Created
September 10, 2009 19:07
-
-
Save beberlei/184744 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
<?php | |
class Zend_Reflection_DocblockParserTest extends PHPUnit_Framework_TestCase | |
{ | |
public function testTokenizesimpleDocBlock() | |
{ | |
$input = "hello world this is a description | |
@param string \$foo | |
@return int"; | |
$t = new Zend_Reflection_DocblockTokenizer(); | |
$tokens = $t->tokenize($input); | |
$parser = new Zend_Reflection_DocblockParser(); | |
$parser->parse($tokens); | |
var_dump($parser); | |
} | |
} | |
class Zend_Reflection_DocblockParser | |
{ | |
private $_ast = array(); | |
public function parse(array &$tokens) | |
{ | |
while(count($tokens) > 0) { | |
$token = array_shift($tokens); | |
switch($token['type']) { | |
case 'tag': | |
$this->_parseTag($token, $tokens); | |
break; | |
case 'text': | |
case 'linebreak': | |
case 'whitespace': | |
$this->_parseText($token, $tokens); | |
break; | |
} | |
} | |
} | |
protected function _parseText($token, array &$tokens) | |
{ | |
$content = $token['content']; | |
while(count($tokens) > 0) { | |
$token = array_shift($tokens); | |
if($token['type'] != "tag") { | |
$content .= $token['content']; | |
} else { | |
array_unshift($tokens, $token); | |
break; | |
} | |
} | |
$this->_ast[] = array('text', $content); | |
} | |
protected function _parseTag($token, array &$tokens) | |
{ | |
switch($token['content']) { | |
case '@param': | |
$this->_removeNextWhitespace($tokens); | |
$type = array_shift($tokens); | |
if($type['type'] !== 'text') { | |
throw new Exception("Param expects a type as first argument."); | |
} | |
$typeContent = $type['content']; | |
$this->_removeNextWhitespace($tokens); | |
$variable = array_shift($tokens); | |
if($variable['type'] != "text") { | |
throw new Exception("@param expects a variable as second argument."); | |
} | |
$variableContent = $variable['content']; | |
$this->_ast[] = array('param', $typeContent, $variableContent); | |
break; | |
case '@return': | |
$this->_removeNextWhitespace($tokens); | |
$type = array_shift($tokens); | |
if($type['type'] !== 'text') { | |
throw new Exception("Param expects a type as first argument."); | |
} | |
$typeContent = $type['content']; | |
$this->_ast[] = array('return', $typeContent); | |
break; | |
default: | |
break; | |
} | |
} | |
protected function _removeNextWhitespace(array &$tokens) | |
{ | |
$wsToken = array_shift($tokens); | |
var_dump($wsToken); | |
if($wsToken['type'] !== "whitespace") { | |
throw new Exception("A whitespace was expected!"); | |
} | |
} | |
} | |
class Zend_Reflection_DocblockTokenizer | |
{ | |
const TOKEN_TAG = '/^(@[a-zA-Z]{1,})/'; | |
const TOKEN_TEXT = '/^([^@_\s\r\n]{1,})/'; | |
const TOKEN_LINEBREAK = '/^([\r\n]+)/'; | |
const TOKEN_WHITESPACE = '/^([\s]{1,})/'; | |
public function tokenize($string) | |
{ | |
$tokens = array("tag" => self::TOKEN_TAG, "text" => self::TOKEN_TEXT, "linebreak" => self::TOKEN_LINEBREAK, "whitespace" => self::TOKEN_WHITESPACE); | |
$scanned = array(); | |
while(strlen($string) > 0) { | |
foreach($tokens AS $type => $token) { | |
if(preg_match($token, $string, $match)) { | |
$scanned[] = array( | |
'type' => $type, | |
'content' => $match[0], | |
); | |
$string = substr($string, strlen($match[0])); | |
} | |
} | |
} | |
return $scanned; | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment