static int next_token(parser_ctx_t *ctx, void *lval)
{
do {
skip_spaces(ctx);
if(ctx->ptr == ctx->end)
return tEOF;
}while(skip_comment(ctx) || skip_html_comment(ctx));
if(isalphaW(*ctx->ptr)) {
int ret = check_keywords(ctx, lval);
if(ret)
return ret;
return parse_identifier(ctx, lval);
}
if(isdigitW(*ctx->ptr))
return parse_numeric_literal(ctx, lval);
switch(*ctx->ptr) {
case '{':
case '(':
case ')':
case '[':
case ']':
case ';':
case ',':
case '~':
case '?':
case ':':
return *ctx->ptr++;
case '}':
*(const WCHAR**)lval = ctx->ptr++;
return '}';
case '.':
if(++ctx->ptr < ctx->end && isdigitW(*ctx->ptr))
return parse_double_literal(ctx, 0, lval);
return '.';
case '<':
if(++ctx->ptr == ctx->end) {
*(int*)lval = EXPR_LESS;
return tRelOper;
}
switch(*ctx->ptr) {
case '=': /* <= */
ctx->ptr++;
*(int*)lval = EXPR_LESSEQ;
return tRelOper;
case '<': /* << */
if(++ctx->ptr < ctx->end && *ctx->ptr == '=') { /* <<= */
ctx->ptr++;
*(int*)lval = EXPR_ASSIGNLSHIFT;
return tAssignOper;
}
*(int*)lval = EXPR_LSHIFT;
return tShiftOper;
default: /* < */
*(int*)lval = EXPR_LESS;
return tRelOper;
}
case '>':
if(++ctx->ptr == ctx->end) { /* > */
*(int*)lval = EXPR_GREATER;
return tRelOper;
}
switch(*ctx->ptr) {
case '=': /* >= */
ctx->ptr++;
*(int*)lval = EXPR_GREATEREQ;
return tRelOper;
case '>': /* >> */
if(++ctx->ptr < ctx->end) {
if(*ctx->ptr == '=') { /* >>= */
ctx->ptr++;
*(int*)lval = EXPR_ASSIGNRSHIFT;
return tAssignOper;
}
if(*ctx->ptr == '>') { /* >>> */
if(++ctx->ptr < ctx->end && *ctx->ptr == '=') { /* >>>= */
ctx->ptr++;
*(int*)lval = EXPR_ASSIGNRRSHIFT;
return tAssignOper;
}
*(int*)lval = EXPR_RRSHIFT;
return tRelOper;
}
}
*(int*)lval = EXPR_RSHIFT;
return tShiftOper;
default:
*(int*)lval = EXPR_GREATER;
return tRelOper;
}
case '+':
ctx->ptr++;
if(ctx->ptr < ctx->end) {
switch(*ctx->ptr) {
case '+': /* ++ */
ctx->ptr++;
return tINC;
case '=': /* += */
ctx->ptr++;
*(int*)lval = EXPR_ASSIGNADD;
return tAssignOper;
}
}
return '+';
case '-':
ctx->ptr++;
if(ctx->ptr < ctx->end) {
switch(*ctx->ptr) {
case '-': /* -- or --> */
ctx->ptr++;
if(ctx->is_html && ctx->nl && ctx->ptr < ctx->end && *ctx->ptr == '>') {
ctx->ptr++;
return tHTMLCOMMENT;
}
return tDEC;
case '=': /* -= */
ctx->ptr++;
*(int*)lval = EXPR_ASSIGNSUB;
return tAssignOper;
}
}
return '-';
case '*':
if(++ctx->ptr < ctx->end && *ctx->ptr == '=') { /* *= */
ctx->ptr++;
*(int*)lval = EXPR_ASSIGNMUL;
return tAssignOper;
}
return '*';
case '%':
if(++ctx->ptr < ctx->end && *ctx->ptr == '=') { /* %= */
ctx->ptr++;
*(int*)lval = EXPR_ASSIGNMOD;
return tAssignOper;
}
return '%';
case '&':
if(++ctx->ptr < ctx->end) {
switch(*ctx->ptr) {
case '=': /* &= */
ctx->ptr++;
*(int*)lval = EXPR_ASSIGNAND;
return tAssignOper;
case '&': /* && */
ctx->ptr++;
return tANDAND;
}
}
return '&';
case '|':
if(++ctx->ptr < ctx->end) {
switch(*ctx->ptr) {
case '=': /* |= */
ctx->ptr++;
*(int*)lval = EXPR_ASSIGNOR;
return tAssignOper;
case '|': /* || */
ctx->ptr++;
return tOROR;
}
}
return '|';
case '^':
if(++ctx->ptr < ctx->end && *ctx->ptr == '=') { /* ^= */
ctx->ptr++;
*(int*)lval = EXPR_ASSIGNXOR;
return tAssignOper;
}
return '^';
case '!':
if(++ctx->ptr < ctx->end && *ctx->ptr == '=') { /* != */
if(++ctx->ptr < ctx->end && *ctx->ptr == '=') { /* !== */
ctx->ptr++;
*(int*)lval = EXPR_NOTEQEQ;
return tEqOper;
}
*(int*)lval = EXPR_NOTEQ;
return tEqOper;
}
return '!';
case '=':
if(++ctx->ptr < ctx->end && *ctx->ptr == '=') { /* == */
if(++ctx->ptr < ctx->end && *ctx->ptr == '=') { /* === */
ctx->ptr++;
*(int*)lval = EXPR_EQEQ;
return tEqOper;
}
*(int*)lval = EXPR_EQ;
return tEqOper;
}
return '=';
case '/':
if(++ctx->ptr < ctx->end) {
if(*ctx->ptr == '=') { /* /= */
ctx->ptr++;
*(int*)lval = EXPR_ASSIGNDIV;
return kDIVEQ;
}
}
return '/';
case '\"':
case '\'':
return parse_string_literal(ctx, lval, *ctx->ptr);
case '_':
case '$':
return parse_identifier(ctx, lval);
case '@':
return '@';
}
WARN("unexpected char '%c' %d\n", *ctx->ptr, *ctx->ptr);
return 0;
}
static BOOL is_identifier_first_char(WCHAR c)
{
return isalphaW(c) || c == '$' || c == '_' || c == '\\';
}
long int strtolW( const WCHAR *nptr, WCHAR **endptr, int base )
{
int negative;
register unsigned long int cutoff;
register unsigned int cutlim;
register unsigned long int i;
register const WCHAR *s;
register WCHAR c;
const WCHAR *save, *end;
int overflow;
if (base < 0 || base == 1 || base > 36) return 0;
save = s = nptr;
/* Skip white space. */
while (isspaceW (*s))
++s;
if (!*s) goto noconv;
/* Check for a sign. */
negative = 0;
if (*s == '-')
{
negative = 1;
++s;
}
else if (*s == '+')
++s;
/* Recognize number prefix and if BASE is zero, figure it out ourselves. */
if (*s == '0')
{
if ((base == 0 || base == 16) && toupperW(s[1]) == 'X')
{
s += 2;
base = 16;
}
else if (base == 0)
base = 8;
}
else if (base == 0)
base = 10;
/* Save the pointer so we can check later if anything happened. */
save = s;
end = NULL;
cutoff = ULONG_MAX / (unsigned long int) base;
cutlim = ULONG_MAX % (unsigned long int) base;
overflow = 0;
i = 0;
c = *s;
for (;c != '\0'; c = *++s)
{
if (s == end)
break;
if (c >= '0' && c <= '9')
c -= '0';
else if (isalphaW (c))
c = toupperW (c) - 'A' + 10;
else
break;
if ((int) c >= base)
break;
/* Check for overflow. */
if (i > cutoff || (i == cutoff && c > cutlim))
overflow = 1;
else
{
i *= (unsigned long int) base;
i += c;
}
}
/* Check if anything actually happened. */
if (s == save)
goto noconv;
/* Store in ENDPTR the address of one character
past the last character we converted. */
if (endptr != NULL)
*endptr = (WCHAR *)s;
/* Check for a value that is within the range of
`unsigned LONG int', but outside the range of `LONG int'. */
if (overflow == 0
&& i > (negative
? -((unsigned long int) (LONG_MIN + 1)) + 1
: (unsigned long int) LONG_MAX))
overflow = 1;
if (overflow)
{
return negative ? LONG_MIN : LONG_MAX;
}
/* Return the result of the appropriate sign. */
return negative ? -i : i;
noconv:
/* We must handle a special case here: the base is 0 or 16 and the
first two characters are '0' and 'x', but the rest are not
hexadecimal digits. This is no error case. We return 0 and
ENDPTR points to the `x`. */
if (endptr != NULL)
{
if (save - nptr >= 2 && toupperW (save[-1]) == 'X'
&& save[-2] == '0')
*endptr = (WCHAR *)&save[-1];
else
/* There was no number to convert. */
*endptr = (WCHAR *)nptr;
}
return 0L;
}
/*********************************************************************
* iswalpha (NTDLL.@)
*
* Checks if a unicode char wc is a letter
*
* RETURNS
* TRUE: The unicode char wc is a letter.
* FALSE: Otherwise
*/
INT __cdecl NTDLL_iswalpha( WCHAR wc )
{
return isalphaW(wc);
}
static int parse_next_token(void *lval, parser_ctx_t *ctx)
{
WCHAR c;
skip_spaces(ctx);
if(ctx->ptr == ctx->end)
return ctx->last_token == tNL ? tEOF : tNL;
c = *ctx->ptr;
if('0' <= c && c <= '9')
return parse_numeric_literal(ctx, lval);
if(isalphaW(c)) {
int ret = check_keywords(ctx);
if(!ret)
return parse_identifier(ctx, lval);
if(ret != tREM)
return ret;
c = '\'';
}
switch(c) {
case '\n':
ctx->ptr++;
return tNL;
case '\'':
return comment_line(ctx);
case ':':
case ')':
case ',':
case '=':
case '+':
case '*':
case '/':
case '^':
case '\\':
case '.':
case '_':
return *ctx->ptr++;
case '-':
if(ctx->is_html && ctx->ptr[1] == '-' && ctx->ptr[2] == '>')
return comment_line(ctx);
ctx->ptr++;
return '-';
case '(':
/* NOTE:
* We resolve empty brackets in lexer instead of parser to avoid complex conflicts
* in call statement special case |f()| without 'call' keyword
*/
ctx->ptr++;
skip_spaces(ctx);
if(*ctx->ptr == ')') {
ctx->ptr++;
return tEMPTYBRACKETS;
}
return '(';
case '"':
return parse_string_literal(ctx, lval);
case '&':
if(*++ctx->ptr == 'h' || *ctx->ptr == 'H')
return parse_hex_literal(ctx, lval);
return '&';
case '<':
switch(*++ctx->ptr) {
case '>':
ctx->ptr++;
return tNEQ;
case '=':
ctx->ptr++;
return tLTEQ;
case '!':
if(ctx->is_html && ctx->ptr[1] == '-' && ctx->ptr[2] == '-')
return comment_line(ctx);
}
return '<';
case '>':
if(*++ctx->ptr == '=') {
ctx->ptr++;
return tGTEQ;
}
return '>';
default:
FIXME("Unhandled char %c in %s\n", *ctx->ptr, debugstr_w(ctx->ptr));
}
return 0;
}
