AbstractParser.php 19.7 KB
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684
<?php
/**
 * Parses doc comments.
 *
 * PHP version 5
 *
 * @category  PHP
 * @package   PHP_CodeSniffer
 * @author    Greg Sherwood <gsherwood@squiz.net>
 * @author    Marc McIntyre <mmcintyre@squiz.net>
 * @copyright 2006-2014 Squiz Pty Ltd (ABN 77 084 670 600)
 * @license   https://github.com/squizlabs/PHP_CodeSniffer/blob/master/licence.txt BSD Licence
 * @link      http://pear.php.net/package/PHP_CodeSniffer
 */

if (class_exists('PHP_CodeSniffer_CommentParser_SingleElement', true) === false) {
    $error = 'Class PHP_CodeSniffer_CommentParser_SingleElement not found';
    throw new PHP_CodeSniffer_Exception($error);
}

if (class_exists('PHP_CodeSniffer_CommentParser_CommentElement', true) === false) {
    $error = 'Class PHP_CodeSniffer_CommentParser_CommentElement not found';
    throw new PHP_CodeSniffer_Exception($error);
}

if (class_exists('PHP_CodeSniffer_CommentParser_ParserException', true) === false) {
    $error = 'Class PHP_CodeSniffer_CommentParser_ParserException not found';
    throw new PHP_CodeSniffer_Exception($error);
}

/**
 * Parses doc comments.
 *
 * This abstract parser handles the following tags:
 *
 * <ul>
 *  <li>The short description and the long description</li>
 *  <li>@see</li>
 *  <li>@link</li>
 *  <li>@deprecated</li>
 *  <li>@since</li>
 * </ul>
 *
 * Extending classes should implement the getAllowedTags() method to return the
 * tags that they wish to process, omitting the tags that this base class
 * processes. When one of these tags in encountered, the process&lt;tag_name&gt;
 * method is called on that class. For example, if a parser's getAllowedTags()
 * method returns \@param as one of its tags, the processParam method will be
 * called so that the parser can process such a tag.
 *
 * The method is passed the tokens that comprise this tag. The tokens array
 * includes the whitespace that exists between the tokens, as separate tokens.
 * It's up to the method to create a element that implements the DocElement
 * interface, which should be returned. The AbstractDocElement class is a helper
 * class that can be used to handle most of the parsing of the tokens into their
 * individual sub elements. It requires that you construct it with the element
 * previous to the element currently being processed, which can be acquired
 * with the protected $previousElement class member of this class.
 *
 * @category  PHP
 * @package   PHP_CodeSniffer
 * @author    Greg Sherwood <gsherwood@squiz.net>
 * @author    Marc McIntyre <mmcintyre@squiz.net>
 * @copyright 2006-2014 Squiz Pty Ltd (ABN 77 084 670 600)
 * @license   https://github.com/squizlabs/PHP_CodeSniffer/blob/master/licence.txt BSD Licence
 * @version   Release: @package_version@
 * @link      http://pear.php.net/package/PHP_CodeSniffer
 */
abstract class PHP_CodeSniffer_CommentParser_AbstractParser
{

    /**
     * The comment element that appears in the doc comment.
     *
     * @var PHP_CodeSniffer_CommentParser_CommentElement
     */
    protected $comment = null;

    /**
     * The string content of the comment.
     *
     * @var string
     */
    protected $commentString = '';

    /**
     * The file that the comment exists in.
     *
     * @var PHP_CodeSniffer_File
     */
    protected $phpcsFile = null;

    /**
     * The word tokens that appear in the comment.
     *
     * Whitespace tokens also appear in this stack, but are separate tokens
     * from words.
     *
     * @var array(string)
     */
    protected $words = array();

    /**
     * An array of all tags found in the comment.
     *
     * @var array(string)
     */
    protected $foundTags = array();

    /**
     * The previous doc element that was processed.
     *
     * null if the current element being processed is the first element in the
     * doc comment.
     *
     * @var PHP_CodeSniffer_CommentParser_DocElement
     */
    protected $previousElement = null;

    /**
     * A list of see elements that appear in this doc comment.
     *
     * @var array(PHP_CodeSniffer_CommentParser_SingleElement)
     */
    protected $sees = array();

    /**
     * A list of see elements that appear in this doc comment.
     *
     * @var array(PHP_CodeSniffer_CommentParser_SingleElement)
     */
    protected $deprecated = null;

    /**
     * A list of see elements that appear in this doc comment.
     *
     * @var array(PHP_CodeSniffer_CommentParser_SingleElement)
     */
    protected $links = array();

    /**
     * A element to represent \@since tags.
     *
     * @var PHP_CodeSniffer_CommentParser_SingleElement
     */
    protected $since = null;

    /**
     * True if the comment has been parsed.
     *
     * @var boolean
     */
    private $_hasParsed = false;

    /**
     * The tags that this class can process.
     *
     * @var array(string)
     */
    private static $_tags = array(
                             'see'        => false,
                             'link'       => false,
                             'deprecated' => true,
                             'since'      => true,
                            );

    /**
     * An array of unknown tags.
     *
     * @var array(string)
     */
    public $unknown = array();

    /**
     * The order of tags.
     *
     * @var array(string)
     */
    public $orders = array();


    /**
     * Constructs a Doc Comment Parser.
     *
     * @param string               $comment   The comment to parse.
     * @param PHP_CodeSniffer_File $phpcsFile The file that this comment is in.
     */
    public function __construct($comment, PHP_CodeSniffer_File $phpcsFile)
    {
        $this->commentString = $comment;
        $this->phpcsFile     = $phpcsFile;

    }//end __construct()


    /**
     * Initiates the parsing of the doc comment.
     *
     * @return void
     * @throws PHP_CodeSniffer_CommentParser_ParserException If the parser finds a
     *                                                       problem with the
     *                                                       comment.
     */
    public function parse()
    {
        if ($this->_hasParsed === false) {
            $this->_parse($this->commentString);
        }

    }//end parse()


    /**
     * Parse the comment.
     *
     * @param string $comment The doc comment to parse.
     *
     * @return void
     * @see _parseWords()
     */
    private function _parse($comment)
    {
        // Firstly, remove the comment tags and any stars from the left side.
        $lines = explode($this->phpcsFile->eolChar, $comment);
        foreach ($lines as &$line) {
            $line = trim($line);

            if ($line !== '') {
                if (substr($line, 0, 3) === '/**') {
                    $line = substr($line, 3);
                } else if (substr($line, -2, 2) === '*/') {
                    $line = substr($line, 0, -2);
                } else if ($line{0} === '*') {
                    $line = substr($line, 1);
                }

                // Add the words to the stack, preserving newlines. Other parsers
                // might be interested in the spaces between words, so tokenize
                // spaces as well as separate tokens.
                $flags = (PREG_SPLIT_DELIM_CAPTURE | PREG_SPLIT_NO_EMPTY);
                $words = preg_split(
                    '|(\s+)|u',
                    $line.$this->phpcsFile->eolChar,
                    -1,
                    $flags
                );

                $this->words = array_merge($this->words, $words);
            }//end if
        }//end foreach

        $this->_parseWords();

    }//end _parse()


    /**
     * Parses each word within the doc comment.
     *
     * @return void
     * @see _parse()
     * @throws PHP_CodeSniffer_CommentParser_ParserException If more than the allowed
     *                                                       number of occurences of
     *                                                       a tag is found.
     */
    private function _parseWords()
    {
        $allowedTags     = (self::$_tags + $this->getAllowedTags());
        $allowedTagNames = array_keys($allowedTags);
        $prevTagPos      = false;
        $wordWasEmpty    = true;

        foreach ($this->words as $wordPos => $word) {
            if (trim($word) !== '') {
                $wordWasEmpty = false;
            }

            if ($word{0} === '@') {
                $tag = substr($word, 1);

                // Filter out @ tags in the comment description.
                // A real comment tag should have whitespace and a newline before it.
                if (isset($this->words[($wordPos - 1)]) === false
                    || trim($this->words[($wordPos - 1)]) !== ''
                ) {
                    continue;
                }

                if (isset($this->words[($wordPos - 2)]) === false
                    || $this->words[($wordPos - 2)] !== $this->phpcsFile->eolChar
                ) {
                    continue;
                }

                $this->foundTags[] = array(
                                      'tag'  => $tag,
                                      'line' => $this->getLine($wordPos),
                                      'pos'  => $wordPos,
                                     );

                if ($prevTagPos !== false) {
                    // There was a tag before this so let's process it.
                    $prevTag = substr($this->words[$prevTagPos], 1);
                    $this->parseTag($prevTag, $prevTagPos, ($wordPos - 1));
                } else {
                    // There must have been a comment before this tag, so
                    // let's process that.
                    $this->parseTag('comment', 0, ($wordPos - 1));
                }

                $prevTagPos = $wordPos;

                if (in_array($tag, $allowedTagNames) === false) {
                    // This is not a tag that we process, but let's check to
                    // see if it is a tag we know about. If we don't know about it,
                    // we add it to a list of unknown tags.
                    $knownTags = array(
                                  'abstract',
                                  'access',
                                  'example',
                                  'filesource',
                                  'global',
                                  'ignore',
                                  'internal',
                                  'name',
                                  'static',
                                  'staticvar',
                                  'todo',
                                  'tutorial',
                                  'uses',
                                  'package_version@',
                                 );

                    if (in_array($tag, $knownTags) === false) {
                        $this->unknown[] = array(
                                            'tag'  => $tag,
                                            'line' => $this->getLine($wordPos),
                                            'pos'  => $wordPos,
                                           );
                    }
                }//end if
            }//end if
        }//end foreach

        // Only process this tag if there was something to process.
        if ($wordWasEmpty === false) {
            if ($prevTagPos === false) {
                // There must only be a comment in this doc comment.
                $this->parseTag('comment', 0, count($this->words));
            } else {
                // Process the last tag element.
                $prevTag  = substr($this->words[$prevTagPos], 1);
                $numWords = count($this->words);
                $endPos   = $numWords;

                if ($prevTag === 'package' || $prevTag === 'subpackage') {
                    // These are single-word tags, so anything after a newline
                    // is really a comment.
                    for ($endPos = $prevTagPos; $endPos < $numWords; $endPos++) {
                        if (strpos($this->words[$endPos], $this->phpcsFile->eolChar) !== false) {
                            break;
                        }
                    }
                }

                $this->parseTag($prevTag, $prevTagPos, $endPos);

                if ($endPos !== $numWords) {
                    // Process the final comment, if it is not empty.
                    $tokens  = array_slice($this->words, ($endPos + 1), $numWords);
                    $content = implode('', $tokens);
                    if (trim($content) !== '') {
                        $this->parseTag('comment', ($endPos + 1), $numWords);
                    }
                }
            }//end if
        }//end if

    }//end _parseWords()


    /**
     * Returns the line that the token exists on in the doc comment.
     *
     * @param int $tokenPos The position in the words stack to find the line
     *                      number for.
     *
     * @return int
     */
    protected function getLine($tokenPos)
    {
        $newlines = 0;
        for ($i = 0; $i < $tokenPos; $i++) {
            $newlines += substr_count($this->phpcsFile->eolChar, $this->words[$i]);
        }

        return $newlines;

    }//end getLine()


    /**
     * Parses see tag element within the doc comment.
     *
     * @param array(string) $tokens The word tokens that comprise this element.
     *
     * @return DocElement The element that represents this see comment.
     */
    protected function parseSee($tokens)
    {
        $see = new PHP_CodeSniffer_CommentParser_SingleElement(
            $this->previousElement,
            $tokens,
            'see',
            $this->phpcsFile
        );

        $this->sees[] = $see;
        return $see;

    }//end parseSee()


    /**
     * Parses the comment element that appears at the top of the doc comment.
     *
     * @param array(string) $tokens The word tokens that comprise this element.
     *
     * @return DocElement The element that represents this comment element.
     */
    protected function parseComment($tokens)
    {
        $this->comment = new PHP_CodeSniffer_CommentParser_CommentElement(
            $this->previousElement,
            $tokens,
            $this->phpcsFile
        );

        return $this->comment;

    }//end parseComment()


    /**
     * Parses \@deprecated tags.
     *
     * @param array(string) $tokens The word tokens that comprise this element.
     *
     * @return DocElement The element that represents this deprecated tag.
     */
    protected function parseDeprecated($tokens)
    {
        $this->deprecated = new PHP_CodeSniffer_CommentParser_SingleElement(
            $this->previousElement,
            $tokens,
            'deprecated',
            $this->phpcsFile
        );

        return $this->deprecated;

    }//end parseDeprecated()


    /**
     * Parses \@since tags.
     *
     * @param array(string) $tokens The word tokens that comprise this element.
     *
     * @return SingleElement The element that represents this since tag.
     */
    protected function parseSince($tokens)
    {
        $this->since = new PHP_CodeSniffer_CommentParser_SingleElement(
            $this->previousElement,
            $tokens,
            'since',
            $this->phpcsFile
        );

        return $this->since;

    }//end parseSince()


    /**
     * Parses \@link tags.
     *
     * @param array(string) $tokens The word tokens that comprise this element.
     *
     * @return SingleElement The element that represents this link tag.
     */
    protected function parseLink($tokens)
    {
        $link = new PHP_CodeSniffer_CommentParser_SingleElement(
            $this->previousElement,
            $tokens,
            'link',
            $this->phpcsFile
        );

        $this->links[] = $link;
        return $link;

    }//end parseLink()


    /**
     * Returns the see elements that appear in this doc comment.
     *
     * @return array(SingleElement)
     */
    public function getSees()
    {
        return $this->sees;

    }//end getSees()


    /**
     * Returns the comment element that appears at the top of this doc comment.
     *
     * @return CommentElement
     */
    public function getComment()
    {
        return $this->comment;

    }//end getComment()


    /**
     * Returns the word list.
     *
     * @return array
     */
    public function getWords()
    {
        return $this->words;

    }//end getWords()


    /**
     * Returns the list of found tags.
     *
     * @return array
     */
    public function getTags()
    {
        return $this->foundTags;

    }//end getTags()


    /**
     * Returns the link elements found in this comment.
     *
     * Returns an empty array if no links are found in the comment.
     *
     * @return array(SingleElement)
     */
    public function getLinks()
    {
        return $this->links;

    }//end getLinks()


    /**
     * Returns the deprecated element found in this comment.
     *
     * Returns null if no element exists in the comment.
     *
     * @return SingleElement
     */
    public function getDeprecated()
    {
        return $this->deprecated;

    }//end getDeprecated()


    /**
     * Returns the since element found in this comment.
     *
     * Returns null if no element exists in the comment.
     *
     * @return SingleElement
     */
    public function getSince()
    {
        return $this->since;

    }//end getSince()


    /**
     * Parses the specified tag.
     *
     * @param string $tag   The tag name to parse (omitting the @ symbol from
     *                      the tag)
     * @param int    $start The position in the word tokens where this element
     *                      started.
     * @param int    $end   The position in the word tokens where this element
     *                      ended.
     *
     * @return void
     * @throws Exception If the process method for the tag cannot be found.
     */
    protected function parseTag($tag, $start, $end)
    {
        $tokens = array_slice($this->words, ($start + 1), ($end - $start));

        $allowedTags     = (self::$_tags + $this->getAllowedTags());
        $allowedTagNames = array_keys($allowedTags);
        if ($tag === 'comment' || in_array($tag, $allowedTagNames) === true) {
            $method = 'parse'.$tag;
            if (method_exists($this, $method) === false) {
                $error = 'Method '.$method.' must be implemented to process '.$tag.' tags';
                throw new Exception($error);
            }

            $this->previousElement = $this->$method($tokens);
        } else {
            $this->previousElement = new PHP_CodeSniffer_CommentParser_SingleElement(
                $this->previousElement,
                $tokens,
                $tag,
                $this->phpcsFile
            );
        }

        $this->orders[] = $tag;

        if ($this->previousElement === null
            || ($this->previousElement instanceof PHP_CodeSniffer_CommentParser_DocElement) === false
        ) {
            throw new Exception('Parse method must return a DocElement');
        }

    }//end parseTag()


    /**
     * Returns a list of tags that this comment parser allows for it's comment.
     *
     * Each tag should indicate if only one entry of this tag can exist in the
     * comment by specifying true as the array value, or false if more than one
     * is allowed. Each tag should omit the @ symbol. Only tags other than
     * the standard tags should be returned.
     *
     * @return array(string => boolean)
     */
    protected abstract function getAllowedTags();


    /**
     * Returns the tag orders (index => tagName).
     *
     * @return array
     */
    public function getTagOrders()
    {
        return $this->orders;

    }//end getTagOrders()


    /**
     * Returns the unknown tags.
     *
     * @return array
     */
    public function getUnknown()
    {
        return $this->unknown;

    }//end getUnknown()


}//end class

?>