lexer.java

java1.6众多例子参考

/*
 * Copyright 1999-2004 The Apache Software Foundation.
 *
 * Licensed under the Apache License, Version 2.0 (the "License");
 * you may not use this file except in compliance with the License.
 * You may obtain a copy of the License at
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */
/*
 * $Id: Lexer.java,v 1.2.4.1 2005/09/10 03:55:45 jeffsuttor Exp $
 */
package com.sun.org.apache.xpath.internal.compiler;

import java.util.Vector;

import com.sun.org.apache.xml.internal.utils.PrefixResolver;
import com.sun.org.apache.xpath.internal.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)
        {
          if (posOfNSSep == (i - 1))
          {
            if (startSubstring != -1)
            {
              if (startSubstring < (i - 1))
                addToTokenQueue(pat.substring(startSubstring, i - 1));
            }

            isNum = false;
            isAttrName = false;
            startSubstring = -1;
            posOfNSSep = -1;

            addToTokenQueue(pat.substring(i - 1, i + 1));

            break;
          }
          else
          {
            posOfNSSep = i;
          }