org.fife.ui.rsyntaxtextarea.modes.CPlusPlusTokenMaker.flex Maven / Gradle / Ivy
The newest version!
/* * 11/19/2004 * * CPlusPlusTokenMaker.java - An object that can take a chunk of text and * return a linked list of tokens representing it in C++. * * 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 parser 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 CPlusPlusTokenMaker.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.COMMENT_MULTILINE:
state = MLC;
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.
*/
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;
}
%}
Letter = [A-Za-z]
LetterOrUnderscore = ({Letter}|"_")
Digit = [0-9]
HexDigit = {Digit}|[A-Fa-f]
OctalDigit = [0-7]
Exponent = [eE][+-]?{Digit}+
PreprocessorWord = define|elif|else|endif|error|if|ifdef|ifndef|include|line|pragma|undef
Trigraph = ("??="|"??("|"??)"|"??/"|"??'"|"??<"|"??>"|"??!"|"??-")
OctEscape1 = ([\\]{OctalDigit})
OctEscape2 = ([\\]{OctalDigit}{OctalDigit})
OctEscape3 = ([\\][0-3]{OctalDigit}{OctalDigit})
OctEscape = ({OctEscape1}|{OctEscape2}|{OctEscape3})
HexEscape = ([\\][xX]{HexDigit}{HexDigit})
AnyChrChr = ([^\'\n\\])
Escape = ([\\]([abfnrtv\'\"\?\\0e]))
UnclosedCharLiteral = ([\']({Escape}|{OctEscape}|{HexEscape}|{Trigraph}|{AnyChrChr}))
CharLiteral = ({UnclosedCharLiteral}[\'])
ErrorUnclosedCharLiteral = ([\'][^\'\n]*)
ErrorCharLiteral = (([\'][\'])|{ErrorUnclosedCharLiteral}[\'])
AnyStrChr = ([^\"\n\\])
FalseTrigraph = (("?"(("?")*)[^\=\(\)\/\'\<\>\!\-\\\?\"\n])|("?"[\=\(\)\/\'\<\>\!\-]))
StringLiteral = ([\"]((((("?")*)({Escape}|{OctEscape}|{HexEscape}|{Trigraph}))|{FalseTrigraph}|{AnyStrChr})*)(("?")*)[\"])
UnclosedStringLiteral = ([\"]([\\].|[^\\\"])*[^\"]?)
ErrorStringLiteral = ({UnclosedStringLiteral}[\"])
LineTerminator = \n
WhiteSpace = [ \t\f]
MLCBegin = "/*"
MLCEnd = "*/"
LineCommentBegin = "//"
NonFloatSuffix = (([uU][lL]?)|([lL][uU]?))
IntegerLiteral = ({Digit}+{Exponent}?{NonFloatSuffix}?)
HexLiteral = ("0"[xX]{HexDigit}+{NonFloatSuffix}?)
FloatLiteral = ((({Digit}*[\.]{Digit}+)|({Digit}+[\.]{Digit}*)){Exponent}?[fFlL]?)
ErrorNumberFormat = (({IntegerLiteral}|{HexLiteral}|{FloatLiteral}){NonSeparator}+)
NonSeparator = ([^\t\f\r\n\ \(\)\{\}\[\]\;\,\.\=\>\<\!\~\?\:\+\-\*\/\&\|\^\%\"\']|"#")
Identifier = ({LetterOrUnderscore}({LetterOrUnderscore}|{Digit}|[$])*)
ErrorIdentifier = ({NonSeparator}+)
URLGenDelim = ([:\/\?#\[\]@])
URLSubDelim = ([\!\$&'\(\)\*\+,;=])
URLUnreserved = ({LetterOrUnderscore}|{Digit}|[\-\.\~])
URLCharacter = ({URLGenDelim}|{URLSubDelim}|{URLUnreserved}|[%])
URLCharacters = ({URLCharacter}*)
URLEndCharacter = ([\/\$]|{Letter}|{Digit})
URL = (((https?|f(tp|ile))"://"|"www.")({URLCharacters}{URLEndCharacter})?)
%state MLC
%state EOL_COMMENT
%%