Set syntax highlighting for existing language using RSyntaxTextArea

Question

I'm using RSyntaxTextArea and I found a guide on syntax highlighting here. However, I have the simple requirement that I only need to modify the list of highlighted keywords (and or functions) from an existing language syntax highlighting style (e.g. SYNTAX_STYLE_CPLUSPLUS).

@Override
public TokenMap getWordsToHighlight() {
   TokenMap tokenMap = new TokenMap();

   tokenMap.put("case",  Token.RESERVED_WORD);
   tokenMap.put("for",   Token.RESERVED_WORD);
   tokenMap.put("if",    Token.RESERVED_WORD);
   tokenMap.put("foo",   Token.RESERVED_WORD); // Added
   tokenMap.put("while", Token.RESERVED_WORD);

   tokenMap.put("printf", Token.FUNCTION);
   tokenMap.put("scanf",  Token.FUNCTION);
   tokenMap.put("fopen",  Token.FUNCTION);

   return tokenMap;
}

I do not want to implement a new language parsing via getTokenList() (like described in the guide) just to do this. The implementation of getWordsToHighlight() also forces you to implement getTokenList(). Isn't there a simpler way? Preferably without hacky solutions like reflection though.

Answer 1

Nevermind, might as well just use the given implementation and fix the undefined variables by prepending the respective data types:

import org.fife.ui.rsyntaxtextarea.AbstractTokenMaker;
import org.fife.ui.rsyntaxtextarea.RSyntaxUtilities;
import org.fife.ui.rsyntaxtextarea.Token;
import org.fife.ui.rsyntaxtextarea.TokenMap;

import javax.swing.text.Segment;

import static org.fife.ui.rsyntaxtextarea.Token.*;
import static org.fife.ui.rsyntaxtextarea.TokenTypes.FUNCTION;
import static org.fife.ui.rsyntaxtextarea.TokenTypes.RESERVED_WORD;

public class KeywordsHighlighting extends AbstractTokenMaker
{
    @Override
    public TokenMap getWordsToHighlight()
    {
        TokenMap tokenMap = new TokenMap();

        tokenMap.put("case", RESERVED_WORD);
        tokenMap.put("for", RESERVED_WORD);
        tokenMap.put("if", RESERVED_WORD);
        tokenMap.put("foo", RESERVED_WORD); // Added
        tokenMap.put("while", RESERVED_WORD);

        tokenMap.put("printf", FUNCTION);
        tokenMap.put("scanf", FUNCTION);
        tokenMap.put("fopen", FUNCTION);

        return tokenMap;
    }

    @Override
    public void addToken(Segment segment, int start, int end, int tokenType, int startOffset)
    {
        if (tokenType == IDENTIFIER)
        {
            int value = wordsToHighlight.get(segment, start, end);
            if (value != -1)
            {
                tokenType = value;
            }
        }

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

    /**
     * Returns a list of tokens representing the given text.
     *
     * @param text           The text to break into tokens.
     * @param startTokenType The token with which to start tokenizing.
     * @param startOffset    The offset at which the line of tokens begins.
     * @return A linked list of tokens representing <code>text</code>.
     */
    public Token getTokenList(Segment text, int startTokenType, int startOffset)
    {

        resetTokenList();

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

        // Token starting offsets are always of the form:
        // 'startOffset + (currentTokenStart-offset)', but since startOffset and
        // offset are constant, tokens' starting positions become:
        // 'newStartOffset+currentTokenStart'.
        int newStartOffset = startOffset - offset;

        int currentTokenStart = offset;
        int currentTokenType = startTokenType;

        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 '"':
                            currentTokenType = Token.LITERAL_STRING_DOUBLE_QUOTE;
                            break;

                        case '#':
                            currentTokenType = Token.COMMENT_EOL;
                            break;

                        default:
                            if (RSyntaxUtilities.isDigit(c))
                            {
                                currentTokenType = Token.LITERAL_NUMBER_DECIMAL_INT;
                                break;
                            } else if (RSyntaxUtilities.isLetter(c) || c == '/' || c == '_')
                            {
                                currentTokenType = Token.IDENTIFIER;
                                break;
                            }

                            // Anything not currently handled - mark as an identifier
                            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.LITERAL_STRING_DOUBLE_QUOTE;
                            break;

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

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

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

                            if (RSyntaxUtilities.isDigit(c))
                            {
                                currentTokenType = Token.LITERAL_NUMBER_DECIMAL_INT;
                                break;
                            } else if (RSyntaxUtilities.isLetter(c) || c == '/' || c == '_')
                            {
                                currentTokenType = Token.IDENTIFIER;
                                break;
                            }

                            // Anything not currently handled - mark as identifier
                            currentTokenType = Token.IDENTIFIER;

                    } // End of switch (c).

                    break;

                default: // Should never happen
                case Token.IDENTIFIER:

                    switch (c)
                    {

                        case ' ':
                        case '\t':
                            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.LITERAL_STRING_DOUBLE_QUOTE;
                            break;

                        default:
                            if (RSyntaxUtilities.isLetterOrDigit(c) || c == '/' || c == '_')
                            {
                                break;   // Still an identifier of some type.
                            }
                            // Otherwise, we're still an identifier (?).

                    } // End of switch (c).

                    break;

                case Token.LITERAL_NUMBER_DECIMAL_INT:

                    switch (c)
                    {

                        case ' ':
                        case '\t':
                            addToken(text, currentTokenStart, i - 1, Token.LITERAL_NUMBER_DECIMAL_INT, newStartOffset + currentTokenStart);
                            currentTokenStart = i;
                            currentTokenType = Token.WHITESPACE;
                            break;

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

                        default:

                            if (RSyntaxUtilities.isDigit(c))
                            {
                                break;   // Still a literal number.
                            }

                            // Otherwise, remember this was a number and start over.
                            addToken(text, currentTokenStart, i - 1, Token.LITERAL_NUMBER_DECIMAL_INT, newStartOffset + currentTokenStart);
                            i--;
                            currentTokenType = Token.NULL;

                    } // End of switch (c).

                    break;

                case Token.COMMENT_EOL:
                    i = end - 1;
                    addToken(text, currentTokenStart, i, currentTokenType, 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.LITERAL_STRING_DOUBLE_QUOTE:
                    if (c == '"')
                    {
                        addToken(text, currentTokenStart, i, Token.LITERAL_STRING_DOUBLE_QUOTE, newStartOffset + currentTokenStart);
                        currentTokenType = Token.NULL;
                    }
                    break;

            } // End of switch (currentTokenType).

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

        switch (currentTokenType)
        {

            // Remember what token type to begin the next line with.
            case Token.LITERAL_STRING_DOUBLE_QUOTE:
                addToken(text, currentTokenStart, end - 1, currentTokenType, newStartOffset + currentTokenStart);
                break;

            // Do nothing if everything was okay.
            case Token.NULL:
                addNullToken();
                break;

            // All other token types don't continue to the next line...
            default:
                addToken(text, currentTokenStart, end - 1, currentTokenType, newStartOffset + currentTokenStart);
                addNullToken();

        }

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

    }
}

The only problem with this is that existing syntax highlighting (like block comments) gets lost.