1
0
mirror of https://github.com/sqlite/sqlite.git synced 2025-11-09 14:21:03 +03:00

Improve the speed of the tokenizer by recognizing that tokens starting

with letters "_", "Y", or "Z" can never be SQL keywords and must be ordinary
identifiers.

FossilOrigin-Name: 16e281ed6219cc229dec7e3f1b40da2304dc270a74fd6ef78d04a088e30e7026
This commit is contained in:
drh
2020-11-27 20:56:16 +00:00
parent cad760d16e
commit d1032f952c
3 changed files with 38 additions and 33 deletions

View File

@@ -27,8 +27,8 @@
** all of them need to be used within the switch.
*/
#define CC_X 0 /* The letter 'x', or start of BLOB literal */
#define CC_KYWD 1 /* Alphabetics or '_'. Usable in a keyword */
#define CC_ID 2 /* unicode characters usable in IDs */
#define CC_KYWD0 1 /* First letter of a keyword */
#define CC_KYWD 2 /* Alphabetics or '_'. Usable in a keyword */
#define CC_DIGIT 3 /* Digits */
#define CC_DOLLAR 4 /* '$' */
#define CC_VARALPHA 5 /* '@', '#', ':'. Alphabetic SQL variables */
@@ -53,20 +53,21 @@
#define CC_AND 24 /* '&' */
#define CC_TILDA 25 /* '~' */
#define CC_DOT 26 /* '.' */
#define CC_ILLEGAL 27 /* Illegal character */
#define CC_NUL 28 /* 0x00 */
#define CC_ID 27 /* unicode characters usable in IDs */
#define CC_ILLEGAL 28 /* Illegal character */
#define CC_NUL 29 /* 0x00 */
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 */ 28, 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,
/* 0x */ 29, 28, 28, 28, 28, 28, 28, 28, 28, 7, 7, 28, 7, 7, 28, 28,
/* 1x */ 28, 28, 28, 28, 28, 28, 28, 28, 28, 28, 28, 28, 28, 28, 28, 28,
/* 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,
/* 5x */ 1, 1, 1, 1, 1, 1, 1, 1, 0, 2, 2, 9, 28, 28, 28, 2,
/* 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,
/* 7x */ 1, 1, 1, 1, 1, 1, 1, 1, 0, 2, 2, 28, 10, 28, 25, 28,
/* 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,
@@ -78,22 +79,22 @@ static const unsigned char aiClass[] = {
#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, 26, 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, 6,
/* 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,
/* Ax */ 27, 25, 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,
/* 0x */ 29, 28, 28, 28, 28, 7, 28, 28, 28, 28, 28, 28, 7, 7, 28, 28,
/* 1x */ 28, 28, 28, 28, 28, 28, 28, 28, 28, 28, 28, 28, 28, 28, 28, 28,
/* 2x */ 28, 28, 28, 28, 28, 7, 28, 28, 28, 28, 28, 28, 28, 28, 28, 28,
/* 3x */ 28, 28, 28, 28, 28, 28, 28, 28, 28, 28, 28, 28, 28, 28, 28, 28,
/* 4x */ 7, 28, 28, 28, 28, 28, 28, 28, 28, 28, 28, 26, 12, 17, 20, 10,
/* 5x */ 24, 28, 28, 28, 28, 28, 28, 28, 28, 28, 15, 4, 21, 18, 19, 28,
/* 6x */ 11, 16, 28, 28, 28, 28, 28, 28, 28, 28, 28, 23, 22, 2, 13, 6,
/* 7x */ 28, 28, 28, 28, 28, 28, 28, 28, 28, 8, 5, 5, 5, 8, 14, 8,
/* 8x */ 28, 1, 1, 1, 1, 1, 1, 1, 1, 1, 28, 28, 28, 28, 28, 28,
/* 9x */ 28, 1, 1, 1, 1, 1, 1, 1, 1, 1, 28, 28, 28, 28, 28, 28,
/* Ax */ 28, 25, 1, 1, 1, 1, 1, 0, 2, 2, 28, 28, 28, 28, 28, 28,
/* Bx */ 28, 28, 28, 28, 28, 28, 28, 28, 28, 28, 9, 28, 28, 28, 28, 28,
/* Cx */ 28, 1, 1, 1, 1, 1, 1, 1, 1, 1, 28, 28, 28, 28, 28, 28,
/* Dx */ 28, 1, 1, 1, 1, 1, 1, 1, 1, 1, 28, 28, 28, 28, 28, 28,
/* Ex */ 28, 28, 1, 1, 1, 1, 1, 0, 2, 2, 28, 28, 28, 28, 28, 28,
/* Fx */ 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 28, 28, 28, 28, 28, 28,
#endif
};
@@ -499,7 +500,7 @@ int sqlite3GetToken(const unsigned char *z, int *tokenType){
if( n==0 ) *tokenType = TK_ILLEGAL;
return i;
}
case CC_KYWD: {
case CC_KYWD0: {
for(i=1; aiClass[z[i]]<=CC_KYWD; i++){}
if( IdChar(z[i]) ){
/* This token started out using characters that can appear in keywords,
@@ -529,6 +530,7 @@ int sqlite3GetToken(const unsigned char *z, int *tokenType){
** SQL keywords start with the letter 'x'. Fall through */
/* no break */ deliberate_fall_through
}
case CC_KYWD:
case CC_ID: {
i = 1;
break;