PHP PHP_CodeSniffer_File::tokenizeString方法代码示例

 /**
  * Processes this test, when one of its tokens is encountered.
  *
  * @param PHP_CodeSniffer_File $phpcsFile The file being scanned.
  * @param int                  $stackPtr  The position of the current token
  *                                        in the stack passed in $tokens.
  *
  * @return void
  */
 public function process(PHP_CodeSniffer_File $phpcsFile, $stackPtr)
 {
     $tokens = $phpcsFile->getTokens();
     // Process whole comment blocks at once, so skip all but the first token.
     if ($stackPtr > 0 && $tokens[$stackPtr]['code'] === $tokens[$stackPtr - 1]['code']) {
         return;
     }
     // Ignore comments at the end of code blocks.
     if (substr($tokens[$stackPtr]['content'], 0, 6) === '//end ') {
         return;
     }
     $content = '';
     if ($phpcsFile->tokenizerType === 'PHP') {
         $content = '<?php ';
     }
     for ($i = $stackPtr; $i < $phpcsFile->numTokens; $i++) {
         if ($tokens[$stackPtr]['code'] !== $tokens[$i]['code']) {
             break;
         }
         /*
             Trim as much off the comment as possible so we don't
             have additional whitespace tokens or comment tokens
         */
         $tokenContent = trim($tokens[$i]['content']);
         if (substr($tokenContent, 0, 2) === '//') {
             $tokenContent = substr($tokenContent, 2);
         }
         if (substr($tokenContent, 0, 1) === '#') {
             $tokenContent = substr($tokenContent, 1);
         }
         if (substr($tokenContent, 0, 3) === '/**') {
             $tokenContent = substr($tokenContent, 3);
         }
         if (substr($tokenContent, 0, 2) === '/*') {
             $tokenContent = substr($tokenContent, 2);
         }
         if (substr($tokenContent, -2) === '*/') {
             $tokenContent = substr($tokenContent, 0, -2);
         }
         if (substr($tokenContent, 0, 1) === '*') {
             $tokenContent = substr($tokenContent, 1);
         }
         $content .= $tokenContent . $phpcsFile->eolChar;
     }
     //end for
     $content = trim($content);
     if ($phpcsFile->tokenizerType === 'PHP') {
         $content .= ' ?>';
     }
     // Quite a few comments use multiple dashes, equals signs etc
     // to frame comments and licence headers.
     $content = preg_replace('/[-=*]+/', '-', $content);
     // Because we are not really parsing code, the tokenizer can throw all sorts
     // of errors that don't mean anything, so ignore them.
     $oldErrors = ini_get('error_reporting');
     ini_set('error_reporting', 0);
     try {
         $stringTokens = PHP_CodeSniffer_File::tokenizeString($content, $phpcsFile->tokenizer, $phpcsFile->eolChar);
     } catch (PHP_CodeSniffer_Exception $e) {
         // We couldn't check the comment, so ignore it.
         ini_set('error_reporting', $oldErrors);
         return;
     }
     ini_set('error_reporting', $oldErrors);
     $emptyTokens = array(T_WHITESPACE => true, T_STRING => true, T_STRING_CONCAT => true, T_ENCAPSED_AND_WHITESPACE => true, T_NONE => true, T_COMMENT => true);
     $numTokens = count($stringTokens);
     /*
         We know what the first two and last two tokens should be
         (because we put them there) so ignore this comment if those
         tokens were not parsed correctly. It obviously means this is not
         valid code.
     */
     // First token is always the opening PHP tag.
     if ($stringTokens[0]['code'] !== T_OPEN_TAG) {
         return;
     }
     // Last token is always the closing PHP tag, unless something went wrong.
     if (isset($stringTokens[$numTokens - 1]) === false || $stringTokens[$numTokens - 1]['code'] !== T_CLOSE_TAG) {
         return;
     }
     // Second last token is always whitespace or a comment, depending
     // on the code inside the comment.
     if ($phpcsFile->tokenizerType === 'PHP' && isset(PHP_CodeSniffer_Tokens::$emptyTokens[$stringTokens[$numTokens - 2]['code']]) === false) {
         return;
     }
     $numComment = 0;
     $numPossible = 0;
     $numCode = 0;
     for ($i = 0; $i < $numTokens; $i++) {
         if (isset($emptyTokens[$stringTokens[$i]['code']]) === true) {
             // Looks like comment.
//.........这里部分代码省略.........

 /**
  * Tokenize a string, PHP_CodeSniffer style
  * @param string $code the code to be tokenized
  * @return array an array of tokens, complete with all the extra information PHPCS provides
  */
 private function getTokens($code)
 {
     new PHP_CodeSniffer();
     $tokenizer = new PHP_CodeSniffer_Tokenizers_PHP();
     return PHP_CodeSniffer_File::tokenizeString($code, $tokenizer);
 }

 /**
  * Processes this test, when one of its tokens is encountered.
  *
  * @param PHP_CodeSniffer_File $phpcsFile The file being scanned.
  * @param int                  $stackPtr  The position of the current token
  *                                        in the stack passed in $tokens.
  *
  * @return void
  */
 public function process(PHP_CodeSniffer_File $phpcsFile, $stackPtr)
 {
     $tokens = $phpcsFile->getTokens();
     // Process whole comment blocks at once, so skip all but the first token.
     if ($stackPtr > 0 && $tokens[$stackPtr]['code'] === $tokens[$stackPtr - 1]['code']) {
         return;
     }
     // Ignore comments at the end of code blocks.
     if (substr($tokens[$stackPtr]['content'], 0, 6) === '//end ') {
         return;
     }
     $content = '';
     if ($phpcsFile->tokenizerType === 'PHP') {
         $content = '<?php ';
     }
     for ($i = $stackPtr; $i < $phpcsFile->numTokens; $i++) {
         if ($tokens[$stackPtr]['code'] !== $tokens[$i]['code']) {
             break;
         }
         /*
             Trim as much off the comment as possible so we don't
             have additional whitespace tokens or comment tokens
         */
         $tokenContent = trim($tokens[$i]['content']);
         if (substr($tokenContent, 0, 2) === '//') {
             $tokenContent = substr($tokenContent, 2);
         }
         if (substr($tokenContent, 0, 1) === '#') {
             $tokenContent = substr($tokenContent, 1);
         }
         if (substr($tokenContent, 0, 3) === '/**') {
             $tokenContent = substr($tokenContent, 3);
         }
         if (substr($tokenContent, 0, 2) === '/*') {
             $tokenContent = substr($tokenContent, 2);
         }
         if (substr($tokenContent, -2) === '*/') {
             $tokenContent = substr($tokenContent, 0, -2);
         }
         if (substr($tokenContent, 0, 1) === '*') {
             $tokenContent = substr($tokenContent, 1);
         }
         $content .= $tokenContent . $phpcsFile->eolChar;
     }
     //end for
     $content = trim($content);
     if ($phpcsFile->tokenizerType === 'PHP') {
         $content .= ' ?>';
     }
     // Quite a few comments use multiple dashes, equals signs etc
     // to frame comments and licence headers.
     $content = preg_replace('/[-=*]+/', '-', $content);
     $stringTokens = PHP_CodeSniffer_File::tokenizeString($content, $phpcsFile->tokenizer, $phpcsFile->eolChar);
     $emptyTokens = array(T_WHITESPACE, T_STRING, T_STRING_CONCAT, T_ENCAPSED_AND_WHITESPACE, T_NONE);
     $numTokens = count($stringTokens);
     /*
         We know what the first two and last two tokens should be
         (because we put them there) so ignore this comment if those
         tokens were not parsed correctly. It obvously means this is not
         valid code.
     */
     // First token is always the opening PHP tag.
     if ($stringTokens[0]['code'] !== T_OPEN_TAG) {
         return;
     }
     // Last token is always the closing PHP tag.
     if ($stringTokens[$numTokens - 1]['code'] !== T_CLOSE_TAG) {
         return;
     }
     // Second last token is always whitespace or a comment, depending
     // on the code inside the comment.
     if (in_array($stringTokens[$numTokens - 2]['code'], PHP_CodeSniffer_Tokens::$emptyTokens) === false) {
         return;
     }
     $numComment = 0;
     $numCode = 0;
     for ($i = 0; $i < $numTokens; $i++) {
         if (in_array($stringTokens[$i]['code'], $emptyTokens) === true) {
             // Looks like comment.
             $numComment++;
         } else {
             // Looks like code.
             $numCode++;
         }
     }
     // We subtract 3 from the token number so we ignore the start/end tokens
     // and their surrounding whitespace. We take 2 off the number of code
     // tokens so we ignore the start/end tokens.
     if ($numTokens > 3) {
         $numTokens -= 3;
     }
//.........这里部分代码省略.........

 /**
  * Tokenizes the given content.
  *
  * @param string $content
  * @return array Array of arrays.
  */
 protected function getCodeSnifferTokensByContent($content)
 {
     if ($this->tokenizer == null) {
         // this is instantiated here just for the required constants used in PHP_CodeSniffer_File:
         new \PHP_CodeSniffer();
         $this->tokenizer = new \PHP_CodeSniffer_Tokenizers_PHP();
     }
     return \PHP_CodeSniffer_File::tokenizeString($content, $this->tokenizer);
 }