[Summary view] [Print] [Text view]

   1  <?php
   2  /**
   3   * PHP_LexerGenerator, a php 5 lexer generator.
   4   * 
   5   * This lexer generator translates a file in a format similar to
   6   * re2c ({@link http://re2c.org}) and translates it into a PHP 5-based lexer
   7   *
   8   * PHP version 5
   9   *
  10   * LICENSE:
  11   * 
  12   * Copyright (c) 2006, Gregory Beaver <[email protected]>
  13   * All rights reserved.
  14   *
  15   * Redistribution and use in source and binary forms, with or without
  16   * modification, are permitted provided that the following conditions
  17   * are met:
  18   *
  19   *     * Redistributions of source code must retain the above copyright
  20   *       notice, this list of conditions and the following disclaimer.
  21   *     * Redistributions in binary form must reproduce the above copyright
  22   *       notice, this list of conditions and the following disclaimer in
  23   *       the documentation and/or other materials provided with the distribution.
  24   *     * Neither the name of the PHP_LexerGenerator nor the names of its
  25   *       contributors may be used to endorse or promote products derived
  26   *       from this software without specific prior written permission.
  27   *
  28   * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS
  29   * IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,
  30   * THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
  31   * PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
  32   * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
  33   * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
  34   * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
  35   * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
  36   * OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
  37   * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
  38   * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  39   *
  40   * @category   php
  41   * @package    PHP_LexerGenerator
  42   * @author     Gregory Beaver <[email protected]>
  43   * @copyright  2006 Gregory Beaver
  44   * @license    http://www.opensource.org/licenses/bsd-license.php New BSD License
  45   * @version    CVS: $Id$
  46   * @since      File available since Release 0.1.0
  47   */
  48  /**
  49   * The Lexer generation parser
  50   */
  51  require_once 'PHP/LexerGenerator/Parser.php';
  52  /**
  53   * Hand-written lexer for lex2php format files
  54   */
  55  require_once 'PHP/LexerGenerator/Lexer.php';
  56  /**
  57   * The basic home class for the lexer generator.  A lexer scans text and
  58   * organizes it into tokens for usage by a parser.
  59   * 
  60   * Sample Usage:
  61   * <code>
  62   * require_once 'PHP/LexerGenerator.php';
  63   * $lex = new PHP_LexerGenerator('/path/to/lexerfile.plex');
  64   * </code>
  65   * 
  66   * A file named "/path/to/lexerfile.php" will be created.
  67   * 
  68   * File format consists of a PHP file containing specially
  69   * formatted comments like so:
  70   * 
  71   * <code>
  72   * /*!lex2php
  73   * {@*}
  74   * </code>
  75   * 
  76   * The first lex2php comment must contain several declarations and define
  77   * all regular expressions.  Declarations (processor instructions) start with
  78   * a "%" symbol and must be:
  79   * 
  80   *  - %counter
  81   *  - %input
  82   *  - %token
  83   *  - %value
  84   *  - %line
  85   * 
  86   * token and counter should define the class variables used to define lexer input
  87   * and the index into the input.  token and value should be used to define the class
  88   * variables used to store the token number and its textual value.  Finally, line
  89   * should be used to define the class variable used to define the current line number
  90   * of scanning.
  91   * 
  92   * For example:
  93   * <code>
  94   * /*!lex2php
  95   * %counter {$this->N}
  96   * %input {$this->data}
  97   * %token {$this->token}
  98   * %value {$this->value}
  99   * %line {%this->linenumber}
 100   * {@*}
 101   * </code>
 102   * 
 103   * Patterns consist of an identifier containing upper or lower-cased letters, and
 104   * a descriptive match pattern.
 105   * 
 106   * Descriptive match patterns may either be regular expressions (regexes) or
 107   * quoted literal strings.  Here are some examples:
 108   * 
 109   * <pre>
 110   * pattern = "quoted literal"
 111   * ANOTHER = /[a-zA-Z_]+/
 112   * </pre>
 113   * 
 114   * Quoted strings must escape the \ and " characters with \" and \\.
 115   * 
 116   * Regex patterns must be in Perl-compatible regular expression format (preg).
 117   * special characters (like \t \n or \x3H) can only be used in regexes, all
 118   * \ will be escaped in literal strings.
 119   * 
 120   * Any sub-patterns must be defined using (?:) instead of ():
 121   *
 122   * <code>
 123   * /*!lex2php
 124   * %counter {$this->N}
 125   * %input {$this->data}
 126   * %token {$this->token}
 127   * %value {$this->value}
 128   * %line {%this->linenumber}
 129   * alpha = /[a-zA-Z]/
 130   * alphaplus = /[a-zA-Z]+/
 131   * number = /[0-9]/
 132   * numerals = /[0-9]+/
 133   * whitespace = /[ \t\n]+/
 134   * blah = "$\""
 135   * blahblah = /a\$/
 136   * GAMEEND = @(?:1\-0|0\-1|1/2\-1/2)@
 137   * PAWNMOVE = /P?[a-h](?:[2-7]|[18]\=(?:Q|R|B|N))|P?[a-h]x[a-h](?:[2-7]|[18]\=(?:Q|R|B|N))/
 138   * {@*}
 139   * </code>
 140   * 
 141   * All regexes must be delimited.  Any legal preg delimiter can be used (as in @ or / in
 142   * the example above)
 143   * 
 144   * 
 145   * @package    PHP_LexerGenerator
 146   * @author     Gregory Beaver <[email protected]>
 147   * @copyright  2006 Gregory Beaver
 148   * @license    http://www.php.net/license/3_01.txt  PHP License 3.01
 149   * @version    0.2.0
 150   * @since      Class available since Release 0.1.0
 151   * @example    TestLexer.plex Example lexer source
 152   * @example    TestLexer.php  Example lexer php code
 153   * @example    usage.php      Example usage of PHP_LexerGenerator
 154   * @example    Lexer.plex     File_ChessPGN lexer source (complex)
 155   * @example    Lexer.php      File_ChessPGN lexer php code
 156   */
 157  
 158  class PHP_LexerGenerator
 159  {
 160      private $lex;
 161      private $parser;
 162      private $outfile;
 163      /**
 164       * Create a lexer file from its skeleton plex file.
 165       *
 166       * @param string $lexerfile path to the plex file
 167       */
 168      function __construct($lexerfile)
 169      {
 170          $this->lex = new PHP_LexerGenerator_Lexer(file_get_contents($lexerfile));
 171          $info = pathinfo($lexerfile);
 172          $this->outfile = $info['dirname'] . DIRECTORY_SEPARATOR .
 173              substr($info['basename'], 0,
 174              strlen($info['basename']) - strlen($info['extension'])) . 'php';
 175          $this->parser = new PHP_LexerGenerator_Parser($this->outfile, $this->lex);
 176          $this->parser->PrintTrace();
 177          while ($this->lex->advance($this->parser)) {
 178              $this->parser->doParse($this->lex->token, $this->lex->value);
 179          }
 180          $this->parser->doParse(0, 0);
 181      }
 182  }
 183  //$a = new PHP_LexerGenerator('/development/File_ChessPGN/ChessPGN/Lexer.plex');
 184  ?>