javascripttokenmaker.java

具有不同语法高亮的编辑器实例

/*
 * 10/08/2004
 *
 * JavaScriptTokenMaker.java - An object that can take a chunk of text and
 *                             return a linked list of <code>Token</code>s
 *                             representing it in the JavaScript programming
 *                             language.
 * Copyright (C) 2004 Robert Futrell
 * [e-mail]
 * www.website.com
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License
 * as published by the Free Software Foundation; either version 2
 * of the License, or any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA  02111-1307, USA.
 */
package org.fife.ui.rsyntaxtextarea.modes;

import javax.swing.text.Segment;

import org.fife.ui.rsyntaxtextarea.*;


/**
 * A token maker that turns text into a linked list of <code>Token</code>s
 * for syntax highlighting in the JavaScript programming language.
 *
 * @author Robert Futrell
 * @version 0.1
 */
public class JavaScriptTokenMaker extends AbstractTokenMaker {

	protected final String operators = "+-*/%!=<>^&|?:";

	protected final String separators = "()[]{}";

	protected final String separators2 = ".,;";	// Characters you don't want syntax highlighted but separate identifiers.

	protected final String hexCharacters = "0123456789ABCDEFabcdef";

	protected final String numberEndChars = "FfLl"; // Characters used to specify literal number types.

	private int currentTokenStart;
	private int currentTokenType;


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


	/**
	 * Constructor.
	 */
	public JavaScriptTokenMaker() {
		super();	// Initializes tokensToHighlight.
	}


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


	/**
	 * Checks the token to give it the exact ID it deserves before
	 * being passed up to the super method.
	 *
	 * @param segment <code>Segment</code> to get text from.
	 * @param start Start offset in <code>segment</code> of token.
	 * @param end End offset in <code>segment</code> of token.
	 * @param tokenType The token's type.
	 * @param startOffset The offset in the document at which the token occurs.
	 */
	public void addToken(Segment segment, int start, int end, int tokenType, int startOffset) {

		switch (tokenType) {
			// Since reserved words, functions, and data types are all passed
			// into here as "identifiers," we have to see what the token
			// really is...
			case Token.IDENTIFIER:
				int value = wordsToHighlight.get(segment, start,end);
				if (value!=-1)
					tokenType = value;
				break;
			case Token.WHITESPACE:
			case Token.SEPARATOR:
			case Token.OPERATOR:
			case Token.ERROR_IDENTIFIER:
			case Token.ERROR_NUMBER_FORMAT:
			case Token.ERROR_STRING_DOUBLE:
			case Token.ERROR_CHAR:
			case Token.COMMENT_EOL:
			case Token.COMMENT_MULTILINE:
			case Token.LITERAL_BOOLEAN:
			case Token.LITERAL_NUMBER_DECIMAL_INT:
			case Token.LITERAL_NUMBER_FLOAT:
			case Token.LITERAL_NUMBER_HEXADECIMAL:
			case Token.LITERAL_STRING_DOUBLE_QUOTE:
			case Token.LITERAL_CHAR:

				break;
			default:
				System.err.println("Unknown tokenType in JavaScriptTokenMaker.addToken: '" + tokenType + "'");
				System.exit(0);
		}

		super.addToken(segment, start, end, tokenType, startOffset);

	}


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


	/**
	 * Returns the words to highlightfor the JavaScript programming language.
	 *
	 * @return A <code>TokenMap</code> containing the words to highlight for
	 *         the JavaScript programming language.
	 * @see org.fife.ui.rsyntaxtextarea.AbstractTokenMaker#getWordsToHighlight
	 */
	public TokenMap getWordsToHighlight() {

		TokenMap tokenMap = new TokenMap(52);

		int reservedWord = Token.RESERVED_WORD;
		tokenMap.put("abstract",						reservedWord);
		tokenMap.put("as",							reservedWord);
		tokenMap.put("break",						reservedWord);
		tokenMap.put("case",						reservedWord);
		tokenMap.put("catch",						reservedWord);
		tokenMap.put("class",						reservedWord);
		tokenMap.put("const",						reservedWord);
		tokenMap.put("continue",						reservedWord);
		tokenMap.put("debugger",						reservedWord);
		tokenMap.put("default",						reservedWord);
		tokenMap.put("delete",						reservedWord);
		tokenMap.put("do",							reservedWord);
		tokenMap.put("else",						reservedWord);
		tokenMap.put("enum",						reservedWord);
		tokenMap.put("export",						reservedWord);
		tokenMap.put("extends",						reservedWord);
		tokenMap.put("final",						reservedWord);
		tokenMap.put("finally",						reservedWord);
		tokenMap.put("for",							reservedWord);
		tokenMap.put("function",						reservedWord);
		tokenMap.put("goto",						reservedWord);
		tokenMap.put("if",							reservedWord);
		tokenMap.put("implements",					reservedWord);
		tokenMap.put("import",						reservedWord);
		tokenMap.put("in",							reservedWord);
		tokenMap.put("instanceof",					reservedWord);
		tokenMap.put("interface",					reservedWord);
		tokenMap.put("item",						reservedWord);
		tokenMap.put("namespace",					reservedWord);
		tokenMap.put("native",						reservedWord);
		tokenMap.put("new",							reservedWord);
		tokenMap.put("null",						reservedWord);
		tokenMap.put("package",						reservedWord);
		tokenMap.put("private",						reservedWord);
		tokenMap.put("protected",					reservedWord);
		tokenMap.put("public",						reservedWord);
		tokenMap.put("return",						reservedWord);
		tokenMap.put("static",						reservedWord);
		tokenMap.put("super",						reservedWord);
		tokenMap.put("switch",						reservedWord);
		tokenMap.put("synchronized",					reservedWord);
		tokenMap.put("this",						reservedWord);
		tokenMap.put("throw",						reservedWord);
		tokenMap.put("throws",						reservedWord);
		tokenMap.put("transient",					reservedWord);
		tokenMap.put("try",							reservedWord);
		tokenMap.put("typeof",						reservedWord);
		tokenMap.put("var",							reservedWord);
		tokenMap.put("void",						reservedWord);
		tokenMap.put("while",						reservedWord);
		tokenMap.put("with",						reservedWord);

		int literalBoolean = Token.LITERAL_BOOLEAN;
		tokenMap.put("false",						literalBoolean);
		tokenMap.put("true",						literalBoolean);

		int dataType = Token.DATA_TYPE;
		tokenMap.put("boolean",						dataType);
		tokenMap.put("byte",						dataType);
		tokenMap.put("char",						dataType);
		tokenMap.put("double",						dataType);
		tokenMap.put("float",						dataType);
		tokenMap.put("int",							dataType);
		tokenMap.put("long",						dataType);
		tokenMap.put("short",						dataType);

		return tokenMap;

	}


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


	/**
	 * Returns the first token in the linked list of tokens generated
	 * from <code>text</code>.  This method must be implemented by
	 * subclasses so they can correctly implement syntax highlighting.
	 *
	 * @param text The text from which to get tokens.
	 * @param initialTokenType The token type we should start with.
	 * @param startOffset The offset into the document at which
	 *                    <code>text</code> starts.
	 * @return The first <code>Token</code> in a linked list representing
	 *         the syntax highlighted text.
	 */
	public Token getTokenList(Segment text, int initialTokenType,
												int startOffset) {


		resetTokenList();

		char[] array = text.array;
		int offset = text.offset;
		int count = text.count;
		int end = offset + count;

		// See, when we find a token, its starting position is always of the
		// form: 'startOffset + (currentTokenStart-offset)'; but since
		// startOffset and offset are constant, tokens' starting positions
		// become: 'newStartOffset+currentTokenStart' for one less subraction
		// operation.
		int newStartOffset = startOffset - offset;

		currentTokenStart = offset;
		currentTokenType  = initialTokenType;
		boolean backslash = false;
		boolean numContainsExponent = false;
		boolean numContainsEndCharacter = false;

		for (int i=offset; i<end; i++) {

			char c = array[i];

			switch (currentTokenType) {

				case Token.NULL:

					currentTokenStart = i;	// Starting a new token here.

					switch (c) {

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

						case '"':
							if (backslash) { // Escaped double quote => call '"' an identifier..
								addToken(text, currentTokenStart,i, Token.IDENTIFIER, newStartOffset+currentTokenStart);
								backslash = false;
							}
							else {
								currentTokenType = Token.ERROR_STRING_DOUBLE;
							}
							break;

						case '\'':
							if (backslash) { // Escaped single quote => call '\'' an identifier.
								addToken(text, currentTokenStart,i, Token.IDENTIFIER, newStartOffset+currentTokenStart);
								backslash = false;
							}
							else {
								currentTokenType = Token.ERROR_CHAR;
							}
							break;

						case '\\':
							addToken(text, currentTokenStart,i, Token.IDENTIFIER, newStartOffset+currentTokenStart);
							currentTokenType = Token.NULL;
							backslash = !backslash;
							break;

						default:
							if (RSyntaxUtilities.isDigit(c)) {
								currentTokenType = Token.LITERAL_NUMBER_DECIMAL_INT;
								break;
							}
							else if (RSyntaxUtilities.isLetter(c) || c=='_') {
								currentTokenType = Token.IDENTIFIER;
								break;
							}
							int indexOf = operators.indexOf(c,0);
							if (indexOf>-1) {
								currentTokenStart = i;
								currentTokenType = Token.OPERATOR;
								break;
							}
							indexOf = separators.indexOf(c,0);
							if (indexOf>-1) {
								addToken(text, currentTokenStart,i, Token.SEPARATOR, newStartOffset+currentTokenStart);
								currentTokenType = Token.NULL;
								break;
							}
							indexOf = separators2.indexOf(c,0);
							if (indexOf>-1) {
								addToken(text, currentTokenStart,i, Token.IDENTIFIER, newStartOffset+currentTokenStart);
								currentTokenType = Token.NULL;
								break;
							}
							else {
								currentTokenType = Token.ERROR_IDENTIFIER;
								break;
							}

					} // End of switch (c).

					break;

				case Token.WHITESPACE:

					switch (c) {

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

						case '\\':