re.java

用java 编写的源码开放的文本编辑器。有很多有用的特性

		      }
		  }
		  
		  longest.end[0] = longest.index;
		  longest.finish(input);
		  return longest;
	      }
	  }
	  mymatch.clear(++anchor);
	  // Append character to buffer if needed
	  if (buffer != null && input.charAt(0) != CharIndexed.OUT_OF_BOUNDS) {
	      buffer.append(input.charAt(0));
	  }
      } while (input.move(1));
      
      // Special handling at end of input for e.g. "$"
      if (minimumLength == 0) {
	  if (match(input, mymatch)) {
	      mymatch.finish(input);
	      return mymatch;
	  }
      }

      return null;
  }

  /**
   * Returns an REMatchEnumeration that can be used to iterate over the
   * matches found in the input text.
   *
   * @param input The input text.
   * @return A non-null REMatchEnumeration instance.
   */
  public REMatchEnumeration getMatchEnumeration(Object input) {
    return getMatchEnumeration(input,0,0);
  }


  /**
   * Returns an REMatchEnumeration that can be used to iterate over the
   * matches found in the input text.
   *
   * @param input The input text.
   * @param index The offset index at which the search should be begin.
   * @return A non-null REMatchEnumeration instance, with its input cursor
   *  set to the index position specified.
   */
  public REMatchEnumeration getMatchEnumeration(Object input, int index) {
    return getMatchEnumeration(input,index,0);
  }

  /**
   * Returns an REMatchEnumeration that can be used to iterate over the
   * matches found in the input text.
   *
   * @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 REMatchEnumeration instance, with its input cursor
   *  set to the index position specified.
   */
  public REMatchEnumeration getMatchEnumeration(Object input, int index, int eflags) {
    return new REMatchEnumeration(this,makeCharIndexed(input,index),index,eflags);
  }


  /**
   * Substitutes the replacement text for the first match found in the input.
   *
   * @param input The input text.
   * @param replace The replacement text, which may contain $x metacharacters (see REMatch.substituteInto).
   * @return A String interpolating the substituted text.
   * @see REMatch#substituteInto
   */
  public String substitute(Object input,String replace) {
    return substitute(input,replace,0,0);
  }

  /**
   * Substitutes the replacement text for the first match found in the input
   * beginning at the specified index position.  Specifying an index
   * effectively causes the regular expression engine to throw away the
   * specified number of characters. 
   *
   * @param input The input text.
   * @param replace The replacement text, which may contain $x metacharacters (see REMatch.substituteInto).
   * @param index The offset index at which the search should be begin.
   * @return A String containing the substring of the input, starting
   *   at the index position, and interpolating the substituted text.
   * @see REMatch#substituteInto
   */
  public String substitute(Object input,String replace,int index) {
    return substitute(input,replace,index,0);
  }

  /**
   * Substitutes the replacement text for the first match found in the input
   * string, beginning at the specified index position and using the
   * specified execution flags.
   *
   * @param input The input text.
   * @param replace The replacement text, which may contain $x metacharacters (see REMatch.substituteInto).
   * @param index The offset index at which the search should be begin.
   * @param eflags The logical OR of any execution flags above.
   * @return A String containing the substring of the input, starting
   *   at the index position, and interpolating the substituted text.
   * @see REMatch#substituteInto
   */
  public String substitute(Object input,String replace,int index,int eflags) {
    return substituteImpl(makeCharIndexed(input,index),replace,index,eflags);
  }

  private String substituteImpl(CharIndexed input,String replace,int index,int eflags) {
    StringBuffer buffer = new StringBuffer();
    REMatch m = getMatchImpl(input,index,eflags,buffer);
    if (m==null) return buffer.toString();
    buffer.append( ((eflags & REG_NO_INTERPOLATE) > 0) ?
		   replace : m.substituteInto(replace) );
    if (input.move(m.end[0])) {
      do {
	buffer.append(input.charAt(0));
      } while (input.move(1));
    }
    return buffer.toString();
  }
  
  /**
   * Substitutes the replacement text for each non-overlapping match found 
   * in the input text.
   *
   * @param input The input text.
   * @param replace The replacement text, which may contain $x metacharacters (see REMatch.substituteInto).
   * @return A String interpolating the substituted text.
   * @see REMatch#substituteInto
   */
  public String substituteAll(Object input,String replace) {
    return substituteAll(input,replace,0,0);
  }

  /**
   * Substitutes the replacement text for each non-overlapping match found 
   * in the input text, starting at the specified index.
   *
   * 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 replace The replacement text, which may contain $x metacharacters (see REMatch.substituteInto).
   * @param index The offset index at which the search should be begin.
   * @return A String containing the substring of the input, starting
   *   at the index position, and interpolating the substituted text.
   * @see REMatch#substituteInto
   */
  public String substituteAll(Object input,String replace,int index) {
    return substituteAll(input,replace,index,0);
  }
 
  /**
   * Substitutes the replacement text for each non-overlapping match found 
   * in the input text, starting at the specified index and using the
   * specified execution flags.
   *
   * @param input The input text.
   * @param replace The replacement text, which may contain $x metacharacters (see REMatch.substituteInto).
   * @param index The offset index at which the search should be begin.
   * @param eflags The logical OR of any execution flags above.
   * @return A String containing the substring of the input, starting
   *   at the index position, and interpolating the substituted text.
   * @see REMatch#substituteInto
   */
  public String substituteAll(Object input,String replace,int index,int eflags) {
    return substituteAllImpl(makeCharIndexed(input,index),replace,index,eflags);
  }

  private String substituteAllImpl(CharIndexed input,String replace,int index,int eflags) {
    StringBuffer buffer = new StringBuffer();
    REMatch m;
    while ((m = getMatchImpl(input,index,eflags,buffer)) != null) {
	buffer.append( ((eflags & REG_NO_INTERPOLATE) > 0) ?
		       replace : m.substituteInto(replace) );
      index = m.getEndIndex();
      if (m.end[0] == 0) {
	char ch = input.charAt(0);
	if (ch != CharIndexed.OUT_OF_BOUNDS) 
	    buffer.append(ch);
	input.move(1);
      } else {
	  input.move(m.end[0]);
      }

      if (!input.isValid()) break;
    }
    return buffer.toString();
  }
  
  /* Helper function for constructor */
  private void addToken(REToken next) {
    if (next == null) return;
    minimumLength += next.getMinimumLength();
    if (firstToken == null) {
	lastToken = firstToken = next;
    } else {
      // if chain returns false, it "rejected" the token due to
      // an optimization, and next was combined with lastToken
      if (lastToken.chain(next)) {
	  lastToken = next;
      }
    }
  }

  private static REToken setRepeated(REToken current, int min, int max, int index) throws REException {
    if (current == null) throw new REException(getLocalizedMessage("repeat.no.token"),REException.REG_BADRPT,index);
    return new RETokenRepeated(current.subIndex,current,min,max);
  }

  private static int getPosixSet(char[] pattern,int index,StringBuffer buf) {
    // Precondition: pattern[index-1] == ':'
    // we will return pos of closing ']'.
    int i;
    for (i=index; i<(pattern.length-1); i++) {
      if ((pattern[i] == ':') && (pattern[i+1] == ']'))
	return i+2;
      buf.append(pattern[i]);
    }
    return index; // didn't match up
  }

  private int getMinMax(char[] input,int index,IntPair minMax,RESyntax syntax) throws REException {
    // Precondition: input[index-1] == '{', minMax != null

    boolean mustMatch = !syntax.get(RESyntax.RE_NO_BK_BRACES);
    int startIndex = index;
    if (index == input.length) {
      if (mustMatch)
        throw new REException(getLocalizedMessage("unmatched.brace"),REException.REG_EBRACE,index);
      else
        return startIndex;
    }
    
    int min,max=0;
    CharUnit unit = new CharUnit();
    StringBuffer buf = new StringBuffer();
    
    // Read string of digits
    do {
      index = getCharUnit(input,index,unit);
      if (Character.isDigit(unit.ch))
        buf.append(unit.ch);
    } while ((index != input.length) && Character.isDigit(unit.ch));

    // Check for {} tomfoolery
    if (buf.length() == 0) {
      if (mustMatch)
        throw new REException(getLocalizedMessage("interval.error"),REException.REG_EBRACE,index);
      else
        return startIndex;
    }

    min = Integer.parseInt(buf.toString());
	
    if ((unit.ch == '}') && (syntax.get(RESyntax.RE_NO_BK_BRACES) ^ unit.bk))
      max = min;
    else if (index == input.length)
      if (mustMatch)
        throw new REException(getLocalizedMessage("interval.no.end"),REException.REG_EBRACE,index);
      else
        return startIndex;
    else if ((unit.ch == ',') && !unit.bk) {
      buf = new StringBuffer();
      // Read string of digits
      while (((index = getCharUnit(input,index,unit)) != input.length) && Character.isDigit(unit.ch))
	buf.append(unit.ch);

      if (!((unit.ch == '}') && (syntax.get(RESyntax.RE_NO_BK_BRACES) ^ unit.bk)))
        if (mustMatch)
          throw new REException(getLocalizedMessage("interval.error"),REException.REG_EBRACE,index);
        else
          return startIndex;

      // This is the case of {x,}
      if (buf.length() == 0) max = Integer.MAX_VALUE;
      else max = Integer.parseInt(buf.toString());
    } else
      if (mustMatch)
        throw new REException(getLocalizedMessage("interval.error"),REException.REG_EBRACE,index);
      else
        return startIndex;

    // We know min and max now, and they are valid.

    minMax.first = min;
    minMax.second = max;

    // return the index following the '}'
    return index;
  }

   /**
    * Return a human readable form of the compiled regular expression,
    * useful for debugging.
    */
   public String toString() {
     StringBuffer sb = new StringBuffer();
     dump(sb);
     return sb.toString();
   }

  void dump(StringBuffer os) {
    os.append('(');
    if (subIndex == 0)
      os.append("?:");
    if (firstToken != null)
      firstToken.dumpAll(os);
    os.append(')');
  }

  // Cast input appropriately or throw exception
  private static CharIndexed makeCharIndexed(Object input, int index) {
      // We could let a String fall through to final input, but since
      // it's the most likely input type, we check it first.
    if (input instanceof String)
      return new CharIndexedString((String) input,index);
    else if (input instanceof char[])
      return new CharIndexedCharArray((char[]) input,index);
    else if (input instanceof StringBuffer)
      return new CharIndexedStringBuffer((StringBuffer) input,index);
    else if (input instanceof InputStream)
      return new CharIndexedInputStream((InputStream) input,index);
    else if (input instanceof Reader)
	return new CharIndexedReader((Reader) input, index);
    else if (input instanceof CharIndexed)
	return (CharIndexed) input; // do we lose index info?
    else 
	return new CharIndexedString(input.toString(), index);
  }
}