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 caseW[] = {'c','a','s','e',0};
34 static const WCHAR classW[] = {'c','l','a','s','s',0};
35 static const WCHAR constW[] = {'c','o','n','s','t',0};
36 static const WCHAR defaultW[] = {'d','e','f','a','u','l','t',0};
37 static const WCHAR dimW[] = {'d','i','m',0};
38 static const WCHAR doW[] = {'d','o',0};
39 static const WCHAR eachW[] = {'e','a','c','h',0};
40 static const WCHAR elseW[] = {'e','l','s','e',0};
41 static const WCHAR elseifW[] = {'e','l','s','e','i','f',0};
42 static const WCHAR emptyW[] = {'e','m','p','t','y',0};
43 static const WCHAR endW[] = {'e','n','d',0};
44 static const WCHAR eqvW[] = {'e','q','v',0};
45 static const WCHAR errorW[] = {'e','r','r','o','r',0};
46 static const WCHAR exitW[] = {'e','x','i','t',0};
47 static const WCHAR explicitW[] = {'e','x','p','l','i','c','i','t',0};
48 static const WCHAR falseW[] = {'f','a','l','s','e',0};
49 static const WCHAR forW[] = {'f','o','r',0};
50 static const WCHAR functionW[] = {'f','u','n','c','t','i','o','n',0};
51 static const WCHAR getW[] = {'g','e','t',0};
52 static const WCHAR gotoW[] = {'g','o','t','o',0};
53 static const WCHAR ifW[] = {'i','f',0};
54 static const WCHAR impW[] = {'i','m','p',0};
55 static const WCHAR inW[] = {'i','n',0};
56 static const WCHAR isW[] = {'i','s',0};
57 static const WCHAR letW[] = {'l','e','t',0};
58 static const WCHAR loopW[] = {'l','o','o','p',0};
59 static const WCHAR meW[] = {'m','e',0};
60 static const WCHAR modW[] = {'m','o','d',0};
61 static const WCHAR newW[] = {'n','e','w',0};
62 static const WCHAR nextW[] = {'n','e','x','t',0};
63 static const WCHAR notW[] = {'n','o','t',0};
64 static const WCHAR nothingW[] = {'n','o','t','h','i','n','g',0};
65 static const WCHAR nullW[] = {'n','u','l','l',0};
66 static const WCHAR onW[] = {'o','n',0};
67 static const WCHAR optionW[] = {'o','p','t','i','o','n',0};
68 static const WCHAR orW[] = {'o','r',0};
69 static const WCHAR privateW[] = {'p','r','i','v','a','t','e',0};
70 static const WCHAR propertyW[] = {'p','r','o','p','e','r','t','y',0};
71 static const WCHAR publicW[] = {'p','u','b','l','i','c',0};
72 static const WCHAR remW[] = {'r','e','m',0};
73 static const WCHAR resumeW[] = {'r','e','s','u','m','e',0};
74 static const WCHAR selectW[] = {'s','e','l','e','c','t',0};
75 static const WCHAR setW[] = {'s','e','t',0};
76 static const WCHAR stepW[] = {'s','t','e','p',0};
77 static const WCHAR stopW[] = {'s','t','o','p',0};
78 static const WCHAR subW[] = {'s','u','b',0};
79 static const WCHAR thenW[] = {'t','h','e','n',0};
80 static const WCHAR toW[] = {'t','o',0};
81 static const WCHAR trueW[] = {'t','r','u','e',0};
82 static const WCHAR untilW[] = {'u','n','t','i','l',0};
83 static const WCHAR wendW[] = {'w','e','n','d',0};
84 static const WCHAR whileW[] = {'w','h','i','l','e',0};
85 static const WCHAR xorW[] = {'x','o','r',0};
109 {explicitW, tEXPLICIT},
112 {functionW, tFUNCTION},
126 {nothingW, tNOTHING},
131 {privateW, tPRIVATE},
132 {propertyW, tPROPERTY},
150 static inline BOOL is_identifier_char(WCHAR c)
152 return isalnumW(c) || c == '_';
155 static int check_keyword(parser_ctx_t *ctx, const WCHAR *word)
157 const WCHAR *p1 = ctx->ptr;
158 const WCHAR *p2 = word;
161 while(p1 < ctx->end && *p2) {
169 if(*p2 || (p1 < ctx->end && is_identifier_char(*p1)))
176 static int check_keywords(parser_ctx_t *ctx)
178 int min = 0, max = sizeof(keywords)/sizeof(keywords[0])-1, r, i;
183 r = check_keyword(ctx, keywords[i].word);
185 return keywords[i].token;
196 static int parse_identifier(parser_ctx_t *ctx, const WCHAR **ret)
198 const WCHAR *ptr = ctx->ptr++;
202 while(ctx->ptr < ctx->end && is_identifier_char(*ctx->ptr))
206 str = parser_alloc(ctx, (len+1)*sizeof(WCHAR));
210 memcpy(str, ptr, (len+1)*sizeof(WCHAR));
216 static int parse_string_literal(parser_ctx_t *ctx, const WCHAR **ret)
218 const WCHAR *ptr = ++ctx->ptr;
222 while(ctx->ptr < ctx->end) {
223 if(*ctx->ptr == '\n') {
224 FIXME("newline inside string literal\n");
228 if(*ctx->ptr == '"') {
229 if(ctx->ptr[1] != '"')
237 if(ctx->ptr == ctx->end) {
238 FIXME("unterminated string literal\n");
244 *ret = rptr = parser_alloc(ctx, (len+1)*sizeof(WCHAR));
248 while(ptr < ctx->ptr) {
259 static int parse_numeric_literal(parser_ctx_t *ctx, void **ret)
263 if(*ctx->ptr == '0' && !('0' <= ctx->ptr[1] && ctx->ptr[1] <= '9') && ctx->ptr[1] != '.')
267 n = n*10 + *ctx->ptr++ - '0';
268 }while('0' <= *ctx->ptr && *ctx->ptr <= '9');
270 if(*ctx->ptr != '.') {
274 return (short)l == l ? tShort : tLong;
278 while('0' <= *++ctx->ptr && *ctx->ptr <= '9')
279 n += (e /= 10.0)*(*ctx->ptr-'0');
286 static int hex_to_int(WCHAR c)
288 if('0' <= c && c <= '9')
290 if('a' <= c && c <= 'f')
292 if('A' <= c && c <= 'F')
297 static int parse_hex_literal(parser_ctx_t *ctx, LONG *ret)
299 const WCHAR *begin = ctx->ptr;
302 while((d = hex_to_int(*++ctx->ptr)) != -1)
305 if(begin + 9 /* max digits+1 */ < ctx->ptr || (*ctx->ptr != '&' && is_identifier_char(*ctx->ptr))) {
306 FIXME("invalid literal\n");
314 return (short)l == l ? tShort : tLong;
317 static void skip_spaces(parser_ctx_t *ctx)
319 while(*ctx->ptr == ' ' || *ctx->ptr == '\t' || *ctx->ptr == '\r')
323 static int comment_line(parser_ctx_t *ctx)
325 ctx->ptr = strchrW(ctx->ptr, '\n');
333 static int parse_next_token(void *lval, parser_ctx_t *ctx)
338 if(ctx->ptr == ctx->end)
339 return ctx->last_token == tNL ? tEOF : tNL;
343 if('0' <= c && c <= '9')
344 return parse_numeric_literal(ctx, lval);
347 int ret = check_keywords(ctx);
349 return parse_identifier(ctx, lval);
360 return comment_line(ctx);
374 if(ctx->is_html && ctx->ptr[1] == '-' && ctx->ptr[2] == '>')
375 return comment_line(ctx);
380 * We resolve empty brackets in lexer instead of parser to avoid complex conflicts
381 * in call statement special case |f()| without 'call' keyword
385 if(*ctx->ptr == ')') {
387 return tEMPTYBRACKETS;
391 return parse_string_literal(ctx, lval);
393 if(*++ctx->ptr == 'h' || *ctx->ptr == 'H')
394 return parse_hex_literal(ctx, lval);
397 switch(*++ctx->ptr) {
405 if(ctx->is_html && ctx->ptr[1] == '-' && ctx->ptr[2] == '-')
406 return comment_line(ctx);
410 if(*++ctx->ptr == '=') {
416 FIXME("Unhandled char %c in %s\n", *ctx->ptr, debugstr_w(ctx->ptr));
422 int parser_lex(void *lval, parser_ctx_t *ctx)
427 ret = parse_next_token(lval, ctx);
430 if(*ctx->ptr != '\n') {
431 FIXME("'_' not followed by newline\n");
437 if(ret != tNL || ctx->last_token != tNL)
440 ctx->last_nl = ctx->ptr-ctx->code;
443 return (ctx->last_token = ret);