2 * Copyright 2008 Jacek Caban for CodeWeavers
4 * This library is free software; you can redistribute it and/or
5 * modify it under the terms of the GNU Lesser General Public
6 * License as published by the Free Software Foundation; either
7 * version 2.1 of the License, or (at your option) any later version.
9 * This library is distributed in the hope that it will be useful,
10 * but WITHOUT ANY WARRANTY; without even the implied warranty of
11 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
12 * Lesser General Public License for more details.
14 * You should have received a copy of the GNU Lesser General Public
15 * License along with this library; if not, write to the Free Software
16 * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301, USA
26 #include "parser.tab.h"
28 #include "wine/debug.h"
29 #include "wine/unicode.h"
31 WINE_DEFAULT_DEBUG_CHANNEL(jscript
);
33 static const WCHAR breakW
[] = {'b','r','e','a','k',0};
34 static const WCHAR caseW
[] = {'c','a','s','e',0};
35 static const WCHAR catchW
[] = {'c','a','t','c','h',0};
36 static const WCHAR continueW
[] = {'c','o','n','t','i','n','u','e',0};
37 static const WCHAR defaultW
[] = {'d','e','f','a','u','l','t',0};
38 static const WCHAR deleteW
[] = {'d','e','l','e','t','e',0};
39 static const WCHAR doW
[] = {'d','o',0};
40 static const WCHAR elseW
[] = {'e','l','s','e',0};
41 static const WCHAR falseW
[] = {'f','a','l','s','e',0};
42 static const WCHAR finallyW
[] = {'f','i','n','a','l','l','y',0};
43 static const WCHAR forW
[] = {'f','o','r',0};
44 static const WCHAR functionW
[] = {'f','u','n','c','t','i','o','n',0};
45 static const WCHAR ifW
[] = {'i','f',0};
46 static const WCHAR inW
[] = {'i','n',0};
47 static const WCHAR instanceofW
[] = {'i','n','s','t','a','n','c','e','o','f',0};
48 static const WCHAR newW
[] = {'n','e','w',0};
49 static const WCHAR nullW
[] = {'n','u','l','l',0};
50 static const WCHAR returnW
[] = {'r','e','t','u','r','n',0};
51 static const WCHAR switchW
[] = {'s','w','i','t','c','h',0};
52 static const WCHAR thisW
[] = {'t','h','i','s',0};
53 static const WCHAR throwW
[] = {'t','h','r','o','w',0};
54 static const WCHAR trueW
[] = {'t','r','u','e',0};
55 static const WCHAR tryW
[] = {'t','r','y',0};
56 static const WCHAR typeofW
[] = {'t','y','p','e','o','f',0};
57 static const WCHAR undefinedW
[] = {'u','n','d','e','f','i','n','e','d',0};
58 static const WCHAR varW
[] = {'v','a','r',0};
59 static const WCHAR voidW
[] = {'v','o','i','d',0};
60 static const WCHAR whileW
[] = {'w','h','i','l','e',0};
61 static const WCHAR withW
[] = {'w','i','t','h',0};
70 {continueW
, kCONTINUE
},
78 {functionW
, kFUNCTION
},
81 {instanceofW
, kINSTANCEOF
},
91 {undefinedW
, kUNDEFINED
},
98 static int lex_error(parser_ctx_t
*ctx
, HRESULT hres
)
104 static int check_keyword(parser_ctx_t
*ctx
, const WCHAR
*word
)
106 const WCHAR
*p1
= ctx
->ptr
;
107 const WCHAR
*p2
= word
;
109 while(p1
< ctx
->end
&& *p2
) {
116 if(*p2
|| (p1
< ctx
->end
&& isalnumW(*p1
)))
123 /* ECMA-262 3rd Edition 7.3 */
124 static BOOL
is_endline(WCHAR c
)
126 return c
== '\n' || c
== '\r' || c
== 0x2028 || c
== 0x2029;
129 static BOOL
is_identifier_char(WCHAR c
)
131 return isalnumW(c
) || c
== '$' || c
== '_' || c
== '\\';
134 static int hex_to_int(WCHAR c
)
136 if('0' <= c
&& c
<= '9')
139 if('a' <= c
&& c
<= 'f')
142 if('A' <= c
&& c
<= 'F')
148 static int check_keywords(parser_ctx_t
*ctx
)
150 int min
= 0, max
= sizeof(keywords
)/sizeof(keywords
[0])-1, r
, i
;
155 r
= check_keyword(ctx
, keywords
[i
].word
);
157 return keywords
[i
].token
;
168 static void skip_spaces(parser_ctx_t
*ctx
)
170 while(ctx
->ptr
< ctx
->end
&& isspaceW(*ctx
->ptr
)) {
171 if(is_endline(*ctx
->ptr
++))
176 static BOOL
skip_comment(parser_ctx_t
*ctx
)
178 if(ctx
->ptr
+1 >= ctx
->end
|| *ctx
->ptr
!= '/')
181 switch(ctx
->ptr
[1]) {
184 while(ctx
->ptr
+1 < ctx
->end
&& (ctx
->ptr
[0] != '*' || ctx
->ptr
[1] != '/'))
187 if(ctx
->ptr
[0] == '*' && ctx
->ptr
[1] == '/') {
190 WARN("unexpected end of file (missing end of comment)\n");
196 while(ctx
->ptr
< ctx
->end
&& !is_endline(*ctx
->ptr
))
206 static BOOL
unescape(WCHAR
*str
)
248 i
= hex_to_int(*++p
);
253 i
= hex_to_int(*++p
);
259 i
= hex_to_int(*++p
);
264 i
= hex_to_int(*++p
);
269 i
= hex_to_int(*++p
);
274 i
= hex_to_int(*++p
);
291 static int parse_identifier(parser_ctx_t
*ctx
, const WCHAR
**ret
)
293 const WCHAR
*ptr
= ctx
->ptr
++;
297 while(ctx
->ptr
< ctx
->end
&& is_identifier_char(*ctx
->ptr
))
302 *ret
= wstr
= parser_alloc(ctx
, (len
+1)*sizeof(WCHAR
));
303 memcpy(wstr
, ptr
, (len
+1)*sizeof(WCHAR
));
306 /* FIXME: unescape */
310 static int parse_string_literal(parser_ctx_t
*ctx
, const WCHAR
**ret
, WCHAR endch
)
312 const WCHAR
*ptr
= ++ctx
->ptr
;
316 while(ctx
->ptr
< ctx
->end
&& *ctx
->ptr
!= endch
) {
317 if(*ctx
->ptr
++ == '\\')
321 if(ctx
->ptr
== ctx
->end
) {
322 WARN("unexpected end of file\n");
323 return lex_error(ctx
, E_FAIL
);
328 *ret
= wstr
= parser_alloc(ctx
, (len
+1)*sizeof(WCHAR
));
329 memcpy(wstr
, ptr
, (len
+1)*sizeof(WCHAR
));
334 if(!unescape(wstr
)) {
335 WARN("unescape failed\n");
336 return lex_error(ctx
, E_FAIL
);
339 return tStringLiteral
;
342 static literal_t
*alloc_int_literal(parser_ctx_t
*ctx
, LONG l
)
344 literal_t
*ret
= parser_alloc(ctx
, sizeof(literal_t
));
352 static int parse_double_literal(parser_ctx_t
*ctx
, LONG int_part
, literal_t
**literal
)
356 if(ctx
->ptr
== ctx
->end
|| !isdigitW(*ctx
->ptr
)) {
357 ERR("No digit after point\n");
362 while(ctx
->ptr
< ctx
->end
&& isdigitW(*ctx
->ptr
))
363 d
+= (tmp
/= 10.0)*(*ctx
->ptr
++ - '0');
365 if(ctx
->ptr
< ctx
->end
&& (*ctx
->ptr
== 'e' || *ctx
->ptr
== 'E')) {
369 if(ctx
->ptr
< ctx
->end
) {
370 if(*ctx
->ptr
== '+') {
372 }else if(*ctx
->ptr
== '-') {
375 }else if(!isdigitW(*ctx
->ptr
)) {
376 WARN("Expected exponent part\n");
377 return lex_error(ctx
, E_FAIL
);
381 if(ctx
->ptr
== ctx
->end
) {
382 WARN("unexpected end of file\n");
383 return lex_error(ctx
, E_FAIL
);
386 while(ctx
->ptr
< ctx
->end
&& isdigitW(*ctx
->ptr
))
387 e
= e
*10 + *ctx
->ptr
++ - '0';
393 *literal
= parser_alloc(ctx
, sizeof(literal_t
));
394 (*literal
)->vt
= VT_R8
;
395 (*literal
)->u
.dval
= d
;
397 return tNumericLiteral
;
400 static int parse_numeric_literal(parser_ctx_t
*ctx
, literal_t
**literal
)
404 l
= *ctx
->ptr
++ - '0';
405 if(ctx
->ptr
== ctx
->end
) {
406 *literal
= alloc_int_literal(ctx
, l
);
407 return tNumericLiteral
;
411 if(*ctx
->ptr
== 'x' || *ctx
->ptr
== 'X') {
412 if(++ctx
->ptr
== ctx
->end
) {
413 ERR("unexpexted end of file\n");
417 while(ctx
->ptr
< ctx
->end
&& (d
= hex_to_int(*ctx
->ptr
)) != -1) {
422 if(ctx
->ptr
< ctx
->end
&& is_identifier_char(*ctx
->ptr
)) {
423 WARN("unexpected identifier char\n");
424 return lex_error(ctx
, E_FAIL
);
427 *literal
= alloc_int_literal(ctx
, l
);
428 return tNumericLiteral
;
431 if(isdigitW(*ctx
->ptr
) || is_identifier_char(*ctx
->ptr
)) {
432 WARN("wrong char after zero\n");
433 return lex_error(ctx
, E_FAIL
);
436 *literal
= alloc_int_literal(ctx
, 0);
439 while(ctx
->ptr
< ctx
->end
&& isdigitW(*ctx
->ptr
))
440 l
= l
*10 + *(ctx
->ptr
++)-'0';
442 if(ctx
->ptr
< ctx
->end
) {
443 if(*ctx
->ptr
== '.') {
445 return parse_double_literal(ctx
, l
, literal
);
448 if(is_identifier_char(*ctx
->ptr
)) {
449 WARN("unexpected identifier char\n");
450 return lex_error(ctx
, E_FAIL
);
454 *literal
= alloc_int_literal(ctx
, l
);
455 return tNumericLiteral
;
458 int parser_lex(void *lval
, parser_ctx_t
*ctx
)
466 if(ctx
->ptr
== ctx
->end
)
468 }while(skip_comment(ctx
));
470 if(isalphaW(*ctx
->ptr
)) {
471 ret
= check_keywords(ctx
);
475 return parse_identifier(ctx
, (const WCHAR
**)lval
);
478 if(isdigitW(*ctx
->ptr
))
479 return parse_numeric_literal(ctx
, lval
);
496 if(++ctx
->ptr
< ctx
->end
&& isdigitW(*ctx
->ptr
))
497 return parse_double_literal(ctx
, 0, lval
);
501 if(++ctx
->ptr
== ctx
->end
) {
502 *(int*)lval
= EXPR_LESS
;
509 *(int*)lval
= EXPR_LESSEQ
;
512 if(++ctx
->ptr
< ctx
->end
&& *ctx
->ptr
== '=') { /* <<= */
514 *(int*)lval
= EXPR_ASSIGNLSHIFT
;
517 *(int*)lval
= EXPR_LSHIFT
;
520 *(int*)lval
= EXPR_LESS
;
525 if(++ctx
->ptr
== ctx
->end
) { /* > */
526 *(int*)lval
= EXPR_GREATER
;
533 *(int*)lval
= EXPR_GREATEREQ
;
536 if(++ctx
->ptr
< ctx
->end
) {
537 if(*ctx
->ptr
== '=') { /* >>= */
539 *(int*)lval
= EXPR_ASSIGNRSHIFT
;
542 if(*ctx
->ptr
== '>') { /* >>> */
543 if(++ctx
->ptr
< ctx
->end
&& *ctx
->ptr
== '=') { /* >>>= */
545 *(int*)lval
= EXPR_ASSIGNRRSHIFT
;
548 *(int*)lval
= EXPR_RRSHIFT
;
552 *(int*)lval
= EXPR_RSHIFT
;
555 *(int*)lval
= EXPR_GREATER
;
561 if(ctx
->ptr
< ctx
->end
) {
568 *(int*)lval
= EXPR_ASSIGNADD
;
576 if(ctx
->ptr
< ctx
->end
) {
583 *(int*)lval
= EXPR_ASSIGNSUB
;
590 if(++ctx
->ptr
< ctx
->end
&& *ctx
->ptr
== '=') { /* *= */
592 *(int*)lval
= EXPR_ASSIGNMUL
;
598 if(++ctx
->ptr
< ctx
->end
&& *ctx
->ptr
== '=') { /* %= */
600 *(int*)lval
= EXPR_ASSIGNMOD
;
606 if(++ctx
->ptr
< ctx
->end
) {
610 *(int*)lval
= EXPR_ASSIGNAND
;
620 if(++ctx
->ptr
< ctx
->end
) {
624 *(int*)lval
= EXPR_ASSIGNOR
;
634 if(++ctx
->ptr
< ctx
->end
&& *ctx
->ptr
== '=') { /* ^= */
636 *(int*)lval
= EXPR_ASSIGNXOR
;
642 if(++ctx
->ptr
< ctx
->end
&& *ctx
->ptr
== '=') { /* != */
643 if(++ctx
->ptr
< ctx
->end
&& *ctx
->ptr
== '=') { /* !== */
645 *(int*)lval
= EXPR_NOTEQEQ
;
648 *(int*)lval
= EXPR_NOTEQ
;
654 if(++ctx
->ptr
< ctx
->end
&& *ctx
->ptr
== '=') { /* == */
655 if(++ctx
->ptr
< ctx
->end
&& *ctx
->ptr
== '=') { /* === */
657 *(int*)lval
= EXPR_EQEQ
;
660 *(int*)lval
= EXPR_EQ
;
666 if(++ctx
->ptr
< ctx
->end
) {
667 if(*ctx
->ptr
== '=') { /* /= */
669 *(int*)lval
= EXPR_ASSIGNMUL
;
677 return parse_string_literal(ctx
, (const WCHAR
**)lval
, *ctx
->ptr
);
681 return parse_identifier(ctx
, lval
);
684 WARN("unexpected char '%c' %d\n", *ctx
->ptr
, *ctx
->ptr
);
688 static void add_object_literal(parser_ctx_t
*ctx
, DispatchEx
*obj
)
690 obj_literal_t
*literal
= parser_alloc(ctx
, sizeof(obj_literal_t
));
693 literal
->next
= ctx
->obj_literals
;
694 ctx
->obj_literals
= literal
;
697 literal_t
*parse_regexp(parser_ctx_t
*ctx
)
699 const WCHAR
*re
, *flags
;
708 while(ctx
->ptr
< ctx
->end
&& (*ctx
->ptr
!= '/' || *(ctx
->ptr
-1) == '\\'))
711 if(ctx
->ptr
== ctx
->end
) {
712 WARN("unexpected end of file\n");
716 re_len
= ctx
->ptr
-re
;
719 while(ctx
->ptr
< ctx
->end
&& isalnumW(*ctx
->ptr
))
722 hres
= create_regexp_str(ctx
->script
, re
, re_len
, flags
, ctx
->ptr
-flags
, ®exp
);
726 add_object_literal(ctx
, regexp
);
728 ret
= parser_alloc(ctx
, sizeof(literal_t
));
729 ret
->vt
= VT_DISPATCH
;
730 ret
->u
.disp
= (IDispatch
*)_IDispatchEx_(regexp
);