org.fife.ui.rsyntaxtextarea.modes.JsonTokenMaker.flex Maven / Gradle / Ivy

Go to download
Show more of this group Show more artifacts with this name
Show all versions of ui4j-ide Show documentation
Web Automation for Java
The newest version!
/*
 * 12/23/2012
 *
 * JsonTokenMaker.java - Scanner for the JSON.
 * 
 * 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.*;


/**
 * Scanner for the JSON.
 *
 * This implementation was created using
 * JFlex 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 AbstractTokenMaker, 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.

 *
 * The actual algorithm generated for scanning has, of course, not been
 * modified.

 *
 * If you wish to regenerate this file yourself, keep in mind the following:
 * 
 *   The generated JsonTokenMaker.java file will contain two
 *       definitions of both zzRefill and yyreset.
 *       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.
 *   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.
 *   You should NOT call yylex() on the generated scanner
 *       directly; rather, you should use getTokenList as you would
 *       with any other TokenMaker instance.
 * 
 *
 * @author Robert Futrell
 * @version 0.5
 *
 */
%%

%public
%class JsonTokenMaker
%extends AbstractJFlexTokenMaker
%unicode
%type org.fife.ui.rsyntaxtextarea.Token


%{


	/**
	 * Constructor.  This must be here because JFlex does not generate a
	 * no-parameter constructor.
	 */
	public JsonTokenMaker() {
	}


	/**
	 * 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, false);
	}


	/**
	 * 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.
	 * @param hyperlink Whether this token is a hyperlink.
	 */
	@Override
	public void addToken(char[] array, int start, int end, int tokenType,
						int startOffset, boolean hyperlink) {
		super.addToken(array, start,end, tokenType, startOffset, hyperlink);
		zzStartRead = zzMarkedPos;
	}


	/**
	 * Returns true always as C-style languages use curly braces
	 * to denote code blocks.
	 *
	 * @return true always.
	 */
	public boolean getCurlyBracesDenoteCodeBlocks() {
		return true;
	}


	public boolean getMarkOccurrencesOfTokenType(int type) {
		return false;
	}


	public boolean getShouldIndentNextLineAfter(Token t) {
		if (t!=null && t.length()==1) {
			char ch = t.charAt(0);
			return ch=='{' || ch=='[';
		}
		return false;
	}


	/**
	 * Returns the first token in the linked list of tokens generated
	 * from text.  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
	 *        text starts.
	 * @return The first Token in a linked list representing
	 *         the syntax highlighted text.
	 */
	public Token getTokenList(Segment text, int initialTokenType, int startOffset) {

		resetTokenList();
		this.offsetShift = -text.offset + startOffset;

		// Start off in the proper state.
		int state = YYINITIAL;
		start = text.offset;

		s = text;
		try {
			yyreset(zzReader);
			yybegin(state);
			return yylex();
		} catch (IOException ioe) {
			ioe.printStackTrace();
			return new TokenImpl();
		}

	}


	/**
	 * Refills the input buffer.
	 *
	 * @return      true if EOF was reached, otherwise
	 *              false.
	 */
	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 
	 * cannot be reused (internal buffer is discarded and lost).
	 * Lexical state is set to YY_INITIAL.
	 *
	 * @param reader   the new input stream 
	 */
	public final void yyreset(java.io.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;
	}


%}

Whitespace				= ([ \t\f]+)
Digit					= ([0-9])
HexDigit				= ({Digit}|[A-Fa-f])
IdentifierStart			= ([^\" \t\f\[\]\{\}\:,0-9\-])
IdentifierPart			= ({IdentifierStart}|{Digit}|[\-])
Identifier				= ({IdentifierStart}{IdentifierPart}*)

AnyCharacterButDoubleQuoteOrBackSlash	= ([^\\\"\n])
EscapedSourceCharacter	= ("u"{HexDigit}{HexDigit}{HexDigit}{HexDigit})
Escape					= ("\\"(([btnfr\"\\/])|{EscapedSourceCharacter}))
StringLiteral			= ([\"]({AnyCharacterButDoubleQuoteOrBackSlash}|{Escape})*[\"])
UnclosedStringLiteral	= ([\"]([\\].|[^\\\"])*[^\"]?)
ErrorStringLiteral		= ({UnclosedStringLiteral}[\"])

IntegerLiteral			= ("-"?{Digit}+)
FloatLiteral			= ({IntegerLiteral}("."({Digit}+))?([eE][+\-]?{Digit}+)?)

BooleanLiteral			= ("true"|"false")

Separator				= ([\{\}\[\]])
Separator2				= ([\:,])

%%

 {

	"null"	 					{ addToken(Token.RESERVED_WORD); }
	{BooleanLiteral}			{ addToken(Token.LITERAL_BOOLEAN); }
	{Identifier}				{ addToken(Token.IDENTIFIER); }
	{Whitespace}				{ addToken(Token.WHITESPACE); }
	{StringLiteral}				{ addToken(Token.LITERAL_STRING_DOUBLE_QUOTE); }
	{UnclosedStringLiteral}		{ addToken(Token.ERROR_STRING_DOUBLE); addNullToken(); return firstToken; }
	{ErrorStringLiteral}		{ addToken(Token.ERROR_STRING_DOUBLE); }
	{Separator}					{ addToken(Token.SEPARATOR); }
	{Separator2}				{ addToken(Token.IDENTIFIER); }
	{IntegerLiteral}			{ addToken(Token.LITERAL_NUMBER_DECIMAL_INT); }
	{FloatLiteral}				{ addToken(Token.LITERAL_NUMBER_FLOAT); }
	\n |
	<>						{ addNullToken(); return firstToken; }

	/* Catch any other (unhandled) characters and flag them as identifiers. */
	.							{ addToken(Token.IDENTIFIER); }

}