org.fife.ui.rsyntaxtextarea.modes.CSharpTokenMaker.flex Maven / Gradle / Ivy
The newest version!
/* * 11/13/2004 * * CSharpTokenMaker.java - An object that can take a chunk of text and return * a linked list of tokens representing it in the C# 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.*; /** * A lexer for the C# programming language. * * 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 * offile will contain two * definitions of bothAbstractTokenMaker, 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 CSharpTokenMaker.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 = Token.NULL;
switch (initialTokenType) {
case Token.LITERAL_STRING_DOUBLE_QUOTE:
state = VERBATIMSTRING;
start = text.offset;
break;
case Token.COMMENT_MULTILINE:
state = DELIMITEDCOMMENT;
start = text.offset;
break;
default:
state = Token.NULL;
}
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.
* @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 java.io.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;
}
%}
/* C1.1 - Line terminators. */
NewlineCharacter = ([\n])
/* C.1.2 - Whitespace. */
Whitespace = ([\t ]+)
/* C.1.3 - Comments */
InputCharacter = ([^\n])
InputCharacters = ({InputCharacter}+)
DocumentationCommentStart = ("///")
SingleLineComment = ("//"([^/]{InputCharacters}?)?)
DelimitedCommentStart = ("/*")
DelimitedCommentEnd = ("*/")
/* C.1.5 - Unicode character escape sequences. */
UnicodeEscape1 = ("\\u"{HexDigit}{HexDigit}{HexDigit}{HexDigit})
UnicodeEscape2 = ("\\U"{HexDigit}{HexDigit}{HexDigit}{HexDigit}{HexDigit}{HexDigit}{HexDigit}{HexDigit})
UnicodeEscapeSequence = ({UnicodeEscape1}|{UnicodeEscape2})
/* C1.6 - Identifiers. */
LetterCharacter = ([A-Za-z]) /* Not accurate - many more Unicode letters, Unicode escapes */
/*
CombiningCharacter = ()
*/
DecimalDigitCharacter = ([0-9])
ConnectingCharacter = ([_\-])
/*
FormattingCharacter = ()
*/
/*
IdentifierPartCharacter = ({LetterCharacter}|{DecimalDigitCharacter}|{ConnectingCharacter}|{CombiningCharacter}|{FormattingCharacter})
*/
IdentifierPartCharacter = ({LetterCharacter}|{DecimalDigitCharacter}|{ConnectingCharacter})
IdentifierPartCharacters = ({IdentifierPartCharacter}+)
IdentifierStartCharacter = ({LetterCharacter}|[_])
IdentifierOrKeyword = ({IdentifierStartCharacter}{IdentifierPartCharacters}?)
Identifier = ("@"?{IdentifierOrKeyword})
/* NOTE: The two below aren't from the C# spec, but we add them so we can */
/* highlight errors. */
NonSeparator = (([^\t\f\r\n\ \(\)\{\}\[\]\;\,\.\=\>\<\!\~\?\:\+\-\*\/\&\|\^\%\"\']|"#"|"\\"))
ErrorIdentifier = ({NonSeparator}+)
/* C1.8 - Literals. */
BooleanLiteral = ("true"|"false")
DecimalDigit = ([0-9])
DecimalDigits = ({DecimalDigit}+)
IntegerTypeSuffix = (([uU][lL]?)|([lL][uU]?))
DecimalIntegerLiteral = ({DecimalDigits}{IntegerTypeSuffix}?)
HexDigit = ([0-9A-Fa-f])
HexDigits = ({HexDigit}+)
HexadecimalIntegerLiteral = ("0"[xX]{HexDigits}{IntegerTypeSuffix}?)
Sign = ([+\-])
ExponentPart = ([eE]{Sign}?{DecimalDigits})
RealTypeSuffix = ([fFdDmM])
RealHelper1 = ({DecimalDigits}"."{DecimalDigits}{ExponentPart}?{RealTypeSuffix}?)
RealHelper2 = ("."{DecimalDigits}{ExponentPart}?{RealTypeSuffix}?)
RealHelper3 = ({DecimalDigits}{ExponentPart}{RealTypeSuffix}?)
RealHelper4 = ({DecimalDigits}{RealTypeSuffix})
RealLiteral = ({RealHelper1}|{RealHelper2}|{RealHelper3}|{RealHelper4})
ErrorNumberFormat = (({DecimalIntegerLiteral}|{HexadecimalIntegerLiteral}|{RealLiteral}){NonSeparator}+)
SingleCharacter = ([^\'\\\n])
SimpleEscapeSequence = ("\\"[\'\"\\0abfnrtv])
HexadecimalEscapeSequence = ("\\x"{HexDigit}{HexDigit}?{HexDigit}?{HexDigit}?)
Character = ({SingleCharacter}|{SimpleEscapeSequence}|{HexadecimalEscapeSequence}|{UnicodeEscapeSequence})
UnclosedCharacterLiteral = ("'"{Character})
CharacterLiteral = ({UnclosedCharacterLiteral}"'")
ErrorUnclosedCharacterLiteral = ("'"[^\'\n]*)
ErrorCharacterLiteral = ("''"|{ErrorUnclosedCharacterLiteral}[\'])
QuoteEscapeSequence = ("\"\"")
SingleVerbatimStringLiteralCharacter = ([^\"])
VerbatimStringLiteralStart = ("@\"")
SingleRegularStringLiteralCharacter = ([^\"\\\n])
RegularStringLiteralCharacter = ({SingleRegularStringLiteralCharacter}|{SimpleEscapeSequence}|{HexadecimalEscapeSequence}|{UnicodeEscapeSequence})
RegularStringLiteralCharacters = ({RegularStringLiteralCharacter}+)
RegularStringLiteral = ([\"]{RegularStringLiteralCharacters}?[\"])
UnclosedRegularStringLiteral = ([\"]([\\].|[^\\\"])*[^\"]?)
ErrorRegularStringLiteral = ({UnclosedRegularStringLiteral}[\"])
/* C.1.9 - Operators and Punctuators. */
OOPHelper1 = (":")
OOPHelper2 = ("+"|"-"|"*"|"/"|"%"|"&"|"|"|"^"|"!"|"~")
OOPHelper3 = ("="|"<"|">"|"?"|"++"|"--"|"&&"|"||"|"<<"|">>")
OOPHelper4 = ("=="|"!="|"<="|">="|"+="|"-="|"*="|"/="|"%="|"&=")
OOPHelper5 = ("|="|"^="|"<<="|">>="|"->")
OperatorOrPunctuator = ({OOPHelper1}|{OOPHelper2}|{OOPHelper3}|{OOPHelper4}|{OOPHelper5})
/* NOTE: We distinguish between operators and separators (punctuators), but */
/* the C# spec doesn't, so the stuff below isn't in the spec. */
Separator = ([\{\}\[\]\(\)])
Separator2 = ([,;])
/* C.1.10 - Pre-processing Directives. */
/* NOTE: We don't do ALL of the PP stuff here as it's unnecessary */
/* for us to know the difference between declarations, diagnostics, */
/* regions, etc. */
ConditionalSymbol = ({IdentifierOrKeyword}) /* Not correct - excludes "true" and "false". */
PPNewLine = ({Whitespace}?{SingleLineComment}?{NewlineCharacter})
PPPrimaryExpression = ({IdentifierOrKeyword}|({Whitespace}?{PPExpression}{Whitespace}?))
PPUnaryExpression = ({PPPrimaryExpression}|("!"{Whitespace}?{PPUnaryExpression}))
PPEqualityExpression = ({PPUnaryExpression}|({Whitespace}?"=="{Whitespace}?{PPUnaryExpression})|({Whitespace}?"!="{Whitespace}?{PPUnaryExpression}))
PPAndExpression = ({PPEqualityExpression}|({Whitespace}?"&&"{Whitespace}?{PPEqualityExpression}))
PPOrExpression = ({PPAndExpression}|({Whitespace}?"||"{Whitespace}?{PPAndExpression}))
PPExpression = ({Whitespace}?{PPOrExpression}{Whitespace}?)
PPWord = ("define"|"undef"|"if"|"elif"|"else"|"endif"|"line"|"error"|"warning"|"region"|"endregion")
PPDirective = ({Whitespace}?"#"{Whitespace}?{PPWord}{InputCharacter}*)
/* URL matching, for comments (not in C# spec) */
URLGenDelim = ([:\/\?#\[\]@])
URLSubDelim = ([\!\$&'\(\)\*\+,;=])
URLUnreserved = ([A-Za-z_]|{DecimalDigitCharacter}|[\-\.\~])
URLCharacter = ({URLGenDelim}|{URLSubDelim}|{URLUnreserved}|[%])
URLCharacters = ({URLCharacter}*)
URLEndCharacter = ([\/\$]|[A-Za-z0-9])
URL = (((https?|f(tp|ile))"://"|"www.")({URLCharacters}{URLEndCharacter})?)
%state DELIMITEDCOMMENT
%state DOCUMENTCOMMENT
%state VERBATIMSTRING
%%