org.fife.ui.rsyntaxtextarea.modes.ScalaTokenMaker.flex Maven / Gradle / Ivy
The newest version!
/* * 8/19/2009 * * ScalaTokenMaker.java - Scanner for the Scala programming language. * * 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 Scala programming language.file will contain two * definitions of both* * 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 ScalaTokenMaker.java
zzRefillandyyreset. * 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. *
yylex() on the generated scanner
* directly; rather, you should use getTokenList as you would
* with any other TokenMaker instance.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;
switch (initialTokenType) {
case Token.LITERAL_STRING_DOUBLE_QUOTE:
state = MULTILINE_STRING_DOUBLE;
break;
case Token.COMMENT_MULTILINE:
state = MLC;
break;
default:
state = YYINITIAL;
}
s = text;
start = text.offset;
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.
* @exception IOException if any I/O-Error occurs.
*/
private boolean zzRefill() throws java.io.IOException {
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) throws IOException {
// '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;
}
%}
/***** BEGIN SCALA-SPECIFIC CHANGES *********/
Upper = ([A-Z\$\_]) /* Plus Unicode category Lu */
Lower = ([a-z]) /* Plus Unicode category Ll */
Letter = ({Upper}|{Lower}) /*Plus Unicode categories Lo, Lt, Nl */
Digit = ([0-9])
OpChar = ([^A-Z\$\_a-z0-9\(\[\]\)\. \t\f])
Op = ({OpChar}+)
IdRest = (({Letter}|{Digit})*([\_]{Op})?)
VarId = ({Lower}{IdRest})
PlainId = ({Upper}{IdRest}|{VarId}) /*|{Op})*/
Id = ({PlainId}) /*({PlainId}|[\']{StringLit}[\'])*/
IntegerLiteral = ({Digit}+[Ll]?)
HexDigit = ({Digit}|[A-Fa-f])
HexLiteral = ("0x"{HexDigit}+)
ExponentPart = ([Ee][+\-]?{Digit}+)
FloatType = ([FfDd])
FloatingPointLiteral = ({Digit}+[\.]{Digit}*{ExponentPart}?{FloatType}? |
[\.]{Digit}+{ExponentPart}?{FloatType}? |
{Digit}+{ExponentPart}{FloatType}? |
{Digit}+{ExponentPart}?{FloatType})
UnclosedCharLiteral = ([\']([\\].|[^\\\'])*[^\']?)
CharLiteral = ({UnclosedCharLiteral}[\'])
UnclosedStringLiteral = ([\"]([\\].|[^\\\"])*[^\"]?)
StringLiteral = ({UnclosedStringLiteral}[\"])
UnclosedBacktickLiteral = ([\`][^\`]+)
BacktickLiteral = ({UnclosedBacktickLiteral}[\`])
/* TODO: Multiline strings */
MLCBegin = ("/*")
MLCEnd = ("*/")
LineCommentBegin = ("//")
/***** END SCALA-SPECIFIC CHANGES *********/
Whitespace = ([ \t\f]+)
LineTerminator = ([\n])
Separator = ([\(\)\{\}\[\]])
URLGenDelim = ([:\/\?#\[\]@])
URLSubDelim = ([\!\$&'\(\)\*\+,;=])
URLUnreserved = ({Letter}|[\_]|{Digit}|[\-\.\~])
URLCharacter = ({URLGenDelim}|{URLSubDelim}|{URLUnreserved}|[%])
URLCharacters = ({URLCharacter}*)
URLEndCharacter = ([\/\$]|{Letter}|{Digit})
URL = (((https?|f(tp|ile))"://"|"www.")({URLCharacters}{URLEndCharacter})?)
%state MULTILINE_STRING_DOUBLE
%state MLC
%state EOL_COMMENT
%%