Fix bobbylight#212: Add yaml syntax highlighting

Author: bobbylight

src/main/java/org/fife/ui/rsyntaxtextarea/DefaultTokenMakerFactory.java

@@ -75,6 +75,7 @@ protected void initTokenMakerMap() {
 		putMapping(SYNTAX_STYLE_VISUAL_BASIC,	pkg + "VisualBasicTokenMaker");
 		putMapping(SYNTAX_STYLE_WINDOWS_BATCH,	pkg + "WindowsBatchTokenMaker");
 		putMapping(SYNTAX_STYLE_XML,			pkg + "XMLTokenMaker");
+		putMapping(SYNTAX_STYLE_YAML,			pkg + "YamlTokenMaker");
 
 	}
 

src/main/java/org/fife/ui/rsyntaxtextarea/SyntaxConstants.java

@@ -305,4 +305,10 @@ public interface SyntaxConstants {
 	String SYNTAX_STYLE_XML			= "text/xml";
 
 
+	/**
+	 * Syntax style for highlighting YAML.
+	 */
+	String SYNTAX_STYLE_YAML		= "text/yaml";
+
+
 }

src/main/java/org/fife/ui/rsyntaxtextarea/modes/YamlTokenMaker.flex

@@ -0,0 +1,236 @@
+/*
+ * 12/29/2016
+ *
+ * This library is distributed under a modified BSD license.  See the included
+ * RSyntaxTextArea.License.txt file for details.
+ */
+package org.fife.ui.rsyntaxtextarea.modes;
+
+import java.io.*;
+import javax.swing.text.Segment;
+
+import org.fife.ui.rsyntaxtextarea.*;
+
+
+/**
+ * This class splits up text into tokens representing a YAML file.<p>
+ *
+ * This implementation was created using
+ * <a href="http://www.jflex.de/">JFlex</a> 1.4.1; however, the generated file
+ * was modified for performance.  Memory allocation needs to be almost
+ * completely removed to be competitive with the handwritten lexers (subclasses
+ * of <code>AbstractTokenMaker</code>, so this class has been modified so that
+ * Strings are never allocated (via yytext()), and the scanner never has to
+ * worry about refilling its buffer (needlessly copying chars around).
+ * We can achieve this because RText always scans exactly 1 line of tokens at a
+ * time, and hands the scanner this line as an array of characters (a Segment
+ * really).  Since tokens contain pointers to char arrays instead of Strings
+ * holding their contents, there is no need for allocating new memory for
+ * Strings.<p>
+ *
+ * The actual algorithm generated for scanning has, of course, not been
+ * modified.<p>
+ *
+ * If you wish to regenerate this file yourself, keep in mind the following:
+ * <ul>
+ *   <li>The generated <code>YamlTokenMaker.java</code> file will
+ *       contain two definitions of both <code>zzRefill</code> and
+ *       <code>yyreset</code>.  You should hand-delete the second of each
+ *       definition (the ones generated by the lexer), as these generated
+ *       methods modify the input buffer, which we'll never have to do.
+ *   <li>You should also change the declaration/definition of zzBuffer to NOT
+ *       be initialized.  This is a needless memory allocation for us since we
+ *       will be pointing the array somewhere else anyway.
+ *   <li>You should NOT call <code>yylex()</code> on the generated scanner
+ *       directly; rather, you should use <code>getTokenList</code> as you would
+ *       with any other <code>TokenMaker</code> instance.
+ * </ul>
+ *
+ * @author Robert Futrell
+ * @version 0.4
+ *
+ */
+%%
+
+%public
+%class YamlTokenMaker
+%extends AbstractJFlexTokenMaker
+%unicode
+%type org.fife.ui.rsyntaxtextarea.Token
+
+
+%{
+
+
+	/**
+	 * Constructor.  This must be here because JFlex does not generate a
+	 * no-parameter constructor.
+	 */
+	public YamlTokenMaker() {
+		super();
+	}
+
+
+	/**
+	 * Adds the token specified to the current linked list of tokens.
+	 *
+	 * @param tokenType The token's type.
+	 */
+	private void addToken(int tokenType) {
+		addToken(zzStartRead, zzMarkedPos-1, tokenType);
+	}
+
+
+	/**
+	 * Adds the token specified to the current linked list of tokens.
+	 *
+	 * @param tokenType The token's type.
+	 */
+	private void addToken(int start, int end, int tokenType) {
+		int so = start + offsetShift;
+		addToken(zzBuffer, start,end, tokenType, so);
+	}
+
+
+	/**
+	 * Adds the token specified to the current linked list of tokens.
+	 *
+	 * @param array The character array.
+	 * @param start The starting offset in the array.
+	 * @param end The ending offset in the array.
+	 * @param tokenType The token's type.
+	 * @param startOffset The offset in the document at which this token
+	 *                    occurs.
+	 */
+	@Override
+	public void addToken(char[] array, int start, int end, int tokenType, int startOffset) {
+		super.addToken(array, start,end, tokenType, startOffset);
+		zzStartRead = zzMarkedPos;
+	}
+
+
+	@Override
+	public String[] getLineCommentStartAndEnd(int languageIndex) {
+		return new String[] { "#", null };
+	}
+
+
+	/**
+	 * 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.
+	 */
+	@Override
+	public Token getTokenList(Segment text, int initialTokenType, int startOffset) {
+
+		resetTokenList();
+		this.offsetShift = -text.offset + startOffset;
+
+		// Start off in the proper state.
+		int state = YYINITIAL;
+		s = text;
+		try {
+			yyreset(zzReader);
+			yybegin(state);
+			return yylex();
+		} catch (IOException ioe) {
+			ioe.printStackTrace();
+			return new TokenImpl();
+		}
+
+	}
+
+
+	/**
+	 * Refills the input buffer.
+	 *
+	 * @return      <code>true</code> if EOF was reached, otherwise
+	 *              <code>false</code>.
+	 */
+	private boolean zzRefill() {
+		return zzCurrentPos>=s.offset+s.count;
+	}
+
+
+	/**
+	 * Resets the scanner to read from a new input stream.
+	 * Does not close the old reader.
+	 *
+	 * All internal variables are reset, the old input stream 
+	 * <b>cannot</b> be reused (internal buffer is discarded and lost).
+	 * Lexical state is set to <tt>YY_INITIAL</tt>.
+	 *
+	 * @param reader   the new input stream 
+	 */
+	public final void yyreset(Reader reader) {
+		// 's' has been updated.
+		zzBuffer = s.array;
+		/*
+		 * We replaced the line below with the two below it because zzRefill
+		 * no longer "refills" the buffer (since the way we do it, it's always
+		 * "full" the first time through, since it points to the segment's
+		 * array).  So, we assign zzEndRead here.
+		 */
+		//zzStartRead = zzEndRead = s.offset;
+		zzStartRead = s.offset;
+		zzEndRead = zzStartRead + s.count - 1;
+		zzCurrentPos = zzMarkedPos = zzPushbackPos = s.offset;
+		zzLexicalState = YYINITIAL;
+		zzReader = reader;
+		zzAtBOL  = true;
+		zzAtEOF  = false;
+	}
+
+
+%}
+
+NonzeroDigit						= ([1-9])
+Digit							= ("0"|{NonzeroDigit})
+HexDigit							= ({Digit}|[A-Fa-f])
+OctalDigit						= ([0-7])
+AnyCharacterButApostropheOrBackSlash	= ([^\\'])
+AnyCharacterButDoubleQuoteOrBackSlash	= ([^\\\"\n])
+EscapedSourceCharacter				= ("u"{HexDigit}{HexDigit}{HexDigit}{HexDigit})
+Escape							= ("\\"(([btnfr\"'\\])|([0123]{OctalDigit}?{OctalDigit}?)|({OctalDigit}{OctalDigit}?)|{EscapedSourceCharacter}))
+
+Operator				= ([\-:?\.&\*!%@`])
+Separator				= ([\(\)\{\}\[\]])
+Separator2				= ([\;,.])
+Identifier				= ([^ \t\n\'\"#\-:?\.&\*!%@`\(\)\{\}\[\]\;,.]+)
+Whitespace				= ([ \t]+)
+Comment					= (#.*)
+CharLiteral				= ([\']({AnyCharacterButApostropheOrBackSlash}|{Escape})*[\'])
+UnclosedCharLiteral		= ([\'][^\'\n]*)
+ErrorCharLiteral		= ({UnclosedCharLiteral}[\'])
+StringLiteral			= ([\"]({AnyCharacterButDoubleQuoteOrBackSlash}|{Escape})*[\"])
+UnclosedStringLiteral	= ([\"]([\\].|[^\\\"])*[^\"]?)
+ErrorStringLiteral		= ({UnclosedStringLiteral}[\"])
+
+%%
+
+<YYINITIAL> {
+	{Identifier}		{ addToken(Token.IDENTIFIER); }
+	{Whitespace}		{ addToken(Token.WHITESPACE); }
+	{Separator}			{ addToken(Token.SEPARATOR); }
+	{Separator2}		{ addToken(Token.IDENTIFIER); }
+	{Operator}			{ addToken(Token.OPERATOR); }
+	
+	{Comment}			{ addToken(Token.COMMENT_EOL); }
+	
+	{CharLiteral}				{ addToken(Token.LITERAL_CHAR); }
+	{UnclosedCharLiteral}		{ addToken(Token.ERROR_CHAR); addNullToken(); return firstToken; }
+	{ErrorCharLiteral}			{ addToken(Token.ERROR_CHAR); }
+	{StringLiteral}				{ addToken(Token.LITERAL_STRING_DOUBLE_QUOTE); }
+	{UnclosedStringLiteral}		{ addToken(Token.ERROR_STRING_DOUBLE); addNullToken(); return firstToken; }
+	{ErrorStringLiteral}		{ addToken(Token.ERROR_STRING_DOUBLE); }
+
+	\n |
+	<<EOF>>				{ addNullToken(); return firstToken; }
+}