SQInteger SQLexer::ReadString(SQInteger ndelim,bool verbatim)
{
INIT_TEMP_STRING();
NEXT();
if(IS_EOB()) return -1;
for(;;) {
while(CUR_CHAR != ndelim) {
switch(CUR_CHAR) {
case SQUIRREL_EOB:
Error(_SC("unfinished string"));
return -1;
case _SC('\n'):
if(!verbatim) Error(_SC("newline in a constant"));
APPEND_CHAR(CUR_CHAR); NEXT();
_currentline++;
break;
case _SC('\\'):
if(verbatim) {
APPEND_CHAR('\\'); NEXT();
}
else {
NEXT();
switch(CUR_CHAR) {
case _SC('x'): NEXT(); {
if(!isxdigit(CUR_CHAR)) Error(_SC("hexadecimal number expected"));
const SQInteger maxdigits = 4;
SQChar temp[maxdigits+1];
SQInteger n = 0;
while(isxdigit(CUR_CHAR) && n < maxdigits) {
temp[n] = CUR_CHAR;
n++;
NEXT();
}
temp[n] = 0;
SQChar *sTemp;
APPEND_CHAR((SQChar)scstrtoul(temp,&sTemp,16));
}
break;
case _SC('t'): APPEND_CHAR(_SC('\t')); NEXT(); break;
case _SC('a'): APPEND_CHAR(_SC('\a')); NEXT(); break;
case _SC('b'): APPEND_CHAR(_SC('\b')); NEXT(); break;
case _SC('n'): APPEND_CHAR(_SC('\n')); NEXT(); break;
case _SC('r'): APPEND_CHAR(_SC('\r')); NEXT(); break;
case _SC('v'): APPEND_CHAR(_SC('\v')); NEXT(); break;
case _SC('f'): APPEND_CHAR(_SC('\f')); NEXT(); break;
case _SC('0'): APPEND_CHAR(_SC('\0')); NEXT(); break;
case _SC('\\'): APPEND_CHAR(_SC('\\')); NEXT(); break;
case _SC('"'): APPEND_CHAR(_SC('"')); NEXT(); break;
case _SC('\''): APPEND_CHAR(_SC('\'')); NEXT(); break;
default:
Error(_SC("unrecognised escaper char"));
break;
}
}
break;
default:
APPEND_CHAR(CUR_CHAR);
NEXT();
}
}
NEXT();
if(verbatim && CUR_CHAR == '"') { //double quotation
APPEND_CHAR(CUR_CHAR);
NEXT();
}
else {
break;
}
}
TERMINATE_BUFFER();
SQInteger len = _longstr.size()-1;
if(ndelim == _SC('\'')) {
if(len == 0) Error(_SC("empty constant"));
if(len > 1) Error(_SC("constant too long"));
_nvalue = _longstr[0];
return TK_INTEGER;
}
_svalue = &_longstr[0];
return TK_STRING_LITERAL;
}
void SQLexer::LexLineComment()
{
do { NEXT(); } while (CUR_CHAR != _SC('\n') && (!IS_EOB()));
}
SQInteger SQLexer::Lex()
{
_lasttokenline = _currentline;
while(CUR_CHAR != SQUIRREL_EOB) {
#if !defined(_UNICODE) && defined(USESJIS)
if (iskanji) {
SQInteger c = CUR_CHAR;
NEXT();
RETURN_TOKEN(c);
}
iskanji = false;
#endif
switch(CUR_CHAR){
case _SC('\t'): case _SC('\r'): case _SC(' '): NEXT(); continue;
case _SC('\n'):
_currentline++;
_prevtoken=_curtoken;
_curtoken=_SC('\n');
NEXT();
_currentcolumn=1;
continue;
case _SC('/'):
NEXT();
switch(CUR_CHAR){
case _SC('*'):
NEXT();
LexBlockComment();
continue;
case _SC('/'):
do { NEXT(); } while (CUR_CHAR != _SC('\n') && (!IS_EOB()));
continue;
case _SC('='):
NEXT();
RETURN_TOKEN(TK_DIVEQ);
continue;
case _SC('>'):
NEXT();
RETURN_TOKEN(TK_ATTR_CLOSE);
continue;
default:
RETURN_TOKEN('/');
}
case _SC('='):
NEXT();
if (CUR_CHAR != _SC('=')){ RETURN_TOKEN('=') }
else { NEXT(); RETURN_TOKEN(TK_EQ); }
case _SC('<'):
NEXT();
if ( CUR_CHAR == _SC('=') ) { NEXT(); RETURN_TOKEN(TK_LE) }
else if ( CUR_CHAR == _SC('-') ) { NEXT(); RETURN_TOKEN(TK_NEWSLOT); }
else if ( CUR_CHAR == _SC('<') ) { NEXT(); RETURN_TOKEN(TK_SHIFTL); }
else if ( CUR_CHAR == _SC('/') ) { NEXT(); RETURN_TOKEN(TK_ATTR_OPEN); }
//else if ( CUR_CHAR == _SC('[') ) { NEXT(); ReadMultilineString(); RETURN_TOKEN(TK_STRING_LITERAL); }
else { RETURN_TOKEN('<') }
case _SC('>'):
NEXT();
if (CUR_CHAR == _SC('=')){ NEXT(); RETURN_TOKEN(TK_GE);}
else if(CUR_CHAR == _SC('>')){
NEXT();
if(CUR_CHAR == _SC('>')){
NEXT();
RETURN_TOKEN(TK_USHIFTR);
}
RETURN_TOKEN(TK_SHIFTR);
}
else { RETURN_TOKEN('>') }
case _SC('!'):
NEXT();
if (CUR_CHAR != _SC('=')){ RETURN_TOKEN('!')}
else { NEXT(); RETURN_TOKEN(TK_NE); }
case _SC('@'): {
SQInteger stype;
NEXT();
if(CUR_CHAR != _SC('"'))
Error(_SC("string expected"));
if((stype=ReadString('"',true))!=-1) {
RETURN_TOKEN(stype);
}
Error(_SC("error parsing the string"));
}
case _SC('"'):
case _SC('\''): {
SQInteger stype;
if((stype=ReadString(CUR_CHAR,false))!=-1){
RETURN_TOKEN(stype);
}
Error(_SC("error parsing the string"));
}
case _SC('{'): case _SC('}'): case _SC('('): case _SC(')'): case _SC('['): case _SC(']'):
case _SC(';'): case _SC(','): case _SC('?'): case _SC('^'): case _SC('~'):
{SQInteger ret = CUR_CHAR;
NEXT(); RETURN_TOKEN(ret); }
case _SC('.'):
NEXT();
if (CUR_CHAR != _SC('.')){ RETURN_TOKEN('.') }
NEXT();
if (CUR_CHAR != _SC('.')){ Error(_SC("invalid token '..'")); }
NEXT();
RETURN_TOKEN(TK_VARPARAMS);
case _SC('&'):
NEXT();
if (CUR_CHAR != _SC('&')){ RETURN_TOKEN('&') }
else { NEXT(); RETURN_TOKEN(TK_AND); }
case _SC('|'):
NEXT();
if (CUR_CHAR != _SC('|')){ RETURN_TOKEN('|') }
else { NEXT(); RETURN_TOKEN(TK_OR); }
case _SC(':'):
NEXT();
if (CUR_CHAR != _SC(':')){ RETURN_TOKEN(':') }
else { NEXT(); RETURN_TOKEN(TK_DOUBLE_COLON); }
case _SC('*'):
NEXT();
if (CUR_CHAR == _SC('=')){ NEXT(); RETURN_TOKEN(TK_MULEQ);}
else RETURN_TOKEN('*');
case _SC('%'):
NEXT();
if (CUR_CHAR == _SC('=')){ NEXT(); RETURN_TOKEN(TK_MODEQ);}
else RETURN_TOKEN('%');
case _SC('-'):
NEXT();
if (CUR_CHAR == _SC('=')){ NEXT(); RETURN_TOKEN(TK_MINUSEQ);}
else if (CUR_CHAR == _SC('-')){ NEXT(); RETURN_TOKEN(TK_MINUSMINUS);}
else RETURN_TOKEN('-');
case _SC('+'):
NEXT();
if (CUR_CHAR == _SC('=')){ NEXT(); RETURN_TOKEN(TK_PLUSEQ);}
else if (CUR_CHAR == _SC('+')){ NEXT(); RETURN_TOKEN(TK_PLUSPLUS);}
else RETURN_TOKEN('+');
case SQUIRREL_EOB:
return 0;
default:{
if (scisdigit(CUR_CHAR)) {
SQInteger ret = ReadNumber();
RETURN_TOKEN(ret);
}
else if (scisalpha(CUR_CHAR) || CUR_CHAR == _SC('_')) {
SQInteger t = ReadID();
RETURN_TOKEN(t);
}
else {
SQInteger c = CUR_CHAR;
if (sciscntrl((int)c)) Error(_SC("unexpected character(control)"));
#if !defined(_UNICODE) && defined(USESJIS)
iskanji = iskanji1(c);
#endif
NEXT();
RETURN_TOKEN(c);
}
RETURN_TOKEN(0);
}
}
