windowsbatchtokenmaker.java

具有不同语法高亮的编辑器实例

						case ' ':
						case '\t':
							currentTokenType = Token.WHITESPACE;
							break;

						case '"':
							currentTokenType = Token.ERROR_STRING_DOUBLE;
							break;

						case '%':
							currentTokenType = Token.VARIABLE;
							break;

						// The "separators".
						case '(':
						case ')':
							addToken(text, currentTokenStart,i, Token.SEPARATOR, newStartOffset+currentTokenStart);
							currentTokenType = Token.NULL;
							break;

						// The "separators2".
						case ',':
						case ';':
							addToken(text, currentTokenStart,i, Token.IDENTIFIER, newStartOffset+currentTokenStart);
							currentTokenType = Token.NULL;
							break;

						default:

							// Just to speed things up a tad, as this will usually be the case (if spaces above failed).
							if (RSyntaxUtilities.isLetterOrDigit(c) || c=='\\') {
								currentTokenType = Token.IDENTIFIER;
								break;
							}

							int indexOf = operators.indexOf(c,0);
							if (indexOf>-1) {
								addToken(text, currentTokenStart,i, Token.OPERATOR, newStartOffset+currentTokenStart);
								currentTokenType = Token.NULL;
								break;
							}
							else {
								currentTokenType = Token.IDENTIFIER;
								break;
							}

					} // End of switch (c).

					break;

				case Token.WHITESPACE:

					switch (c) {

						case ' ':
						case '\t':
							break;	// Still whitespace.

						case '"':
							addToken(text, currentTokenStart,i-1, Token.WHITESPACE, newStartOffset+currentTokenStart);
							currentTokenStart = i;
							currentTokenType = Token.ERROR_STRING_DOUBLE;
							break;

						case '%':
							addToken(text, currentTokenStart,i-1, Token.WHITESPACE, newStartOffset+currentTokenStart);
							currentTokenStart = i;
							currentTokenType = Token.VARIABLE;
							break;

						// The "separators".
						case '(':
						case ')':
							addToken(text, currentTokenStart,i-1, Token.WHITESPACE, newStartOffset+currentTokenStart);
							addToken(text, i,i, Token.SEPARATOR, newStartOffset+i);
							currentTokenType = Token.NULL;
							break;

						// The "separators2".
						case ',':
						case ';':
							addToken(text, currentTokenStart,i-1, Token.WHITESPACE, newStartOffset+currentTokenStart);
							addToken(text, i,i, Token.IDENTIFIER, newStartOffset+i);
							currentTokenType = Token.NULL;
							break;

						default:	// Add the whitespace token and start anew.

							addToken(text, currentTokenStart,i-1, Token.WHITESPACE, newStartOffset+currentTokenStart);
							currentTokenStart = i;

							// Just to speed things up a tad, as this will usually be the case (if spaces above failed).
							if (RSyntaxUtilities.isLetterOrDigit(c) || c=='\\') {
								currentTokenType = Token.IDENTIFIER;
								break;
							}

							int indexOf = operators.indexOf(c,0);
							if (indexOf>-1) {
								addToken(text, currentTokenStart,i, Token.OPERATOR, newStartOffset+currentTokenStart);
								currentTokenType = Token.NULL;
								break;
							}
							else {
								currentTokenType = Token.IDENTIFIER;
							}

					} // End of switch (c).

					break;

				case Token.IDENTIFIER:

					switch (c) {

						case ' ':
						case '\t':
							// Check for REM comments.
							if (i-currentTokenStart==3 &&
								(array[i-3]=='r' || array[i-3]=='R') &&
								(array[i-2]=='e' || array[i-2]=='E') &&
								(array[i-1]=='m' || array[i-1]=='M')) {
									currentTokenType = Token.COMMENT_EOL;
									break;
							}
							addToken(text, currentTokenStart,i-1, Token.IDENTIFIER, newStartOffset+currentTokenStart);
							currentTokenStart = i;
							currentTokenType = Token.WHITESPACE;
							break;

						case '"':
							addToken(text, currentTokenStart,i-1, Token.IDENTIFIER, newStartOffset+currentTokenStart);
							currentTokenStart = i;
							currentTokenType = Token.ERROR_STRING_DOUBLE;
							break;

						case '%':
							addToken(text, currentTokenStart,i-1, Token.IDENTIFIER, newStartOffset+currentTokenStart);
							currentTokenStart = i;
							currentTokenType = Token.VARIABLE;
							break;

						// Should be part of identifiers, but not at end of "REM".
						case '\\':
							// Check for REM comments.
							if (i-currentTokenStart==3 &&
								(array[i-3]=='r' || array[i-3]=='R') &&
								(array[i-2]=='e' || array[i-2]=='E') &&
								(array[i-1]=='m' || array[i-1]=='M')) {
									currentTokenType = Token.COMMENT_EOL;
							}
							break;

						case '.':
						case '_':
							break;	// Characters good for identifiers.

						// The "separators".
						case '(':
						case ')':
							addToken(text, currentTokenStart,i-1, Token.IDENTIFIER, newStartOffset+currentTokenStart);
							addToken(text, i,i, Token.SEPARATOR, newStartOffset+i);
							currentTokenType = Token.NULL;
							break;

						// The "separators2".
						case ',':
						case ';':
							addToken(text, currentTokenStart,i-1, Token.IDENTIFIER, newStartOffset+currentTokenStart);
							addToken(text, i,i, Token.IDENTIFIER, newStartOffset+i);
							currentTokenType = Token.NULL;
							break;

						default:

							// Just to speed things up a tad, as this will usually be the case.
							if (RSyntaxUtilities.isLetterOrDigit(c) || c=='\\') {
								break;
							}

							int indexOf = operators.indexOf(c);
							if (indexOf>-1) {
								addToken(text, currentTokenStart,i-1, Token.IDENTIFIER, newStartOffset+currentTokenStart);
								addToken(text, i,i, Token.OPERATOR, newStartOffset+i);
								currentTokenType = Token.NULL;
								break;
							}

							// Otherwise, fall through and assume we're still okay as an IDENTIFIER...

					} // End of switch (c).

					break;

				case Token.COMMENT_EOL:
					i = end - 1;
					addToken(text, currentTokenStart,i, Token.COMMENT_EOL, newStartOffset+currentTokenStart);
					// We need to set token type to null so at the bottom we don't add one more token.
					currentTokenType = Token.NULL;
					break;

				case Token.ERROR_STRING_DOUBLE:

					if (c=='"') {
						addToken(text, currentTokenStart,i, Token.LITERAL_STRING_DOUBLE_QUOTE, newStartOffset+currentTokenStart);
						currentTokenStart = i + 1;
						currentTokenType = Token.NULL;
					}
					// Otherwise, we're still an unclosed string...

					break;

				case Token.VARIABLE:

						if (i==currentTokenStart+1) { // first character after '%'.
							bracketVariable = false;
							switch (c) {
								case '{':
									bracketVariable = true;
									break;
								default:
									if (RSyntaxUtilities.isLetter(c) || c==' ') { // No tab, just space; spaces are okay in variable names.
										break;
									}
									else if (RSyntaxUtilities.isDigit(c)) { // Single-digit command-line argument ("%1").
										addToken(text, currentTokenStart,i, Token.VARIABLE, newStartOffset+currentTokenStart);
										currentTokenType = Token.NULL;
										break;
									}
									else { // Anything else, ???.
										addToken(text, currentTokenStart,i-1, Token.VARIABLE, newStartOffset+currentTokenStart); // ???
										i--;
										currentTokenType = Token.NULL;
										break;
									}
							} // End of switch (c).
						}
						else { // Character other than first after the '%'.
							if (bracketVariable==true) {
								if (c=='}') {
									addToken(text, currentTokenStart,i, Token.VARIABLE, newStartOffset+currentTokenStart);
									currentTokenType = Token.NULL;
								}
							}
							else {
								if (c=='%') {
									addToken(text, currentTokenStart,i, Token.VARIABLE, newStartOffset+currentTokenStart);
									currentTokenType = Token.NULL;
								}
							}
							break;
						}
						break;

				default:

					System.err.println("Invalid currentTokenType: " + currentTokenType + "; c=='" + c + "'");
					System.exit(0);

			} // End of switch (currentTokenType).

		} // End of for (int i=offset; i<end; i++).

		// Deal with the (possibly there) last token.
		if (currentTokenType != Token.NULL) {

				// Check for REM comments.
				if (end-currentTokenStart==3 &&
					(array[end-3]=='r' || array[end-3]=='R') &&
					(array[end-2]=='e' || array[end-2]=='E') &&
					(array[end-1]=='m' || array[end-1]=='M')) {
						currentTokenType = Token.COMMENT_EOL;
				}

				addToken(text, currentTokenStart,end-1, currentTokenType, newStartOffset+currentTokenStart);
		}

		addNullToken();

		// Return the first token in our linked list.
		return firstToken;

	}


/*****************************************************************************/

}