re.java

Mac OS X 10.4.9 for x86 Source Code gcc 实现源代码

      //  \< if ????
      else if (unit.bk && (unit.ch == '<')) {
	  addToken(currentToken);
	  currentToken = new RETokenWordBoundary(subIndex, RETokenWordBoundary.BEGIN, false);
      } 

      // WORD END OPERATOR 
      //  \> if ????
      else if (unit.bk && (unit.ch == '>')) {
	  addToken(currentToken);
	  currentToken = new RETokenWordBoundary(subIndex, RETokenWordBoundary.END, false);
      } 

      // NON-WORD BREAK OPERATOR
      // \B if ????

      else if (unit.bk && (unit.ch == 'B') && syntax.get(RESyntax.RE_STRING_ANCHORS)) {
	  addToken(currentToken);
	  currentToken = new RETokenWordBoundary(subIndex, RETokenWordBoundary.BEGIN | RETokenWordBoundary.END, true);
      } 

      
      // DIGIT OPERATOR
      //  \d if RE_CHAR_CLASS_ESCAPES is set
      
      else if (unit.bk && (unit.ch == 'd') && syntax.get(RESyntax.RE_CHAR_CLASS_ESCAPES)) {
	addToken(currentToken);
	currentToken = new RETokenPOSIX(subIndex,RETokenPOSIX.DIGIT,insens,false);
      }

      // NON-DIGIT OPERATOR
      //  \D

	else if (unit.bk && (unit.ch == 'D') && syntax.get(RESyntax.RE_CHAR_CLASS_ESCAPES)) {
	  addToken(currentToken);
	  currentToken = new RETokenPOSIX(subIndex,RETokenPOSIX.DIGIT,insens,true);
	}

	// NEWLINE ESCAPE
        //  \n

	else if (unit.bk && (unit.ch == 'n')) {
	  addToken(currentToken);
	  currentToken = new RETokenChar(subIndex,'\n',false);
	}

	// RETURN ESCAPE
        //  \r

	else if (unit.bk && (unit.ch == 'r')) {
	  addToken(currentToken);
	  currentToken = new RETokenChar(subIndex,'\r',false);
	}

	// WHITESPACE OPERATOR
        //  \s if RE_CHAR_CLASS_ESCAPES is set

	else if (unit.bk && (unit.ch == 's') && syntax.get(RESyntax.RE_CHAR_CLASS_ESCAPES)) {
	  addToken(currentToken);
	  currentToken = new RETokenPOSIX(subIndex,RETokenPOSIX.SPACE,insens,false);
	}

	// NON-WHITESPACE OPERATOR
        //  \S

	else if (unit.bk && (unit.ch == 'S') && syntax.get(RESyntax.RE_CHAR_CLASS_ESCAPES)) {
	  addToken(currentToken);
	  currentToken = new RETokenPOSIX(subIndex,RETokenPOSIX.SPACE,insens,true);
	}

	// TAB ESCAPE
        //  \t

	else if (unit.bk && (unit.ch == 't')) {
	  addToken(currentToken);
	  currentToken = new RETokenChar(subIndex,'\t',false);
	}

	// ALPHANUMERIC OPERATOR
        //  \w

	else if (unit.bk && (unit.ch == 'w') && syntax.get(RESyntax.RE_CHAR_CLASS_ESCAPES)) {
	  addToken(currentToken);
	  currentToken = new RETokenPOSIX(subIndex,RETokenPOSIX.ALNUM,insens,false);
	}

	// NON-ALPHANUMERIC OPERATOR
        //  \W

	else if (unit.bk && (unit.ch == 'W') && syntax.get(RESyntax.RE_CHAR_CLASS_ESCAPES)) {
	  addToken(currentToken);
	  currentToken = new RETokenPOSIX(subIndex,RETokenPOSIX.ALNUM,insens,true);
	}

	// END OF STRING OPERATOR
        //  \Z

	else if (unit.bk && (unit.ch == 'Z') && syntax.get(RESyntax.RE_STRING_ANCHORS)) {
	  addToken(currentToken);
	  currentToken = new RETokenEnd(subIndex,null);
	}

	// NON-SPECIAL CHARACTER (or escape to make literal)
        //  c | \* for example

	else {  // not a special character
	  addToken(currentToken);
	  currentToken = new RETokenChar(subIndex,unit.ch,insens);
	} 
      } // end while

    // Add final buffered token and an EndSub marker
    addToken(currentToken);
      
    if (branches != null) {
	branches.addElement(new RE(firstToken,lastToken,numSubs,subIndex,minimumLength));
	branches.trimToSize(); // compact the Vector
	minimumLength = 0;
	firstToken = lastToken = null;
	addToken(new RETokenOneOf(subIndex,branches,false));
    } 
    else addToken(new RETokenEndSub(subIndex));

  }

  private static int getCharUnit(char[] input, int index, CharUnit unit, boolean quot) throws REException {
    unit.ch = input[index++];
    if (unit.bk = (unit.ch == '\\' && (!quot || index >= input.length || input[index] == 'E')))
      if (index < input.length)
	unit.ch = input[index++];
      else throw new REException(getLocalizedMessage("ends.with.backslash"),REException.REG_ESCAPE,index);
    return index;
  }

  /**
   * Checks if the regular expression matches the input in its entirety.
   *
   * @param input The input text.
   */
  public boolean isMatch(Object input) {
    return isMatch(input,0,0);
  }
  
  /**
   * Checks if the input string, starting from index, is an exact match of
   * this regular expression.
   *
   * @param input The input text.
   * @param index The offset index at which the search should be begin.
   */
  public boolean isMatch(Object input,int index) {
    return isMatch(input,index,0);
  }
  

  /**
   * Checks if the input, starting from index and using the specified
   * execution flags, is an exact match of this regular expression.
   *
   * @param input The input text.
   * @param index The offset index at which the search should be begin.
   * @param eflags The logical OR of any execution flags above.
   */
  public boolean isMatch(Object input,int index,int eflags) {
    return isMatchImpl(makeCharIndexed(input,index),index,eflags);
  }

  private boolean isMatchImpl(CharIndexed input, int index, int eflags) {
    if (firstToken == null)  // Trivial case
      return (input.charAt(0) == CharIndexed.OUT_OF_BOUNDS);
    REMatch m = new REMatch(numSubs, index, eflags);
    if (firstToken.match(input, m)) {
	while (m != null) {
	    if (input.charAt(m.index) == CharIndexed.OUT_OF_BOUNDS) {
		return true;
	    }
	    m = m.next;
	}
    }
    return false;
  }
    
  /**
   * Returns the maximum number of subexpressions in this regular expression.
   * If the expression contains branches, the value returned will be the
   * maximum subexpressions in any of the branches.
   */
  public int getNumSubs() {
    return numSubs;
  }

  // Overrides REToken.setUncle
  void setUncle(REToken uncle) {
      if (lastToken != null) {
	  lastToken.setUncle(uncle);
      } else super.setUncle(uncle); // to deal with empty subexpressions
  }

  // Overrides REToken.chain

  boolean chain(REToken next) {
    super.chain(next);
    setUncle(next);
    return true;
  }

  /**
   * Returns the minimum number of characters that could possibly
   * constitute a match of this regular expression.
   */
  public int getMinimumLength() {
      return minimumLength;
  }

  /**
   * Returns an array of all matches found in the input.
   *
   * If the regular expression allows the empty string to match, it will
   * substitute matches at all positions except the end of the input.
   *
   * @param input The input text.
   * @return a non-null (but possibly zero-length) array of matches
   */
  public REMatch[] getAllMatches(Object input) {
    return getAllMatches(input,0,0);
  }

  /**
   * Returns an array of all matches found in the input,
   * beginning at the specified index position.
   *
   * If the regular expression allows the empty string to match, it will
   * substitute matches at all positions except the end of the input.
   *
   * @param input The input text.
   * @param index The offset index at which the search should be begin.
   * @return a non-null (but possibly zero-length) array of matches
   */
  public REMatch[] getAllMatches(Object input, int index) {
    return getAllMatches(input,index,0);
  }

  /**
   * Returns an array of all matches found in the input string,
   * beginning at the specified index position and using the specified
   * execution flags.
   *
   * If the regular expression allows the empty string to match, it will
   * substitute matches at all positions except the end of the input.
   *
   * @param input The input text.
   * @param index The offset index at which the search should be begin.
   * @param eflags The logical OR of any execution flags above.
   * @return a non-null (but possibly zero-length) array of matches
   */
  public REMatch[] getAllMatches(Object input, int index, int eflags) {
    return getAllMatchesImpl(makeCharIndexed(input,index),index,eflags);
  }

  // this has been changed since 1.03 to be non-overlapping matches
  private REMatch[] getAllMatchesImpl(CharIndexed input, int index, int eflags) {
    Vector all = new Vector();
    REMatch m = null;
    while ((m = getMatchImpl(input,index,eflags,null)) != null) {
      all.addElement(m);
      index = m.getEndIndex();
      if (m.end[0] == 0) {   // handle pathological case of zero-length match
	index++;
	input.move(1);
      } else {
	input.move(m.end[0]);
      }
      if (!input.isValid()) break;
    }
    REMatch[] mset = new REMatch[all.size()];
    all.copyInto(mset);
    return mset;
  }
  
    /* Implements abstract method REToken.match() */
    boolean match(CharIndexed input, REMatch mymatch) { 
	if (firstToken == null) return next(input, mymatch);

	// Note the start of this subexpression
	mymatch.start[subIndex] = mymatch.index;

	return firstToken.match(input, mymatch);
    }
  
  /**
   * Returns the first match found in the input.  If no match is found,
   * null is returned.
   *
   * @param input The input text.
   * @return An REMatch instance referencing the match, or null if none.
   */
  public REMatch getMatch(Object input) {
    return getMatch(input,0,0);
  }
  
  /**
   * Returns the first match found in the input, beginning
   * the search at the specified index.  If no match is found,
   * returns null.
   *
   * @param input The input text.
   * @param index The offset within the text to begin looking for a match.
   * @return An REMatch instance referencing the match, or null if none.
   */
  public REMatch getMatch(Object input, int index) {
    return getMatch(input,index,0);
  }
  
  /**
   * Returns the first match found in the input, beginning
   * the search at the specified index, and using the specified
   * execution flags.  If no match is found, returns null.
   *
   * @param input The input text.
   * @param index The offset index at which the search should be begin.
   * @param eflags The logical OR of any execution flags above.
   * @return An REMatch instance referencing the match, or null if none.
   */
  public REMatch getMatch(Object input, int index, int eflags) {
    return getMatch(input,index,eflags,null);
  }

  /**
   * Returns the first match found in the input, beginning the search
   * at the specified index, and using the specified execution flags.
   * If no match is found, returns null.  If a StringBuffer is
   * provided and is non-null, the contents of the input text from the
   * index to the beginning of the match (or to the end of the input,
   * if there is no match) are appended to the StringBuffer.
   *
   * @param input The input text.
   * @param index The offset index at which the search should be begin.
   * @param eflags The logical OR of any execution flags above.
   * @param buffer The StringBuffer to save pre-match text in.
   * @return An REMatch instance referencing the match, or null if none.  */
  public REMatch getMatch(Object input, int index, int eflags, StringBuffer buffer) {
    return getMatchImpl(makeCharIndexed(input,index),index,eflags,buffer);
  }

  REMatch getMatchImpl(CharIndexed input, int anchor, int eflags, StringBuffer buffer) {
      // Create a new REMatch to hold results
      REMatch mymatch = new REMatch(numSubs, anchor, eflags);