diff options
Diffstat (limited to 'src/tokenize.c')
| -rw-r--r-- | src/tokenize.c | 201 |
1 files changed, 142 insertions, 59 deletions
diff --git a/src/tokenize.c b/src/tokenize.c index b85e35dc1..19a5ddf04 100644 --- a/src/tokenize.c +++ b/src/tokenize.c @@ -18,12 +18,92 @@ #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 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_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 into their +** 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. Only alphabetic characters and underscores -** need to be translated. +** 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] @@ -57,7 +137,7 @@ const unsigned char ebcdicToAscii[] = { ** returned. If the input is not a keyword, TK_ID is returned. ** ** The implementation of this routine was generated by a program, -** mkkeywordhash.h, located in the tool subdirectory of the distribution. +** mkkeywordhash.c, located in the tool subdirectory of the distribution. ** The output of the mkkeywordhash.c program is written into a file ** named keywordhash.h and then included into this source file by ** the #include below. @@ -110,13 +190,15 @@ int sqlite3IsIdChar(u8 c){ return IdChar(c); } /* -** Return the length of the token that begins at z[0]. +** Return the length (in bytes) 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( *z ){ - case ' ': case '\t': case '\n': case '\f': case '\r': { + switch( aiClass[*z] ){ /* Switch on the character-class of the first byte + ** of the token. See the comment on the CC_ defines + ** above. */ + case CC_SPACE: { testcase( z[0]==' ' ); testcase( z[0]=='\t' ); testcase( z[0]=='\n' ); @@ -126,7 +208,7 @@ int sqlite3GetToken(const unsigned char *z, int *tokenType){ *tokenType = TK_SPACE; return i; } - case '-': { + case CC_MINUS: { if( z[1]=='-' ){ for(i=2; (c=z[i])!=0 && c!='\n'; i++){} *tokenType = TK_SPACE; /* IMP: R-22934-25134 */ @@ -135,27 +217,27 @@ int sqlite3GetToken(const unsigned char *z, int *tokenType){ *tokenType = TK_MINUS; return 1; } - case '(': { + case CC_LP: { *tokenType = TK_LP; return 1; } - case ')': { + case CC_RP: { *tokenType = TK_RP; return 1; } - case ';': { + case CC_SEMI: { *tokenType = TK_SEMI; return 1; } - case '+': { + case CC_PLUS: { *tokenType = TK_PLUS; return 1; } - case '*': { + case CC_STAR: { *tokenType = TK_STAR; return 1; } - case '/': { + case CC_SLASH: { if( z[1]!='*' || z[2]==0 ){ *tokenType = TK_SLASH; return 1; @@ -165,15 +247,15 @@ int sqlite3GetToken(const unsigned char *z, int *tokenType){ *tokenType = TK_SPACE; /* IMP: R-22934-25134 */ return i; } - case '%': { + case CC_PERCENT: { *tokenType = TK_REM; return 1; } - case '=': { + case CC_EQ: { *tokenType = TK_EQ; return 1 + (z[1]=='='); } - case '<': { + case CC_LT: { if( (c=z[1])=='=' ){ *tokenType = TK_LE; return 2; @@ -188,7 +270,7 @@ int sqlite3GetToken(const unsigned char *z, int *tokenType){ return 1; } } - case '>': { + case CC_GT: { if( (c=z[1])=='=' ){ *tokenType = TK_GE; return 2; @@ -200,16 +282,16 @@ int sqlite3GetToken(const unsigned char *z, int *tokenType){ return 1; } } - case '!': { + case CC_BANG: { if( z[1]!='=' ){ *tokenType = TK_ILLEGAL; - return 2; + return 1; }else{ *tokenType = TK_NE; return 2; } } - case '|': { + case CC_PIPE: { if( z[1]!='|' ){ *tokenType = TK_BITOR; return 1; @@ -218,21 +300,19 @@ int sqlite3GetToken(const unsigned char *z, int *tokenType){ return 2; } } - case ',': { + case CC_COMMA: { *tokenType = TK_COMMA; return 1; } - case '&': { + case CC_AND: { *tokenType = TK_BITAND; return 1; } - case '~': { + case CC_TILDA: { *tokenType = TK_BITNOT; return 1; } - case '`': - case '\'': - case '"': { + case CC_QUOTE: { int delim = z[0]; testcase( delim=='`' ); testcase( delim=='\'' ); @@ -257,7 +337,7 @@ int sqlite3GetToken(const unsigned char *z, int *tokenType){ return i; } } - case '.': { + case CC_DOT: { #ifndef SQLITE_OMIT_FLOATING_POINT if( !sqlite3Isdigit(z[1]) ) #endif @@ -268,8 +348,7 @@ int sqlite3GetToken(const unsigned char *z, int *tokenType){ /* If the next character is a digit, this is a floating point ** number that begins with ".". 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': { + 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' ); @@ -304,22 +383,18 @@ int sqlite3GetToken(const unsigned char *z, int *tokenType){ } return i; } - case '[': { + case CC_QUOTE2: { for(i=1, c=z[0]; c!=']' && (c=z[i])!=0; i++){} *tokenType = c==']' ? TK_ID : TK_ILLEGAL; return i; } - case '?': { + case CC_VARNUM: { *tokenType = TK_VARIABLE; for(i=1; sqlite3Isdigit(z[i]); i++){} return i; } -#ifndef SQLITE_OMIT_TCL_VARIABLE - case '$': -#endif - case '@': /* For compatibility with MS SQL Server */ - case '#': - case ':': { + case CC_DOLLAR: + case CC_VARALPHA: { int n = 0; testcase( z[0]=='$' ); testcase( z[0]=='@' ); testcase( z[0]==':' ); testcase( z[0]=='#' ); @@ -348,8 +423,20 @@ int sqlite3GetToken(const unsigned char *z, int *tokenType){ if( n==0 ) *tokenType = TK_ILLEGAL; return i; } + case CC_KYWD: { + for(i=1; aiClass[z[i]]<=CC_KYWD; i++){} + if( IdChar(z[i]) ){ + /* This token started out using characters that can appear in keywords, + ** but z[i] is a character not allowed within keywords, so this must + ** be an identifier instead */ + i++; + break; + } + *tokenType = TK_ID; + return keywordCode((char*)z, i, tokenType); + } + case CC_X: { #ifndef SQLITE_OMIT_BLOB_LITERAL - case 'x': case 'X': { testcase( z[0]=='x' ); testcase( z[0]=='X' ); if( z[1]=='\'' ){ *tokenType = TK_BLOB; @@ -361,20 +448,22 @@ int sqlite3GetToken(const unsigned char *z, int *tokenType){ if( z[i] ) i++; return i; } - /* Otherwise fall through to the next case */ - } #endif + /* If it is not a BLOB literal, then it must be an ID, since no + ** SQL keywords start with the letter 'x'. Fall through */ + } + case CC_ID: { + i = 1; + break; + } default: { - if( !IdChar(*z) ){ - break; - } - for(i=1; IdChar(z[i]); i++){} - *tokenType = TK_ID; - return keywordCode((char*)z, i, tokenType); + *tokenType = TK_ILLEGAL; + return 1; } } - *tokenType = TK_ILLEGAL; - return 1; + while( IdChar(z[i]) ){ i++; } + *tokenType = TK_ID; + return i; } /* @@ -390,7 +479,6 @@ int sqlite3RunParser(Parse *pParse, const char *zSql, char **pzErrMsg){ void *pEngine; /* The LEMON-generated LALR(1) parser */ int tokenType; /* type of the next token */ int lastTokenParsed = -1; /* type of the previous token */ - u8 enableLookaside; /* Saved value of db->lookaside.bEnabled */ sqlite3 *db = pParse->db; /* The database connection */ int mxSqlLen; /* Max length of an SQL string */ @@ -406,16 +494,14 @@ int sqlite3RunParser(Parse *pParse, const char *zSql, char **pzErrMsg){ /* sqlite3ParserTrace(stdout, "parser: "); */ pEngine = sqlite3ParserAlloc(sqlite3Malloc); if( pEngine==0 ){ - db->mallocFailed = 1; - return SQLITE_NOMEM; + sqlite3OomFault(db); + return SQLITE_NOMEM_BKPT; } assert( pParse->pNewTable==0 ); assert( pParse->pNewTrigger==0 ); assert( pParse->nVar==0 ); assert( pParse->nzVar==0 ); assert( pParse->azVar==0 ); - enableLookaside = db->lookaside.bEnabled; - if( db->lookaside.pStart ) db->lookaside.bEnabled = 1; while( zSql[i]!=0 ){ assert( i>=0 ); pParse->sLastToken.z = &zSql[i]; @@ -428,7 +514,6 @@ int sqlite3RunParser(Parse *pParse, const char *zSql, char **pzErrMsg){ if( tokenType>=TK_SPACE ){ assert( tokenType==TK_SPACE || tokenType==TK_ILLEGAL ); if( db->u1.isInterrupted ){ - sqlite3ErrorMsg(pParse, "interrupt"); pParse->rc = SQLITE_INTERRUPT; break; } @@ -438,18 +523,17 @@ int sqlite3RunParser(Parse *pParse, const char *zSql, char **pzErrMsg){ break; } }else{ - if( tokenType==TK_SEMI ) pParse->zTail = &zSql[i]; sqlite3Parser(pEngine, tokenType, pParse->sLastToken, pParse); lastTokenParsed = tokenType; if( pParse->rc!=SQLITE_OK || db->mallocFailed ) break; } } assert( nErr==0 ); + pParse->zTail = &zSql[i]; if( pParse->rc==SQLITE_OK && db->mallocFailed==0 ){ assert( zSql[i]==0 ); if( lastTokenParsed!=TK_SEMI ){ sqlite3Parser(pEngine, TK_SEMI, pParse->sLastToken, pParse); - pParse->zTail = &zSql[i]; } if( pParse->rc==SQLITE_OK && db->mallocFailed==0 ){ sqlite3Parser(pEngine, 0, pParse->sLastToken, pParse); @@ -463,9 +547,8 @@ int sqlite3RunParser(Parse *pParse, const char *zSql, char **pzErrMsg){ sqlite3_mutex_leave(sqlite3MallocMutex()); #endif /* YYDEBUG */ sqlite3ParserFree(pEngine, sqlite3_free); - db->lookaside.bEnabled = enableLookaside; if( db->mallocFailed ){ - pParse->rc = SQLITE_NOMEM; + pParse->rc = SQLITE_NOMEM_BKPT; } if( pParse->rc!=SQLITE_OK && pParse->rc!=SQLITE_DONE && pParse->zErrMsg==0 ){ pParse->zErrMsg = sqlite3MPrintf(db, "%s", sqlite3ErrStr(pParse->rc)); |