re.java

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

      if (quot)
      	unit.bk = false;

      // ALTERNATION OPERATOR
      //  \| or | (if RE_NO_BK_VBAR) or newline (if RE_NEWLINE_ALT)
      //  not available if RE_LIMITED_OPS is set

      // TODO: the '\n' literal here should be a test against REToken.newline,
      // which unfortunately may be more than a single character.
      if ( ( (unit.ch == '|' && (syntax.get(RESyntax.RE_NO_BK_VBAR) ^ (unit.bk || quot)))
	     || (syntax.get(RESyntax.RE_NEWLINE_ALT) && (unit.ch == '\n') && !(unit.bk || quot)) )
	   && !syntax.get(RESyntax.RE_LIMITED_OPS)) {
	// make everything up to here be a branch. create vector if nec.
	addToken(currentToken);
	RE theBranch = new RE(firstToken, lastToken, numSubs, subIndex, minimumLength);
	minimumLength = 0;
	if (branches == null) {
	    branches = new Vector();
	}
	branches.addElement(theBranch);
	firstToken = lastToken = currentToken = null;
      }
      
      // INTERVAL OPERATOR:
      //  {x} | {x,} | {x,y}  (RE_INTERVALS && RE_NO_BK_BRACES)
      //  \{x\} | \{x,\} | \{x,y\} (RE_INTERVALS && !RE_NO_BK_BRACES)
      //
      // OPEN QUESTION: 
      //  what is proper interpretation of '{' at start of string?

      else if ((unit.ch == '{') && syntax.get(RESyntax.RE_INTERVALS) && (syntax.get(RESyntax.RE_NO_BK_BRACES) ^ (unit.bk || quot))) {
	int newIndex = getMinMax(pattern,index,minMax,syntax);
        if (newIndex > index) {
          if (minMax.first > minMax.second)
            throw new REException(getLocalizedMessage("interval.order"),REException.REG_BADRPT,newIndex);
          if (currentToken == null)
            throw new REException(getLocalizedMessage("repeat.no.token"),REException.REG_BADRPT,newIndex);
          if (currentToken instanceof RETokenRepeated) 
            throw new REException(getLocalizedMessage("repeat.chained"),REException.REG_BADRPT,newIndex);
          if (currentToken instanceof RETokenWordBoundary || currentToken instanceof RETokenWordBoundary)
            throw new REException(getLocalizedMessage("repeat.assertion"),REException.REG_BADRPT,newIndex);
          if ((currentToken.getMinimumLength() == 0) && (minMax.second == Integer.MAX_VALUE))
            throw new REException(getLocalizedMessage("repeat.empty.token"),REException.REG_BADRPT,newIndex);
          index = newIndex;
          currentToken = setRepeated(currentToken,minMax.first,minMax.second,index); 
        }
        else {
          addToken(currentToken);
          currentToken = new RETokenChar(subIndex,unit.ch,insens);
        } 
      }
      
      // LIST OPERATOR:
      //  [...] | [^...]

      else if ((unit.ch == '[') && !(unit.bk || quot)) {
	Vector options = new Vector();
	boolean negative = false;
	char lastChar = 0;
	if (index == pLength) throw new REException(getLocalizedMessage("unmatched.bracket"),REException.REG_EBRACK,index);
	
	// Check for initial caret, negation
	if ((ch = pattern[index]) == '^') {
	  negative = true;
	  if (++index == pLength) throw new REException(getLocalizedMessage("class.no.end"),REException.REG_EBRACK,index);
	  ch = pattern[index];
	}

	// Check for leading right bracket literal
	if (ch == ']') {
	  lastChar = ch;
	  if (++index == pLength) throw new REException(getLocalizedMessage("class.no.end"),REException.REG_EBRACK,index);
	}

	while ((ch = pattern[index++]) != ']') {
	  if ((ch == '-') && (lastChar != 0)) {
	    if (index == pLength) throw new REException(getLocalizedMessage("class.no.end"),REException.REG_EBRACK,index);
	    if ((ch = pattern[index]) == ']') {
	      options.addElement(new RETokenChar(subIndex,lastChar,insens));
	      lastChar = '-';
	    } else {
	      options.addElement(new RETokenRange(subIndex,lastChar,ch,insens));
	      lastChar = 0;
	      index++;
	    }
          } else if ((ch == '\\') && syntax.get(RESyntax.RE_BACKSLASH_ESCAPE_IN_LISTS)) {
            if (index == pLength) throw new REException(getLocalizedMessage("class.no.end"),REException.REG_EBRACK,index);
	    int posixID = -1;
	    boolean negate = false;
            char asciiEsc = 0;
	    if (("dswDSW".indexOf(pattern[index]) != -1) && syntax.get(RESyntax.RE_CHAR_CLASS_ESC_IN_LISTS)) {
	      switch (pattern[index]) {
	      case 'D':
		negate = true;
	      case 'd':
		posixID = RETokenPOSIX.DIGIT;
		break;
	      case 'S':
		negate = true;
	      case 's':
		posixID = RETokenPOSIX.SPACE;
		break;
	      case 'W':
		negate = true;
	      case 'w':
		posixID = RETokenPOSIX.ALNUM;
		break;
	      }
	    }
            else if ("nrt".indexOf(pattern[index]) != -1) {
              switch (pattern[index]) {
                case 'n':
                  asciiEsc = '\n';
                  break;
                case 't':
                  asciiEsc = '\t';
                  break;
                case 'r':
                  asciiEsc = '\r';
                  break;
              }
            }
	    if (lastChar != 0) options.addElement(new RETokenChar(subIndex,lastChar,insens));
	    
	    if (posixID != -1) {
	      options.addElement(new RETokenPOSIX(subIndex,posixID,insens,negate));
	    } else if (asciiEsc != 0) {
	      lastChar = asciiEsc;
	    } else {
	      lastChar = pattern[index];
	    }
	    ++index;
	  } else if ((ch == '[') && (syntax.get(RESyntax.RE_CHAR_CLASSES)) && (index < pLength) && (pattern[index] == ':')) {
	    StringBuffer posixSet = new StringBuffer();
	    index = getPosixSet(pattern,index+1,posixSet);
	    int posixId = RETokenPOSIX.intValue(posixSet.toString());
	    if (posixId != -1)
	      options.addElement(new RETokenPOSIX(subIndex,posixId,insens,false));
	  } else {
	    if (lastChar != 0) options.addElement(new RETokenChar(subIndex,lastChar,insens));
	    lastChar = ch;
	  }
	  if (index == pLength) throw new REException(getLocalizedMessage("class.no.end"),REException.REG_EBRACK,index);
	} // while in list
	// Out of list, index is one past ']'
	    
	if (lastChar != 0) options.addElement(new RETokenChar(subIndex,lastChar,insens));
	    
	// Create a new RETokenOneOf
	addToken(currentToken);
	options.trimToSize();
	currentToken = new RETokenOneOf(subIndex,options,negative);
      }

      // SUBEXPRESSIONS
      //  (...) | \(...\) depending on RE_NO_BK_PARENS

      else if ((unit.ch == '(') && (syntax.get(RESyntax.RE_NO_BK_PARENS) ^ (unit.bk || quot))) {
	boolean pure = false;
	boolean comment = false;
        boolean lookAhead = false;
        boolean negativelh = false;
	if ((index+1 < pLength) && (pattern[index] == '?')) {
	  switch (pattern[index+1]) {
          case '!':
            if (syntax.get(RESyntax.RE_LOOKAHEAD)) {
              pure = true;
              negativelh = true;
              lookAhead = true;
              index += 2;
            }
            break;
          case '=':
            if (syntax.get(RESyntax.RE_LOOKAHEAD)) {
              pure = true;
              lookAhead = true;
              index += 2;
            }
            break;
	  case ':':
	    if (syntax.get(RESyntax.RE_PURE_GROUPING)) {
	      pure = true;
	      index += 2;
	    }
	    break;
	  case '#':
	    if (syntax.get(RESyntax.RE_COMMENTS)) {
	      comment = true;
	    }
	    break;
          default:
            throw new REException(getLocalizedMessage("repeat.no.token"), REException.REG_BADRPT, index);
	  }
	}

	if (index >= pLength) {
	    throw new REException(getLocalizedMessage("unmatched.paren"), REException.REG_ESUBREG,index);
	}

	// find end of subexpression
	int endIndex = index;
	int nextIndex = index;
	int nested = 0;

	while ( ((nextIndex = getCharUnit(pattern,endIndex,unit,false)) > 0)
		&& !(nested == 0 && (unit.ch == ')') && (syntax.get(RESyntax.RE_NO_BK_PARENS) ^ (unit.bk || quot))) )
	  if ((endIndex = nextIndex) >= pLength)
	    throw new REException(getLocalizedMessage("subexpr.no.end"),REException.REG_ESUBREG,nextIndex);
	  else if (unit.ch == '(' && (syntax.get(RESyntax.RE_NO_BK_PARENS) ^ (unit.bk || quot)))
	    nested++;
	  else if (unit.ch == ')' && (syntax.get(RESyntax.RE_NO_BK_PARENS) ^ (unit.bk || quot)))
	    nested--;

	// endIndex is now position at a ')','\)' 
	// nextIndex is end of string or position after ')' or '\)'

	if (comment) index = nextIndex;
	else { // not a comment
	  // create RE subexpression as token.
	  addToken(currentToken);
	  if (!pure) {
	    numSubs++;
	  }

	  int useIndex = (pure || lookAhead) ? 0 : nextSub + numSubs;
	  currentToken = new RE(String.valueOf(pattern,index,endIndex-index).toCharArray(),cflags,syntax,useIndex,nextSub + numSubs);
	  numSubs += ((RE) currentToken).getNumSubs();

          if (lookAhead) {
	      currentToken = new RETokenLookAhead(currentToken,negativelh);
	  }

	  index = nextIndex;
	} // not a comment
      } // subexpression
    
      // UNMATCHED RIGHT PAREN
      // ) or \) throw exception if
      // !syntax.get(RESyntax.RE_UNMATCHED_RIGHT_PAREN_ORD)
      else if (!syntax.get(RESyntax.RE_UNMATCHED_RIGHT_PAREN_ORD) && ((unit.ch == ')') && (syntax.get(RESyntax.RE_NO_BK_PARENS) ^ (unit.bk || quot)))) {
	throw new REException(getLocalizedMessage("unmatched.paren"),REException.REG_EPAREN,index);
      }

      // START OF LINE OPERATOR
      //  ^

      else if ((unit.ch == '^') && !(unit.bk || quot)) {
	addToken(currentToken);
	currentToken = null;
	addToken(new RETokenStart(subIndex,((cflags & REG_MULTILINE) > 0) ? syntax.getLineSeparator() : null));
      }

      // END OF LINE OPERATOR
      //  $

      else if ((unit.ch == '$') && !(unit.bk || quot)) {
	addToken(currentToken);
	currentToken = null;
	addToken(new RETokenEnd(subIndex,((cflags & REG_MULTILINE) > 0) ? syntax.getLineSeparator() : null));
      }

      // MATCH-ANY-CHARACTER OPERATOR (except possibly newline and null)
      //  .

      else if ((unit.ch == '.') && !(unit.bk || quot)) {
	addToken(currentToken);
	currentToken = new RETokenAny(subIndex,syntax.get(RESyntax.RE_DOT_NEWLINE) || ((cflags & REG_DOT_NEWLINE) > 0),syntax.get(RESyntax.RE_DOT_NOT_NULL));
      }

      // ZERO-OR-MORE REPEAT OPERATOR
      //  *

      else if ((unit.ch == '*') && !(unit.bk || quot)) {
	if (currentToken == null)
          throw new REException(getLocalizedMessage("repeat.no.token"),REException.REG_BADRPT,index);
	if (currentToken instanceof RETokenRepeated)
          throw new REException(getLocalizedMessage("repeat.chained"),REException.REG_BADRPT,index);
	if (currentToken instanceof RETokenWordBoundary || currentToken instanceof RETokenWordBoundary)
	  throw new REException(getLocalizedMessage("repeat.assertion"),REException.REG_BADRPT,index);
	if (currentToken.getMinimumLength() == 0)
	  throw new REException(getLocalizedMessage("repeat.empty.token"),REException.REG_BADRPT,index);
	currentToken = setRepeated(currentToken,0,Integer.MAX_VALUE,index);
      }

      // ONE-OR-MORE REPEAT OPERATOR
      //  + | \+ depending on RE_BK_PLUS_QM
      //  not available if RE_LIMITED_OPS is set

      else if ((unit.ch == '+') && !syntax.get(RESyntax.RE_LIMITED_OPS) && (!syntax.get(RESyntax.RE_BK_PLUS_QM) ^ (unit.bk || quot))) {
	if (currentToken == null)
          throw new REException(getLocalizedMessage("repeat.no.token"),REException.REG_BADRPT,index);
	if (currentToken instanceof RETokenRepeated)
          throw new REException(getLocalizedMessage("repeat.chained"),REException.REG_BADRPT,index);
	if (currentToken instanceof RETokenWordBoundary || currentToken instanceof RETokenWordBoundary)
	  throw new REException(getLocalizedMessage("repeat.assertion"),REException.REG_BADRPT,index);
	if (currentToken.getMinimumLength() == 0)
	  throw new REException(getLocalizedMessage("repeat.empty.token"),REException.REG_BADRPT,index);
	currentToken = setRepeated(currentToken,1,Integer.MAX_VALUE,index);
      }

      // ZERO-OR-ONE REPEAT OPERATOR / STINGY MATCHING OPERATOR
      //  ? | \? depending on RE_BK_PLUS_QM
      //  not available if RE_LIMITED_OPS is set
      //  stingy matching if RE_STINGY_OPS is set and it follows a quantifier

      else if ((unit.ch == '?') && !syntax.get(RESyntax.RE_LIMITED_OPS) && (!syntax.get(RESyntax.RE_BK_PLUS_QM) ^ (unit.bk || quot))) {
	if (currentToken == null) throw new REException(getLocalizedMessage("repeat.no.token"),REException.REG_BADRPT,index);

	// Check for stingy matching on RETokenRepeated
	if (currentToken instanceof RETokenRepeated) {
          if (syntax.get(RESyntax.RE_STINGY_OPS) && !((RETokenRepeated)currentToken).isStingy())
            ((RETokenRepeated)currentToken).makeStingy();
          else
            throw new REException(getLocalizedMessage("repeat.chained"),REException.REG_BADRPT,index);
        }
        else if (currentToken instanceof RETokenWordBoundary || currentToken instanceof RETokenWordBoundary)
          throw new REException(getLocalizedMessage("repeat.assertion"),REException.REG_BADRPT,index);
	else
	  currentToken = setRepeated(currentToken,0,1,index);
      }
	
      // BACKREFERENCE OPERATOR
      //  \1 \2 ... \9
      // not available if RE_NO_BK_REFS is set

      else if (unit.bk && Character.isDigit(unit.ch) && !syntax.get(RESyntax.RE_NO_BK_REFS)) {
	addToken(currentToken);
	currentToken = new RETokenBackRef(subIndex,Character.digit(unit.ch,10),insens);
      }

      // START OF STRING OPERATOR
      //  \A if RE_STRING_ANCHORS is set
      
      else if (unit.bk && (unit.ch == 'A') && syntax.get(RESyntax.RE_STRING_ANCHORS)) {
	addToken(currentToken);
	currentToken = new RETokenStart(subIndex,null);
      }

      // 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, false);
      } 

      // WORD BEGIN OPERATOR