Many hyperlinks are disabled.
Use anonymous login
to enable hyperlinks.
Changes In Branch tokenizer-char-class Excluding Merge-Ins
This is equivalent to a diff from ab269e7205 to 04f7da77c1
2016-02-08
| ||
19:36 | Changes to help the tokenizer run about 33% faster. (check-in: a050e6f096 user: drh tags: trunk) | |
19:15 | Add code to get the tokenizer character-class logic working for EBCDIC. (Closed-Leaf check-in: 04f7da77c1 user: drh tags: tokenizer-char-class) | |
03:23 | Faster keywordCode() implementation by taking advantage of the fact that the input is always pure ASCII alphabetic and underscore and that the keyword table is always upper-case. (check-in: ff406b9701 user: drh tags: tokenizer-char-class) | |
02:30 | Demonstrate a much faster sqlite3GetToken() routine by using a lookup table to map initial token characters into a character class. This check-in does not work for EBCDIC. More optimization needed. (check-in: 9115baa191 user: drh tags: tokenizer-char-class) | |
2016-02-07
| ||
20:39 | Fix harmless compiler warning in 'srcck1' tool and add it to the clean targets. (check-in: 852a529a8b user: mistachkin tags: trunk) | |
00:08 | Add the sourcetest target to Makefile.msc. (check-in: ab269e7205 user: drh tags: trunk) | |
2016-02-06
| ||
22:32 | Add a utility program that looks for assert(), NEVER(), ALWAYS(), and testcase() macros that have side-effects, and reports errors when they are found. Also fix a bug that this utility detected as it was being tested. (check-in: b0b4624fc5 user: drh tags: trunk) | |
Changes to src/tokenize.c.
︙ | ︙ | |||
14 15 16 17 18 19 20 21 | ** 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 "sqliteInt.h" #include <stdlib.h> /* | > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > | | > | > | 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 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 58 59 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 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 | ** 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 "sqliteInt.h" #include <stdlib.h> /* Character classes for tokenizing ** ** In the sqlite3GetToken() function, a switch() on aiClass[c] is implemented ** using a lookup table, whereas a switch() directly on c uses a binary search. ** The lookup table is much faster. To maximize speed, and to ensure that ** a lookup table is used, all of the classes need to be small integers and ** all of them need to be used within the switch. */ #define CC_X 0 /* The letter 'x' or 'X'. Start of x'01234fed' */ #define CC_KYWD 1 /* Alphabetics or '_'. Usable in a keyword */ #define CC_ID 2 /* unicode characters usable in IDs */ #define CC_DIGIT 3 /* Digits */ #define CC_DOLLAR 4 /* '$' */ #define CC_VARALPHA 5 /* '@', '#', ':'. Alphabetic SQL variables */ #define CC_VARNUM 6 /* '?'. Numeric SQL variables */ #define CC_SPACE 7 /* Space characters */ #define CC_QUOTE 8 /* '"', '\'', or '`'. String literals, quoted ids */ #define CC_QUOTE2 9 /* '['. [...] style quoted ids */ #define CC_PIPE 10 /* '|'. Bitwise OR or concatenate */ #define CC_MINUS 11 /* '-'. Minus or SQL-style comment */ #define CC_LT 12 /* '<'. Part of < or <= or <> */ #define CC_GT 13 /* '>'. Part of > or >= */ #define CC_EQ 14 /* '='. Part of = or == */ #define CC_BANG 15 /* '!'. Part of != */ #define CC_SLASH 16 /* '/'. / or c-style comment */ #define CC_LP 17 /* '(' */ #define CC_RP 18 /* ')' */ #define CC_SEMI 19 /* ';' */ #define CC_PLUS 20 /* '+' */ #define CC_STAR 21 /* '*' */ #define CC_PERCENT 22 /* '%' */ #define CC_COMMA 23 /* ',' */ #define CC_AND 24 /* '&' */ #define CC_TILDA 25 /* '~' */ #define CC_DOT 26 /* '.' */ #define CC_ILLEGAL 27 /* Illegal character */ static const unsigned char aiClass[] = { #ifdef SQLITE_ASCII /* x0 x1 x2 x3 x4 x5 x6 x7 x8 x9 xa xb xc xd xe xf */ /* 0x */ 27, 27, 27, 27, 27, 27, 27, 27, 27, 7, 7, 27, 7, 7, 27, 27, /* 1x */ 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, /* 2x */ 7, 15, 8, 5, 4, 22, 24, 8, 17, 18, 21, 20, 23, 11, 26, 16, /* 3x */ 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 5, 19, 12, 14, 13, 6, /* 4x */ 5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, /* 5x */ 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 9, 27, 27, 27, 1, /* 6x */ 8, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, /* 7x */ 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 27, 10, 27, 25, 27, /* 8x */ 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, /* 9x */ 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, /* Ax */ 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, /* Bx */ 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, /* Cx */ 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, /* Dx */ 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, /* Ex */ 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, /* Fx */ 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2 #endif #ifdef SQLITE_EBCDIC /* x0 x1 x2 x3 x4 x5 x6 x7 x8 x9 xa xb xc xd xe xf */ /* 0x */ 27, 27, 27, 27, 27, 7, 27, 27, 27, 27, 27, 27, 7, 7, 27, 27, /* 1x */ 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, /* 2x */ 27, 27, 27, 27, 27, 7, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, /* 3x */ 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, /* 4x */ 7, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 12, 17, 20, 10, /* 5x */ 24, 27, 27, 27, 27, 27, 27, 27, 27, 27, 15, 4, 21, 18, 19, 27, /* 6x */ 11, 16, 27, 27, 27, 27, 27, 27, 27, 27, 27, 23, 22, 1, 13, 7, /* 7x */ 27, 27, 27, 27, 27, 27, 27, 27, 27, 8, 5, 5, 5, 8, 14, 8, /* 8x */ 27, 1, 1, 1, 1, 1, 1, 1, 1, 1, 27, 27, 27, 27, 27, 27, /* 9x */ 27, 1, 1, 1, 1, 1, 1, 1, 1, 1, 27, 27, 27, 27, 27, 27, /* 9x */ 25, 1, 1, 1, 1, 1, 1, 0, 1, 1, 27, 27, 27, 27, 27, 27, /* Bx */ 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 9, 27, 27, 27, 27, 27, /* Cx */ 27, 1, 1, 1, 1, 1, 1, 1, 1, 1, 27, 27, 27, 27, 27, 27, /* Dx */ 27, 1, 1, 1, 1, 1, 1, 1, 1, 1, 27, 27, 27, 27, 27, 27, /* Ex */ 27, 27, 1, 1, 1, 1, 1, 0, 1, 1, 27, 27, 27, 27, 27, 27, /* Fx */ 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 27, 27, 27, 27, 27, 27, #endif }; /* ** The charMap() macro maps alphabetic characters (only) into their ** lower-case ASCII equivalent. On ASCII machines, this is just ** an upper-to-lower case map. On EBCDIC machines we also need ** to adjust the encoding. The mapping is only valid for alphabetics ** which are the only characters for which this feature is used. ** ** Used by keywordhash.h */ #ifdef SQLITE_ASCII # define charMap(X) sqlite3UpperToLower[(unsigned char)X] #endif #ifdef SQLITE_EBCDIC # define charMap(X) ebcdicToAscii[(unsigned char)X] const unsigned char ebcdicToAscii[] = { |
︙ | ︙ | |||
111 112 113 114 115 116 117 | /* ** Return the length of the token that begins at z[0]. ** Store the token type in *tokenType before returning. */ int sqlite3GetToken(const unsigned char *z, int *tokenType){ int i, c; | | | | | | | | | | | | | | | | | | | | < < | 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 | /* ** Return the length of the token that begins at z[0]. ** Store the token type in *tokenType before returning. */ int sqlite3GetToken(const unsigned char *z, int *tokenType){ int i, c; switch( aiClass[*z] ){ case CC_SPACE: { testcase( z[0]==' ' ); testcase( z[0]=='\t' ); testcase( z[0]=='\n' ); testcase( z[0]=='\f' ); testcase( z[0]=='\r' ); for(i=1; sqlite3Isspace(z[i]); i++){} *tokenType = TK_SPACE; return i; } case CC_MINUS: { if( z[1]=='-' ){ for(i=2; (c=z[i])!=0 && c!='\n'; i++){} *tokenType = TK_SPACE; /* IMP: R-22934-25134 */ return i; } *tokenType = TK_MINUS; return 1; } case CC_LP: { *tokenType = TK_LP; return 1; } case CC_RP: { *tokenType = TK_RP; return 1; } case CC_SEMI: { *tokenType = TK_SEMI; return 1; } case CC_PLUS: { *tokenType = TK_PLUS; return 1; } case CC_STAR: { *tokenType = TK_STAR; return 1; } case CC_SLASH: { if( z[1]!='*' || z[2]==0 ){ *tokenType = TK_SLASH; return 1; } for(i=3, c=z[2]; (c!='*' || z[i]!='/') && (c=z[i])!=0; i++){} if( c ) i++; *tokenType = TK_SPACE; /* IMP: R-22934-25134 */ return i; } case CC_PERCENT: { *tokenType = TK_REM; return 1; } case CC_EQ: { *tokenType = TK_EQ; return 1 + (z[1]=='='); } case CC_LT: { if( (c=z[1])=='=' ){ *tokenType = TK_LE; return 2; }else if( c=='>' ){ *tokenType = TK_NE; return 2; }else if( c=='<' ){ *tokenType = TK_LSHIFT; return 2; }else{ *tokenType = TK_LT; return 1; } } case CC_GT: { if( (c=z[1])=='=' ){ *tokenType = TK_GE; return 2; }else if( c=='>' ){ *tokenType = TK_RSHIFT; return 2; }else{ *tokenType = TK_GT; return 1; } } case CC_BANG: { if( z[1]!='=' ){ *tokenType = TK_ILLEGAL; return 2; }else{ *tokenType = TK_NE; return 2; } } case CC_PIPE: { if( z[1]!='|' ){ *tokenType = TK_BITOR; return 1; }else{ *tokenType = TK_CONCAT; return 2; } } case CC_COMMA: { *tokenType = TK_COMMA; return 1; } case CC_AND: { *tokenType = TK_BITAND; return 1; } case CC_TILDA: { *tokenType = TK_BITNOT; return 1; } case CC_QUOTE: { int delim = z[0]; testcase( delim=='`' ); testcase( delim=='\'' ); testcase( delim=='"' ); for(i=1; (c=z[i])!=0; i++){ if( c==delim ){ if( z[i+1]==delim ){ |
︙ | ︙ | |||
253 254 255 256 257 258 259 | *tokenType = TK_ID; return i+1; }else{ *tokenType = TK_ILLEGAL; return i; } } | | | < | 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 | *tokenType = TK_ID; return i+1; }else{ *tokenType = TK_ILLEGAL; return i; } } case CC_DOT: { #ifndef SQLITE_OMIT_FLOATING_POINT if( !sqlite3Isdigit(z[1]) ) #endif { *tokenType = TK_DOT; return 1; } /* If the next character is a digit, this is a floating point ** number that begins with ".". Fall thru into the next case */ } case CC_DIGIT: { testcase( z[0]=='0' ); testcase( z[0]=='1' ); testcase( z[0]=='2' ); testcase( z[0]=='3' ); testcase( z[0]=='4' ); testcase( z[0]=='5' ); testcase( z[0]=='6' ); testcase( z[0]=='7' ); testcase( z[0]=='8' ); testcase( z[0]=='9' ); *tokenType = TK_INTEGER; #ifndef SQLITE_OMIT_HEX_INTEGER if( z[0]=='0' && (z[1]=='x' || z[1]=='X') && sqlite3Isxdigit(z[2]) ){ |
︙ | ︙ | |||
300 301 302 303 304 305 306 | #endif while( IdChar(z[i]) ){ *tokenType = TK_ILLEGAL; i++; } return i; } | | | < | < < | < | 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 | #endif while( IdChar(z[i]) ){ *tokenType = TK_ILLEGAL; i++; } return i; } case CC_QUOTE2: { for(i=1, c=z[0]; c!=']' && (c=z[i])!=0; i++){} *tokenType = c==']' ? TK_ID : TK_ILLEGAL; return i; } case CC_VARNUM: { *tokenType = TK_VARIABLE; for(i=1; sqlite3Isdigit(z[i]); i++){} return i; } case CC_DOLLAR: case CC_VARALPHA: { int n = 0; testcase( z[0]=='$' ); testcase( z[0]=='@' ); testcase( z[0]==':' ); testcase( z[0]=='#' ); *tokenType = TK_VARIABLE; for(i=1; (c=z[i])!=0; i++){ if( IdChar(c) ){ n++; |
︙ | ︙ | |||
345 346 347 348 349 350 351 | break; } } if( n==0 ) *tokenType = TK_ILLEGAL; return i; } #ifndef SQLITE_OMIT_BLOB_LITERAL | | | > | < | < | > > > | > | | > > > > > | 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 | break; } } if( n==0 ) *tokenType = TK_ILLEGAL; return i; } #ifndef SQLITE_OMIT_BLOB_LITERAL case CC_X: { testcase( z[0]=='x' ); testcase( z[0]=='X' ); if( z[1]=='\'' ){ *tokenType = TK_BLOB; for(i=2; sqlite3Isxdigit(z[i]); i++){} if( z[i]!='\'' || i%2 ){ *tokenType = TK_ILLEGAL; while( z[i] && z[i]!='\'' ){ i++; } } if( z[i] ) i++; return i; } i = 1; break; } #endif case CC_KYWD: { for(i=1; aiClass[z[i]]<=CC_KYWD; i++){} if( IdChar(z[i]) ){ i++; break; } *tokenType = TK_ID; return keywordCode((char*)z, i, tokenType); } case CC_ID: { i = 1; break; } default: { *tokenType = TK_ILLEGAL; return 1; } } while( IdChar(z[i]) ){ i++; } *tokenType = TK_ID; return i; } /* ** Run the parser on the given SQL string. The parser structure is ** passed in. An SQLITE_ status code is returned. If an error occurs ** then an and attempt is made to write an error message into ** memory obtained from sqlite3_malloc() and to make *pzErrMsg point to that |
︙ | ︙ |
Changes to tool/mkkeywordhash.c.
︙ | ︙ | |||
273 274 275 276 277 278 279 | { "WHEN", "TK_WHEN", ALWAYS }, { "WHERE", "TK_WHERE", ALWAYS }, }; /* Number of keywords */ static int nKeyword = (sizeof(aKeywordTable)/sizeof(aKeywordTable[0])); | | > > > | 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 | { "WHEN", "TK_WHEN", ALWAYS }, { "WHERE", "TK_WHERE", ALWAYS }, }; /* Number of keywords */ static int nKeyword = (sizeof(aKeywordTable)/sizeof(aKeywordTable[0])); /* Map all alphabetic characters into lower-case for hashing. This is ** only valid for alphabetics. In particular it does not work for '_' ** and so the hash cannot be on a keyword position that might be an '_'. */ #define charMap(X) (0x20|(X)) /* ** Comparision function for two Keyword records */ static int keywordCompare1(const void *a, const void *b){ const Keyword *pA = (Keyword*)a; |
︙ | ︙ | |||
561 562 563 564 565 566 567 | if( j>=5 ){ printf("\n"); j = 0; } } printf("%s };\n", j==0 ? "" : "\n"); | | > | | | > | > > > > > > > | | < | | 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 | if( j>=5 ){ printf("\n"); j = 0; } } printf("%s };\n", j==0 ? "" : "\n"); printf(" int i, j;\n"); printf(" const char *zKW;\n"); printf(" if( n>=2 ){\n"); printf(" i = ((charMap(z[0])*4) ^ (charMap(z[n-1])*3) ^ n) %% %d;\n", bestSize); printf(" for(i=((int)aHash[i])-1; i>=0; i=((int)aNext[i])-1){\n"); printf(" if( aLen[i]!=n ) continue;\n"); printf(" j = 0;\n"); printf(" zKW = &zText[aOffset[i]];\n"); printf("#ifdef SQLITE_ASCII\n"); printf(" while( j<n && (z[j]&~0x20)==zKW[j] ){ j++; }\n"); printf("#endif\n"); printf("#ifdef SQLITE_EBCDIC\n"); printf(" while( j<n && toupper(z[j])==zKW[j] ){ j++; }\n"); printf("#endif\n"); printf(" if( j<n ) continue;\n"); for(i=0; i<nKeyword; i++){ printf(" testcase( i==%d ); /* %s */\n", i, aKeywordTable[i].zOrigName); } printf(" *pType = aCode[i];\n"); printf(" break;\n"); printf(" }\n"); printf(" }\n"); printf(" return n;\n"); printf("}\n"); printf("int sqlite3KeywordCode(const unsigned char *z, int n){\n"); printf(" int id = TK_ID;\n"); printf(" keywordCode((char*)z, n, &id);\n"); printf(" return id;\n"); printf("}\n"); printf("#define SQLITE_N_KEYWORD %d\n", nKeyword); return 0; } |