index 2fbbf5475ece78fe38086faded6fed64781a4950..49a4898987e9b5cad78f470bc47c67af236eb4cc 100644 (file)
#include "libpq/pqformat.h"
#include "miscadmin.h"
#include "parser/scansup.h"
+#include "port/pg_bswap.h"
#include "regex/regex.h"
#include "utils/builtins.h"
#include "utils/bytea.h"
static int
bttextcmp_abbrev(Datum x, Datum y, SortSupport ssup)
{
- char *a = (char *) &x;
- char *b = (char *) &y;
- int result;
-
- result = memcmp(a, b, sizeof(Datum));
-
/*
- * When result = 0, the core system will call bttextfastcmp_c() or
+ * When 0 is returned, the core system will call bttextfastcmp_c() or
* bttextfastcmp_locale(). Even a strcmp() on two non-truncated strxfrm()
* blobs cannot indicate *equality* authoritatively, for the same reason
* that there is a strcoll() tie-breaker call to strcmp() in varstr_cmp().
*/
- return result;
+ if (x > y)
+ return 1;
+ else if (x == y)
+ return 0;
+ else
+ return -1;
}
/*
* Conversion routine for sortsupport. Converts original text to abbreviated
* key representation. Our encoding strategy is simple -- pack the first 8
- * bytes of a strxfrm() blob into a Datum.
+ * bytes of a strxfrm() blob into a Datum (on little-endian machines, the 8
+ * bytes are stored in reverse order), and treat it as an unsigned integer.
*/
static Datum
bttext_abbrev_convert(Datum original, SortSupport ssup)
@@ -2104,6 +2105,16 @@ bttext_abbrev_convert(Datum original, SortSupport ssup)
addHyperLogLog(&tss->abbr_card, hash);
+ /*
+ * Byteswap on little-endian machines.
+ *
+ * This is needed so that bttextcmp_abbrev() (an unsigned integer 3-way
+ * comparator) works correctly on all platforms. If we didn't do this,
+ * the comparator would have to call memcmp() with a pair of pointers to
+ * the first byte of each abbreviated key, which is slower.
+ */
+ res = DatumBigEndianToNative(res);
+
/* Don't leak memory here */
if (PointerGetDatum(authoritative) != original)
pfree(authoritative);
index 6555942c9214901615200e88ce2ca84489d3f590..e9cf93233fae65a34684cdcd19d34d028940af67 100644 (file)
((x << 8) & 0x00ff0000) | \
((x >> 8) & 0x0000ff00) | \
((x >> 24) & 0x000000ff))
-#endif /* HAVE__BUILTIN_BSWAP32 */
+#endif /* HAVE__BUILTIN_BSWAP32 */
#ifdef HAVE__BUILTIN_BSWAP64
#define BSWAP64(x) __builtin_bswap64(x)
((x >> 24) & 0x0000000000ff0000UL) | \
((x >> 40) & 0x000000000000ff00UL) | \
((x >> 56) & 0x00000000000000ffUL))
-#endif /* HAVE__BUILTIN_BSWAP64 */
+#endif /* HAVE__BUILTIN_BSWAP64 */
+
+/*
+ * Rearrange the bytes of a Datum from big-endian order into the native byte
+ * order. On big-endian machines, this does nothing at all. Note that the C
+ * type Datum is an unsigned integer type on all platforms.
+ *
+ * One possible application of the DatumBigEndianToNative() macro is to make
+ * bitwise comparisons cheaper. A simple 3-way comparison of Datums
+ * transformed by the macro (based on native, unsigned comparisons) will return
+ * the same result as a memcmp() of the corresponding original Datums, but can
+ * be much cheaper. It's generally safe to do this on big-endian systems
+ * without any special transformation occurring first.
+ */
+#ifdef WORDS_BIGENDIAN
+#define DatumBigEndianToNative(x) (x)
+#else /* !WORDS_BIGENDIAN */
+#if SIZEOF_DATUM == 8
+#define DatumBigEndianToNative(x) BSWAP64(x)
+#else /* SIZEOF_DATUM != 8 */
+#define DatumBigEndianToNative(x) BSWAP32(x)
+#endif /* SIZEOF_DATUM == 8 */
+#endif /* WORDS_BIGENDIAN */
#endif /* PG_BSWAP_H */