/home/mip/mip/public/img/credit/datatables/Parser.tar
ParserInterface.php 0000644 00000000516 15152054360 0010335 0 ustar 00 <?php
declare(strict_types=1);
namespace Dotenv\Parser;
interface ParserInterface
{
/**
* Parse content into an entry array.
*
* @param string $content
*
* @throws \Dotenv\Exception\InvalidFileException
*
* @return \Dotenv\Parser\Entry[]
*/
public function parse(string $content);
}
Handler/IdentifierHandler.php 0000644 00000003126 15152054360 0012215 0 ustar 00 <?php
/*
* This file is part of the Symfony package.
*
* (c) Fabien Potencier <fabien@symfony.com>
*
* For the full copyright and license information, please view the LICENSE
* file that was distributed with this source code.
*/
namespace Symfony\Component\CssSelector\Parser\Handler;
use Symfony\Component\CssSelector\Parser\Reader;
use Symfony\Component\CssSelector\Parser\Token;
use Symfony\Component\CssSelector\Parser\Tokenizer\TokenizerEscaping;
use Symfony\Component\CssSelector\Parser\Tokenizer\TokenizerPatterns;
use Symfony\Component\CssSelector\Parser\TokenStream;
/**
* CSS selector comment handler.
*
* This component is a port of the Python cssselect library,
* which is copyright Ian Bicking, @see https://github.com/SimonSapin/cssselect.
*
* @author Jean-François Simon <jeanfrancois.simon@sensiolabs.com>
*
* @internal
*/
class IdentifierHandler implements HandlerInterface
{
private $patterns;
private $escaping;
public function __construct(TokenizerPatterns $patterns, TokenizerEscaping $escaping)
{
$this->patterns = $patterns;
$this->escaping = $escaping;
}
/**
* {@inheritdoc}
*/
public function handle(Reader $reader, TokenStream $stream): bool
{
$match = $reader->findPattern($this->patterns->getIdentifierPattern());
if (!$match) {
return false;
}
$value = $this->escaping->escapeUnicode($match[0]);
$stream->push(new Token(Token::TYPE_IDENTIFIER, $value, $reader->getPosition()));
$reader->moveForward(\strlen($match[0]));
return true;
}
}
Handler/StringHandler.php 0000644 00000004607 15152054360 0011406 0 ustar 00 <?php
/*
* This file is part of the Symfony package.
*
* (c) Fabien Potencier <fabien@symfony.com>
*
* For the full copyright and license information, please view the LICENSE
* file that was distributed with this source code.
*/
namespace Symfony\Component\CssSelector\Parser\Handler;
use Symfony\Component\CssSelector\Exception\InternalErrorException;
use Symfony\Component\CssSelector\Exception\SyntaxErrorException;
use Symfony\Component\CssSelector\Parser\Reader;
use Symfony\Component\CssSelector\Parser\Token;
use Symfony\Component\CssSelector\Parser\Tokenizer\TokenizerEscaping;
use Symfony\Component\CssSelector\Parser\Tokenizer\TokenizerPatterns;
use Symfony\Component\CssSelector\Parser\TokenStream;
/**
* CSS selector comment handler.
*
* This component is a port of the Python cssselect library,
* which is copyright Ian Bicking, @see https://github.com/SimonSapin/cssselect.
*
* @author Jean-François Simon <jeanfrancois.simon@sensiolabs.com>
*
* @internal
*/
class StringHandler implements HandlerInterface
{
private $patterns;
private $escaping;
public function __construct(TokenizerPatterns $patterns, TokenizerEscaping $escaping)
{
$this->patterns = $patterns;
$this->escaping = $escaping;
}
/**
* {@inheritdoc}
*/
public function handle(Reader $reader, TokenStream $stream): bool
{
$quote = $reader->getSubstring(1);
if (!\in_array($quote, ["'", '"'])) {
return false;
}
$reader->moveForward(1);
$match = $reader->findPattern($this->patterns->getQuotedStringPattern($quote));
if (!$match) {
throw new InternalErrorException(sprintf('Should have found at least an empty match at %d.', $reader->getPosition()));
}
// check unclosed strings
if (\strlen($match[0]) === $reader->getRemainingLength()) {
throw SyntaxErrorException::unclosedString($reader->getPosition() - 1);
}
// check quotes pairs validity
if ($quote !== $reader->getSubstring(1, \strlen($match[0]))) {
throw SyntaxErrorException::unclosedString($reader->getPosition() - 1);
}
$string = $this->escaping->escapeUnicodeAndNewLine($match[0]);
$stream->push(new Token(Token::TYPE_STRING, $string, $reader->getPosition()));
$reader->moveForward(\strlen($match[0]) + 1);
return true;
}
}
Handler/WhitespaceHandler.php 0000644 00000002247 15152054360 0012232 0 ustar 00 <?php
/*
* This file is part of the Symfony package.
*
* (c) Fabien Potencier <fabien@symfony.com>
*
* For the full copyright and license information, please view the LICENSE
* file that was distributed with this source code.
*/
namespace Symfony\Component\CssSelector\Parser\Handler;
use Symfony\Component\CssSelector\Parser\Reader;
use Symfony\Component\CssSelector\Parser\Token;
use Symfony\Component\CssSelector\Parser\TokenStream;
/**
* CSS selector whitespace handler.
*
* This component is a port of the Python cssselect library,
* which is copyright Ian Bicking, @see https://github.com/SimonSapin/cssselect.
*
* @author Jean-François Simon <jeanfrancois.simon@sensiolabs.com>
*
* @internal
*/
class WhitespaceHandler implements HandlerInterface
{
/**
* {@inheritdoc}
*/
public function handle(Reader $reader, TokenStream $stream): bool
{
$match = $reader->findPattern('~^[ \t\r\n\f]+~');
if (false === $match) {
return false;
}
$stream->push(new Token(Token::TYPE_WHITESPACE, $match[0], $reader->getPosition()));
$reader->moveForward(\strlen($match[0]));
return true;
}
}
Handler/HandlerInterface.php 0000644 00000001410 15152054360 0012025 0 ustar 00 <?php
/*
* This file is part of the Symfony package.
*
* (c) Fabien Potencier <fabien@symfony.com>
*
* For the full copyright and license information, please view the LICENSE
* file that was distributed with this source code.
*/
namespace Symfony\Component\CssSelector\Parser\Handler;
use Symfony\Component\CssSelector\Parser\Reader;
use Symfony\Component\CssSelector\Parser\TokenStream;
/**
* CSS selector handler interface.
*
* This component is a port of the Python cssselect library,
* which is copyright Ian Bicking, @see https://github.com/SimonSapin/cssselect.
*
* @author Jean-François Simon <jeanfrancois.simon@sensiolabs.com>
*
* @internal
*/
interface HandlerInterface
{
public function handle(Reader $reader, TokenStream $stream): bool;
}
Handler/NumberHandler.php 0000644 00000002562 15152054360 0011366 0 ustar 00 <?php
/*
* This file is part of the Symfony package.
*
* (c) Fabien Potencier <fabien@symfony.com>
*
* For the full copyright and license information, please view the LICENSE
* file that was distributed with this source code.
*/
namespace Symfony\Component\CssSelector\Parser\Handler;
use Symfony\Component\CssSelector\Parser\Reader;
use Symfony\Component\CssSelector\Parser\Token;
use Symfony\Component\CssSelector\Parser\Tokenizer\TokenizerPatterns;
use Symfony\Component\CssSelector\Parser\TokenStream;
/**
* CSS selector comment handler.
*
* This component is a port of the Python cssselect library,
* which is copyright Ian Bicking, @see https://github.com/SimonSapin/cssselect.
*
* @author Jean-François Simon <jeanfrancois.simon@sensiolabs.com>
*
* @internal
*/
class NumberHandler implements HandlerInterface
{
private $patterns;
public function __construct(TokenizerPatterns $patterns)
{
$this->patterns = $patterns;
}
/**
* {@inheritdoc}
*/
public function handle(Reader $reader, TokenStream $stream): bool
{
$match = $reader->findPattern($this->patterns->getNumberPattern());
if (!$match) {
return false;
}
$stream->push(new Token(Token::TYPE_NUMBER, $match[0], $reader->getPosition()));
$reader->moveForward(\strlen($match[0]));
return true;
}
}
Handler/CommentHandler.php 0000644 00000002162 15152054360 0011534 0 ustar 00 <?php
/*
* This file is part of the Symfony package.
*
* (c) Fabien Potencier <fabien@symfony.com>
*
* For the full copyright and license information, please view the LICENSE
* file that was distributed with this source code.
*/
namespace Symfony\Component\CssSelector\Parser\Handler;
use Symfony\Component\CssSelector\Parser\Reader;
use Symfony\Component\CssSelector\Parser\TokenStream;
/**
* CSS selector comment handler.
*
* This component is a port of the Python cssselect library,
* which is copyright Ian Bicking, @see https://github.com/SimonSapin/cssselect.
*
* @author Jean-François Simon <jeanfrancois.simon@sensiolabs.com>
*
* @internal
*/
class CommentHandler implements HandlerInterface
{
/**
* {@inheritdoc}
*/
public function handle(Reader $reader, TokenStream $stream): bool
{
if ('/*' !== $reader->getSubstring(2)) {
return false;
}
$offset = $reader->getOffset('*/');
if (false === $offset) {
$reader->moveToEnd();
} else {
$reader->moveForward($offset + 2);
}
return true;
}
}
Handler/HashHandler.php 0000644 00000003104 15152054360 0011012 0 ustar 00 <?php
/*
* This file is part of the Symfony package.
*
* (c) Fabien Potencier <fabien@symfony.com>
*
* For the full copyright and license information, please view the LICENSE
* file that was distributed with this source code.
*/
namespace Symfony\Component\CssSelector\Parser\Handler;
use Symfony\Component\CssSelector\Parser\Reader;
use Symfony\Component\CssSelector\Parser\Token;
use Symfony\Component\CssSelector\Parser\Tokenizer\TokenizerEscaping;
use Symfony\Component\CssSelector\Parser\Tokenizer\TokenizerPatterns;
use Symfony\Component\CssSelector\Parser\TokenStream;
/**
* CSS selector comment handler.
*
* This component is a port of the Python cssselect library,
* which is copyright Ian Bicking, @see https://github.com/SimonSapin/cssselect.
*
* @author Jean-François Simon <jeanfrancois.simon@sensiolabs.com>
*
* @internal
*/
class HashHandler implements HandlerInterface
{
private $patterns;
private $escaping;
public function __construct(TokenizerPatterns $patterns, TokenizerEscaping $escaping)
{
$this->patterns = $patterns;
$this->escaping = $escaping;
}
/**
* {@inheritdoc}
*/
public function handle(Reader $reader, TokenStream $stream): bool
{
$match = $reader->findPattern($this->patterns->getHashPattern());
if (!$match) {
return false;
}
$value = $this->escaping->escapeUnicode($match[1]);
$stream->push(new Token(Token::TYPE_HASH, $value, $reader->getPosition()));
$reader->moveForward(\strlen($match[0]));
return true;
}
}
Parser.php 0000644 00000003323 15152054360 0006513 0 ustar 00 <?php
declare(strict_types=1);
namespace Dotenv\Parser;
use Dotenv\Exception\InvalidFileException;
use Dotenv\Util\Regex;
use GrahamCampbell\ResultType\Result;
use GrahamCampbell\ResultType\Success;
final class Parser implements ParserInterface
{
/**
* Parse content into an entry array.
*
* @param string $content
*
* @throws \Dotenv\Exception\InvalidFileException
*
* @return \Dotenv\Parser\Entry[]
*/
public function parse(string $content)
{
return Regex::split("/(\r\n|\n|\r)/", $content)->mapError(static function () {
return 'Could not split into separate lines.';
})->flatMap(static function (array $lines) {
return self::process(Lines::process($lines));
})->mapError(static function (string $error) {
throw new InvalidFileException(\sprintf('Failed to parse dotenv file. %s', $error));
})->success()->get();
}
/**
* Convert the raw entries into proper entries.
*
* @param string[] $entries
*
* @return \GrahamCampbell\ResultType\Result<\Dotenv\Parser\Entry[],string>
*/
private static function process(array $entries)
{
/** @var \GrahamCampbell\ResultType\Result<\Dotenv\Parser\Entry[],string> */
return \array_reduce($entries, static function (Result $result, string $raw) {
return $result->flatMap(static function (array $entries) use ($raw) {
return EntryParser::parse($raw)->map(static function (Entry $entry) use ($entries) {
/** @var \Dotenv\Parser\Entry[] */
return \array_merge($entries, [$entry]);
});
});
}, Success::create([]));
}
}
Token.php 0000644 00000004714 15152054360 0006344 0 ustar 00 <?php
/*
* This file is part of the Symfony package.
*
* (c) Fabien Potencier <fabien@symfony.com>
*
* For the full copyright and license information, please view the LICENSE
* file that was distributed with this source code.
*/
namespace Symfony\Component\CssSelector\Parser;
/**
* CSS selector token.
*
* This component is a port of the Python cssselect library,
* which is copyright Ian Bicking, @see https://github.com/SimonSapin/cssselect.
*
* @author Jean-François Simon <jeanfrancois.simon@sensiolabs.com>
*
* @internal
*/
class Token
{
public const TYPE_FILE_END = 'eof';
public const TYPE_DELIMITER = 'delimiter';
public const TYPE_WHITESPACE = 'whitespace';
public const TYPE_IDENTIFIER = 'identifier';
public const TYPE_HASH = 'hash';
public const TYPE_NUMBER = 'number';
public const TYPE_STRING = 'string';
private $type;
private $value;
private $position;
public function __construct(?string $type, ?string $value, ?int $position)
{
$this->type = $type;
$this->value = $value;
$this->position = $position;
}
public function getType(): ?int
{
return $this->type;
}
public function getValue(): ?string
{
return $this->value;
}
public function getPosition(): ?int
{
return $this->position;
}
public function isFileEnd(): bool
{
return self::TYPE_FILE_END === $this->type;
}
public function isDelimiter(array $values = []): bool
{
if (self::TYPE_DELIMITER !== $this->type) {
return false;
}
if (empty($values)) {
return true;
}
return \in_array($this->value, $values);
}
public function isWhitespace(): bool
{
return self::TYPE_WHITESPACE === $this->type;
}
public function isIdentifier(): bool
{
return self::TYPE_IDENTIFIER === $this->type;
}
public function isHash(): bool
{
return self::TYPE_HASH === $this->type;
}
public function isNumber(): bool
{
return self::TYPE_NUMBER === $this->type;
}
public function isString(): bool
{
return self::TYPE_STRING === $this->type;
}
public function __toString(): string
{
if ($this->value) {
return sprintf('<%s "%s" at %s>', $this->type, $this->value, $this->position);
}
return sprintf('<%s at %s>', $this->type, $this->position);
}
}
Reader.php 0000644 00000003532 15152054360 0006463 0 ustar 00 <?php
/*
* This file is part of the Symfony package.
*
* (c) Fabien Potencier <fabien@symfony.com>
*
* For the full copyright and license information, please view the LICENSE
* file that was distributed with this source code.
*/
namespace Symfony\Component\CssSelector\Parser;
/**
* CSS selector reader.
*
* This component is a port of the Python cssselect library,
* which is copyright Ian Bicking, @see https://github.com/SimonSapin/cssselect.
*
* @author Jean-François Simon <jeanfrancois.simon@sensiolabs.com>
*
* @internal
*/
class Reader
{
private $source;
private $length;
private $position = 0;
public function __construct(string $source)
{
$this->source = $source;
$this->length = \strlen($source);
}
public function isEOF(): bool
{
return $this->position >= $this->length;
}
public function getPosition(): int
{
return $this->position;
}
public function getRemainingLength(): int
{
return $this->length - $this->position;
}
public function getSubstring(int $length, int $offset = 0): string
{
return substr($this->source, $this->position + $offset, $length);
}
public function getOffset(string $string)
{
$position = strpos($this->source, $string, $this->position);
return false === $position ? false : $position - $this->position;
}
/**
* @return array|false
*/
public function findPattern(string $pattern)
{
$source = substr($this->source, $this->position);
if (preg_match($pattern, $source, $matches)) {
return $matches;
}
return false;
}
public function moveForward(int $length)
{
$this->position += $length;
}
public function moveToEnd()
{
$this->position = $this->length;
}
}
TokenStream.php 0000644 00000006660 15152054360 0007522 0 ustar 00 <?php
/*
* This file is part of the Symfony package.
*
* (c) Fabien Potencier <fabien@symfony.com>
*
* For the full copyright and license information, please view the LICENSE
* file that was distributed with this source code.
*/
namespace Symfony\Component\CssSelector\Parser;
use Symfony\Component\CssSelector\Exception\InternalErrorException;
use Symfony\Component\CssSelector\Exception\SyntaxErrorException;
/**
* CSS selector token stream.
*
* This component is a port of the Python cssselect library,
* which is copyright Ian Bicking, @see https://github.com/SimonSapin/cssselect.
*
* @author Jean-François Simon <jeanfrancois.simon@sensiolabs.com>
*
* @internal
*/
class TokenStream
{
/**
* @var Token[]
*/
private $tokens = [];
/**
* @var Token[]
*/
private $used = [];
/**
* @var int
*/
private $cursor = 0;
/**
* @var Token|null
*/
private $peeked;
/**
* @var bool
*/
private $peeking = false;
/**
* Pushes a token.
*
* @return $this
*/
public function push(Token $token): self
{
$this->tokens[] = $token;
return $this;
}
/**
* Freezes stream.
*
* @return $this
*/
public function freeze(): self
{
return $this;
}
/**
* Returns next token.
*
* @throws InternalErrorException If there is no more token
*/
public function getNext(): Token
{
if ($this->peeking) {
$this->peeking = false;
$this->used[] = $this->peeked;
return $this->peeked;
}
if (!isset($this->tokens[$this->cursor])) {
throw new InternalErrorException('Unexpected token stream end.');
}
return $this->tokens[$this->cursor++];
}
/**
* Returns peeked token.
*/
public function getPeek(): Token
{
if (!$this->peeking) {
$this->peeked = $this->getNext();
$this->peeking = true;
}
return $this->peeked;
}
/**
* Returns used tokens.
*
* @return Token[]
*/
public function getUsed(): array
{
return $this->used;
}
/**
* Returns nex identifier token.
*
* @return string The identifier token value
*
* @throws SyntaxErrorException If next token is not an identifier
*/
public function getNextIdentifier(): string
{
$next = $this->getNext();
if (!$next->isIdentifier()) {
throw SyntaxErrorException::unexpectedToken('identifier', $next);
}
return $next->getValue();
}
/**
* Returns nex identifier or star delimiter token.
*
* @return string|null The identifier token value or null if star found
*
* @throws SyntaxErrorException If next token is not an identifier or a star delimiter
*/
public function getNextIdentifierOrStar(): ?string
{
$next = $this->getNext();
if ($next->isIdentifier()) {
return $next->getValue();
}
if ($next->isDelimiter(['*'])) {
return null;
}
throw SyntaxErrorException::unexpectedToken('identifier or "*"', $next);
}
/**
* Skips next whitespace if any.
*/
public function skipWhitespace()
{
$peek = $this->getPeek();
if ($peek->isWhitespace()) {
$this->getNext();
}
}
}
Tokenizer/TokenizerEscaping.php 0000644 00000003360 15152054360 0012656 0 ustar 00 <?php
/*
* This file is part of the Symfony package.
*
* (c) Fabien Potencier <fabien@symfony.com>
*
* For the full copyright and license information, please view the LICENSE
* file that was distributed with this source code.
*/
namespace Symfony\Component\CssSelector\Parser\Tokenizer;
/**
* CSS selector tokenizer escaping applier.
*
* This component is a port of the Python cssselect library,
* which is copyright Ian Bicking, @see https://github.com/SimonSapin/cssselect.
*
* @author Jean-François Simon <jeanfrancois.simon@sensiolabs.com>
*
* @internal
*/
class TokenizerEscaping
{
private $patterns;
public function __construct(TokenizerPatterns $patterns)
{
$this->patterns = $patterns;
}
public function escapeUnicode(string $value): string
{
$value = $this->replaceUnicodeSequences($value);
return preg_replace($this->patterns->getSimpleEscapePattern(), '$1', $value);
}
public function escapeUnicodeAndNewLine(string $value): string
{
$value = preg_replace($this->patterns->getNewLineEscapePattern(), '', $value);
return $this->escapeUnicode($value);
}
private function replaceUnicodeSequences(string $value): string
{
return preg_replace_callback($this->patterns->getUnicodeEscapePattern(), function ($match) {
$c = hexdec($match[1]);
if (0x80 > $c %= 0x200000) {
return \chr($c);
}
if (0x800 > $c) {
return \chr(0xC0 | $c >> 6).\chr(0x80 | $c & 0x3F);
}
if (0x10000 > $c) {
return \chr(0xE0 | $c >> 12).\chr(0x80 | $c >> 6 & 0x3F).\chr(0x80 | $c & 0x3F);
}
return '';
}, $value);
}
}
Tokenizer/TokenizerPatterns.php 0000644 00000005331 15152054360 0012725 0 ustar 00 <?php
/*
* This file is part of the Symfony package.
*
* (c) Fabien Potencier <fabien@symfony.com>
*
* For the full copyright and license information, please view the LICENSE
* file that was distributed with this source code.
*/
namespace Symfony\Component\CssSelector\Parser\Tokenizer;
/**
* CSS selector tokenizer patterns builder.
*
* This component is a port of the Python cssselect library,
* which is copyright Ian Bicking, @see https://github.com/SimonSapin/cssselect.
*
* @author Jean-François Simon <jeanfrancois.simon@sensiolabs.com>
*
* @internal
*/
class TokenizerPatterns
{
private $unicodeEscapePattern;
private $simpleEscapePattern;
private $newLineEscapePattern;
private $escapePattern;
private $stringEscapePattern;
private $nonAsciiPattern;
private $nmCharPattern;
private $nmStartPattern;
private $identifierPattern;
private $hashPattern;
private $numberPattern;
private $quotedStringPattern;
public function __construct()
{
$this->unicodeEscapePattern = '\\\\([0-9a-f]{1,6})(?:\r\n|[ \n\r\t\f])?';
$this->simpleEscapePattern = '\\\\(.)';
$this->newLineEscapePattern = '\\\\(?:\n|\r\n|\r|\f)';
$this->escapePattern = $this->unicodeEscapePattern.'|\\\\[^\n\r\f0-9a-f]';
$this->stringEscapePattern = $this->newLineEscapePattern.'|'.$this->escapePattern;
$this->nonAsciiPattern = '[^\x00-\x7F]';
$this->nmCharPattern = '[_a-z0-9-]|'.$this->escapePattern.'|'.$this->nonAsciiPattern;
$this->nmStartPattern = '[_a-z]|'.$this->escapePattern.'|'.$this->nonAsciiPattern;
$this->identifierPattern = '-?(?:'.$this->nmStartPattern.')(?:'.$this->nmCharPattern.')*';
$this->hashPattern = '#((?:'.$this->nmCharPattern.')+)';
$this->numberPattern = '[+-]?(?:[0-9]*\.[0-9]+|[0-9]+)';
$this->quotedStringPattern = '([^\n\r\f%s]|'.$this->stringEscapePattern.')*';
}
public function getNewLineEscapePattern(): string
{
return '~^'.$this->newLineEscapePattern.'~';
}
public function getSimpleEscapePattern(): string
{
return '~^'.$this->simpleEscapePattern.'~';
}
public function getUnicodeEscapePattern(): string
{
return '~^'.$this->unicodeEscapePattern.'~i';
}
public function getIdentifierPattern(): string
{
return '~^'.$this->identifierPattern.'~i';
}
public function getHashPattern(): string
{
return '~^'.$this->hashPattern.'~i';
}
public function getNumberPattern(): string
{
return '~^'.$this->numberPattern.'~';
}
public function getQuotedStringPattern(string $quote): string
{
return '~^'.sprintf($this->quotedStringPattern, $quote).'~i';
}
}
Tokenizer/Tokenizer.php 0000644 00000003762 15152054360 0011212 0 ustar 00 <?php
/*
* This file is part of the Symfony package.
*
* (c) Fabien Potencier <fabien@symfony.com>
*
* For the full copyright and license information, please view the LICENSE
* file that was distributed with this source code.
*/
namespace Symfony\Component\CssSelector\Parser\Tokenizer;
use Symfony\Component\CssSelector\Parser\Handler;
use Symfony\Component\CssSelector\Parser\Reader;
use Symfony\Component\CssSelector\Parser\Token;
use Symfony\Component\CssSelector\Parser\TokenStream;
/**
* CSS selector tokenizer.
*
* This component is a port of the Python cssselect library,
* which is copyright Ian Bicking, @see https://github.com/SimonSapin/cssselect.
*
* @author Jean-François Simon <jeanfrancois.simon@sensiolabs.com>
*
* @internal
*/
class Tokenizer
{
/**
* @var Handler\HandlerInterface[]
*/
private $handlers;
public function __construct()
{
$patterns = new TokenizerPatterns();
$escaping = new TokenizerEscaping($patterns);
$this->handlers = [
new Handler\WhitespaceHandler(),
new Handler\IdentifierHandler($patterns, $escaping),
new Handler\HashHandler($patterns, $escaping),
new Handler\StringHandler($patterns, $escaping),
new Handler\NumberHandler($patterns),
new Handler\CommentHandler(),
];
}
/**
* Tokenize selector source code.
*/
public function tokenize(Reader $reader): TokenStream
{
$stream = new TokenStream();
while (!$reader->isEOF()) {
foreach ($this->handlers as $handler) {
if ($handler->handle($reader, $stream)) {
continue 2;
}
}
$stream->push(new Token(Token::TYPE_DELIMITER, $reader->getSubstring(1), $reader->getPosition()));
$reader->moveForward(1);
}
return $stream
->push(new Token(Token::TYPE_FILE_END, null, $reader->getPosition()))
->freeze();
}
}
Shortcut/HashParser.php 0000644 00000003064 15152054360 0011134 0 ustar 00 <?php
/*
* This file is part of the Symfony package.
*
* (c) Fabien Potencier <fabien@symfony.com>
*
* For the full copyright and license information, please view the LICENSE
* file that was distributed with this source code.
*/
namespace Symfony\Component\CssSelector\Parser\Shortcut;
use Symfony\Component\CssSelector\Node\ElementNode;
use Symfony\Component\CssSelector\Node\HashNode;
use Symfony\Component\CssSelector\Node\SelectorNode;
use Symfony\Component\CssSelector\Parser\ParserInterface;
/**
* CSS selector hash parser shortcut.
*
* This component is a port of the Python cssselect library,
* which is copyright Ian Bicking, @see https://github.com/SimonSapin/cssselect.
*
* @author Jean-François Simon <jeanfrancois.simon@sensiolabs.com>
*
* @internal
*/
class HashParser implements ParserInterface
{
/**
* {@inheritdoc}
*/
public function parse(string $source): array
{
// Matches an optional namespace, optional element, and required id
// $source = 'test|input#ab6bd_field';
// $matches = array (size=4)
// 0 => string 'test|input#ab6bd_field' (length=22)
// 1 => string 'test' (length=4)
// 2 => string 'input' (length=5)
// 3 => string 'ab6bd_field' (length=11)
if (preg_match('/^(?:([a-z]++)\|)?+([\w-]++|\*)?+#([\w-]++)$/i', trim($source), $matches)) {
return [
new SelectorNode(new HashNode(new ElementNode($matches[1] ?: null, $matches[2] ?: null), $matches[3])),
];
}
return [];
}
}
Shortcut/EmptyStringParser.php 0000644 00000002316 15152054360 0012535 0 ustar 00 <?php
/*
* This file is part of the Symfony package.
*
* (c) Fabien Potencier <fabien@symfony.com>
*
* For the full copyright and license information, please view the LICENSE
* file that was distributed with this source code.
*/
namespace Symfony\Component\CssSelector\Parser\Shortcut;
use Symfony\Component\CssSelector\Node\ElementNode;
use Symfony\Component\CssSelector\Node\SelectorNode;
use Symfony\Component\CssSelector\Parser\ParserInterface;
/**
* CSS selector class parser shortcut.
*
* This shortcut ensure compatibility with previous version.
* - The parser fails to parse an empty string.
* - In the previous version, an empty string matches each tags.
*
* This component is a port of the Python cssselect library,
* which is copyright Ian Bicking, @see https://github.com/SimonSapin/cssselect.
*
* @author Jean-François Simon <jeanfrancois.simon@sensiolabs.com>
*
* @internal
*/
class EmptyStringParser implements ParserInterface
{
/**
* {@inheritdoc}
*/
public function parse(string $source): array
{
// Matches an empty string
if ('' == $source) {
return [new SelectorNode(new ElementNode(null, '*'))];
}
return [];
}
}
Shortcut/ClassParser.php 0000644 00000003074 15152054360 0011317 0 ustar 00 <?php
/*
* This file is part of the Symfony package.
*
* (c) Fabien Potencier <fabien@symfony.com>
*
* For the full copyright and license information, please view the LICENSE
* file that was distributed with this source code.
*/
namespace Symfony\Component\CssSelector\Parser\Shortcut;
use Symfony\Component\CssSelector\Node\ClassNode;
use Symfony\Component\CssSelector\Node\ElementNode;
use Symfony\Component\CssSelector\Node\SelectorNode;
use Symfony\Component\CssSelector\Parser\ParserInterface;
/**
* CSS selector class parser shortcut.
*
* This component is a port of the Python cssselect library,
* which is copyright Ian Bicking, @see https://github.com/SimonSapin/cssselect.
*
* @author Jean-François Simon <jeanfrancois.simon@sensiolabs.com>
*
* @internal
*/
class ClassParser implements ParserInterface
{
/**
* {@inheritdoc}
*/
public function parse(string $source): array
{
// Matches an optional namespace, optional element, and required class
// $source = 'test|input.ab6bd_field';
// $matches = array (size=4)
// 0 => string 'test|input.ab6bd_field' (length=22)
// 1 => string 'test' (length=4)
// 2 => string 'input' (length=5)
// 3 => string 'ab6bd_field' (length=11)
if (preg_match('/^(?:([a-z]++)\|)?+([\w-]++|\*)?+\.([\w-]++)$/i', trim($source), $matches)) {
return [
new SelectorNode(new ClassNode(new ElementNode($matches[1] ?: null, $matches[2] ?: null), $matches[3])),
];
}
return [];
}
}
Shortcut/ElementParser.php 0000644 00000002554 15152054360 0011645 0 ustar 00 <?php
/*
* This file is part of the Symfony package.
*
* (c) Fabien Potencier <fabien@symfony.com>
*
* For the full copyright and license information, please view the LICENSE
* file that was distributed with this source code.
*/
namespace Symfony\Component\CssSelector\Parser\Shortcut;
use Symfony\Component\CssSelector\Node\ElementNode;
use Symfony\Component\CssSelector\Node\SelectorNode;
use Symfony\Component\CssSelector\Parser\ParserInterface;
/**
* CSS selector element parser shortcut.
*
* This component is a port of the Python cssselect library,
* which is copyright Ian Bicking, @see https://github.com/SimonSapin/cssselect.
*
* @author Jean-François Simon <jeanfrancois.simon@sensiolabs.com>
*
* @internal
*/
class ElementParser implements ParserInterface
{
/**
* {@inheritdoc}
*/
public function parse(string $source): array
{
// Matches an optional namespace, required element or `*`
// $source = 'testns|testel';
// $matches = array (size=3)
// 0 => string 'testns|testel' (length=13)
// 1 => string 'testns' (length=6)
// 2 => string 'testel' (length=6)
if (preg_match('/^(?:([a-z]++)\|)?([\w-]++|\*)$/i', trim($source), $matches)) {
return [new SelectorNode(new ElementNode($matches[1] ?: null, $matches[2]))];
}
return [];
}
}
Value.php 0000644 00000003064 15152066060 0006335 0 ustar 00 <?php
declare(strict_types=1);
namespace Dotenv\Parser;
use Dotenv\Util\Str;
final class Value
{
/**
* The string representation of the parsed value.
*
* @var string
*/
private $chars;
/**
* The locations of the variables in the value.
*
* @var int[]
*/
private $vars;
/**
* Internal constructor for a value.
*
* @param string $chars
* @param int[] $vars
*
* @return void
*/
private function __construct(string $chars, array $vars)
{
$this->chars = $chars;
$this->vars = $vars;
}
/**
* Create an empty value instance.
*
* @return \Dotenv\Parser\Value
*/
public static function blank()
{
return new self('', []);
}
/**
* Create a new value instance, appending the characters.
*
* @param string $chars
* @param bool $var
*
* @return \Dotenv\Parser\Value
*/
public function append(string $chars, bool $var)
{
return new self(
$this->chars.$chars,
$var ? \array_merge($this->vars, [Str::len($this->chars)]) : $this->vars
);
}
/**
* Get the string representation of the parsed value.
*
* @return string
*/
public function getChars()
{
return $this->chars;
}
/**
* Get the locations of the variables in the value.
*
* @return int[]
*/
public function getVars()
{
$vars = $this->vars;
\rsort($vars);
return $vars;
}
}
Entry.php 0000644 00000001766 15152066060 0006371 0 ustar 00 <?php
declare(strict_types=1);
namespace Dotenv\Parser;
use PhpOption\Option;
final class Entry
{
/**
* The entry name.
*
* @var string
*/
private $name;
/**
* The entry value.
*
* @var \Dotenv\Parser\Value|null
*/
private $value;
/**
* Create a new entry instance.
*
* @param string $name
* @param \Dotenv\Parser\Value|null $value
*
* @return void
*/
public function __construct(string $name, Value $value = null)
{
$this->name = $name;
$this->value = $value;
}
/**
* Get the entry name.
*
* @return string
*/
public function getName()
{
return $this->name;
}
/**
* Get the entry value.
*
* @return \PhpOption\Option<\Dotenv\Parser\Value>
*/
public function getValue()
{
/** @var \PhpOption\Option<\Dotenv\Parser\Value> */
return Option::fromValue($this->value);
}
}
Lines.php 0000644 00000006113 15152066060 0006331 0 ustar 00 <?php
declare(strict_types=1);
namespace Dotenv\Parser;
use Dotenv\Util\Regex;
use Dotenv\Util\Str;
final class Lines
{
/**
* This class is a singleton.
*
* @codeCoverageIgnore
*
* @return void
*/
private function __construct()
{
//
}
/**
* Process the array of lines of environment variables.
*
* This will produce an array of raw entries, one per variable.
*
* @param string[] $lines
*
* @return string[]
*/
public static function process(array $lines)
{
$output = [];
$multiline = false;
$multilineBuffer = [];
foreach ($lines as $line) {
[$multiline, $line, $multilineBuffer] = self::multilineProcess($multiline, $line, $multilineBuffer);
if (!$multiline && !self::isCommentOrWhitespace($line)) {
$output[] = $line;
}
}
return $output;
}
/**
* Used to make all multiline variable process.
*
* @param bool $multiline
* @param string $line
* @param string[] $buffer
*
* @return array{bool,string,string[]}
*/
private static function multilineProcess(bool $multiline, string $line, array $buffer)
{
$startsOnCurrentLine = $multiline ? false : self::looksLikeMultilineStart($line);
// check if $line can be multiline variable
if ($startsOnCurrentLine) {
$multiline = true;
}
if ($multiline) {
\array_push($buffer, $line);
if (self::looksLikeMultilineStop($line, $startsOnCurrentLine)) {
$multiline = false;
$line = \implode("\n", $buffer);
$buffer = [];
}
}
return [$multiline, $line, $buffer];
}
/**
* Determine if the given line can be the start of a multiline variable.
*
* @param string $line
*
* @return bool
*/
private static function looksLikeMultilineStart(string $line)
{
return Str::pos($line, '="')->map(static function () use ($line) {
return self::looksLikeMultilineStop($line, true) === false;
})->getOrElse(false);
}
/**
* Determine if the given line can be the start of a multiline variable.
*
* @param string $line
* @param bool $started
*
* @return bool
*/
private static function looksLikeMultilineStop(string $line, bool $started)
{
if ($line === '"') {
return true;
}
return Regex::occurrences('/(?=([^\\\\]"))/', \str_replace('\\\\', '', $line))->map(static function (int $count) use ($started) {
return $started ? $count > 1 : $count >= 1;
})->success()->getOrElse(false);
}
/**
* Determine if the line in the file is a comment or whitespace.
*
* @param string $line
*
* @return bool
*/
private static function isCommentOrWhitespace(string $line)
{
$line = \trim($line);
return $line === '' || (isset($line[0]) && $line[0] === '#');
}
}
Lexer.php 0000644 00000002370 15152066060 0006337 0 ustar 00 <?php
declare(strict_types=1);
namespace Dotenv\Parser;
final class Lexer
{
/**
* The regex for each type of token.
*/
private const PATTERNS = [
'[\r\n]{1,1000}', '[^\S\r\n]{1,1000}', '\\\\', '\'', '"', '\\#', '\\$', '([^(\s\\\\\'"\\#\\$)]|\\(|\\)){1,1000}',
];
/**
* This class is a singleton.
*
* @codeCoverageIgnore
*
* @return void
*/
private function __construct()
{
//
}
/**
* Convert content into a token stream.
*
* Multibyte string processing is not needed here, and nether is error
* handling, for performance reasons.
*
* @param string $content
*
* @return \Generator<string>
*/
public static function lex(string $content)
{
static $regex;
if ($regex === null) {
$regex = '(('.\implode(')|(', self::PATTERNS).'))A';
}
$offset = 0;
while (isset($content[$offset])) {
if (!\preg_match($regex, $content, $matches, 0, $offset)) {
throw new \Error(\sprintf('Lexer encountered unexpected character [%s].', $content[$offset]));
}
$offset += \strlen($matches[0]);
yield $matches[0];
}
}
}
EntryParser.php 0000644 00000030240 15152066060 0007533 0 ustar 00 <?php
declare(strict_types=1);
namespace Dotenv\Parser;
use Dotenv\Util\Regex;
use Dotenv\Util\Str;
use GrahamCampbell\ResultType\Error;
use GrahamCampbell\ResultType\Result;
use GrahamCampbell\ResultType\Success;
final class EntryParser
{
private const INITIAL_STATE = 0;
private const UNQUOTED_STATE = 1;
private const SINGLE_QUOTED_STATE = 2;
private const DOUBLE_QUOTED_STATE = 3;
private const ESCAPE_SEQUENCE_STATE = 4;
private const WHITESPACE_STATE = 5;
private const COMMENT_STATE = 6;
private const REJECT_STATES = [self::SINGLE_QUOTED_STATE, self::DOUBLE_QUOTED_STATE, self::ESCAPE_SEQUENCE_STATE];
/**
* This class is a singleton.
*
* @codeCoverageIgnore
*
* @return void
*/
private function __construct()
{
//
}
/**
* Parse a raw entry into a proper entry.
*
* That is, turn a raw environment variable entry into a name and possibly
* a value. We wrap the answer in a result type.
*
* @param string $entry
*
* @return \GrahamCampbell\ResultType\Result<\Dotenv\Parser\Entry,string>
*/
public static function parse(string $entry)
{
return self::splitStringIntoParts($entry)->flatMap(static function (array $parts) {
[$name, $value] = $parts;
return self::parseName($name)->flatMap(static function (string $name) use ($value) {
/** @var Result<Value|null,string> */
$parsedValue = $value === null ? Success::create(null) : self::parseValue($value);
return $parsedValue->map(static function (?Value $value) use ($name) {
return new Entry($name, $value);
});
});
});
}
/**
* Split the compound string into parts.
*
* @param string $line
*
* @return \GrahamCampbell\ResultType\Result<array{string,string|null},string>
*/
private static function splitStringIntoParts(string $line)
{
/** @var array{string,string|null} */
$result = Str::pos($line, '=')->map(static function () use ($line) {
return \array_map('trim', \explode('=', $line, 2));
})->getOrElse([$line, null]);
if ($result[0] === '') {
/** @var \GrahamCampbell\ResultType\Result<array{string,string|null},string> */
return Error::create(self::getErrorMessage('an unexpected equals', $line));
}
/** @var \GrahamCampbell\ResultType\Result<array{string,string|null},string> */
return Success::create($result);
}
/**
* Parse the given variable name.
*
* That is, strip the optional quotes and leading "export" from the
* variable name. We wrap the answer in a result type.
*
* @param string $name
*
* @return \GrahamCampbell\ResultType\Result<string,string>
*/
private static function parseName(string $name)
{
if (Str::len($name) > 8 && Str::substr($name, 0, 6) === 'export' && \ctype_space(Str::substr($name, 6, 1))) {
$name = \ltrim(Str::substr($name, 6));
}
if (self::isQuotedName($name)) {
$name = Str::substr($name, 1, -1);
}
if (!self::isValidName($name)) {
/** @var \GrahamCampbell\ResultType\Result<string,string> */
return Error::create(self::getErrorMessage('an invalid name', $name));
}
/** @var \GrahamCampbell\ResultType\Result<string,string> */
return Success::create($name);
}
/**
* Is the given variable name quoted?
*
* @param string $name
*
* @return bool
*/
private static function isQuotedName(string $name)
{
if (Str::len($name) < 3) {
return false;
}
$first = Str::substr($name, 0, 1);
$last = Str::substr($name, -1, 1);
return ($first === '"' && $last === '"') || ($first === '\'' && $last === '\'');
}
/**
* Is the given variable name valid?
*
* @param string $name
*
* @return bool
*/
private static function isValidName(string $name)
{
return Regex::matches('~(*UTF8)\A[\p{Ll}\p{Lu}\p{M}\p{N}_.]+\z~', $name)->success()->getOrElse(false);
}
/**
* Parse the given variable value.
*
* This has the effect of stripping quotes and comments, dealing with
* special characters, and locating nested variables, but not resolving
* them. Formally, we run a finite state automaton with an output tape: a
* transducer. We wrap the answer in a result type.
*
* @param string $value
*
* @return \GrahamCampbell\ResultType\Result<\Dotenv\Parser\Value,string>
*/
private static function parseValue(string $value)
{
if (\trim($value) === '') {
/** @var \GrahamCampbell\ResultType\Result<\Dotenv\Parser\Value,string> */
return Success::create(Value::blank());
}
return \array_reduce(\iterator_to_array(Lexer::lex($value)), static function (Result $data, string $token) {
return $data->flatMap(static function (array $data) use ($token) {
return self::processToken($data[1], $token)->map(static function (array $val) use ($data) {
return [$data[0]->append($val[0], $val[1]), $val[2]];
});
});
}, Success::create([Value::blank(), self::INITIAL_STATE]))->flatMap(static function (array $result) {
/** @psalm-suppress DocblockTypeContradiction */
if (in_array($result[1], self::REJECT_STATES, true)) {
/** @var \GrahamCampbell\ResultType\Result<\Dotenv\Parser\Value,string> */
return Error::create('a missing closing quote');
}
/** @var \GrahamCampbell\ResultType\Result<\Dotenv\Parser\Value,string> */
return Success::create($result[0]);
})->mapError(static function (string $err) use ($value) {
return self::getErrorMessage($err, $value);
});
}
/**
* Process the given token.
*
* @param int $state
* @param string $token
*
* @return \GrahamCampbell\ResultType\Result<array{string,bool,int},string>
*/
private static function processToken(int $state, string $token)
{
switch ($state) {
case self::INITIAL_STATE:
if ($token === '\'') {
/** @var \GrahamCampbell\ResultType\Result<array{string,bool,int},string> */
return Success::create(['', false, self::SINGLE_QUOTED_STATE]);
} elseif ($token === '"') {
/** @var \GrahamCampbell\ResultType\Result<array{string,bool,int},string> */
return Success::create(['', false, self::DOUBLE_QUOTED_STATE]);
} elseif ($token === '#') {
/** @var \GrahamCampbell\ResultType\Result<array{string,bool,int},string> */
return Success::create(['', false, self::COMMENT_STATE]);
} elseif ($token === '$') {
/** @var \GrahamCampbell\ResultType\Result<array{string,bool,int},string> */
return Success::create([$token, true, self::UNQUOTED_STATE]);
} else {
/** @var \GrahamCampbell\ResultType\Result<array{string,bool,int},string> */
return Success::create([$token, false, self::UNQUOTED_STATE]);
}
case self::UNQUOTED_STATE:
if ($token === '#') {
/** @var \GrahamCampbell\ResultType\Result<array{string,bool,int},string> */
return Success::create(['', false, self::COMMENT_STATE]);
} elseif (\ctype_space($token)) {
/** @var \GrahamCampbell\ResultType\Result<array{string,bool,int},string> */
return Success::create(['', false, self::WHITESPACE_STATE]);
} elseif ($token === '$') {
/** @var \GrahamCampbell\ResultType\Result<array{string,bool,int},string> */
return Success::create([$token, true, self::UNQUOTED_STATE]);
} else {
/** @var \GrahamCampbell\ResultType\Result<array{string,bool,int},string> */
return Success::create([$token, false, self::UNQUOTED_STATE]);
}
case self::SINGLE_QUOTED_STATE:
if ($token === '\'') {
/** @var \GrahamCampbell\ResultType\Result<array{string,bool,int},string> */
return Success::create(['', false, self::WHITESPACE_STATE]);
} else {
/** @var \GrahamCampbell\ResultType\Result<array{string,bool,int},string> */
return Success::create([$token, false, self::SINGLE_QUOTED_STATE]);
}
case self::DOUBLE_QUOTED_STATE:
if ($token === '"') {
/** @var \GrahamCampbell\ResultType\Result<array{string,bool,int},string> */
return Success::create(['', false, self::WHITESPACE_STATE]);
} elseif ($token === '\\') {
/** @var \GrahamCampbell\ResultType\Result<array{string,bool,int},string> */
return Success::create(['', false, self::ESCAPE_SEQUENCE_STATE]);
} elseif ($token === '$') {
/** @var \GrahamCampbell\ResultType\Result<array{string,bool,int},string> */
return Success::create([$token, true, self::DOUBLE_QUOTED_STATE]);
} else {
/** @var \GrahamCampbell\ResultType\Result<array{string,bool,int},string> */
return Success::create([$token, false, self::DOUBLE_QUOTED_STATE]);
}
case self::ESCAPE_SEQUENCE_STATE:
if ($token === '"' || $token === '\\') {
/** @var \GrahamCampbell\ResultType\Result<array{string,bool,int},string> */
return Success::create([$token, false, self::DOUBLE_QUOTED_STATE]);
} elseif ($token === '$') {
/** @var \GrahamCampbell\ResultType\Result<array{string,bool,int},string> */
return Success::create([$token, false, self::DOUBLE_QUOTED_STATE]);
} else {
$first = Str::substr($token, 0, 1);
if (\in_array($first, ['f', 'n', 'r', 't', 'v'], true)) {
/** @var \GrahamCampbell\ResultType\Result<array{string,bool,int},string> */
return Success::create([\stripcslashes('\\'.$first).Str::substr($token, 1), false, self::DOUBLE_QUOTED_STATE]);
} else {
/** @var \GrahamCampbell\ResultType\Result<array{string,bool,int},string> */
return Error::create('an unexpected escape sequence');
}
}
case self::WHITESPACE_STATE:
if ($token === '#') {
/** @var \GrahamCampbell\ResultType\Result<array{string,bool,int},string> */
return Success::create(['', false, self::COMMENT_STATE]);
} elseif (!\ctype_space($token)) {
/** @var \GrahamCampbell\ResultType\Result<array{string,bool,int},string> */
return Error::create('unexpected whitespace');
} else {
/** @var \GrahamCampbell\ResultType\Result<array{string,bool,int},string> */
return Success::create(['', false, self::WHITESPACE_STATE]);
}
case self::COMMENT_STATE:
/** @var \GrahamCampbell\ResultType\Result<array{string,bool,int},string> */
return Success::create(['', false, self::COMMENT_STATE]);
default:
throw new \Error('Parser entered invalid state.');
}
}
/**
* Generate a friendly error message.
*
* @param string $cause
* @param string $subject
*
* @return string
*/
private static function getErrorMessage(string $cause, string $subject)
{
return \sprintf(
'Encountered %s at [%s].',
$cause,
\strtok($subject, "\n")
);
}
}
CommentStrategy/LocalComment.php 0000644 00000002046 15152100467 0012762 0 ustar 00 <?php
namespace Egulias\EmailValidator\Parser\CommentStrategy;
use Egulias\EmailValidator\EmailLexer;
use Egulias\EmailValidator\Result\Result;
use Egulias\EmailValidator\Result\ValidEmail;
use Egulias\EmailValidator\Warning\CFWSNearAt;
use Egulias\EmailValidator\Result\InvalidEmail;
use Egulias\EmailValidator\Result\Reason\ExpectingATEXT;
class LocalComment implements CommentStrategy
{
/**
* @var array
*/
private $warnings = [];
public function exitCondition(EmailLexer $lexer, int $openedParenthesis): bool
{
return !$lexer->isNextToken(EmailLexer::S_AT);
}
public function endOfLoopValidations(EmailLexer $lexer): Result
{
if (!$lexer->isNextToken(EmailLexer::S_AT)) {
return new InvalidEmail(new ExpectingATEXT('ATEX is not expected after closing comments'), $lexer->current->value);
}
$this->warnings[CFWSNearAt::CODE] = new CFWSNearAt();
return new ValidEmail();
}
public function getWarnings(): array
{
return $this->warnings;
}
}
CommentStrategy/CommentStrategy.php 0000644 00000001015 15152100467 0013525 0 ustar 00 <?php
namespace Egulias\EmailValidator\Parser\CommentStrategy;
use Egulias\EmailValidator\EmailLexer;
use Egulias\EmailValidator\Result\Result;
use Egulias\EmailValidator\Warning\Warning;
interface CommentStrategy
{
/**
* Return "true" to continue, "false" to exit
*/
public function exitCondition(EmailLexer $lexer, int $openedParenthesis): bool;
public function endOfLoopValidations(EmailLexer $lexer): Result;
/**
* @return Warning[]
*/
public function getWarnings(): array;
}
CommentStrategy/DomainComment.php 0000644 00000002032 15152100467 0013132 0 ustar 00 <?php
namespace Egulias\EmailValidator\Parser\CommentStrategy;
use Egulias\EmailValidator\EmailLexer;
use Egulias\EmailValidator\Result\Result;
use Egulias\EmailValidator\Result\ValidEmail;
use Egulias\EmailValidator\Result\InvalidEmail;
use Egulias\EmailValidator\Result\Reason\ExpectingATEXT;
class DomainComment implements CommentStrategy
{
public function exitCondition(EmailLexer $lexer, int $openedParenthesis): bool
{
return !($openedParenthesis === 0 && $lexer->isNextToken(EmailLexer::S_DOT));
}
public function endOfLoopValidations(EmailLexer $lexer): Result
{
//test for end of string
if (!$lexer->isNextToken(EmailLexer::S_DOT)) {
return new InvalidEmail(new ExpectingATEXT('DOT not found near CLOSEPARENTHESIS'), $lexer->current->value);
}
//add warning
//Address is valid within the message but cannot be used unmodified for the envelope
return new ValidEmail();
}
public function getWarnings(): array
{
return [];
}
}
DoubleQuote.php 0000644 00000006201 15152100467 0007505 0 ustar 00 <?php
namespace Egulias\EmailValidator\Parser;
use Egulias\EmailValidator\EmailLexer;
use Egulias\EmailValidator\Result\ValidEmail;
use Egulias\EmailValidator\Result\InvalidEmail;
use Egulias\EmailValidator\Warning\CFWSWithFWS;
use Egulias\EmailValidator\Warning\QuotedString;
use Egulias\EmailValidator\Result\Reason\ExpectingATEXT;
use Egulias\EmailValidator\Result\Reason\UnclosedQuotedString;
use Egulias\EmailValidator\Result\Result;
class DoubleQuote extends PartParser
{
public function parse(): Result
{
$validQuotedString = $this->checkDQUOTE();
if ($validQuotedString->isInvalid()) {
return $validQuotedString;
}
$special = [
EmailLexer::S_CR => true,
EmailLexer::S_HTAB => true,
EmailLexer::S_LF => true
];
$invalid = [
EmailLexer::C_NUL => true,
EmailLexer::S_HTAB => true,
EmailLexer::S_CR => true,
EmailLexer::S_LF => true
];
$setSpecialsWarning = true;
$this->lexer->moveNext();
while (!$this->lexer->current->isA(EmailLexer::S_DQUOTE) && !$this->lexer->current->isA(EmailLexer::S_EMPTY)) {
if (isset($special[$this->lexer->current->type]) && $setSpecialsWarning) {
$this->warnings[CFWSWithFWS::CODE] = new CFWSWithFWS();
$setSpecialsWarning = false;
}
if ($this->lexer->current->isA(EmailLexer::S_BACKSLASH) && $this->lexer->isNextToken(EmailLexer::S_DQUOTE)) {
$this->lexer->moveNext();
}
$this->lexer->moveNext();
if (!$this->escaped() && isset($invalid[$this->lexer->current->type])) {
return new InvalidEmail(new ExpectingATEXT("Expecting ATEXT between DQUOTE"), $this->lexer->current->value);
}
}
$prev = $this->lexer->getPrevious();
if ($prev->isA(EmailLexer::S_BACKSLASH)) {
$validQuotedString = $this->checkDQUOTE();
if ($validQuotedString->isInvalid()) {
return $validQuotedString;
}
}
if (!$this->lexer->isNextToken(EmailLexer::S_AT) && !$prev->isA(EmailLexer::S_BACKSLASH)) {
return new InvalidEmail(new ExpectingATEXT("Expecting ATEXT between DQUOTE"), $this->lexer->current->value);
}
return new ValidEmail();
}
protected function checkDQUOTE(): Result
{
$previous = $this->lexer->getPrevious();
if ($this->lexer->isNextToken(EmailLexer::GENERIC) && $previous->isA(EmailLexer::GENERIC)) {
$description = 'https://tools.ietf.org/html/rfc5322#section-3.2.4 - quoted string should be a unit';
return new InvalidEmail(new ExpectingATEXT($description), $this->lexer->current->value);
}
try {
$this->lexer->find(EmailLexer::S_DQUOTE);
} catch (\Exception $e) {
return new InvalidEmail(new UnclosedQuotedString(), $this->lexer->current->value);
}
$this->warnings[QuotedString::CODE] = new QuotedString($previous->value, $this->lexer->current->value);
return new ValidEmail();
}
}
DomainPart.php 0000644 00000024741 15152100467 0007324 0 ustar 00 <?php
namespace Egulias\EmailValidator\Parser;
use Doctrine\Common\Lexer\Token;
use Egulias\EmailValidator\EmailLexer;
use Egulias\EmailValidator\Warning\TLD;
use Egulias\EmailValidator\Result\Result;
use Egulias\EmailValidator\Result\ValidEmail;
use Egulias\EmailValidator\Result\InvalidEmail;
use Egulias\EmailValidator\Result\Reason\DotAtEnd;
use Egulias\EmailValidator\Result\Reason\DotAtStart;
use Egulias\EmailValidator\Warning\DeprecatedComment;
use Egulias\EmailValidator\Result\Reason\CRLFAtTheEnd;
use Egulias\EmailValidator\Result\Reason\LabelTooLong;
use Egulias\EmailValidator\Result\Reason\NoDomainPart;
use Egulias\EmailValidator\Result\Reason\ConsecutiveAt;
use Egulias\EmailValidator\Result\Reason\DomainTooLong;
use Egulias\EmailValidator\Result\Reason\CharNotAllowed;
use Egulias\EmailValidator\Result\Reason\DomainHyphened;
use Egulias\EmailValidator\Result\Reason\ExpectingATEXT;
use Egulias\EmailValidator\Parser\CommentStrategy\DomainComment;
use Egulias\EmailValidator\Result\Reason\ExpectingDomainLiteralClose;
use Egulias\EmailValidator\Parser\DomainLiteral as DomainLiteralParser;
class DomainPart extends PartParser
{
public const DOMAIN_MAX_LENGTH = 253;
public const LABEL_MAX_LENGTH = 63;
/**
* @var string
*/
protected $domainPart = '';
/**
* @var string
*/
protected $label = '';
public function parse(): Result
{
$this->lexer->clearRecorded();
$this->lexer->startRecording();
$this->lexer->moveNext();
$domainChecks = $this->performDomainStartChecks();
if ($domainChecks->isInvalid()) {
return $domainChecks;
}
if ($this->lexer->current->isA(EmailLexer::S_AT)) {
return new InvalidEmail(new ConsecutiveAt(), $this->lexer->current->value);
}
$result = $this->doParseDomainPart();
if ($result->isInvalid()) {
return $result;
}
$end = $this->checkEndOfDomain();
if ($end->isInvalid()) {
return $end;
}
$this->lexer->stopRecording();
$this->domainPart = $this->lexer->getAccumulatedValues();
$length = strlen($this->domainPart);
if ($length > self::DOMAIN_MAX_LENGTH) {
return new InvalidEmail(new DomainTooLong(), $this->lexer->current->value);
}
return new ValidEmail();
}
private function checkEndOfDomain(): Result
{
$prev = $this->lexer->getPrevious();
if ($prev->isA(EmailLexer::S_DOT)) {
return new InvalidEmail(new DotAtEnd(), $this->lexer->current->value);
}
if ($prev->isA(EmailLexer::S_HYPHEN)) {
return new InvalidEmail(new DomainHyphened('Hypen found at the end of the domain'), $prev->value);
}
if ($this->lexer->current->isA(EmailLexer::S_SP)) {
return new InvalidEmail(new CRLFAtTheEnd(), $prev->value);
}
return new ValidEmail();
}
private function performDomainStartChecks(): Result
{
$invalidTokens = $this->checkInvalidTokensAfterAT();
if ($invalidTokens->isInvalid()) {
return $invalidTokens;
}
$missingDomain = $this->checkEmptyDomain();
if ($missingDomain->isInvalid()) {
return $missingDomain;
}
if ($this->lexer->current->isA(EmailLexer::S_OPENPARENTHESIS)) {
$this->warnings[DeprecatedComment::CODE] = new DeprecatedComment();
}
return new ValidEmail();
}
private function checkEmptyDomain(): Result
{
$thereIsNoDomain = $this->lexer->current->isA(EmailLexer::S_EMPTY) ||
($this->lexer->current->isA(EmailLexer::S_SP) &&
!$this->lexer->isNextToken(EmailLexer::GENERIC));
if ($thereIsNoDomain) {
return new InvalidEmail(new NoDomainPart(), $this->lexer->current->value);
}
return new ValidEmail();
}
private function checkInvalidTokensAfterAT(): Result
{
if ($this->lexer->current->isA(EmailLexer::S_DOT)) {
return new InvalidEmail(new DotAtStart(), $this->lexer->current->value);
}
if ($this->lexer->current->isA(EmailLexer::S_HYPHEN)) {
return new InvalidEmail(new DomainHyphened('After AT'), $this->lexer->current->value);
}
return new ValidEmail();
}
protected function parseComments(): Result
{
$commentParser = new Comment($this->lexer, new DomainComment());
$result = $commentParser->parse();
$this->warnings = [...$this->warnings, ...$commentParser->getWarnings()];
return $result;
}
protected function doParseDomainPart(): Result
{
$tldMissing = true;
$hasComments = false;
$domain = '';
do {
$prev = $this->lexer->getPrevious();
$notAllowedChars = $this->checkNotAllowedChars($this->lexer->current);
if ($notAllowedChars->isInvalid()) {
return $notAllowedChars;
}
if (
$this->lexer->current->isA(EmailLexer::S_OPENPARENTHESIS) ||
$this->lexer->current->isA(EmailLexer::S_CLOSEPARENTHESIS)
) {
$hasComments = true;
$commentsResult = $this->parseComments();
//Invalid comment parsing
if ($commentsResult->isInvalid()) {
return $commentsResult;
}
}
$dotsResult = $this->checkConsecutiveDots();
if ($dotsResult->isInvalid()) {
return $dotsResult;
}
if ($this->lexer->current->isA(EmailLexer::S_OPENBRACKET)) {
$literalResult = $this->parseDomainLiteral();
$this->addTLDWarnings($tldMissing);
return $literalResult;
}
$labelCheck = $this->checkLabelLength();
if ($labelCheck->isInvalid()) {
return $labelCheck;
}
$FwsResult = $this->parseFWS();
if ($FwsResult->isInvalid()) {
return $FwsResult;
}
$domain .= $this->lexer->current->value;
if ($this->lexer->current->isA(EmailLexer::S_DOT) && $this->lexer->isNextToken(EmailLexer::GENERIC)) {
$tldMissing = false;
}
$exceptionsResult = $this->checkDomainPartExceptions($prev, $hasComments);
if ($exceptionsResult->isInvalid()) {
return $exceptionsResult;
}
$this->lexer->moveNext();
} while (!$this->lexer->current->isA(EmailLexer::S_EMPTY));
$labelCheck = $this->checkLabelLength(true);
if ($labelCheck->isInvalid()) {
return $labelCheck;
}
$this->addTLDWarnings($tldMissing);
$this->domainPart = $domain;
return new ValidEmail();
}
/**
* @param Token<int, string> $token
*
* @return Result
*/
private function checkNotAllowedChars(Token $token): Result
{
$notAllowed = [EmailLexer::S_BACKSLASH => true, EmailLexer::S_SLASH => true];
if (isset($notAllowed[$token->type])) {
return new InvalidEmail(new CharNotAllowed(), $token->value);
}
return new ValidEmail();
}
/**
* @return Result
*/
protected function parseDomainLiteral(): Result
{
try {
$this->lexer->find(EmailLexer::S_CLOSEBRACKET);
} catch (\RuntimeException $e) {
return new InvalidEmail(new ExpectingDomainLiteralClose(), $this->lexer->current->value);
}
$domainLiteralParser = new DomainLiteralParser($this->lexer);
$result = $domainLiteralParser->parse();
$this->warnings = [...$this->warnings, ...$domainLiteralParser->getWarnings()];
return $result;
}
/**
* @param Token<int, string> $prev
* @param bool $hasComments
*
* @return Result
*/
protected function checkDomainPartExceptions(Token $prev, bool $hasComments): Result
{
if ($this->lexer->current->isA(EmailLexer::S_OPENBRACKET) && $prev->type !== EmailLexer::S_AT) {
return new InvalidEmail(new ExpectingATEXT('OPENBRACKET not after AT'), $this->lexer->current->value);
}
if ($this->lexer->current->isA(EmailLexer::S_HYPHEN) && $this->lexer->isNextToken(EmailLexer::S_DOT)) {
return new InvalidEmail(new DomainHyphened('Hypen found near DOT'), $this->lexer->current->value);
}
if (
$this->lexer->current->isA(EmailLexer::S_BACKSLASH)
&& $this->lexer->isNextToken(EmailLexer::GENERIC)
) {
return new InvalidEmail(new ExpectingATEXT('Escaping following "ATOM"'), $this->lexer->current->value);
}
return $this->validateTokens($hasComments);
}
protected function validateTokens(bool $hasComments): Result
{
$validDomainTokens = array(
EmailLexer::GENERIC => true,
EmailLexer::S_HYPHEN => true,
EmailLexer::S_DOT => true,
);
if ($hasComments) {
$validDomainTokens[EmailLexer::S_OPENPARENTHESIS] = true;
$validDomainTokens[EmailLexer::S_CLOSEPARENTHESIS] = true;
}
if (!isset($validDomainTokens[$this->lexer->current->type])) {
return new InvalidEmail(new ExpectingATEXT('Invalid token in domain: ' . $this->lexer->current->value), $this->lexer->current->value);
}
return new ValidEmail();
}
private function checkLabelLength(bool $isEndOfDomain = false): Result
{
if ($this->lexer->current->isA(EmailLexer::S_DOT) || $isEndOfDomain) {
if ($this->isLabelTooLong($this->label)) {
return new InvalidEmail(new LabelTooLong(), $this->lexer->current->value);
}
$this->label = '';
}
$this->label .= $this->lexer->current->value;
return new ValidEmail();
}
private function isLabelTooLong(string $label): bool
{
if (preg_match('/[^\x00-\x7F]/', $label)) {
idn_to_ascii($label, IDNA_DEFAULT, INTL_IDNA_VARIANT_UTS46, $idnaInfo);
return (bool) ($idnaInfo['errors'] & IDNA_ERROR_LABEL_TOO_LONG);
}
return strlen($label) > self::LABEL_MAX_LENGTH;
}
private function addTLDWarnings(bool $isTLDMissing): void
{
if ($isTLDMissing) {
$this->warnings[TLD::CODE] = new TLD();
}
}
public function domainPart(): string
{
return $this->domainPart;
}
}
IDLeftPart.php 0000644 00000000602 15152100467 0007212 0 ustar 00 <?php
namespace Egulias\EmailValidator\Parser;
use Egulias\EmailValidator\Result\Result;
use Egulias\EmailValidator\Result\InvalidEmail;
use Egulias\EmailValidator\Result\Reason\CommentsInIDRight;
class IDLeftPart extends LocalPart
{
protected function parseComments(): Result
{
return new InvalidEmail(new CommentsInIDRight(), $this->lexer->current->value);
}
}
FoldingWhiteSpace.php 0000644 00000005352 15152100467 0010622 0 ustar 00 <?php
namespace Egulias\EmailValidator\Parser;
use Egulias\EmailValidator\EmailLexer;
use Egulias\EmailValidator\Warning\CFWSNearAt;
use Egulias\EmailValidator\Result\InvalidEmail;
use Egulias\EmailValidator\Warning\CFWSWithFWS;
use Egulias\EmailValidator\Result\Reason\CRNoLF;
use Egulias\EmailValidator\Result\Reason\AtextAfterCFWS;
use Egulias\EmailValidator\Result\Reason\CRLFAtTheEnd;
use Egulias\EmailValidator\Result\Reason\CRLFX2;
use Egulias\EmailValidator\Result\Reason\ExpectingCTEXT;
use Egulias\EmailValidator\Result\Result;
use Egulias\EmailValidator\Result\ValidEmail;
class FoldingWhiteSpace extends PartParser
{
public const FWS_TYPES = [
EmailLexer::S_SP,
EmailLexer::S_HTAB,
EmailLexer::S_CR,
EmailLexer::S_LF,
EmailLexer::CRLF
];
public function parse(): Result
{
if (!$this->isFWS()) {
return new ValidEmail();
}
$previous = $this->lexer->getPrevious();
$resultCRLF = $this->checkCRLFInFWS();
if ($resultCRLF->isInvalid()) {
return $resultCRLF;
}
if ($this->lexer->current->isA(EmailLexer::S_CR)) {
return new InvalidEmail(new CRNoLF(), $this->lexer->current->value);
}
if ($this->lexer->isNextToken(EmailLexer::GENERIC) && !$previous->isA(EmailLexer::S_AT)) {
return new InvalidEmail(new AtextAfterCFWS(), $this->lexer->current->value);
}
if ($this->lexer->current->isA(EmailLexer::S_LF) || $this->lexer->current->isA(EmailLexer::C_NUL)) {
return new InvalidEmail(new ExpectingCTEXT(), $this->lexer->current->value);
}
if ($this->lexer->isNextToken(EmailLexer::S_AT) || $previous->isA(EmailLexer::S_AT)) {
$this->warnings[CFWSNearAt::CODE] = new CFWSNearAt();
} else {
$this->warnings[CFWSWithFWS::CODE] = new CFWSWithFWS();
}
return new ValidEmail();
}
protected function checkCRLFInFWS(): Result
{
if (!$this->lexer->current->isA(EmailLexer::CRLF)) {
return new ValidEmail();
}
if (!$this->lexer->isNextTokenAny(array(EmailLexer::S_SP, EmailLexer::S_HTAB))) {
return new InvalidEmail(new CRLFX2(), $this->lexer->current->value);
}
//this has no coverage. Condition is repeated from above one
if (!$this->lexer->isNextTokenAny(array(EmailLexer::S_SP, EmailLexer::S_HTAB))) {
return new InvalidEmail(new CRLFAtTheEnd(), $this->lexer->current->value);
}
return new ValidEmail();
}
protected function isFWS(): bool
{
if ($this->escaped()) {
return false;
}
return in_array($this->lexer->current->type, self::FWS_TYPES);
}
}
DomainLiteral.php 0000644 00000016001 15152100467 0010000 0 ustar 00 <?php
namespace Egulias\EmailValidator\Parser;
use Egulias\EmailValidator\EmailLexer;
use Egulias\EmailValidator\Result\Result;
use Egulias\EmailValidator\Result\ValidEmail;
use Egulias\EmailValidator\Result\InvalidEmail;
use Egulias\EmailValidator\Warning\CFWSWithFWS;
use Egulias\EmailValidator\Warning\IPV6BadChar;
use Egulias\EmailValidator\Result\Reason\CRNoLF;
use Egulias\EmailValidator\Warning\IPV6ColonEnd;
use Egulias\EmailValidator\Warning\IPV6MaxGroups;
use Egulias\EmailValidator\Warning\ObsoleteDTEXT;
use Egulias\EmailValidator\Warning\AddressLiteral;
use Egulias\EmailValidator\Warning\IPV6ColonStart;
use Egulias\EmailValidator\Warning\IPV6Deprecated;
use Egulias\EmailValidator\Warning\IPV6GroupCount;
use Egulias\EmailValidator\Warning\IPV6DoubleColon;
use Egulias\EmailValidator\Result\Reason\ExpectingDTEXT;
use Egulias\EmailValidator\Result\Reason\UnusualElements;
use Egulias\EmailValidator\Warning\DomainLiteral as WarningDomainLiteral;
class DomainLiteral extends PartParser
{
public const IPV4_REGEX = '/\\b(?:(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)\\.){3}(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)$/';
public const OBSOLETE_WARNINGS = [
EmailLexer::INVALID,
EmailLexer::C_DEL,
EmailLexer::S_LF,
EmailLexer::S_BACKSLASH
];
public function parse(): Result
{
$this->addTagWarnings();
$IPv6TAG = false;
$addressLiteral = '';
do {
if ($this->lexer->current->isA(EmailLexer::C_NUL)) {
return new InvalidEmail(new ExpectingDTEXT(), $this->lexer->current->value);
}
$this->addObsoleteWarnings();
if ($this->lexer->isNextTokenAny(array(EmailLexer::S_OPENBRACKET, EmailLexer::S_OPENBRACKET))) {
return new InvalidEmail(new ExpectingDTEXT(), $this->lexer->current->value);
}
if ($this->lexer->isNextTokenAny(
array(EmailLexer::S_HTAB, EmailLexer::S_SP, EmailLexer::CRLF)
)) {
$this->warnings[CFWSWithFWS::CODE] = new CFWSWithFWS();
$this->parseFWS();
}
if ($this->lexer->isNextToken(EmailLexer::S_CR)) {
return new InvalidEmail(new CRNoLF(), $this->lexer->current->value);
}
if ($this->lexer->current->isA(EmailLexer::S_BACKSLASH)) {
return new InvalidEmail(new UnusualElements($this->lexer->current->value), $this->lexer->current->value);
}
if ($this->lexer->current->isA(EmailLexer::S_IPV6TAG)) {
$IPv6TAG = true;
}
if ($this->lexer->current->isA(EmailLexer::S_CLOSEBRACKET)) {
break;
}
$addressLiteral .= $this->lexer->current->value;
} while ($this->lexer->moveNext());
//Encapsulate
$addressLiteral = str_replace('[', '', $addressLiteral);
$isAddressLiteralIPv4 = $this->checkIPV4Tag($addressLiteral);
if (!$isAddressLiteralIPv4) {
return new ValidEmail();
}
$addressLiteral = $this->convertIPv4ToIPv6($addressLiteral);
if (!$IPv6TAG) {
$this->warnings[WarningDomainLiteral::CODE] = new WarningDomainLiteral();
return new ValidEmail();
}
$this->warnings[AddressLiteral::CODE] = new AddressLiteral();
$this->checkIPV6Tag($addressLiteral);
return new ValidEmail();
}
/**
* @param string $addressLiteral
* @param int $maxGroups
*/
public function checkIPV6Tag($addressLiteral, $maxGroups = 8): void
{
$prev = $this->lexer->getPrevious();
if ($prev->isA(EmailLexer::S_COLON)) {
$this->warnings[IPV6ColonEnd::CODE] = new IPV6ColonEnd();
}
$IPv6 = substr($addressLiteral, 5);
//Daniel Marschall's new IPv6 testing strategy
$matchesIP = explode(':', $IPv6);
$groupCount = count($matchesIP);
$colons = strpos($IPv6, '::');
if (count(preg_grep('/^[0-9A-Fa-f]{0,4}$/', $matchesIP, PREG_GREP_INVERT)) !== 0) {
$this->warnings[IPV6BadChar::CODE] = new IPV6BadChar();
}
if ($colons === false) {
// We need exactly the right number of groups
if ($groupCount !== $maxGroups) {
$this->warnings[IPV6GroupCount::CODE] = new IPV6GroupCount();
}
return;
}
if ($colons !== strrpos($IPv6, '::')) {
$this->warnings[IPV6DoubleColon::CODE] = new IPV6DoubleColon();
return;
}
if ($colons === 0 || $colons === (strlen($IPv6) - 2)) {
// RFC 4291 allows :: at the start or end of an address
//with 7 other groups in addition
++$maxGroups;
}
if ($groupCount > $maxGroups) {
$this->warnings[IPV6MaxGroups::CODE] = new IPV6MaxGroups();
} elseif ($groupCount === $maxGroups) {
$this->warnings[IPV6Deprecated::CODE] = new IPV6Deprecated();
}
}
public function convertIPv4ToIPv6(string $addressLiteralIPv4): string
{
$matchesIP = [];
$IPv4Match = preg_match(self::IPV4_REGEX, $addressLiteralIPv4, $matchesIP);
// Extract IPv4 part from the end of the address-literal (if there is one)
if ($IPv4Match > 0) {
$index = (int) strrpos($addressLiteralIPv4, $matchesIP[0]);
//There's a match but it is at the start
if ($index > 0) {
// Convert IPv4 part to IPv6 format for further testing
return substr($addressLiteralIPv4, 0, $index) . '0:0';
}
}
return $addressLiteralIPv4;
}
/**
* @param string $addressLiteral
*
* @return bool
*/
protected function checkIPV4Tag($addressLiteral): bool
{
$matchesIP = [];
$IPv4Match = preg_match(self::IPV4_REGEX, $addressLiteral, $matchesIP);
// Extract IPv4 part from the end of the address-literal (if there is one)
if ($IPv4Match > 0) {
$index = strrpos($addressLiteral, $matchesIP[0]);
//There's a match but it is at the start
if ($index === 0) {
$this->warnings[AddressLiteral::CODE] = new AddressLiteral();
return false;
}
}
return true;
}
private function addObsoleteWarnings(): void
{
if (in_array($this->lexer->current->type, self::OBSOLETE_WARNINGS)) {
$this->warnings[ObsoleteDTEXT::CODE] = new ObsoleteDTEXT();
}
}
private function addTagWarnings(): void
{
if ($this->lexer->isNextToken(EmailLexer::S_COLON)) {
$this->warnings[IPV6ColonStart::CODE] = new IPV6ColonStart();
}
if ($this->lexer->isNextToken(EmailLexer::S_IPV6TAG)) {
$lexer = clone $this->lexer;
$lexer->moveNext();
if ($lexer->isNextToken(EmailLexer::S_DOUBLECOLON)) {
$this->warnings[IPV6ColonStart::CODE] = new IPV6ColonStart();
}
}
}
}
IDRightPart.php 0000644 00000001714 15152100467 0007402 0 ustar 00 <?php
namespace Egulias\EmailValidator\Parser;
use Egulias\EmailValidator\EmailLexer;
use Egulias\EmailValidator\Result\Result;
use Egulias\EmailValidator\Result\ValidEmail;
use Egulias\EmailValidator\Result\InvalidEmail;
use Egulias\EmailValidator\Result\Reason\ExpectingATEXT;
class IDRightPart extends DomainPart
{
protected function validateTokens(bool $hasComments): Result
{
$invalidDomainTokens = [
EmailLexer::S_DQUOTE => true,
EmailLexer::S_SQUOTE => true,
EmailLexer::S_BACKTICK => true,
EmailLexer::S_SEMICOLON => true,
EmailLexer::S_GREATERTHAN => true,
EmailLexer::S_LOWERTHAN => true,
];
if (isset($invalidDomainTokens[$this->lexer->current->type])) {
return new InvalidEmail(new ExpectingATEXT('Invalid token in domain: ' . $this->lexer->current->value), $this->lexer->current->value);
}
return new ValidEmail();
}
}
LocalPart.php 0000644 00000012440 15152100467 0007140 0 ustar 00 <?php
namespace Egulias\EmailValidator\Parser;
use Egulias\EmailValidator\EmailLexer;
use Egulias\EmailValidator\Result\Result;
use Egulias\EmailValidator\Result\ValidEmail;
use Egulias\EmailValidator\Result\InvalidEmail;
use Egulias\EmailValidator\Warning\LocalTooLong;
use Egulias\EmailValidator\Result\Reason\DotAtEnd;
use Egulias\EmailValidator\Result\Reason\DotAtStart;
use Egulias\EmailValidator\Result\Reason\ConsecutiveDot;
use Egulias\EmailValidator\Result\Reason\ExpectingATEXT;
use Egulias\EmailValidator\Parser\CommentStrategy\LocalComment;
class LocalPart extends PartParser
{
public const INVALID_TOKENS = [
EmailLexer::S_COMMA => EmailLexer::S_COMMA,
EmailLexer::S_CLOSEBRACKET => EmailLexer::S_CLOSEBRACKET,
EmailLexer::S_OPENBRACKET => EmailLexer::S_OPENBRACKET,
EmailLexer::S_GREATERTHAN => EmailLexer::S_GREATERTHAN,
EmailLexer::S_LOWERTHAN => EmailLexer::S_LOWERTHAN,
EmailLexer::S_COLON => EmailLexer::S_COLON,
EmailLexer::S_SEMICOLON => EmailLexer::S_SEMICOLON,
EmailLexer::INVALID => EmailLexer::INVALID
];
/**
* @var string
*/
private $localPart = '';
public function parse(): Result
{
$this->lexer->startRecording();
while (!$this->lexer->current->isA(EmailLexer::S_AT) && !$this->lexer->current->isA(EmailLexer::S_EMPTY)) {
if ($this->hasDotAtStart()) {
return new InvalidEmail(new DotAtStart(), $this->lexer->current->value);
}
if ($this->lexer->current->isA(EmailLexer::S_DQUOTE)) {
$dquoteParsingResult = $this->parseDoubleQuote();
//Invalid double quote parsing
if ($dquoteParsingResult->isInvalid()) {
return $dquoteParsingResult;
}
}
if (
$this->lexer->current->isA(EmailLexer::S_OPENPARENTHESIS) ||
$this->lexer->current->isA(EmailLexer::S_CLOSEPARENTHESIS)
) {
$commentsResult = $this->parseComments();
//Invalid comment parsing
if ($commentsResult->isInvalid()) {
return $commentsResult;
}
}
if ($this->lexer->current->isA(EmailLexer::S_DOT) && $this->lexer->isNextToken(EmailLexer::S_DOT)) {
return new InvalidEmail(new ConsecutiveDot(), $this->lexer->current->value);
}
if (
$this->lexer->current->isA(EmailLexer::S_DOT) &&
$this->lexer->isNextToken(EmailLexer::S_AT)
) {
return new InvalidEmail(new DotAtEnd(), $this->lexer->current->value);
}
$resultEscaping = $this->validateEscaping();
if ($resultEscaping->isInvalid()) {
return $resultEscaping;
}
$resultToken = $this->validateTokens(false);
if ($resultToken->isInvalid()) {
return $resultToken;
}
$resultFWS = $this->parseLocalFWS();
if ($resultFWS->isInvalid()) {
return $resultFWS;
}
$this->lexer->moveNext();
}
$this->lexer->stopRecording();
$this->localPart = rtrim($this->lexer->getAccumulatedValues(), '@');
if (strlen($this->localPart) > LocalTooLong::LOCAL_PART_LENGTH) {
$this->warnings[LocalTooLong::CODE] = new LocalTooLong();
}
return new ValidEmail();
}
protected function validateTokens(bool $hasComments): Result
{
if (isset(self::INVALID_TOKENS[$this->lexer->current->type])) {
return new InvalidEmail(new ExpectingATEXT('Invalid token found'), $this->lexer->current->value);
}
return new ValidEmail();
}
public function localPart(): string
{
return $this->localPart;
}
private function parseLocalFWS(): Result
{
$foldingWS = new FoldingWhiteSpace($this->lexer);
$resultFWS = $foldingWS->parse();
if ($resultFWS->isValid()) {
$this->warnings = [...$this->warnings, ...$foldingWS->getWarnings()];
}
return $resultFWS;
}
private function hasDotAtStart(): bool
{
return $this->lexer->current->isA(EmailLexer::S_DOT) && $this->lexer->getPrevious()->isA(EmailLexer::S_EMPTY);
}
private function parseDoubleQuote(): Result
{
$dquoteParser = new DoubleQuote($this->lexer);
$parseAgain = $dquoteParser->parse();
$this->warnings = [...$this->warnings, ...$dquoteParser->getWarnings()];
return $parseAgain;
}
protected function parseComments(): Result
{
$commentParser = new Comment($this->lexer, new LocalComment());
$result = $commentParser->parse();
$this->warnings = [...$this->warnings, ...$commentParser->getWarnings()];
return $result;
}
private function validateEscaping(): Result
{
//Backslash found
if (!$this->lexer->current->isA(EmailLexer::S_BACKSLASH)) {
return new ValidEmail();
}
if ($this->lexer->isNextToken(EmailLexer::GENERIC)) {
return new InvalidEmail(new ExpectingATEXT('Found ATOM after escaping'), $this->lexer->current->value);
}
return new ValidEmail();
}
}
PartParser.php 0000644 00000003003 15152100467 0007335 0 ustar 00 <?php
namespace Egulias\EmailValidator\Parser;
use Egulias\EmailValidator\EmailLexer;
use Egulias\EmailValidator\Result\InvalidEmail;
use Egulias\EmailValidator\Result\Reason\ConsecutiveDot;
use Egulias\EmailValidator\Result\Result;
use Egulias\EmailValidator\Result\ValidEmail;
use Egulias\EmailValidator\Warning\Warning;
abstract class PartParser
{
/**
* @var Warning[]
*/
protected $warnings = [];
/**
* @var EmailLexer
*/
protected $lexer;
public function __construct(EmailLexer $lexer)
{
$this->lexer = $lexer;
}
abstract public function parse(): Result;
/**
* @return Warning[]
*/
public function getWarnings()
{
return $this->warnings;
}
protected function parseFWS(): Result
{
$foldingWS = new FoldingWhiteSpace($this->lexer);
$resultFWS = $foldingWS->parse();
$this->warnings = [...$this->warnings, ...$foldingWS->getWarnings()];
return $resultFWS;
}
protected function checkConsecutiveDots(): Result
{
if ($this->lexer->current->isA(EmailLexer::S_DOT) && $this->lexer->isNextToken(EmailLexer::S_DOT)) {
return new InvalidEmail(new ConsecutiveDot(), $this->lexer->current->value);
}
return new ValidEmail();
}
protected function escaped(): bool
{
$previous = $this->lexer->getPrevious();
return $previous->isA(EmailLexer::S_BACKSLASH)
&& !$this->lexer->current->isA(EmailLexer::GENERIC);
}
}
Comment.php 0000644 00000006122 15152100467 0006661 0 ustar 00 <?php
namespace Egulias\EmailValidator\Parser;
use Egulias\EmailValidator\EmailLexer;
use Egulias\EmailValidator\Result\Result;
use Egulias\EmailValidator\Warning\QuotedPart;
use Egulias\EmailValidator\Result\InvalidEmail;
use Egulias\EmailValidator\Parser\CommentStrategy\CommentStrategy;
use Egulias\EmailValidator\Result\Reason\UnclosedComment;
use Egulias\EmailValidator\Result\Reason\UnOpenedComment;
use Egulias\EmailValidator\Warning\Comment as WarningComment;
class Comment extends PartParser
{
/**
* @var int
*/
private $openedParenthesis = 0;
/**
* @var CommentStrategy
*/
private $commentStrategy;
public function __construct(EmailLexer $lexer, CommentStrategy $commentStrategy)
{
$this->lexer = $lexer;
$this->commentStrategy = $commentStrategy;
}
public function parse(): Result
{
if ($this->lexer->current->isA(EmailLexer::S_OPENPARENTHESIS)) {
$this->openedParenthesis++;
if ($this->noClosingParenthesis()) {
return new InvalidEmail(new UnclosedComment(), $this->lexer->current->value);
}
}
if ($this->lexer->current->isA(EmailLexer::S_CLOSEPARENTHESIS)) {
return new InvalidEmail(new UnOpenedComment(), $this->lexer->current->value);
}
$this->warnings[WarningComment::CODE] = new WarningComment();
$moreTokens = true;
while ($this->commentStrategy->exitCondition($this->lexer, $this->openedParenthesis) && $moreTokens) {
if ($this->lexer->isNextToken(EmailLexer::S_OPENPARENTHESIS)) {
$this->openedParenthesis++;
}
$this->warnEscaping();
if ($this->lexer->isNextToken(EmailLexer::S_CLOSEPARENTHESIS)) {
$this->openedParenthesis--;
}
$moreTokens = $this->lexer->moveNext();
}
if ($this->openedParenthesis >= 1) {
return new InvalidEmail(new UnclosedComment(), $this->lexer->current->value);
}
if ($this->openedParenthesis < 0) {
return new InvalidEmail(new UnOpenedComment(), $this->lexer->current->value);
}
$finalValidations = $this->commentStrategy->endOfLoopValidations($this->lexer);
$this->warnings = [...$this->warnings, ...$this->commentStrategy->getWarnings()];
return $finalValidations;
}
/**
* @return void
*/
private function warnEscaping(): void
{
//Backslash found
if (!$this->lexer->current->isA(EmailLexer::S_BACKSLASH)) {
return;
}
if (!$this->lexer->isNextTokenAny(array(EmailLexer::S_SP, EmailLexer::S_HTAB, EmailLexer::C_DEL))) {
return;
}
$this->warnings[QuotedPart::CODE] =
new QuotedPart($this->lexer->getPrevious()->type, $this->lexer->current->type);
}
private function noClosingParenthesis(): bool
{
try {
$this->lexer->find(EmailLexer::S_CLOSEPARENTHESIS);
return false;
} catch (\RuntimeException $e) {
return true;
}
}
}
MarkdownParser.php 0000644 00000027575 15152113047 0010233 0 ustar 00 <?php
declare(strict_types=1);
/*
* This file is part of the league/commonmark package.
*
* (c) Colin O'Dell <colinodell@gmail.com>
*
* Original code based on the CommonMark JS reference parser (https://bitly.com/commonmark-js)
* - (c) John MacFarlane
*
* Additional code based on commonmark-java (https://github.com/commonmark/commonmark-java)
* - (c) Atlassian Pty Ltd
*
* For the full copyright and license information, please view the LICENSE
* file that was distributed with this source code.
*/
namespace League\CommonMark\Parser;
use League\CommonMark\Environment\EnvironmentInterface;
use League\CommonMark\Event\DocumentParsedEvent;
use League\CommonMark\Event\DocumentPreParsedEvent;
use League\CommonMark\Exception\CommonMarkException;
use League\CommonMark\Input\MarkdownInput;
use League\CommonMark\Node\Block\Document;
use League\CommonMark\Node\Block\Paragraph;
use League\CommonMark\Parser\Block\BlockContinueParserInterface;
use League\CommonMark\Parser\Block\BlockContinueParserWithInlinesInterface;
use League\CommonMark\Parser\Block\BlockStart;
use League\CommonMark\Parser\Block\BlockStartParserInterface;
use League\CommonMark\Parser\Block\DocumentBlockParser;
use League\CommonMark\Parser\Block\ParagraphParser;
use League\CommonMark\Reference\ReferenceInterface;
use League\CommonMark\Reference\ReferenceMap;
final class MarkdownParser implements MarkdownParserInterface
{
/** @psalm-readonly */
private EnvironmentInterface $environment;
/** @psalm-readonly-allow-private-mutation */
private int $maxNestingLevel;
/** @psalm-readonly-allow-private-mutation */
private ReferenceMap $referenceMap;
/** @psalm-readonly-allow-private-mutation */
private int $lineNumber = 0;
/** @psalm-readonly-allow-private-mutation */
private Cursor $cursor;
/**
* @var array<int, BlockContinueParserInterface>
*
* @psalm-readonly-allow-private-mutation
*/
private array $activeBlockParsers = [];
/**
* @var array<int, BlockContinueParserWithInlinesInterface>
*
* @psalm-readonly-allow-private-mutation
*/
private array $closedBlockParsers = [];
public function __construct(EnvironmentInterface $environment)
{
$this->environment = $environment;
}
private function initialize(): void
{
$this->referenceMap = new ReferenceMap();
$this->lineNumber = 0;
$this->activeBlockParsers = [];
$this->closedBlockParsers = [];
$this->maxNestingLevel = $this->environment->getConfiguration()->get('max_nesting_level');
}
/**
* @throws CommonMarkException
*/
public function parse(string $input): Document
{
$this->initialize();
$documentParser = new DocumentBlockParser($this->referenceMap);
$this->activateBlockParser($documentParser);
$preParsedEvent = new DocumentPreParsedEvent($documentParser->getBlock(), new MarkdownInput($input));
$this->environment->dispatch($preParsedEvent);
$markdownInput = $preParsedEvent->getMarkdown();
foreach ($markdownInput->getLines() as $lineNumber => $line) {
$this->lineNumber = $lineNumber;
$this->parseLine($line);
}
// finalizeAndProcess
$this->closeBlockParsers(\count($this->activeBlockParsers), $this->lineNumber);
$this->processInlines();
$this->environment->dispatch(new DocumentParsedEvent($documentParser->getBlock()));
return $documentParser->getBlock();
}
/**
