dlls/vbscript/lex.c

   1 /*
   2  * Copyright 2011 Jacek Caban for CodeWeavers
   3  *
   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.
   8  *
   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.
  13  *
  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
  17  */
  18
  19 #include <assert.h>
  20
  21 #include "vbscript.h"
  22 #include "parse.h"
  23 #include "parser.tab.h"
  24
  25 #include "wine/debug.h"
  26
  27 WINE_DEFAULT_DEBUG_CHANNEL(vbscript);
  28
  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};
  78
  79 static const struct {
  80     const WCHAR *word;
  81     int token;
  82 } keywords[] = {
  83     {andW,       tAND},
  84     {byrefW,     tBYREF},
  85     {byvalW,     tBYVAL},
  86     {callW,      tCALL},
  87     {classW,     tCLASS},
  88     {defaultW,   tDEFAULT},
  89     {dimW,       tDIM},
  90     {doW,        tDO},
  91     {elseW,      tELSE},
  92     {elseifW,    tELSEIF},
  93     {emptyW,     tEMPTY},
  94     {endW,       tEND},
  95     {eqvW,       tEQV},
  96     {errorW,     tERROR},
  97     {exitW,      tEXIT},
  98     {explicitW,  tEXPLICIT},
  99     {falseW,     tFALSE},
 100     {functionW,  tFUNCTION},
 101     {getW,       tGET},
 102     {gotoW,      tGOTO},
 103     {ifW,        tIF},
 104     {impW,       tIMP},
 105     {isW,        tIS},
 106     {letW,       tLET},
 107     {loopW,      tLOOP},
 108     {meW,        tME},
 109     {modW,       tMOD},
 110     {newW,       tNEW},
 111     {nextW,      tNEXT},
 112     {notW,       tNOT},
 113     {nothingW,   tNOTHING},
 114     {nullW,      tNULL},
 115     {onW,        tON},
 116     {optionW,    tOPTION},
 117     {orW,        tOR},
 118     {privateW,   tPRIVATE},
 119     {propertyW,  tPROPERTY},
 120     {publicW,    tPUBLIC},
 121     {remW,       tREM},
 122     {resumeW,    tRESUME},
 123     {setW,       tSET},
 124     {stopW,      tSTOP},
 125     {subW,       tSUB},
 126     {thenW,      tTHEN},
 127     {trueW,      tTRUE},
 128     {untilW,     tUNTIL},
 129     {wendW,      tWEND},
 130     {whileW,     tWHILE},
 131     {xorW,       tXOR}
 132 };
 133
 134 static inline BOOL is_identifier_char(WCHAR c)
 135 {
 136     return isalnumW(c) || c == '_';
 137 }
 138
 139 static int check_keyword(parser_ctx_t *ctx, const WCHAR *word)
 140 {
 141     const WCHAR *p1 = ctx->ptr;
 142     const WCHAR *p2 = word;
 143     WCHAR c;
 144
 145     while(p1 < ctx->end && *p2) {
 146         c = tolowerW(*p1);
 147         if(c != *p2)
 148             return c - *p2;
 149         p1++;
 150         p2++;
 151     }
 152
 153     if(*p2 || (p1 < ctx->end && is_identifier_char(*p1)))
 154         return 1;
 155
 156     ctx->ptr = p1;
 157     return 0;
 158 }
 159
 160 static int check_keywords(parser_ctx_t *ctx)
 161 {
 162     int min = 0, max = sizeof(keywords)/sizeof(keywords[0])-1, r, i;
 163
 164     while(min <= max) {
 165         i = (min+max)/2;
 166
 167         r = check_keyword(ctx, keywords[i].word);
 168         if(!r)
 169             return keywords[i].token;
 170
 171         if(r > 0)
 172             min = i+1;
 173         else
 174             max = i-1;
 175     }
 176
 177     return 0;
 178 }
 179
 180 static int parse_identifier(parser_ctx_t *ctx, const WCHAR **ret)
 181 {
 182     const WCHAR *ptr = ctx->ptr++;
 183     WCHAR *str;
 184     int len;
 185
 186     while(ctx->ptr < ctx->end && is_identifier_char(*ctx->ptr))
 187         ctx->ptr++;
 188     len = ctx->ptr-ptr;
 189
 190     str = parser_alloc(ctx, (len+1)*sizeof(WCHAR));
 191     if(!str)
 192         return 0;
 193
 194     memcpy(str, ptr, (len+1)*sizeof(WCHAR));
 195     str[len] = 0;
 196     *ret = str;
 197     return tIdentifier;
 198 }
 199
 200 static int parse_string_literal(parser_ctx_t *ctx, const WCHAR **ret)
 201 {
 202     const WCHAR *ptr = ++ctx->ptr;
 203     WCHAR *rptr;
 204     int len = 0;
 205
 206     while(ctx->ptr < ctx->end) {
 207         if(*ctx->ptr == '\n') {
 208             FIXME("newline inside string literal\n");
 209             return 0;
 210         }
 211
 212        if(*ctx->ptr == '"') {
 213             if(ctx->ptr[1] != '"')
 214                 break;
 215             len--;
 216             ctx->ptr++;
 217         }
 218         ctx->ptr++;
 219     }
 220
 221     if(ctx->ptr == ctx->end) {
 222         FIXME("unterminated string literal\n");
 223         return 0;
 224     }
 225
 226     len += ctx->ptr-ptr;
 227
 228     *ret = rptr = parser_alloc(ctx, (len+1)*sizeof(WCHAR));
 229     if(!rptr)
 230         return 0;
 231
 232     while(ptr < ctx->ptr) {
 233         if(*ptr == '"')
 234             ptr++;
 235         *rptr++ = *ptr++;
 236     }
 237
 238     *rptr = 0;
 239     ctx->ptr++;
 240     return tString;
 241 }
 242
 243 static void skip_spaces(parser_ctx_t *ctx)
 244 {
 245     while(*ctx->ptr == ' ' || *ctx->ptr == '\t' || *ctx->ptr == '\r')
 246         ctx->ptr++;
 247 }
 248
 249 static int parse_next_token(void *lval, parser_ctx_t *ctx)
 250 {
 251     WCHAR c;
 252
 253     skip_spaces(ctx);
 254     if(ctx->ptr == ctx->end)
 255         return ctx->last_token == tNL ? tEOF : tNL;
 256
 257     c = *ctx->ptr;
 258
 259     if(isalphaW(c)) {
 260         int ret = check_keywords(ctx);
 261         if(!ret)
 262             return parse_identifier(ctx, lval);
 263         return ret;
 264     }
 265
 266     switch(c) {
 267     case '\n':
 268         ctx->ptr++;
 269         return tNL;
 270     case '\'':
 271         ctx->ptr = strchrW(ctx->ptr, '\n');
 272         if(ctx->ptr)
 273             ctx->ptr++;
 274         else
 275             ctx->ptr = ctx->end;
 276         return tNL;
 277     case ')':
 278     case ',':
 279     case '=':
 280     case '+':
 281     case '-':
 282     case '*':
 283     case '/':
 284     case '^':
 285     case '\\':
 286     case '.':
 287         return *ctx->ptr++;
 288     case '(':
 289         /* NOTE:
 290          * We resolve empty brackets in lexer instead of parser to avoid complex conflicts
 291          * in call statement special case |f()| without 'call' keyword
 292          */
 293         ctx->ptr++;
 294         skip_spaces(ctx);
 295         if(*ctx->ptr == ')') {
 296             ctx->ptr++;
 297             return tEMPTYBRACKETS;
 298         }
 299         return '(';
 300     case '"':
 301         return parse_string_literal(ctx, lval);
 302     default:
 303         FIXME("Unhandled char %c in %s\n", *ctx->ptr, debugstr_w(ctx->ptr));
 304     }
 305
 306     return 0;
 307 }
 308
 309 int parser_lex(void *lval, parser_ctx_t *ctx)
 310 {
 311     int ret;
 312
 313     while(1) {
 314         ret = parse_next_token(lval, ctx);
 315         if(ret != tNL || ctx->last_token != tNL)
 316             break;
 317
 318         ctx->last_nl = ctx->ptr-ctx->code;
 319     }
 320
 321     return (ctx->last_token = ret);
 322 }