CSS.php 21.4 KB
Newer Older
Ketan's avatar
Ketan committed
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
<?php
/**
 * Tokenizes CSS code.
 *
 * @author    Greg Sherwood <gsherwood@squiz.net>
 * @copyright 2006-2015 Squiz Pty Ltd (ABN 77 084 670 600)
 * @license   https://github.com/squizlabs/PHP_CodeSniffer/blob/master/licence.txt BSD Licence
 */

namespace PHP_CodeSniffer\Tokenizers;

use PHP_CodeSniffer\Util;
use PHP_CodeSniffer\Config;
use PHP_CodeSniffer\Exceptions\TokenizerException;

class CSS extends PHP
{


    /**
     * Initialise the tokenizer.
     *
     * Pre-checks the content to see if it looks minified.
     *
     * @param string                  $content The content to tokenize,
     * @param \PHP_CodeSniffer\Config $config  The config data for the run.
     * @param string                  $eolChar The EOL char used in the content.
     *
     * @return void
     * @throws TokenizerException If the file appears to be minified.
     */
    public function __construct($content, Config $config, $eolChar='\n')
    {
        if ($this->isMinifiedContent($content, $eolChar) === true) {
            throw new TokenizerException('File appears to be minified and cannot be processed');
        }

        return parent::__construct($content, $config, $eolChar);

    }//end __construct()


    /**
     * Creates an array of tokens when given some CSS code.
     *
     * Uses the PHP tokenizer to do all the tricky work
     *
     * @param string $string The string to tokenize.
     *
     * @return array
     */
    public function tokenize($string)
    {
        if (PHP_CODESNIFFER_VERBOSITY > 1) {
            echo "\t*** START CSS TOKENIZING 1ST PASS ***".PHP_EOL;
        }

        // If the content doesn't have an EOL char on the end, add one so
        // the open and close tags we add are parsed correctly.
        $eolAdded = false;
        if (substr($string, (strlen($this->eolChar) * -1)) !== $this->eolChar) {
            $string  .= $this->eolChar;
            $eolAdded = true;
        }

        $string = str_replace('<?php', '^PHPCS_CSS_T_OPEN_TAG^', $string);
        $string = str_replace('?>', '^PHPCS_CSS_T_CLOSE_TAG^', $string);
        $tokens = parent::tokenize('<?php '.$string.'?>');

        $finalTokens    = [];
        $finalTokens[0] = [
            'code'    => T_OPEN_TAG,
            'type'    => 'T_OPEN_TAG',
            'content' => '',
        ];

        $newStackPtr      = 1;
        $numTokens        = count($tokens);
        $multiLineComment = false;
        for ($stackPtr = 1; $stackPtr < $numTokens; $stackPtr++) {
            $token = $tokens[$stackPtr];

            // CSS files don't have lists, breaks etc, so convert these to
            // standard strings early so they can be converted into T_STYLE
            // tokens and joined with other strings if needed.
            if ($token['code'] === T_BREAK
                || $token['code'] === T_LIST
                || $token['code'] === T_DEFAULT
                || $token['code'] === T_SWITCH
                || $token['code'] === T_FOR
                || $token['code'] === T_FOREACH
                || $token['code'] === T_WHILE
                || $token['code'] === T_DEC
            ) {
                $token['type'] = 'T_STRING';
                $token['code'] = T_STRING;
            }

            if (PHP_CODESNIFFER_VERBOSITY > 1) {
                $type    = $token['type'];
                $content = Util\Common::prepareForOutput($token['content']);
                echo "\tProcess token $stackPtr: $type => $content".PHP_EOL;
            }

            if ($token['code'] === T_BITWISE_XOR
                && $tokens[($stackPtr + 1)]['content'] === 'PHPCS_CSS_T_OPEN_TAG'
            ) {
                $content = '<?php';
                for ($stackPtr = ($stackPtr + 3); $stackPtr < $numTokens; $stackPtr++) {
                    if ($tokens[$stackPtr]['code'] === T_BITWISE_XOR
                        && $tokens[($stackPtr + 1)]['content'] === 'PHPCS_CSS_T_CLOSE_TAG'
                    ) {
                        // Add the end tag and ignore the * we put at the end.
                        $content  .= '?>';
                        $stackPtr += 2;
                        break;
                    } else {
                        $content .= $tokens[$stackPtr]['content'];
                    }
                }

                if (PHP_CODESNIFFER_VERBOSITY > 1) {
                    echo "\t\t=> Found embedded PHP code: ";
                    $cleanContent = Util\Common::prepareForOutput($content);
                    echo $cleanContent.PHP_EOL;
                }

                $finalTokens[$newStackPtr] = [
                    'type'    => 'T_EMBEDDED_PHP',
                    'code'    => T_EMBEDDED_PHP,
                    'content' => $content,
                ];

                $newStackPtr++;
                continue;
            }//end if

            if ($token['code'] === T_GOTO_LABEL) {
                // Convert these back to T_STRING followed by T_COLON so we can
                // more easily process style definitions.
                $finalTokens[$newStackPtr] = [
                    'type'    => 'T_STRING',
                    'code'    => T_STRING,
                    'content' => substr($token['content'], 0, -1),
                ];
                $newStackPtr++;
                $finalTokens[$newStackPtr] = [
                    'type'    => 'T_COLON',
                    'code'    => T_COLON,
                    'content' => ':',
                ];
                $newStackPtr++;
                continue;
            }

            if ($token['code'] === T_FUNCTION) {
                // There are no functions in CSS, so convert this to a string.
                $finalTokens[$newStackPtr] = [
                    'type'    => 'T_STRING',
                    'code'    => T_STRING,
                    'content' => $token['content'],
                ];

                $newStackPtr++;
                continue;
            }

            if ($token['code'] === T_COMMENT
                && substr($token['content'], 0, 2) === '/*'
            ) {
                // Multi-line comment. Record it so we can ignore other
                // comment tags until we get out of this one.
                $multiLineComment = true;
            }

            if ($token['code'] === T_COMMENT
                && $multiLineComment === false
                && (substr($token['content'], 0, 2) === '//'
                || $token['content']{0} === '#')
            ) {
                $content = ltrim($token['content'], '#/');

                // Guard against PHP7+ syntax errors by stripping
                // leading zeros so the content doesn't look like an invalid int.
                $leadingZero = false;
                if ($content{0} === '0') {
                    $content     = '1'.$content;
                    $leadingZero = true;
                }

                $commentTokens = parent::tokenize('<?php '.$content.'?>');

                // The first and last tokens are the open/close tags.
                array_shift($commentTokens);
                array_pop($commentTokens);

                if ($leadingZero === true) {
                    $commentTokens[0]['content'] = substr($commentTokens[0]['content'], 1);
                    $content = substr($content, 1);
                }

                if ($token['content']{0} === '#') {
                    // The # character is not a comment in CSS files, so
                    // determine what it means in this context.
                    $firstContent = $commentTokens[0]['content'];

                    // If the first content is just a number, it is probably a
                    // colour like 8FB7DB, which PHP splits into 8 and FB7DB.
                    if (($commentTokens[0]['code'] === T_LNUMBER
                        || $commentTokens[0]['code'] === T_DNUMBER)
                        && $commentTokens[1]['code'] === T_STRING
                    ) {
                        $firstContent .= $commentTokens[1]['content'];
                        array_shift($commentTokens);
                    }

                    // If the first content looks like a colour and not a class
                    // definition, join the tokens together.
                    if (preg_match('/^[ABCDEF0-9]+$/i', $firstContent) === 1
                        && $commentTokens[1]['content'] !== '-'
                    ) {
                        array_shift($commentTokens);
                        // Work out what we trimmed off above and remember to re-add it.
                        $trimmed = substr($token['content'], 0, (strlen($token['content']) - strlen($content)));
                        $finalTokens[$newStackPtr] = [
                            'type'    => 'T_COLOUR',
                            'code'    => T_COLOUR,
                            'content' => $trimmed.$firstContent,
                        ];
                    } else {
                        $finalTokens[$newStackPtr] = [
                            'type'    => 'T_HASH',
                            'code'    => T_HASH,
                            'content' => '#',
                        ];
                    }
                } else {
                    $finalTokens[$newStackPtr] = [
                        'type'    => 'T_STRING',
                        'code'    => T_STRING,
                        'content' => '//',
                    ];
                }//end if

                $newStackPtr++;

                array_splice($tokens, $stackPtr, 1, $commentTokens);
                $numTokens = count($tokens);
                $stackPtr--;
                continue;
            }//end if

            if ($token['code'] === T_COMMENT
                && substr($token['content'], -2) === '*/'
            ) {
                // Multi-line comment is done.
                $multiLineComment = false;
            }

            $finalTokens[$newStackPtr] = $token;
            $newStackPtr++;
        }//end for

        if (PHP_CODESNIFFER_VERBOSITY > 1) {
            echo "\t*** END CSS TOKENIZING 1ST PASS ***".PHP_EOL;
            echo "\t*** START CSS TOKENIZING 2ND PASS ***".PHP_EOL;
        }

        // A flag to indicate if we are inside a style definition,
        // which is defined using curly braces.
        $inStyleDef = false;

        // A flag to indicate if an At-rule like "@media" is used, which will result
        // in nested curly brackets.
        $asperandStart = false;

        $numTokens = count($finalTokens);
        for ($stackPtr = 0; $stackPtr < $numTokens; $stackPtr++) {
            $token = $finalTokens[$stackPtr];

            if (PHP_CODESNIFFER_VERBOSITY > 1) {
                $type    = $token['type'];
                $content = Util\Common::prepareForOutput($token['content']);
                echo "\tProcess token $stackPtr: $type => $content".PHP_EOL;
            }

            switch ($token['code']) {
            case T_OPEN_CURLY_BRACKET:
                // Opening curly brackets for an At-rule do not start a style
                // definition. We also reset the asperand flag here because the next
                // opening curly bracket could be indeed the start of a style
                // definition.
                if ($asperandStart === true) {
                    if (PHP_CODESNIFFER_VERBOSITY > 1) {
                        if ($inStyleDef === true) {
                            echo "\t\t* style definition closed *".PHP_EOL;
                        }

                        if ($asperandStart === true) {
                            echo "\t\t* at-rule definition closed *".PHP_EOL;
                        }
                    }

                    $inStyleDef    = false;
                    $asperandStart = false;
                } else {
                    $inStyleDef = true;
                    if (PHP_CODESNIFFER_VERBOSITY > 1) {
                        echo "\t\t* style definition opened *".PHP_EOL;
                    }
                }
                break;
            case T_CLOSE_CURLY_BRACKET:
                if (PHP_CODESNIFFER_VERBOSITY > 1) {
                    if ($inStyleDef === true) {
                        echo "\t\t* style definition closed *".PHP_EOL;
                    }

                    if ($asperandStart === true) {
                        echo "\t\t* at-rule definition closed *".PHP_EOL;
                    }
                }

                $inStyleDef    = false;
                $asperandStart = false;
                break;
            case T_MINUS:
                // Minus signs are often used instead of spaces inside
                // class names, IDs and styles.
                if ($finalTokens[($stackPtr + 1)]['code'] === T_STRING) {
                    if ($finalTokens[($stackPtr - 1)]['code'] === T_STRING) {
                        $newContent = $finalTokens[($stackPtr - 1)]['content'].'-'.$finalTokens[($stackPtr + 1)]['content'];

                        if (PHP_CODESNIFFER_VERBOSITY > 1) {
                            echo "\t\t* token is a string joiner; ignoring this and previous token".PHP_EOL;
                            $old = Util\Common::prepareForOutput($finalTokens[($stackPtr + 1)]['content']);
                            $new = Util\Common::prepareForOutput($newContent);
                            echo "\t\t=> token ".($stackPtr + 1)." content changed from \"$old\" to \"$new\"".PHP_EOL;
                        }

                        $finalTokens[($stackPtr + 1)]['content'] = $newContent;
                        unset($finalTokens[$stackPtr]);
                        unset($finalTokens[($stackPtr - 1)]);
                    } else {
                        $newContent = '-'.$finalTokens[($stackPtr + 1)]['content'];

                        $finalTokens[($stackPtr + 1)]['content'] = $newContent;
                        unset($finalTokens[$stackPtr]);
                    }
                } else if ($finalTokens[($stackPtr + 1)]['code'] === T_LNUMBER) {
                    // They can also be used to provide negative numbers.
                    if (PHP_CODESNIFFER_VERBOSITY > 1) {
                        echo "\t\t* token is part of a negative number; adding content to next token and ignoring *".PHP_EOL;
                        $content = Util\Common::prepareForOutput($finalTokens[($stackPtr + 1)]['content']);
                        echo "\t\t=> token ".($stackPtr + 1)." content changed from \"$content\" to \"-$content\"".PHP_EOL;
                    }

                    $finalTokens[($stackPtr + 1)]['content'] = '-'.$finalTokens[($stackPtr + 1)]['content'];
                    unset($finalTokens[$stackPtr]);
                }//end if
                break;
            case T_COLON:
                // Only interested in colons that are defining styles.
                if ($inStyleDef === false) {
                    break;
                }

                for ($x = ($stackPtr - 1); $x >= 0; $x--) {
                    if (isset(Util\Tokens::$emptyTokens[$finalTokens[$x]['code']]) === false) {
                        break;
                    }
                }

                if (PHP_CODESNIFFER_VERBOSITY > 1) {
                    $type = $finalTokens[$x]['type'];
                    echo "\t\t=> token $x changed from $type to T_STYLE".PHP_EOL;
                }

                $finalTokens[$x]['type'] = 'T_STYLE';
                $finalTokens[$x]['code'] = T_STYLE;
                break;
            case T_STRING:
                if (strtolower($token['content']) === 'url') {
                    // Find the next content.
                    for ($x = ($stackPtr + 1); $x < $numTokens; $x++) {
                        if (isset(Util\Tokens::$emptyTokens[$finalTokens[$x]['code']]) === false) {
                            break;
                        }
                    }

                    // Needs to be in the format "url(" for it to be a URL.
                    if ($finalTokens[$x]['code'] !== T_OPEN_PARENTHESIS) {
                        continue 2;
                    }

                    // Make sure the content isn't empty.
                    for ($y = ($x + 1); $y < $numTokens; $y++) {
                        if (isset(Util\Tokens::$emptyTokens[$finalTokens[$y]['code']]) === false) {
                            break;
                        }
                    }

                    if ($finalTokens[$y]['code'] === T_CLOSE_PARENTHESIS) {
                        continue 2;
                    }

                    if (PHP_CODESNIFFER_VERBOSITY > 1) {
                        for ($i = ($stackPtr + 1); $i <= $y; $i++) {
                            $type    = $finalTokens[$i]['type'];
                            $content = Util\Common::prepareForOutput($finalTokens[$i]['content']);
                            echo "\tProcess token $i: $type => $content".PHP_EOL;
                        }

                        echo "\t\t* token starts a URL *".PHP_EOL;
                    }

                    // Join all the content together inside the url() statement.
                    $newContent = '';
                    for ($i = ($x + 2); $i < $numTokens; $i++) {
                        if ($finalTokens[$i]['code'] === T_CLOSE_PARENTHESIS) {
                            break;
                        }

                        $newContent .= $finalTokens[$i]['content'];
                        if (PHP_CODESNIFFER_VERBOSITY > 1) {
                            $content = Util\Common::prepareForOutput($finalTokens[$i]['content']);
                            echo "\t\t=> token $i added to URL string and ignored: $content".PHP_EOL;
                        }

                        unset($finalTokens[$i]);
                    }

                    $stackPtr = $i;

                    // If the content inside the "url()" is in double quotes
                    // there will only be one token and so we don't have to do
                    // anything except change its type. If it is not empty,
                    // we need to do some token merging.
                    $finalTokens[($x + 1)]['type'] = 'T_URL';
                    $finalTokens[($x + 1)]['code'] = T_URL;

                    if ($newContent !== '') {
                        $finalTokens[($x + 1)]['content'] .= $newContent;
                        if (PHP_CODESNIFFER_VERBOSITY > 1) {
                            $content = Util\Common::prepareForOutput($finalTokens[($x + 1)]['content']);
                            echo "\t\t=> token content changed to: $content".PHP_EOL;
                        }
                    }
                } else if ($finalTokens[$stackPtr]['content'][0] === '-'
                    && $finalTokens[($stackPtr + 1)]['code'] === T_STRING
                ) {
                    if (isset($finalTokens[($stackPtr - 1)]) === true
                        && $finalTokens[($stackPtr - 1)]['code'] === T_STRING
                    ) {
                        $newContent = $finalTokens[($stackPtr - 1)]['content'].$finalTokens[$stackPtr]['content'].$finalTokens[($stackPtr + 1)]['content'];

                        if (PHP_CODESNIFFER_VERBOSITY > 1) {
                            echo "\t\t* token is a string joiner; ignoring this and previous token".PHP_EOL;
                            $old = Util\Common::prepareForOutput($finalTokens[($stackPtr + 1)]['content']);
                            $new = Util\Common::prepareForOutput($newContent);
                            echo "\t\t=> token ".($stackPtr + 1)." content changed from \"$old\" to \"$new\"".PHP_EOL;
                        }

                        $finalTokens[($stackPtr + 1)]['content'] = $newContent;
                        unset($finalTokens[$stackPtr]);
                        unset($finalTokens[($stackPtr - 1)]);
                    } else {
                        $newContent = $finalTokens[$stackPtr]['content'].$finalTokens[($stackPtr + 1)]['content'];

                        $finalTokens[($stackPtr + 1)]['content'] = $newContent;
                        unset($finalTokens[$stackPtr]);
                    }
                }//end if
                break;
            case T_ASPERAND:
                $asperandStart = true;
                if (PHP_CODESNIFFER_VERBOSITY > 1) {
                    echo "\t\t* at-rule definition opened *".PHP_EOL;
                }
                break;
            default:
                // Nothing special to be done with this token.
                break;
            }//end switch
        }//end for

        // Reset the array keys to avoid gaps.
        $finalTokens = array_values($finalTokens);
        $numTokens   = count($finalTokens);

        // Blank out the content of the end tag.
        $finalTokens[($numTokens - 1)]['content'] = '';

        if ($eolAdded === true) {
            // Strip off the extra EOL char we added for tokenizing.
            $finalTokens[($numTokens - 2)]['content'] = substr(
                $finalTokens[($numTokens - 2)]['content'],
                0,
                (strlen($this->eolChar) * -1)
            );

            if ($finalTokens[($numTokens - 2)]['content'] === '') {
                unset($finalTokens[($numTokens - 2)]);
                $finalTokens = array_values($finalTokens);
                $numTokens   = count($finalTokens);
            }
        }

        if (PHP_CODESNIFFER_VERBOSITY > 1) {
            echo "\t*** END CSS TOKENIZING 2ND PASS ***".PHP_EOL;
        }

        return $finalTokens;

    }//end tokenize()


    /**
     * Performs additional processing after main tokenizing.
     *
     * @return void
     */
    public function processAdditional()
    {
        /*
            We override this method because we don't want the PHP version to
            run during CSS processing because it is wasted processing time.
        */

    }//end processAdditional()


}//end class