DBD-SQLite
view release on metacpan or search on metacpan
** ^If the third parameter to sqlite3_bind_text() is not NULL, then
** it should be a pointer to well-formed UTF8 text.
** ^If the third parameter to sqlite3_bind_text16() is not NULL, then
** it should be a pointer to well-formed UTF16 text.
** ^If the third parameter to sqlite3_bind_text64() is not NULL, then
** it should be a pointer to a well-formed unicode string that is
** either UTF8 if the sixth parameter is SQLITE_UTF8, or UTF16
** otherwise.
**
** [[byte-order determination rules]] ^The byte-order of
** UTF16 input text is determined by the byte-order mark (BOM, U+FEFF)
** found in first character, which is removed, or in the absence of a BOM
** the byte order is the native byte order of the host
** machine for sqlite3_bind_text16() or the byte order specified in
** the 6th parameter for sqlite3_bind_text64().)^
** ^If UTF16 input text contains invalid unicode
** characters, then SQLite might change those invalid characters
** into the unicode replacement character: U+FFFD.
**
** ^(In those routines that have a fourth argument, its value is the
** number of bytes in the parameter. To be clear: the value is the
** number of <u>bytes</u> in the value, not the number of characters.)^
** copy the content of the parameter nor call a destructor on the content
** when it has finished using that result.
** ^If the 4th parameter to the sqlite3_result_text* interfaces
** or sqlite3_result_blob is the special constant SQLITE_TRANSIENT
** then SQLite makes a copy of the result into space obtained
** from [sqlite3_malloc()] before it returns.
**
** ^For the sqlite3_result_text16(), sqlite3_result_text16le(), and
** sqlite3_result_text16be() routines, and for sqlite3_result_text64()
** when the encoding is not UTF8, if the input UTF16 begins with a
** byte-order mark (BOM, U+FEFF) then the BOM is removed from the
** string and the rest of the string is interpreted according to the
** byte-order specified by the BOM. ^The byte-order specified by
** the BOM at the beginning of the text overrides the byte-order
** specified by the interface procedure. ^So, for example, if
** sqlite3_result_text16le() is invoked with text that begins
** with bytes 0xfe, 0xff (a big-endian byte-order mark) then the
** first two bytes of input are skipped and the remaining input
** is interpreted as UTF16BE text.
**
** ^For UTF16 input text to the sqlite3_result_text16(),
** sqlite3_result_text16be(), sqlite3_result_text16le(), and
** sqlite3_result_text64() routines, if the text contains invalid
** UTF16 characters, the invalid characters might be converted
** 11110uuu 10uuzzzz 10yyyyyy 10xxxxxx 000uuuuu zzzzyyyy yyxxxxxx
**
**
** Notes on UTF-16: (with wwww+1==uuuuu)
**
** Word-0 Word-1 Value
** 110110ww wwzzzzyy 110111yy yyxxxxxx 000uuuuu zzzzyyyy yyxxxxxx
** zzzzyyyy yyxxxxxx 00000000 zzzzyyyy yyxxxxxx
**
**
** BOM or Byte Order Mark:
** 0xff 0xfe little-endian utf-16 follows
** 0xfe 0xff big-endian utf-16 follows
**
*/
/* #include "sqliteInt.h" */
/* #include <assert.h> */
/* #include "vdbeInt.h" */
#if !defined(SQLITE_AMALGAMATION) && SQLITE_BYTEORDER==0
/*
#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_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
/* x0 x1 x2 x3 x4 x5 x6 x7 x8 x9 xa xb xc xd xe xf */
/* 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, 2, 2, 9, 28, 28, 28, 2,
#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 */
/* no break */ deliberate_fall_through
}
case CC_KYWD:
case CC_ID: {
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;
** ^If the third parameter to sqlite3_bind_text() is not NULL, then
** it should be a pointer to well-formed UTF8 text.
** ^If the third parameter to sqlite3_bind_text16() is not NULL, then
** it should be a pointer to well-formed UTF16 text.
** ^If the third parameter to sqlite3_bind_text64() is not NULL, then
** it should be a pointer to a well-formed unicode string that is
** either UTF8 if the sixth parameter is SQLITE_UTF8, or UTF16
** otherwise.
**
** [[byte-order determination rules]] ^The byte-order of
** UTF16 input text is determined by the byte-order mark (BOM, U+FEFF)
** found in first character, which is removed, or in the absence of a BOM
** the byte order is the native byte order of the host
** machine for sqlite3_bind_text16() or the byte order specified in
** the 6th parameter for sqlite3_bind_text64().)^
** ^If UTF16 input text contains invalid unicode
** characters, then SQLite might change those invalid characters
** into the unicode replacement character: U+FFFD.
**
** ^(In those routines that have a fourth argument, its value is the
** number of bytes in the parameter. To be clear: the value is the
** number of <u>bytes</u> in the value, not the number of characters.)^
** copy the content of the parameter nor call a destructor on the content
** when it has finished using that result.
** ^If the 4th parameter to the sqlite3_result_text* interfaces
** or sqlite3_result_blob is the special constant SQLITE_TRANSIENT
** then SQLite makes a copy of the result into space obtained
** from [sqlite3_malloc()] before it returns.
**
** ^For the sqlite3_result_text16(), sqlite3_result_text16le(), and
** sqlite3_result_text16be() routines, and for sqlite3_result_text64()
** when the encoding is not UTF8, if the input UTF16 begins with a
** byte-order mark (BOM, U+FEFF) then the BOM is removed from the
** string and the rest of the string is interpreted according to the
** byte-order specified by the BOM. ^The byte-order specified by
** the BOM at the beginning of the text overrides the byte-order
** specified by the interface procedure. ^So, for example, if
** sqlite3_result_text16le() is invoked with text that begins
** with bytes 0xfe, 0xff (a big-endian byte-order mark) then the
** first two bytes of input are skipped and the remaining input
** is interpreted as UTF16BE text.
**
** ^For UTF16 input text to the sqlite3_result_text16(),
** sqlite3_result_text16be(), sqlite3_result_text16le(), and
** sqlite3_result_text64() routines, if the text contains invalid
** UTF16 characters, the invalid characters might be converted
( run in 0.438 second using v1.01-cache-2.11-cpan-e9daa2b36ef )