lexer.java

来自「java jdk 1.4的源码」· Java 代码 · 共 694 行 · 第 1/2 页

/*
 * The Apache Software License, Version 1.1
 *
 *
 * Copyright (c) 1999 The Apache Software Foundation.  All rights 
 * reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 *
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer. 
 *
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in
 *    the documentation and/or other materials provided with the
 *    distribution.
 *
 * 3. The end-user documentation included with the redistribution,
 *    if any, must include the following acknowledgment:  
 *       "This product includes software developed by the
 *        Apache Software Foundation (http://www.apache.org/)."
 *    Alternately, this acknowledgment may appear in the software itself,
 *    if and wherever such third-party acknowledgments normally appear.
 *
 * 4. The names "Xalan" and "Apache Software Foundation" must
 *    not be used to endorse or promote products derived from this
 *    software without prior written permission. For written 
 *    permission, please contact [e-mail].
 *
 * 5. Products derived from this software may not be called "Apache",
 *    nor may "Apache" appear in their name, without prior written
 *    permission of the Apache Software Foundation.
 *
 * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESSED OR IMPLIED
 * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
 * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
 * DISCLAIMED.  IN NO EVENT SHALL THE APACHE SOFTWARE FOUNDATION OR
 * ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
 * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
 * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
 * USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
 * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
 * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
 * OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 * SUCH DAMAGE.
 * ====================================================================
 *
 * This software consists of voluntary contributions made by many
 * individuals on behalf of the Apache Software Foundation and was
 * originally based on software copyright (c) 1999, Lotus
 * Development Corporation., http://www.lotus.com.  For more
 * information on the Apache Software Foundation, please see
 * <http://www.apache.org/>.
 */
package org.apache.xpath.compiler;

import java.util.Vector;

import org.apache.xml.utils.PrefixResolver;
import org.apache.xpath.res.XPATHErrorResources;

/**
 * This class is in charge of lexical processing of the XPath
 * expression into tokens.
 */
class Lexer
{

  /**
   * The target XPath.
   */
  private Compiler m_compiler;

  /**
   * The prefix resolver to map prefixes to namespaces in the XPath.
   */
  PrefixResolver m_namespaceContext;

  /**
   * The XPath processor object.
   */
  XPathParser m_processor;

  /**
   * This value is added to each element name in the TARGETEXTRA
   * that is a 'target' (right-most top-level element name).
   */
  static final int TARGETEXTRA = 10000;

  /**
   * Ignore this, it is going away.
   * This holds a map to the m_tokenQueue that tells where the top-level elements are.
   * It is used for pattern matching so the m_tokenQueue can be walked backwards.
   * Each element that is a 'target', (right-most top level element name) has
   * TARGETEXTRA added to it.
   *
   */
  private int m_patternMap[] = new int[100];

  /**
   * Ignore this, it is going away.
   * The number of elements that m_patternMap maps;
   */
  private int m_patternMapSize;

  /**
   * Create a Lexer object.
   *
   * @param compiler The owning compiler for this lexer.
   * @param resolver The prefix resolver for mapping qualified name prefixes 
   *                 to namespace URIs.
   * @param xpathProcessor The parser that is processing strings to opcodes.
   */
  Lexer(Compiler compiler, PrefixResolver resolver,
        XPathParser xpathProcessor)
  {

    m_compiler = compiler;
    m_namespaceContext = resolver;
    m_processor = xpathProcessor;
  }

  /**
   * Walk through the expression and build a token queue, and a map of the top-level
   * elements.
   * @param pat XSLT Expression.
   *
   * @throws javax.xml.transform.TransformerException
   */
  void tokenize(String pat) throws javax.xml.transform.TransformerException
  {
    tokenize(pat, null);
  }

  /**
   * Walk through the expression and build a token queue, and a map of the top-level
   * elements.
   * @param pat XSLT Expression.
   * @param targetStrings Vector to hold Strings, may be null.
   *
   * @throws javax.xml.transform.TransformerException
   */
  void tokenize(String pat, Vector targetStrings)
          throws javax.xml.transform.TransformerException
  {

    m_compiler.m_currentPattern = pat;
    m_patternMapSize = 0; 

    // This needs to grow too.
    m_compiler.m_opMap = new OpMapVector(OpMap.MAXTOKENQUEUESIZE * 5, OpMap.BLOCKTOKENQUEUESIZE * 5, OpMap.MAPINDEX_LENGTH);

    int nChars = pat.length();
    int startSubstring = -1; 
    int posOfNSSep = -1;
    boolean isStartOfPat = true;
    boolean isAttrName = false;
    boolean isNum = false;

    // Nesting of '[' so we can know if the given element should be
    // counted inside the m_patternMap.
    int nesting = 0;

    // char[] chars = pat.toCharArray();
    for (int i = 0; i < nChars; i++)
    {
      char c = pat.charAt(i);

      switch (c)
      {
      case '\"' :
      {
        if (startSubstring != -1)
        {
          isNum = false;
          isStartOfPat = mapPatternElemPos(nesting, isStartOfPat, isAttrName);
          isAttrName = false;

          if (-1 != posOfNSSep)
          {
            posOfNSSep = mapNSTokens(pat, startSubstring, posOfNSSep, i);
          }
          else
          {
            addToTokenQueue(pat.substring(startSubstring, i));
          }
        }

        startSubstring = i;

        for (i++; (i < nChars) && ((c = pat.charAt(i)) != '\"'); i++);

        if (c == '\"' && i < nChars)
        {
          addToTokenQueue(pat.substring(startSubstring, i + 1));

          startSubstring = -1;
        }
        else
        {
          m_processor.error(XPATHErrorResources.ER_EXPECTED_DOUBLE_QUOTE,
                            null);  //"misquoted literal... expected double quote!");
        }
      }
      break;
      case '\'' :
        if (startSubstring != -1)
        {
          isNum = false;
          isStartOfPat = mapPatternElemPos(nesting, isStartOfPat, isAttrName);
          isAttrName = false;

          if (-1 != posOfNSSep)
          {
            posOfNSSep = mapNSTokens(pat, startSubstring, posOfNSSep, i);
          }
          else
          {
            addToTokenQueue(pat.substring(startSubstring, i));
          }
        }

        startSubstring = i;

        for (i++; (i < nChars) && ((c = pat.charAt(i)) != '\''); i++);

        if (c == '\'' && i < nChars)
        {
          addToTokenQueue(pat.substring(startSubstring, i + 1));

          startSubstring = -1;
        }
        else
        {
          m_processor.error(XPATHErrorResources.ER_EXPECTED_SINGLE_QUOTE,
                            null);  //"misquoted literal... expected single quote!");
        }
        break;
      case 0x0A :
      case 0x0D :
      case ' ' :
      case '\t' :
        if (startSubstring != -1)
        {
          isNum = false;
          isStartOfPat = mapPatternElemPos(nesting, isStartOfPat, isAttrName);
          isAttrName = false;

          if (-1 != posOfNSSep)
          {
            posOfNSSep = mapNSTokens(pat, startSubstring, posOfNSSep, i);
          }
          else
          {
            addToTokenQueue(pat.substring(startSubstring, i));
          }

          startSubstring = -1;
        }
        break;
      case '@' :
        isAttrName = true;

      // fall-through on purpose
      case '-' :
        if ('-' == c)
        {
          if (!(isNum || (startSubstring == -1)))
          {
            break;
          }

          isNum = false;
        }

      // fall-through on purpose
      case '(' :
      case '[' :
      case ')' :
      case ']' :
      case '|' :
      case '/' :
      case '*' :
      case '+' :
      case '=' :
      case ',' :
      case '\\' :  // Unused at the moment
      case '^' :  // Unused at the moment
      case '!' :  // Unused at the moment
      case '$' :
      case '<' :
      case '>' :
        if (startSubstring != -1)
        {
          isNum = false;
          isStartOfPat = mapPatternElemPos(nesting, isStartOfPat, isAttrName);
          isAttrName = false;

          if (-1 != posOfNSSep)
          {
            posOfNSSep = mapNSTokens(pat, startSubstring, posOfNSSep, i);
          }
          else
          {
            addToTokenQueue(pat.substring(startSubstring, i));
          }

          startSubstring = -1;
        }
        else if (('/' == c) && isStartOfPat)
        {
          isStartOfPat = mapPatternElemPos(nesting, isStartOfPat, isAttrName);
        }
        else if ('*' == c)
        {
          isStartOfPat = mapPatternElemPos(nesting, isStartOfPat, isAttrName);
          isAttrName = false;
        }

        if (0 == nesting)
        {
          if ('|' == c)
          {
            if (null != targetStrings)
            {
              recordTokenString(targetStrings);
            }

            isStartOfPat = true;
          }
        }

        if ((')' == c) || (']' == c))
        {
          nesting--;
        }
        else if (('(' == c) || ('[' == c))
        {
          nesting++;
        }

        addToTokenQueue(pat.substring(i, i + 1));
        break;
      case ':' :
        if (i>0)