@Override
public Handle range(GrammarAST a, GrammarAST b) {
ATNState left = newState(a);
ATNState right = newState(b);
int t1 = CharSupport.getCharValueFromGrammarCharLiteral(a.getText());
int t2 = CharSupport.getCharValueFromGrammarCharLiteral(b.getText());
left.addTransition(new RangeTransition(right, t1, t2));
a.atnState = left;
b.atnState = left;
return new Handle(left, right);
}
/**
* Given a token type, get a meaningful name for it such as the ID or string literal. If this is a
* lexer and the ttype is in the char vocabulary, compute an ANTLR-valid (possibly escaped) char
* literal.
*/
public String getTokenDisplayName(int ttype) {
// inside any target's char range and is lexer grammar?
if (isLexer() && ttype >= Lexer.MIN_CHAR_VALUE && ttype <= Lexer.MAX_CHAR_VALUE) {
return CharSupport.getANTLRCharLiteralForChar(ttype);
}
if (ttype == Token.EOF) {
return "EOF";
}
if (ttype == Token.INVALID_TYPE) {
return INVALID_TOKEN_NAME;
}
if (ttype >= 0
&& ttype < typeToStringLiteralList.size()
&& typeToStringLiteralList.get(ttype) != null) {
return typeToStringLiteralList.get(ttype);
}
if (ttype >= 0 && ttype < typeToTokenList.size() && typeToTokenList.get(ttype) != null) {
return typeToTokenList.get(ttype);
}
return String.valueOf(ttype);
}
public IntervalSet getSetFromCharSetLiteral(GrammarAST charSetAST) {
String chars = charSetAST.getText();
chars = chars.substring(1, chars.length() - 1);
String cset = '"' + chars + '"';
IntervalSet set = new IntervalSet();
// unescape all valid escape char like \n, leaving escaped dashes as '\-'
// so we can avoid seeing them as '-' range ops.
chars = CharSupport.getStringFromGrammarStringLiteral(cset);
// now make x-y become set of char
int n = chars.length();
for (int i = 0; i < n; i++) {
int c = chars.charAt(i);
if (c == '\\' && (i + 1) < n && chars.charAt(i + 1) == '-') { // \-
set.add('-');
i++;
} else if ((i + 2) < n && chars.charAt(i + 1) == '-') { // range x-y
int x = c;
int y = chars.charAt(i + 2);
if (x <= y) set.add(x, y);
i += 2;
} else {
set.add(c);
}
}
return set;
}
@Override
public Handle lexerCallCommand(GrammarAST ID, GrammarAST arg) {
LexerAction lexerAction = createLexerAction(ID, arg);
if (lexerAction != null) {
return action(ID, lexerAction);
}
// fall back to standard action generation for the command
ST cmdST =
codegenTemplates.getInstanceOf("Lexer" + CharSupport.capitalize(ID.getText()) + "Command");
if (cmdST == null) {
g.tool.errMgr.grammarError(
ErrorType.INVALID_LEXER_COMMAND, g.fileName, ID.token, ID.getText());
return epsilon(ID);
}
if (cmdST.impl.formalArguments == null || !cmdST.impl.formalArguments.containsKey("arg")) {
g.tool.errMgr.grammarError(
ErrorType.UNWANTED_LEXER_COMMAND_ARGUMENT, g.fileName, ID.token, ID.getText());
return epsilon(ID);
}
cmdST.add("arg", arg.getText());
cmdST.add("grammar", arg.g);
return action(cmdST.render());
}
protected int getTokenType(@NotNull GrammarAST atom) {
int ttype;
if (g.isLexer()) {
ttype = CharSupport.getCharValueFromGrammarCharLiteral(atom.getText());
} else {
ttype = g.getTokenType(atom.getText());
}
return ttype;
}
@Override
public Handle set(GrammarAST associatedAST, List<GrammarAST> alts, boolean invert) {
ATNState left = newState(associatedAST);
ATNState right = newState(associatedAST);
IntervalSet set = new IntervalSet();
for (GrammarAST t : alts) {
if (t.getType() == ANTLRParser.RANGE) {
int a = CharSupport.getCharValueFromGrammarCharLiteral(t.getChild(0).getText());
int b = CharSupport.getCharValueFromGrammarCharLiteral(t.getChild(1).getText());
set.add(a, b);
} else if (t.getType() == ANTLRParser.LEXER_CHAR_SET) {
set.addAll(getSetFromCharSetLiteral(t));
} else if (t.getType() == ANTLRParser.STRING_LITERAL) {
int c = CharSupport.getCharValueFromGrammarCharLiteral(t.getText());
if (c != -1) {
set.add(c);
} else {
g.tool.errMgr.grammarError(
ErrorType.INVALID_LITERAL_IN_LEXER_SET, g.fileName, t.getToken(), t.getText());
}
} else if (t.getType() == ANTLRParser.TOKEN_REF) {
g.tool.errMgr.grammarError(
ErrorType.UNSUPPORTED_REFERENCE_IN_LEXER_SET, g.fileName, t.getToken(), t.getText());
}
}
if (invert) {
left.addTransition(new NotSetTransition(right, set));
} else {
Transition transition;
if (set.getIntervals().size() == 1) {
Interval interval = set.getIntervals().get(0);
transition = new RangeTransition(right, interval.a, interval.b);
} else {
transition = new SetTransition(right, set);
}
left.addTransition(transition);
}
associatedAST.atnState = left;
return new Handle(left, right);
}
/**
* For a lexer, a string is a sequence of char to match. That is, "fog" is treated as 'f' 'o' 'g'
* not as a single transition in the DFA. Machine== o-'f'->o-'o'->o-'g'->o and has n+1
* states for n characters.
*/
@Override
public Handle stringLiteral(TerminalAST stringLiteralAST) {
String chars = stringLiteralAST.getText();
chars = CharSupport.getStringFromGrammarStringLiteral(chars);
int n = chars.length();
ATNState left = newState(stringLiteralAST);
ATNState prev = left;
ATNState right = null;
for (int i = 0; i < n; i++) {
right = newState(stringLiteralAST);
prev.addTransition(new AtomTransition(right, chars.charAt(i)));
prev = right;
}
stringLiteralAST.atnState = left;
return new Handle(left, right);
}
/**
* Given a token type, get a meaningful name for it such as the ID or string literal. If this is a
* lexer and the ttype is in the char vocabulary, compute an ANTLR-valid (possibly escaped) char
* literal.
*/
public String getTokenDisplayName(int ttype) {
String tokenName = null;
// inside any target's char range and is lexer grammar?
if (isLexer() && ttype >= Lexer.MIN_CHAR_VALUE && ttype <= Lexer.MAX_CHAR_VALUE) {
return CharSupport.getANTLRCharLiteralForChar(ttype);
} else if (ttype == Token.EOF) {
tokenName = "EOF";
} else {
if (ttype < typeToTokenList.size()) {
tokenName = typeToTokenList.get(ttype);
if (tokenName != null
&& tokenName.startsWith(AUTO_GENERATED_TOKEN_NAME_PREFIX)
&& ttype < typeToStringLiteralList.size()
&& typeToStringLiteralList.get(ttype) != null) {
tokenName = typeToStringLiteralList.get(ttype);
}
} else {
tokenName = String.valueOf(ttype);
}
}
// tool.log("grammar", "getTokenDisplayName ttype="+ttype+", name="+tokenName);
return tokenName;
}