2 * Copyright 2011 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
23 #include "parser.tab.h"
25 #include "wine/debug.h"
27 WINE_DEFAULT_DEBUG_CHANNEL(vbscript);
29 static const WCHAR andW[] = {'a','n','d',0};
30 static const WCHAR byrefW[] = {'b','y','r','e','f',0};
31 static const WCHAR byvalW[] = {'b','y','v','a','l',0};
32 static const WCHAR callW[] = {'c','a','l','l',0};
33 static const WCHAR classW[] = {'c','l','a','s','s',0};
34 static const WCHAR defaultW[] = {'d','e','f','a','u','l','t',0};
35 static const WCHAR dimW[] = {'d','i','m',0};
36 static const WCHAR doW[] = {'d','o',0};
37 static const WCHAR elseW[] = {'e','l','s','e',0};
38 static const WCHAR elseifW[] = {'e','l','s','e','i','f',0};
39 static const WCHAR emptyW[] = {'e','m','p','t','y',0};
40 static const WCHAR endW[] = {'e','n','d',0};
41 static const WCHAR eqvW[] = {'e','q','v',0};
42 static const WCHAR errorW[] = {'e','r','r','o','r',0};
43 static const WCHAR exitW[] = {'e','x','i','t',0};
44 static const WCHAR explicitW[] = {'e','x','p','l','i','c','i','t',0};
45 static const WCHAR falseW[] = {'f','a','l','s','e',0};
46 static const WCHAR functionW[] = {'f','u','n','c','t','i','o','n',0};
47 static const WCHAR getW[] = {'g','e','t',0};
48 static const WCHAR gotoW[] = {'g','o','t','o',0};
49 static const WCHAR ifW[] = {'i','f',0};
50 static const WCHAR impW[] = {'i','m','p',0};
51 static const WCHAR isW[] = {'i','s',0};
52 static const WCHAR letW[] = {'l','e','t',0};
53 static const WCHAR loopW[] = {'l','o','o','p',0};
54 static const WCHAR meW[] = {'m','e',0};
55 static const WCHAR modW[] = {'m','o','d',0};
56 static const WCHAR newW[] = {'n','e','w',0};
57 static const WCHAR nextW[] = {'n','e','x','t',0};
58 static const WCHAR notW[] = {'n','o','t',0};
59 static const WCHAR nothingW[] = {'n','o','t','h','i','n','g',0};
60 static const WCHAR nullW[] = {'n','u','l','l',0};
61 static const WCHAR onW[] = {'o','n',0};
62 static const WCHAR optionW[] = {'o','p','t','i','o','n',0};
63 static const WCHAR orW[] = {'o','r',0};
64 static const WCHAR privateW[] = {'p','r','i','v','a','t','e',0};
65 static const WCHAR propertyW[] = {'p','r','o','p','e','r','t','y',0};
66 static const WCHAR publicW[] = {'p','u','b','l','i','c',0};
67 static const WCHAR remW[] = {'r','e','m',0};
68 static const WCHAR resumeW[] = {'r','e','s','u','m','e',0};
69 static const WCHAR setW[] = {'s','e','t',0};
70 static const WCHAR stopW[] = {'s','t','o','p',0};
71 static const WCHAR subW[] = {'s','u','b',0};
72 static const WCHAR thenW[] = {'t','h','e','n',0};
73 static const WCHAR trueW[] = {'t','r','u','e',0};
74 static const WCHAR untilW[] = {'u','n','t','i','l',0};
75 static const WCHAR wendW[] = {'w','e','n','d',0};
76 static const WCHAR whileW[] = {'w','h','i','l','e',0};
77 static const WCHAR xorW[] = {'x','o','r',0};
98 {explicitW, tEXPLICIT},
100 {functionW, tFUNCTION},
113 {nothingW, tNOTHING},
118 {privateW, tPRIVATE},
119 {propertyW, tPROPERTY},
134 static inline BOOL is_identifier_char(WCHAR c)
136 return isalnumW(c) || c == '_';
139 static int check_keyword(parser_ctx_t *ctx, const WCHAR *word)
141 const WCHAR *p1 = ctx->ptr;
142 const WCHAR *p2 = word;
145 while(p1 < ctx->end && *p2) {
153 if(*p2 || (p1 < ctx->end && is_identifier_char(*p1)))
160 static int check_keywords(parser_ctx_t *ctx)
162 int min = 0, max = sizeof(keywords)/sizeof(keywords[0])-1, r, i;
167 r = check_keyword(ctx, keywords[i].word);
169 return keywords[i].token;
180 static int parse_identifier(parser_ctx_t *ctx, const WCHAR **ret)
182 const WCHAR *ptr = ctx->ptr++;
186 while(ctx->ptr < ctx->end && is_identifier_char(*ctx->ptr))
190 str = parser_alloc(ctx, (len+1)*sizeof(WCHAR));
194 memcpy(str, ptr, (len+1)*sizeof(WCHAR));
200 static int parse_string_literal(parser_ctx_t *ctx, const WCHAR **ret)
202 const WCHAR *ptr = ++ctx->ptr;
206 while(ctx->ptr < ctx->end) {
207 if(*ctx->ptr == '\n') {
208 FIXME("newline inside string literal\n");
212 if(*ctx->ptr == '"') {
213 if(ctx->ptr[1] != '"')
221 if(ctx->ptr == ctx->end) {
222 FIXME("unterminated string literal\n");
228 *ret = rptr = parser_alloc(ctx, (len+1)*sizeof(WCHAR));
232 while(ptr < ctx->ptr) {
243 static int parse_numeric_literal(parser_ctx_t *ctx, void **ret)
247 if(*ctx->ptr == '0' && !('0' <= ctx->ptr[1] && ctx->ptr[1] <= '9') && ctx->ptr[1] != '.')
251 n = n*10 + *ctx->ptr++ - '0';
252 }while('0' <= *ctx->ptr && *ctx->ptr <= '9');
254 if(*ctx->ptr != '.') {
258 return (short)l == l ? tShort : tLong;
262 while('0' <= *++ctx->ptr && *ctx->ptr <= '9')
263 n += (e /= 10.0)*(*ctx->ptr-'0');
270 static int hex_to_int(WCHAR c)
272 if('0' <= c && c <= '9')
274 if('a' <= c && c <= 'f')
276 if('A' <= c && c <= 'F')
281 static int parse_hex_literal(parser_ctx_t *ctx, LONG *ret)
283 const WCHAR *begin = ctx->ptr;
286 while((d = hex_to_int(*++ctx->ptr)) != -1)
289 if(begin + 9 /* max digits+1 */ < ctx->ptr || *ctx->ptr != '&') {
290 FIXME("invalid literal\n");
296 return (short)l == l ? tShort : tLong;
299 static void skip_spaces(parser_ctx_t *ctx)
301 while(*ctx->ptr == ' ' || *ctx->ptr == '\t' || *ctx->ptr == '\r')
305 static int parse_next_token(void *lval, parser_ctx_t *ctx)
310 if(ctx->ptr == ctx->end)
311 return ctx->last_token == tNL ? tEOF : tNL;
315 if('0' <= c && c <= '9')
316 return parse_numeric_literal(ctx, lval);
319 int ret = check_keywords(ctx);
321 return parse_identifier(ctx, lval);
332 ctx->ptr = strchrW(ctx->ptr, '\n');
352 * We resolve empty brackets in lexer instead of parser to avoid complex conflicts
353 * in call statement special case |f()| without 'call' keyword
357 if(*ctx->ptr == ')') {
359 return tEMPTYBRACKETS;
363 return parse_string_literal(ctx, lval);
365 if(*++ctx->ptr == 'h' || *ctx->ptr == 'H')
366 return parse_hex_literal(ctx, lval);
369 switch(*++ctx->ptr) {
379 if(*++ctx->ptr == '=') {
385 FIXME("Unhandled char %c in %s\n", *ctx->ptr, debugstr_w(ctx->ptr));
391 int parser_lex(void *lval, parser_ctx_t *ctx)
396 ret = parse_next_token(lval, ctx);
397 if(ret != tNL || ctx->last_token != tNL)
400 ctx->last_nl = ctx->ptr-ctx->code;
403 return (ctx->last_token = ret);