/**
* <strong>[11.8.3] Numeric Literals</strong>
*
* <pre>
* NumericLiteral ::
* DecimalLiteral
* BinaryIntegerLiteral
* OctalIntegerLiteral
* HexIntegerLiteral
* </pre>
*/
private Token readNumberLiteral(int c) {
if (c == '0') {
int d = input.get();
if (d == 'x' || d == 'X') {
number = readHexIntegerLiteral();
} else if (d == 'b' || d == 'B') {
number = readBinaryIntegerLiteral();
} else if (d == 'o' || d == 'O') {
number = readOctalIntegerLiteral();
} else if (isDecimalDigit(d)
&& parser.isEnabled(CompatibilityOption.LegacyOctalIntegerLiteral)) {
input.unget(d);
number = readLegacyOctalIntegerLiteral();
} else {
input.unget(d);
number = readDecimalLiteral(c);
}
} else {
number = readDecimalLiteral(c);
}
return Token.NUMBER;
}
/**
* <strong>[11.5] Token</strong>
*
* <pre>
* Token ::
* IdentifierName
* Punctuator
* NumericLiteral
* StringLiteral
* Template
* </pre>
*/
private Token scanToken() {
TokenStreamInput input = this.input;
int c;
for (; ; ) {
c = input.get();
if (c == TokenStreamInput.EOF) {
return Token.EOF;
} else if (c <= 0x20) {
if (c == 0x09 || c == 0x0B || c == 0x0C || c == 0x20) {
// skip over whitespace
continue;
}
if (c == '\n') {
incrementLineAndUpdate();
continue;
}
if (c == '\r') {
match('\n');
incrementLineAndUpdate();
continue;
}
} else if (c >= 0xA0) {
if (isWhitespace(c)) {
// skip over whitespace
continue;
}
if (isLineTerminator(c)) {
incrementLineAndUpdate();
continue;
}
}
break;
}
updateSourcePosition();
if (DEBUG) System.out.printf("scanToken() -> %c\n", (char) c);
switch (c) {
case '\'':
case '"':
return readString(c);
case '0':
case '1':
case '2':
case '3':
case '4':
case '5':
case '6':
case '7':
case '8':
case '9':
return readNumberLiteral(c);
case 'A':
case 'B':
case 'C':
case 'D':
case 'E':
case 'F':
case 'G':
case 'H':
case 'I':
case 'J':
case 'K':
case 'L':
case 'M':
case 'N':
case 'O':
case 'P':
case 'Q':
case 'R':
case 'S':
case 'T':
case 'U':
case 'V':
case 'W':
case 'X':
case 'Y':
case 'Z':
case 'a':
case 'b':
case 'c':
case 'd':
case 'e':
case 'f':
case 'g':
case 'h':
case 'i':
case 'j':
case 'k':
case 'l':
case 'm':
case 'n':
case 'o':
case 'p':
case 'q':
case 'r':
case 's':
case 't':
case 'u':
case 'v':
case 'w':
case 'x':
case 'y':
case 'z':
case '$':
case '_':
return readIdentifier(c);
case '{':
return Token.LC;
case '}':
return Token.RC;
case '(':
return Token.LP;
case ')':
return Token.RP;
case '[':
return Token.LB;
case ']':
return Token.RB;
case '.':
switch (input.peek(0)) {
case '0':
case '1':
case '2':
case '3':
case '4':
case '5':
case '6':
case '7':
case '8':
case '9':
return readNumberLiteral(c);
case '.':
if (input.peek(1) == '.') {
mustMatch('.');
mustMatch('.');
return Token.TRIPLE_DOT;
}
}
return Token.DOT;
case ';':
return Token.SEMI;
case ',':
return Token.COMMA;
case '~':
return Token.BITNOT;
case '?':
return Token.HOOK;
case ':':
return Token.COLON;
case '<':
if (match('<')) {
if (match('=')) {
return Token.ASSIGN_SHL;
} else {
return Token.SHL;
}
} else if (match('=')) {
return Token.LE;
} else if (input.peek(0) == '!'
&& input.peek(1) == '-'
&& input.peek(2) == '-'
&& parser.isEnabled(CompatibilityOption.HTMLComments)) {
// html start-comment
mustMatch('!');
mustMatch('-');
mustMatch('-');
readSingleComment();
return Token.COMMENT;
} else {
return Token.LT;
}
case '>':
if (match('>')) {
if (match('>')) {
if (match('=')) {
return Token.ASSIGN_USHR;
} else {
return Token.USHR;
}
} else if (match('=')) {
return Token.ASSIGN_SHR;
} else {
return Token.SHR;
}
} else if (match('=')) {
return Token.GE;
} else {
return Token.GT;
}
case '=':
if (match('=')) {
if (match('=')) {
return Token.SHEQ;
} else {
return Token.EQ;
}
} else if (match('>')) {
return Token.ARROW;
} else {
return Token.ASSIGN;
}
case '!':
if (match('=')) {
if (match('=')) {
return Token.SHNE;
} else {
return Token.NE;
}
} else {
return Token.NOT;
}
case '+':
if (match('+')) {
return Token.INC;
} else if (match('=')) {
return Token.ASSIGN_ADD;
} else {
return Token.ADD;
}
case '-':
if (match('-')) {
if (input.peek(0) == '>'
&& hasLineTerminator
&& parser.isEnabled(CompatibilityOption.HTMLComments)) {
// html end-comment at line start
mustMatch('>');
readSingleComment();
return Token.COMMENT;
}
return Token.DEC;
} else if (match('=')) {
return Token.ASSIGN_SUB;
} else {
return Token.SUB;
}
case '*':
if (match('=')) {
return Token.ASSIGN_MUL;
} else {
return Token.MUL;
}
case '%':
if (match('=')) {
return Token.ASSIGN_MOD;
} else {
return Token.MOD;
}
case '/':
if (match('=')) {
return Token.ASSIGN_DIV;
} else if (match('/')) {
readSingleComment();
return Token.COMMENT;
} else if (match('*')) {
readMultiComment();
return Token.COMMENT;
} else {
return Token.DIV;
}
case '&':
if (match('&')) {
return Token.AND;
} else if (match('=')) {
return Token.ASSIGN_BITAND;
} else {
return Token.BITAND;
}
case '|':
if (match('|')) {
return Token.OR;
} else if (match('=')) {
return Token.ASSIGN_BITOR;
} else {
return Token.BITOR;
}
case '^':
if (match('=')) {
return Token.ASSIGN_BITXOR;
} else {
return Token.BITXOR;
}
case '`':
return Token.TEMPLATE;
}
if (c == '\\') {
mustMatch('u');
c = readUnicode();
}
if (isIdentifierStart(c)) {
return readIdentifier(c);
}
return Token.ERROR;
}
/**
* <strong>[11.8.4] String Literals</strong>
*
* <pre>
* StringLiteral ::
* " DoubleStringCharacters<sub>opt</sub> "
* ' SingleStringCharacters<sub>opt</sub> '
* DoubleStringCharacters ::
* DoubleStringCharacter DoubleStringCharacters<sub>opt</sub>
* SingleStringCharacters ::
* SingleStringCharacter SingleStringCharacters<sub>opt</sub>
* DoubleStringCharacter ::
* SourceCharacter but not one of " or \ or LineTerminator
* \ EscapeSequence
* LineContinuation
* SingleStringCharacter ::
* SourceCharacter but not one of ' or \ or LineTerminator
* \ EscapeSequence
* LineContinuation
* LineContinuation ::
* \ LineTerminatorSequence
* EscapeSequence ::
* CharacterEscapeSequence
* 0 [lookahead ∉ DecimalDigit]
* HexEscapeSequence
* UnicodeEscapeSequence
* CharacterEscapeSequence ::
* SingleEscapeCharacter
* NonEscapeCharacter
* SingleEscapeCharacter :: one of
* ' " \ b f n r t v
* NonEscapeCharacter ::
* SourceCharacter but not one of EscapeCharacter or LineTerminator
* EscapeCharacter ::
* SingleEscapeCharacter
* DecimalDigit
* x
* u
* HexEscapeSequence ::
* x HexDigit HexDigit
* UnicodeEscapeSequence ::
* u HexDigit HexDigit HexDigit HexDigit
* u{ HexDigits }
* </pre>
*
* <strong>[B.1.2] String Literals</strong>
*
* <pre>
* EscapeSequence ::
* CharacterEscapeSequence
* OctalEscapeSequence
* HexEscapeSequence
* UnicodeEscapeSequence
* </pre>
*/
private Token readString(int quoteChar) {
assert quoteChar == '"' || quoteChar == '\'';
final int EOF = TokenStreamInput.EOF;
TokenStreamInput input = this.input;
int start = input.position();
StringBuffer buffer = this.buffer();
hasEscape = false;
for (; ; ) {
int c = input.get();
if (c == EOF) {
throw eofError(Messages.Key.UnterminatedStringLiteral);
}
if (c == quoteChar) {
buffer.add(input.range(start, input.position() - 1));
break;
}
if (isLineTerminator(c)) {
throw error(Messages.Key.UnterminatedStringLiteral);
}
if (c != '\\') {
continue;
}
buffer.add(input.range(start, input.position() - 1));
hasEscape = true;
c = input.get();
if (isLineTerminator(c)) {
// line continuation
if (c == '\r' && match('\n')) {
// \r\n sequence
}
incrementLine();
start = input.position();
continue;
}
// escape sequences
switch (c) {
case 'b':
c = '\b';
break;
case 'f':
c = '\f';
break;
case 'n':
c = '\n';
break;
case 'r':
c = '\r';
break;
case 't':
c = '\t';
break;
case 'v':
c = '\u000B';
break;
case 'x':
c = (hexDigit(input.get()) << 4) | hexDigit(input.get());
if (c < 0) {
throw error(Messages.Key.InvalidHexEscape);
}
break;
case 'u':
c = readUnicode();
break;
case '0':
if (isDecimalDigit(input.peek(0))) {
if (!parser.isEnabled(CompatibilityOption.OctalEscapeSequence)) {
throw error(Messages.Key.InvalidNULLEscape);
}
c = readOctalEscape(c);
} else {
c = '\0';
}
break;
case '1':
case '2':
case '3':
case '4':
case '5':
case '6':
case '7':
if (!parser.isEnabled(CompatibilityOption.OctalEscapeSequence)) {
throw error(Messages.Key.StrictModeOctalEscapeSequence);
}
c = readOctalEscape(c);
break;
case '8':
case '9':
// FIXME: spec bug - undefined behaviour for \8 and \9
if (!parser.isEnabled(CompatibilityOption.OctalEscapeSequence)) {
throw error(Messages.Key.StrictModeOctalEscapeSequence);
}
// fall-through
case '"':
case '\'':
case '\\':
default:
// fall-through
}
buffer.addCodepoint(c);
start = input.position();
}
return Token.STRING;
}