tokenize.c 10 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19
/*
** 2001 September 15
**
** The author disclaims copyright to this source code.  In place of
** a legal notice, here is a blessing:
**
**    May you do good and not evil.
**    May you find forgiveness for yourself and forgive others.
**    May you share freely, never taking more than you give.
**
*************************************************************************
** An tokenizer for SQL
**
** This file contains C code that splits an SQL input string up into
** individual tokens and sends those tokens one-by-one over to the
** parser for analysis.
*/

#include <ctype.h>
20
#include <stdarg.h>
21
#include <stdlib.h>
22 23 24

#include "windef.h"
#include "winbase.h"
25 26 27
#include "wine/debug.h"
#include "winnls.h"
#include "query.h"
28
#include "sql.tab.h"
29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57

WINE_DEFAULT_DEBUG_CHANNEL(msi);

/*
** All the keywords of the SQL language are stored as in a hash
** table composed of instances of the following structure.
*/
typedef struct Keyword Keyword;
struct Keyword {
  const char *zName;             /* The keyword name */
  int tokenType;           /* The token value for this keyword */
};

/*
** These are the keywords
*/
static const Keyword aKeywordTable[] = {
  { "ABORT", TK_ABORT },
  { "AFTER", TK_AFTER },
  { "ALL", TK_ALL },
  { "AND", TK_AND },
  { "AS", TK_AS },
  { "ASC", TK_ASC },
  { "BEFORE", TK_BEFORE },
  { "BEGIN", TK_BEGIN },
  { "BETWEEN", TK_BETWEEN },
  { "BY", TK_BY },
  { "CASCADE", TK_CASCADE },
  { "CASE", TK_CASE },
58 59
  { "CHAR", TK_CHAR },
  { "CHARACTER", TK_CHAR },
60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89
  { "CHECK", TK_CHECK },
  { "CLUSTER", TK_CLUSTER },
  { "COLLATE", TK_COLLATE },
  { "COMMIT", TK_COMMIT },
  { "CONFLICT", TK_CONFLICT },
  { "CONSTRAINT", TK_CONSTRAINT },
  { "COPY", TK_COPY },
  { "CREATE", TK_CREATE },
  { "CROSS", TK_JOIN_KW },
  { "DEFAULT", TK_DEFAULT },
  { "DEFERRED", TK_DEFERRED },
  { "DEFERRABLE", TK_DEFERRABLE },
  { "DELETE", TK_DELETE },
  { "DELIMITERS", TK_DELIMITERS },
  { "DESC", TK_DESC },
  { "DISTINCT", TK_DISTINCT },
  { "DROP", TK_DROP },
  { "END", TK_END },
  { "EACH", TK_EACH },
  { "ELSE", TK_ELSE },
  { "EXCEPT", TK_EXCEPT },
  { "EXPLAIN", TK_EXPLAIN },
  { "FAIL", TK_FAIL },
  { "FOR", TK_FOR },
  { "FOREIGN", TK_FOREIGN },
  { "FROM", TK_FROM },
  { "FULL", TK_JOIN_KW },
  { "GLOB", TK_GLOB },
  { "GROUP", TK_GROUP },
  { "HAVING", TK_HAVING },
90
  { "HOLD", TK_HOLD },
91 92 93 94 95 96 97 98
  { "IGNORE", TK_IGNORE },
  { "IMMEDIATE", TK_IMMEDIATE },
  { "IN", TK_IN },
  { "INDEX", TK_INDEX },
  { "INITIALLY", TK_INITIALLY },
  { "INNER", TK_JOIN_KW },
  { "INSERT", TK_INSERT },
  { "INSTEAD", TK_INSTEAD },
99
  { "INT", TK_INT },
100 101 102 103 104 105 106 107 108
  { "INTERSECT", TK_INTERSECT },
  { "INTO", TK_INTO },
  { "IS", TK_IS },
  { "ISNULL", TK_ISNULL },
  { "JOIN", TK_JOIN },
  { "KEY", TK_KEY },
  { "LEFT", TK_JOIN_KW },
  { "LIKE", TK_LIKE },
  { "LIMIT", TK_LIMIT },
109
  { "LOCALIZABLE", TK_LOCALIZABLE },
110 111
  { "LONG", TK_LONG },
  { "LONGCHAR", TK_LONGCHAR },
112 113 114 115 116
  { "MATCH", TK_MATCH },
  { "NATURAL", TK_JOIN_KW },
  { "NOT", TK_NOT },
  { "NOTNULL", TK_NOTNULL },
  { "NULL", TK_NULL },
117
  { "OBJECT", TK_OBJECT },
118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134
  { "OF", TK_OF },
  { "OFFSET", TK_OFFSET },
  { "ON", TK_ON },
  { "OR", TK_OR },
  { "ORDER", TK_ORDER },
  { "OUTER", TK_JOIN_KW },
  { "PRAGMA", TK_PRAGMA },
  { "PRIMARY", TK_PRIMARY },
  { "RAISE", TK_RAISE },
  { "REFERENCES", TK_REFERENCES },
  { "REPLACE", TK_REPLACE },
  { "RESTRICT", TK_RESTRICT },
  { "RIGHT", TK_JOIN_KW },
  { "ROLLBACK", TK_ROLLBACK },
  { "ROW", TK_ROW },
  { "SELECT", TK_SELECT },
  { "SET", TK_SET },
135
  { "SHORT", TK_SHORT },
136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160
  { "STATEMENT", TK_STATEMENT },
  { "TABLE", TK_TABLE },
  { "TEMP", TK_TEMP },
  { "TEMPORARY", TK_TEMP },
  { "THEN", TK_THEN },
  { "TRANSACTION", TK_TRANSACTION },
  { "TRIGGER", TK_TRIGGER },
  { "UNION", TK_UNION },
  { "UNIQUE", TK_UNIQUE },
  { "UPDATE", TK_UPDATE },
  { "USING", TK_USING },
  { "VACUUM", TK_VACUUM },
  { "VALUES", TK_VALUES },
  { "VIEW", TK_VIEW },
  { "WHEN", TK_WHEN },
  { "WHERE", TK_WHERE },
};

#define KEYWORD_COUNT ( sizeof aKeywordTable/sizeof (Keyword) )

/*
** This function looks up an identifier to determine if it is a
** keyword.  If it is a keyword, the token code of that keyword is 
** returned.  If the input is not a keyword, TK_ID is returned.
*/
161
static int sqliteKeywordCode(const WCHAR *z, int n){
162
  UINT i, len;
163 164 165
  char buffer[0x10];

  len = WideCharToMultiByte( CP_ACP, 0, z, n, buffer, sizeof buffer, NULL, NULL );
166 167
  for(i=0; i<len; i++)
      buffer[i] = toupper(buffer[i]);
168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320
  for(i=0; i<KEYWORD_COUNT; i++)
  {
      if(memcmp(buffer, aKeywordTable[i].zName, len))
          continue;
      if(strlen(aKeywordTable[i].zName) == len )
          return aKeywordTable[i].tokenType;
  }
  return TK_ID;
}


/*
** If X is a character that can be used in an identifier then
** isIdChar[X] will be 1.  Otherwise isIdChar[X] will be 0.
**
** In this implementation, an identifier can be a string of
** alphabetic characters, digits, and "_" plus any character
** with the high-order bit set.  The latter rule means that
** any sequence of UTF-8 characters or characters taken from
** an extended ISO8859 character set can form an identifier.
*/
static const char isIdChar[] = {
/* x0 x1 x2 x3 x4 x5 x6 x7 x8 x9 xA xB xC xD xE xF */
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  /* 0x */
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  /* 1x */
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  /* 2x */
    1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0,  /* 3x */
    0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,  /* 4x */
    1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 1,  /* 5x */
    0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,  /* 6x */
    1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0,  /* 7x */
    1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,  /* 8x */
    1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,  /* 9x */
    1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,  /* Ax */
    1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,  /* Bx */
    1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,  /* Cx */
    1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,  /* Dx */
    1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,  /* Ex */
    1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,  /* Fx */
};


/*
** Return the length of the token that begins at z[0].  Return
** -1 if the token is (or might be) incomplete.  Store the token
** type in *tokenType before returning.
*/
int sqliteGetToken(const WCHAR *z, int *tokenType){
  int i;
  switch( *z ){
    case ' ': case '\t': case '\n': case '\f': case '\r': {
      for(i=1; isspace(z[i]); i++){}
      *tokenType = TK_SPACE;
      return i;
    }
    case '-': {
      if( z[1]==0 ) return -1;
      if( z[1]=='-' ){
        for(i=2; z[i] && z[i]!='\n'; i++){}
        *tokenType = TK_COMMENT;
        return i;
      }
      *tokenType = TK_MINUS;
      return 1;
    }
    case '(': {
      if( z[1]=='+' && z[2]==')' ){
        *tokenType = TK_ORACLE_OUTER_JOIN;
        return 3;
      }else{
        *tokenType = TK_LP;
        return 1;
      }
    }
    case ')': {
      *tokenType = TK_RP;
      return 1;
    }
    case ';': {
      *tokenType = TK_SEMI;
      return 1;
    }
    case '+': {
      *tokenType = TK_PLUS;
      return 1;
    }
    case '*': {
      *tokenType = TK_STAR;
      return 1;
    }
    case '/': {
      if( z[1]!='*' || z[2]==0 ){
        *tokenType = TK_SLASH;
        return 1;
      }
      for(i=3; z[i] && (z[i]!='/' || z[i-1]!='*'); i++){}
      if( z[i] ) i++;
      *tokenType = TK_COMMENT;
      return i;
    }
    case '%': {
      *tokenType = TK_REM;
      return 1;
    }
    case '=': {
      *tokenType = TK_EQ;
      return 1 + (z[1]=='=');
    }
    case '<': {
      if( z[1]=='=' ){
        *tokenType = TK_LE;
        return 2;
      }else if( z[1]=='>' ){
        *tokenType = TK_NE;
        return 2;
      }else if( z[1]=='<' ){
        *tokenType = TK_LSHIFT;
        return 2;
      }else{
        *tokenType = TK_LT;
        return 1;
      }
    }
    case '>': {
      if( z[1]=='=' ){
        *tokenType = TK_GE;
        return 2;
      }else if( z[1]=='>' ){
        *tokenType = TK_RSHIFT;
        return 2;
      }else{
        *tokenType = TK_GT;
        return 1;
      }
    }
    case '!': {
      if( z[1]!='=' ){
        *tokenType = TK_ILLEGAL;
        return 2;
      }else{
        *tokenType = TK_NE;
        return 2;
      }
    }
    case '|': {
      if( z[1]!='|' ){
        *tokenType = TK_BITOR;
        return 1;
      }else{
        *tokenType = TK_CONCAT;
        return 2;
      }
    }
321 322 323 324
    case '?': {
      *tokenType = TK_WILDCARD;
      return 1;
    }
325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348
    case ',': {
      *tokenType = TK_COMMA;
      return 1;
    }
    case '&': {
      *tokenType = TK_BITAND;
      return 1;
    }
    case '~': {
      *tokenType = TK_BITNOT;
      return 1;
    }
    case '`': case '\'': case '"': {
      int delim = z[0];
      for(i=1; z[i]; i++){
        if( z[i]==delim ){
          if( z[i+1]==delim ){
            i++;
          }else{
            break;
          }
        }
      }
      if( z[i] ) i++;
349 350 351 352
      if( delim == '`' )
        *tokenType = TK_ID;
      else
        *tokenType = TK_STRING;
353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400
      return i;
    }
    case '.': {
      if( !isdigit(z[1]) ){
        *tokenType = TK_DOT;
        return 1;
      }
      /* Fall thru into the next case */
    }
    case '0': case '1': case '2': case '3': case '4':
    case '5': case '6': case '7': case '8': case '9': {
      *tokenType = TK_INTEGER;
      for(i=1; isdigit(z[i]); i++){}
      if( z[i]=='.' ){
        i++;
        while( isdigit(z[i]) ){ i++; }
        *tokenType = TK_FLOAT;
      }
      if( (z[i]=='e' || z[i]=='E') &&
           ( isdigit(z[i+1]) 
            || ((z[i+1]=='+' || z[i+1]=='-') && isdigit(z[i+2]))
           )
      ){
        i += 2;
        while( isdigit(z[i]) ){ i++; }
        *tokenType = TK_FLOAT;
      }else if( z[0]=='.' ){
        *tokenType = TK_FLOAT;
      }
      return i;
    }
    case '[': {
      for(i=1; z[i] && z[i-1]!=']'; i++){}
      *tokenType = TK_ID;
      return i;
    }
    default: {
      if( !isIdChar[*z] ){
        break;
      }
      for(i=1; isIdChar[z[i]]; i++){}
      *tokenType = sqliteKeywordCode(z, i);
      return i;
    }
  }
  *tokenType = TK_ILLEGAL;
  return 1;
}