif ($c === '!' and substr($src, $i, 8) === '![CDATA[') {
$state = self::ST_CDATA;
$mark = $i + 8;
// past opening tag
} elseif ($c === '!' and strtoupper(substr($src, $i, 8)) === '!DOCTYPE') {
$state = self::ST_DOCTYPE;
} elseif (self::isWhiteChar($c)) {
$state = self::ST_TEXT;
} else {
$mark = $i;
// mark node name start
$attributes = array();
$attribute = "";
$state = self::ST_TAG_NAME;
}
break;
case self::ST_TAG_NAME:
if (self::isWhiteChar($c) || $c === '/' || $c === '>') {
$tagname = substr($src, $mark, $i - $mark);
if (!$this->isValidQName($tagname)) {
$this->raiseError("Invalid tag name '{$tagname}'");
}
if ($c === '/') {
$state = self::ST_TAG_SINGLE;
} elseif ($c === '>') {
$mark = $i + 1;
// mark text start
$state = self::ST_TEXT;
$builder->onElementStart($tagname, $attributes);
} else {
$state = self::ST_TAG_ATTRIBUTES;
}
}
break;
case self::ST_TAG_CLOSE:
if ($c === '>') {
$tagname = rtrim(substr($src, $mark, $i - $mark));
$builder->onElementClose($tagname);
$mark = $i + 1;
// mark text start
$state = self::ST_TEXT;
}
break;
case self::ST_TAG_SINGLE:
if ($c !== '>') {
$this->raiseError("Expected '/>', but found '/{$c}' inside tag < {$tagname} >");
}
$mark = $i + 1;
// mark text start
$state = self::ST_TEXT;
$builder->onElementStart($tagname, $attributes);
$builder->onElementClose($tagname);
break;
case self::ST_TAG_BETWEEN_ATTRIBUTE:
case self::ST_TAG_ATTRIBUTES:
if ($c === '>') {
$mark = $i + 1;
// mark text start
$state = self::ST_TEXT;
$builder->onElementStart($tagname, $attributes);
} elseif ($c === '/') {
$state = self::ST_TAG_SINGLE;
} elseif (self::isWhiteChar($c)) {
$state = self::ST_TAG_ATTRIBUTES;
} elseif ($state === self::ST_TAG_ATTRIBUTES && $this->isValidQName($c)) {
$mark = $i;
// mark attribute key start
$state = self::ST_ATTR_KEY;
} else {
$this->raiseError("Unexpected character '{$c}' between attributes of < {$tagname} >");
}
break;
case self::ST_COMMENT:
if ($c === '>' && $i > $mark + 4 && substr($src, $i - 2, 2) === '--') {
if (preg_match('/^-|--|-$/', substr($src, $mark + 4, $i - $mark + 1 - 7))) {
$this->raiseError("Ill-formed comment. XML comments are not allowed to contain '--' or start/end with '-': " . substr($src, $mark + 4, $i - $mark + 1 - 7));
}
$builder->onComment($this->checkEncoding(substr($src, $mark + 4, $i - $mark + 1 - 7)));
$mark = $i + 1;
// mark text start
$state = self::ST_TEXT;
}
break;
case self::ST_CDATA:
if ($c === '>' and substr($src, $i - 2, 2) === ']]') {
$builder->onCDATASection($this->checkEncoding(substr($src, $mark, $i - $mark - 2)));
$mark = $i + 1;
// mark text start
$state = self::ST_TEXT;
}
break;
case self::ST_XMLDEC:
if ($c === '?' && substr($src, $i, 2) === '?>') {
$builder->onXmlDecl($this->checkEncoding(substr($src, $mark, $i - $mark + 2)));
$i++;
// skip '>'
$mark = $i + 1;
// mark text start
$state = self::ST_TEXT;
}
break;
case self::ST_DOCTYPE:
if ($c === '[') {
$customDoctype = true;
} elseif ($customDoctype && $c === '>' && substr($src, $i - 1, 2) === ']>') {
$customDoctype = false;
$builder->onDocType($this->checkEncoding(substr($src, $mark, $i - $mark + 1)));
$mark = $i + 1;
// mark text start
$state = self::ST_TEXT;
} elseif (!$customDoctype && $c === '>') {
$customDoctype = false;
$builder->onDocType($this->checkEncoding(substr($src, $mark, $i - $mark + 1)));
$mark = $i + 1;
// mark text start
$state = self::ST_TEXT;
}
break;
case self::ST_PREPROC:
if ($c === '>' and substr($src, $i - 1, 1) === '?') {
$builder->onProcessingInstruction($this->checkEncoding(substr($src, $mark, $i - $mark + 1)));
$mark = $i + 1;
// mark text start
$state = self::ST_TEXT;
}
break;
case self::ST_ATTR_KEY:
if ($c === '=' || self::isWhiteChar($c)) {
$attribute = substr($src, $mark, $i - $mark);
if (!$this->isValidQName($attribute)) {
$this->raiseError("Invalid attribute name '{$attribute}' in < {$tagname} >");
}
if (isset($attributes[$attribute])) {
$this->raiseError("Attribute {$attribute} in < {$tagname} > is defined more than once");
}
if ($c === '=') {
$state = self::ST_ATTR_VALUE;
} else {
/* white char */
$state = self::ST_ATTR_EQ;
}
} elseif ($c === '/' || $c === '>') {
$attribute = substr($src, $mark, $i - $mark);
if (!$this->isValidQName($attribute)) {
$this->raiseError("Invalid attribute name '{$attribute}'");
}
$this->raiseError("Attribute {$attribute} does not have value (found end of tag instead of '=')");
}
break;
case self::ST_ATTR_EQ:
if ($c === '=') {
$state = self::ST_ATTR_VALUE;
} elseif (!self::isWhiteChar($c)) {
$this->raiseError("Attribute {$attribute} in < {$tagname} > does not have value (found character '{$c}' instead of '=')");
}
break;
case self::ST_ATTR_VALUE:
if (self::isWhiteChar($c)) {
} elseif ($c === '"' or $c === '\'') {
$quoteStyle = $c;
$state = self::ST_ATTR_QUOTE;
$mark = $i + 1;
// mark attribute real value start
} else {
$this->raiseError("Value of attribute {$attribute} in < {$tagname} > is not in quotes (found character '{$c}' instead of quote)");
}
break;
case self::ST_ATTR_QUOTE:
if ($c === $quoteStyle) {
$attributes[$attribute] = $this->sanitizeEscapedText($this->checkEncoding(substr($src, $mark, $i - $mark)));
// PHPTAL's code generator assumes input is escaped for double-quoted strings. Single-quoted attributes need to be converted.
// FIXME: it should be escaped at later stage.
$attributes[$attribute] = str_replace('"', """, $attributes[$attribute]);
$state = self::ST_TAG_BETWEEN_ATTRIBUTE;
}
break;
}
}
if ($state === self::ST_TEXT) {
if ($i > $mark) {
$text = substr($src, $mark, $i - $mark);
if (!ctype_space($text)) {
$this->raiseError("Characters found after end of the root element (wrap document in < tal:block > to avoid this error)");
}
}
} else {
if ($state === self::ST_ROOT) {
$msg = "Document does not have any tags";
} else {
$msg = "Finished document in unexpected state: " . self::$state_names[$state] . " is not finished";
}
$this->raiseError($msg);
}
$builder->onDocumentEnd();
} catch (PHPTAL_TemplateException $e) {
$e->hintSrcPosition($this->_file, $this->_line);
throw $e;
}
return $builder;
}
public function __construct()
{
$this->result = '';
parent::__construct();
}
/**
* parse currently set template
* @return string (compiled PHP code)
*/
protected function parse()
{
self::setIncludePath();
require_once 'PHPTAL/Dom/DocumentBuilder.php';
require_once 'PHPTAL/Php/CodeGenerator.php';
self::restoreIncludePath();
// instantiate the PHPTAL source parser
$parser = new PHPTAL_Dom_SaxXmlParser($this->_encoding);
$builder = new PHPTAL_Dom_DocumentBuilder();
$builder->stripComments($this->_stripComments);
$data = $this->_source->getData();
$realpath = $this->_source->getRealPath();
if ($this->_prefilter) {
$data = $this->_prefilter->filter($data);
}
$tree = $parser->parseString($builder, $data, $realpath)->getResult();
$generator = new PHPTAL_Php_CodeGenerator($this->getFunctionName(), $this->_source->getRealPath(), $this->_encoding, $this->_outputMode, $this->getCodePath());
$result = $generator->generateCode($tree);
return $result;
}
