082a0130c2
Signed-off-by: Gergely POLONKAI (W00d5t0ck) <polesz@w00d5t0ck.info>
266 lines
7.1 KiB
PHP
266 lines
7.1 KiB
PHP
<?php
|
|
/*
|
|
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
|
* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
|
* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
|
|
* A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
|
|
* OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
|
* SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT 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.
|
|
*
|
|
* This software consists of voluntary contributions made by many individuals
|
|
* and is licensed under the LGPL. For more information, see
|
|
* <http://www.doctrine-project.org>.
|
|
*/
|
|
|
|
namespace Doctrine\Common;
|
|
|
|
/**
|
|
* Base class for writing simple lexers, i.e. for creating small DSLs.
|
|
*
|
|
* @since 2.0
|
|
* @author Guilherme Blanco <guilhermeblanco@hotmail.com>
|
|
* @author Jonathan Wage <jonwage@gmail.com>
|
|
* @author Roman Borschel <roman@code-factory.org>
|
|
* @todo Rename: AbstractLexer
|
|
*/
|
|
abstract class Lexer
|
|
{
|
|
/**
|
|
* @var array Array of scanned tokens
|
|
*/
|
|
private $tokens = array();
|
|
|
|
/**
|
|
* @var integer Current lexer position in input string
|
|
*/
|
|
private $position = 0;
|
|
|
|
/**
|
|
* @var integer Current peek of current lexer position
|
|
*/
|
|
private $peek = 0;
|
|
|
|
/**
|
|
* @var array The next token in the input.
|
|
*/
|
|
public $lookahead;
|
|
|
|
/**
|
|
* @var array The last matched/seen token.
|
|
*/
|
|
public $token;
|
|
|
|
/**
|
|
* Sets the input data to be tokenized.
|
|
*
|
|
* The Lexer is immediately reset and the new input tokenized.
|
|
* Any unprocessed tokens from any previous input are lost.
|
|
*
|
|
* @param string $input The input to be tokenized.
|
|
*/
|
|
public function setInput($input)
|
|
{
|
|
$this->tokens = array();
|
|
$this->reset();
|
|
$this->scan($input);
|
|
}
|
|
|
|
/**
|
|
* Resets the lexer.
|
|
*/
|
|
public function reset()
|
|
{
|
|
$this->lookahead = null;
|
|
$this->token = null;
|
|
$this->peek = 0;
|
|
$this->position = 0;
|
|
}
|
|
|
|
/**
|
|
* Resets the peek pointer to 0.
|
|
*/
|
|
public function resetPeek()
|
|
{
|
|
$this->peek = 0;
|
|
}
|
|
|
|
/**
|
|
* Resets the lexer position on the input to the given position.
|
|
*
|
|
* @param integer $position Position to place the lexical scanner
|
|
*/
|
|
public function resetPosition($position = 0)
|
|
{
|
|
$this->position = $position;
|
|
}
|
|
|
|
/**
|
|
* Checks whether a given token matches the current lookahead.
|
|
*
|
|
* @param integer|string $token
|
|
* @return boolean
|
|
*/
|
|
public function isNextToken($token)
|
|
{
|
|
return null !== $this->lookahead && $this->lookahead['type'] === $token;
|
|
}
|
|
|
|
/**
|
|
* Checks whether any of the given tokens matches the current lookahead
|
|
*
|
|
* @param array $tokens
|
|
* @return boolean
|
|
*/
|
|
public function isNextTokenAny(array $tokens)
|
|
{
|
|
return null !== $this->lookahead && in_array($this->lookahead['type'], $tokens, true);
|
|
}
|
|
|
|
/**
|
|
* Moves to the next token in the input string.
|
|
*
|
|
* A token is an associative array containing three items:
|
|
* - 'value' : the string value of the token in the input string
|
|
* - 'type' : the type of the token (identifier, numeric, string, input
|
|
* parameter, none)
|
|
* - 'position' : the position of the token in the input string
|
|
*
|
|
* @return array|null the next token; null if there is no more tokens left
|
|
*/
|
|
public function moveNext()
|
|
{
|
|
$this->peek = 0;
|
|
$this->token = $this->lookahead;
|
|
$this->lookahead = (isset($this->tokens[$this->position]))
|
|
? $this->tokens[$this->position++] : null;
|
|
|
|
return $this->lookahead !== null;
|
|
}
|
|
|
|
/**
|
|
* Tells the lexer to skip input tokens until it sees a token with the given value.
|
|
*
|
|
* @param $type The token type to skip until.
|
|
*/
|
|
public function skipUntil($type)
|
|
{
|
|
while ($this->lookahead !== null && $this->lookahead['type'] !== $type) {
|
|
$this->moveNext();
|
|
}
|
|
}
|
|
|
|
/**
|
|
* Checks if given value is identical to the given token
|
|
*
|
|
* @param mixed $value
|
|
* @param integer $token
|
|
* @return boolean
|
|
*/
|
|
public function isA($value, $token)
|
|
{
|
|
return $this->getType($value) === $token;
|
|
}
|
|
|
|
/**
|
|
* Moves the lookahead token forward.
|
|
*
|
|
* @return array | null The next token or NULL if there are no more tokens ahead.
|
|
*/
|
|
public function peek()
|
|
{
|
|
if (isset($this->tokens[$this->position + $this->peek])) {
|
|
return $this->tokens[$this->position + $this->peek++];
|
|
} else {
|
|
return null;
|
|
}
|
|
}
|
|
|
|
/**
|
|
* Peeks at the next token, returns it and immediately resets the peek.
|
|
*
|
|
* @return array|null The next token or NULL if there are no more tokens ahead.
|
|
*/
|
|
public function glimpse()
|
|
{
|
|
$peek = $this->peek();
|
|
$this->peek = 0;
|
|
return $peek;
|
|
}
|
|
|
|
/**
|
|
* Scans the input string for tokens.
|
|
*
|
|
* @param string $input a query string
|
|
*/
|
|
protected function scan($input)
|
|
{
|
|
static $regex;
|
|
|
|
if ( ! isset($regex)) {
|
|
$regex = '/(' . implode(')|(', $this->getCatchablePatterns()) . ')|'
|
|
. implode('|', $this->getNonCatchablePatterns()) . '/i';
|
|
}
|
|
|
|
$flags = PREG_SPLIT_NO_EMPTY | PREG_SPLIT_DELIM_CAPTURE | PREG_SPLIT_OFFSET_CAPTURE;
|
|
$matches = preg_split($regex, $input, -1, $flags);
|
|
|
|
foreach ($matches as $match) {
|
|
// Must remain before 'value' assignment since it can change content
|
|
$type = $this->getType($match[0]);
|
|
|
|
$this->tokens[] = array(
|
|
'value' => $match[0],
|
|
'type' => $type,
|
|
'position' => $match[1],
|
|
);
|
|
}
|
|
}
|
|
|
|
/**
|
|
* Gets the literal for a given token.
|
|
*
|
|
* @param integer $token
|
|
* @return string
|
|
*/
|
|
public function getLiteral($token)
|
|
{
|
|
$className = get_class($this);
|
|
$reflClass = new \ReflectionClass($className);
|
|
$constants = $reflClass->getConstants();
|
|
|
|
foreach ($constants as $name => $value) {
|
|
if ($value === $token) {
|
|
return $className . '::' . $name;
|
|
}
|
|
}
|
|
|
|
return $token;
|
|
}
|
|
|
|
/**
|
|
* Lexical catchable patterns.
|
|
*
|
|
* @return array
|
|
*/
|
|
abstract protected function getCatchablePatterns();
|
|
|
|
/**
|
|
* Lexical non-catchable patterns.
|
|
*
|
|
* @return array
|
|
*/
|
|
abstract protected function getNonCatchablePatterns();
|
|
|
|
/**
|
|
* Retrieve token type. Also processes the token value if necessary.
|
|
*
|
|
* @param string $value
|
|
* @return integer
|
|
*/
|
|
abstract protected function getType(&$value);
|
|
} |