diff options
Diffstat (limited to 'src')
| -rw-r--r-- | src/tokenize.c | 25 |
1 files changed, 17 insertions, 8 deletions
diff --git a/src/tokenize.c b/src/tokenize.c index 5e01de2b9..5d250e6f6 100644 --- a/src/tokenize.c +++ b/src/tokenize.c @@ -56,6 +56,7 @@ #define CC_ID 27 /* unicode characters usable in IDs */ #define CC_ILLEGAL 28 /* Illegal character */ #define CC_NUL 29 /* 0x00 */ +#define CC_BOM 30 /* First byte of UTF8 BOM: 0xEF 0xBB 0xBF */ static const unsigned char aiClass[] = { #ifdef SQLITE_ASCII @@ -68,14 +69,14 @@ static const unsigned char aiClass[] = { /* 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, 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, -/* 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 +/* 8x */ 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, +/* 9x */ 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, +/* Ax */ 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, +/* Bx */ 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, +/* Cx */ 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, +/* Dx */ 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, +/* Ex */ 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 30, +/* Fx */ 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27 #endif #ifdef SQLITE_EBCDIC /* x0 x1 x2 x3 x4 x5 x6 x7 x8 x9 xa xb xc xd xe xf */ @@ -535,6 +536,14 @@ int sqlite3GetToken(const unsigned char *z, int *tokenType){ i = 1; break; } + case CC_BOM: { + if( z[1]==0xbb && z[2]==0xbf ){ + *tokenType = TK_SPACE; + return 3; + } + i = 1; + break; + } case CC_NUL: { *tokenType = TK_ILLEGAL; return 0; |