Add comparison operators and btree indexing support for type bytea.

From Joe Conway.

src/backend/utils/adt/selfuncs.c

@@ -15,7 +15,7 @@
  *
  *
  * IDENTIFICATION
- *	  $Header: /cvsroot/pgsql/src/backend/utils/adt/selfuncs.c,v 1.95 2001/07/16 05:06:59 tgl Exp $
+ *	  $Header: /cvsroot/pgsql/src/backend/utils/adt/selfuncs.c,v 1.96 2001/08/13 18:45:35 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -134,8 +134,16 @@ static void convert_string_to_scalar(unsigned char *value,
 						 double *scaledlobound,
 						 unsigned char *hibound,
 						 double *scaledhibound);
+static void convert_bytea_to_scalar(Datum value,
+						 double *scaledvalue,
+						 Datum lobound,
+						 double *scaledlobound,
+						 Datum hibound,
+						 double *scaledhibound);
 static double convert_one_string_to_scalar(unsigned char *value,
 							 int rangelo, int rangehi);
+static double convert_one_bytea_to_scalar(unsigned char *value, int valuelen,
+							 int rangelo, int rangehi);
 static unsigned char *convert_string_datum(Datum value, Oid typid);
 static double convert_timevalue_to_scalar(Datum value, Oid typid);
 static double get_att_numdistinct(Query *root, Var *var,
@@ -1664,6 +1672,9 @@ icnlikejoinsel(PG_FUNCTION_ARGS)
  * which is explained below.  The reason why this routine deals with
  * three values at a time, not just one, is that we need it for strings.
  *
+ * The bytea datatype is just enough different from strings that it has
+ * to be treated separately.
+ *
  * The several datatypes representing absolute times are all converted
  * to Timestamp, which is actually a double, and then we just use that
  * double value.  Note this will give bad results for the various "special"
@@ -1718,6 +1729,17 @@ convert_to_scalar(Datum value, Oid valuetypid, double *scaledvalue,
 				return true;
 			}
 
+		/*
+		 * Built-in bytea type
+		 */
+		case BYTEAOID:
+			{
+				convert_bytea_to_scalar(value, scaledvalue,
+										lobound, scaledlobound,
+										hibound, scaledhibound);
+				return true;
+			}
+
 		/*
 		 * Built-in time types
 		 */
@@ -1996,6 +2018,99 @@ convert_string_datum(Datum value, Oid typid)
 	return (unsigned char *) val;
 }
 
+/*
+ * Do convert_to_scalar()'s work for any bytea data type.
+ *
+ * Very similar to convert_string_to_scalar except we can't assume
+ * null-termination and therefore pass explicit lengths around.
+ *
+ * Also, assumptions about likely "normal" ranges of characters have been
+ * removed - a data range of 0..255 is always used, for now.  (Perhaps
+ * someday we will add information about actual byte data range to
+ * pg_statistic.)
+ */
+static void
+convert_bytea_to_scalar(Datum value,
+						double *scaledvalue,
+						Datum lobound,
+						double *scaledlobound,
+						Datum hibound,
+						double *scaledhibound)
+{
+	int			rangelo,
+				rangehi,
+				valuelen = VARSIZE(DatumGetPointer(value)) - VARHDRSZ,
+				loboundlen = VARSIZE(DatumGetPointer(lobound)) - VARHDRSZ,
+				hiboundlen = VARSIZE(DatumGetPointer(hibound)) - VARHDRSZ,
+				i,
+				minlen;
+	unsigned char *valstr = (unsigned char *) VARDATA(DatumGetPointer(value)),
+				*lostr = (unsigned char *) VARDATA(DatumGetPointer(lobound)),
+				*histr = (unsigned char *) VARDATA(DatumGetPointer(hibound));
+
+	/*
+	 * Assume bytea data is uniformly distributed across all byte values.
+	 */
+	rangelo = 0;
+	rangehi = 255;
+
+	/*
+	 * Now strip any common prefix of the three strings.
+	 */
+	minlen = Min(Min(valuelen, loboundlen), hiboundlen);
+	for (i = 0; i < minlen; i++)
+	{
+		if (*lostr != *histr || *lostr != *valstr)
+			break;
+		lostr++, histr++, valstr++;
+		loboundlen--, hiboundlen--, valuelen--;
+	}
+
+	/*
+	 * Now we can do the conversions.
+	 */
+	*scaledvalue = convert_one_bytea_to_scalar(valstr, valuelen, rangelo, rangehi);
+	*scaledlobound = convert_one_bytea_to_scalar(lostr, loboundlen, rangelo, rangehi);
+	*scaledhibound = convert_one_bytea_to_scalar(histr, hiboundlen, rangelo, rangehi);
+}
+
+static double
+convert_one_bytea_to_scalar(unsigned char *value, int valuelen,
+							int rangelo, int rangehi)
+{
+	double		num,
+				denom,
+				base;
+
+	if (valuelen <= 0)
+		return 0.0;				/* empty string has scalar value 0 */
+
+	/*
+	 * Since base is 256, need not consider more than about 10
+	 * chars (even this many seems like overkill)
+	 */
+	if (valuelen > 10)
+		valuelen = 10;
+
+	/* Convert initial characters to fraction */
+	base = rangehi - rangelo + 1;
+	num = 0.0;
+	denom = base;
+	while (valuelen-- > 0)
+	{
+		int			ch = *value++;
+
+		if (ch < rangelo)
+			ch = rangelo - 1;
+		else if (ch > rangehi)
+			ch = rangehi + 1;
+		num += ((double) (ch - rangelo)) / denom;
+		denom *= base;
+	}
+
+	return num;
+}
+
 /*
  * Do convert_to_scalar()'s work for any timevalue data type.
  */

src/backend/utils/adt/varlena.c

@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $Header: /cvsroot/pgsql/src/backend/utils/adt/varlena.c,v 1.70 2001/05/03 19:00:36 tgl Exp $
+ *	  $Header: /cvsroot/pgsql/src/backend/utils/adt/varlena.c,v 1.71 2001/08/13 18:45:35 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -875,3 +875,162 @@ name_text(PG_FUNCTION_ARGS)
 
 	PG_RETURN_TEXT_P(result);
 }
+
+
+/*****************************************************************************
+ *	Comparison Functions used for bytea
+ *
+ * Note: btree indexes need these routines not to leak memory; therefore,
+ * be careful to free working copies of toasted datums.  Most places don't
+ * need to be so careful.
+ *****************************************************************************/
+
+Datum
+byteaeq(PG_FUNCTION_ARGS)
+{
+	bytea	    *arg1 = PG_GETARG_BYTEA_P(0);
+	bytea   	*arg2 = PG_GETARG_BYTEA_P(1);
+	int			len1,
+				len2;
+	bool		result;
+
+	len1 = VARSIZE(arg1) - VARHDRSZ;
+	len2 = VARSIZE(arg2) - VARHDRSZ;
+
+	/* fast path for different-length inputs */
+	if (len1 != len2)
+		result = false;
+	else
+		result = (memcmp(VARDATA(arg1), VARDATA(arg2), len1) == 0);
+
+	PG_FREE_IF_COPY(arg1, 0);
+	PG_FREE_IF_COPY(arg2, 1);
+
+	PG_RETURN_BOOL(result);
+}
+
+Datum
+byteane(PG_FUNCTION_ARGS)
+{
+	bytea		*arg1 = PG_GETARG_BYTEA_P(0);
+	bytea		*arg2 = PG_GETARG_BYTEA_P(1);
+	int			len1,
+				len2;
+	bool		result;
+
+	len1 = VARSIZE(arg1) - VARHDRSZ;
+	len2 = VARSIZE(arg2) - VARHDRSZ;
+
+	/* fast path for different-length inputs */
+	if (len1 != len2)
+		result = true;
+	else
+		result = (memcmp(VARDATA(arg1), VARDATA(arg2), len1) != 0);
+
+	PG_FREE_IF_COPY(arg1, 0);
+	PG_FREE_IF_COPY(arg2, 1);
+
+	PG_RETURN_BOOL(result);
+}
+
+Datum
+bytealt(PG_FUNCTION_ARGS)
+{
+	bytea		*arg1 = PG_GETARG_BYTEA_P(0);
+	bytea		*arg2 = PG_GETARG_BYTEA_P(1);
+	int			len1,
+				len2;
+	int			cmp;
+
+	len1 = VARSIZE(arg1) - VARHDRSZ;
+	len2 = VARSIZE(arg2) - VARHDRSZ;
+
+	cmp = memcmp(VARDATA(arg1), VARDATA(arg2), Min(len1, len2));
+
+	PG_FREE_IF_COPY(arg1, 0);
+	PG_FREE_IF_COPY(arg2, 1);
+
+	PG_RETURN_BOOL((cmp < 0) || ((cmp == 0) && (len1 < len2)));
+}
+
+Datum
+byteale(PG_FUNCTION_ARGS)
+{
+	bytea		*arg1 = PG_GETARG_BYTEA_P(0);
+	bytea		*arg2 = PG_GETARG_BYTEA_P(1);
+	int			len1,
+				len2;
+	int			cmp;
+
+	len1 = VARSIZE(arg1) - VARHDRSZ;
+	len2 = VARSIZE(arg2) - VARHDRSZ;
+
+	cmp = memcmp(VARDATA(arg1), VARDATA(arg2), Min(len1, len2));
+
+	PG_FREE_IF_COPY(arg1, 0);
+	PG_FREE_IF_COPY(arg2, 1);
+
+	PG_RETURN_BOOL((cmp < 0) || ((cmp == 0) && (len1 <= len2)));
+}
+
+Datum
+byteagt(PG_FUNCTION_ARGS)
+{
+	bytea		*arg1 = PG_GETARG_BYTEA_P(0);
+	bytea		*arg2 = PG_GETARG_BYTEA_P(1);
+	int			len1,
+				len2;
+	int			cmp;
+
+	len1 = VARSIZE(arg1) - VARHDRSZ;
+	len2 = VARSIZE(arg2) - VARHDRSZ;
+
+	cmp = memcmp(VARDATA(arg1), VARDATA(arg2), Min(len1, len2));
+
+	PG_FREE_IF_COPY(arg1, 0);
+	PG_FREE_IF_COPY(arg2, 1);
+
+	PG_RETURN_BOOL((cmp > 0) || ((cmp == 0) && (len1 > len2)));
+}
+
+Datum
+byteage(PG_FUNCTION_ARGS)
+{
+	bytea		*arg1 = PG_GETARG_BYTEA_P(0);
+	bytea		*arg2 = PG_GETARG_BYTEA_P(1);
+	int			len1,
+				len2;
+	int			cmp;
+
+	len1 = VARSIZE(arg1) - VARHDRSZ;
+	len2 = VARSIZE(arg2) - VARHDRSZ;
+
+	cmp = memcmp(VARDATA(arg1), VARDATA(arg2), Min(len1, len2));
+
+	PG_FREE_IF_COPY(arg1, 0);
+	PG_FREE_IF_COPY(arg2, 1);
+
+	PG_RETURN_BOOL((cmp > 0) || ((cmp == 0) && (len1 >= len2)));
+}
+
+Datum
+byteacmp(PG_FUNCTION_ARGS)
+{
+	bytea		*arg1 = PG_GETARG_BYTEA_P(0);
+	bytea		*arg2 = PG_GETARG_BYTEA_P(1);
+	int			len1,
+				len2;
+	int			cmp;
+
+	len1 = VARSIZE(arg1) - VARHDRSZ;
+	len2 = VARSIZE(arg2) - VARHDRSZ;
+
+	cmp = memcmp(VARDATA(arg1), VARDATA(arg2), Min(len1, len2));
+	if ((cmp == 0) && (len1 != len2))
+		cmp = (len1 < len2) ? -1 : 1;
+
+	PG_FREE_IF_COPY(arg1, 0);
+	PG_FREE_IF_COPY(arg2, 1);
+
+	PG_RETURN_INT32(cmp);
+}

src/include/catalog/catversion.h

@@ -37,7 +37,7 @@
  * Portions Copyright (c) 1996-2001, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $Id: catversion.h,v 1.87 2001/08/10 18:57:39 tgl Exp $
+ * $Id: catversion.h,v 1.88 2001/08/13 18:45:36 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -53,6 +53,6 @@
  */
 
 /*							yyyymmddN */
-#define CATALOG_VERSION_NO	200108101
+#define CATALOG_VERSION_NO	200108131
 
 #endif

src/include/catalog/pg_amop.h

@@ -8,7 +8,7 @@
  * Portions Copyright (c) 1996-2001, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $Id: pg_amop.h,v 1.39 2001/08/10 18:57:39 tgl Exp $
+ * $Id: pg_amop.h,v 1.40 2001/08/13 18:45:36 tgl Exp $
  *
  * NOTES
  *	 the genbki.sh script reads this file and generates .bki
@@ -249,6 +249,16 @@ DATA(insert (  403 1077 1062 3 ));
 DATA(insert (  403 1077 1069 4 ));
 DATA(insert (  403 1077 1068 5 ));
 
+/*
+ *	nbtree bytea_ops
+ */
+
+DATA(insert (  403 1961 1957 1 ));
+DATA(insert (  403 1961 1958 2 ));
+DATA(insert (  403 1961 1955 3 ));
+DATA(insert (  403 1961 1960 4 ));
+DATA(insert (  403 1961 1959 5 ));
+
 /*
  *	nbtree date_ops
  */

src/include/catalog/pg_amproc.h

@@ -10,7 +10,7 @@
  * Portions Copyright (c) 1996-2001, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $Id: pg_amproc.h,v 1.28 2001/08/10 18:57:39 tgl Exp $
+ * $Id: pg_amproc.h,v 1.29 2001/08/13 18:45:36 tgl Exp $
  *
  * NOTES
  *	  the genbki.sh script reads this file and generates .bki
@@ -101,6 +101,7 @@ DATA(insert (403 1690 1693 1));
 DATA(insert (403 1399 1358 1));
 DATA(insert (403  424 1596 1));
 DATA(insert (403  425 1672 1));
+DATA(insert (403 1961 1954 1));
 
 
 /* hash */

src/include/catalog/pg_opclass.h

@@ -8,7 +8,7 @@
  * Portions Copyright (c) 1996-2001, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $Id: pg_opclass.h,v 1.37 2001/01/24 19:43:21 momjian Exp $
+ * $Id: pg_opclass.h,v 1.38 2001/08/13 18:45:36 tgl Exp $
  *
  * NOTES
  *	  the genbki.sh script reads this file and generates .bki
@@ -123,5 +123,7 @@ DATA(insert OID =  424 (	bit_ops		   1560   ));
 DESCR("");
 DATA(insert OID =  425 (	varbit_ops	   1562   ));
 DESCR("");
+DATA(insert OID = 1961 (	bytea_ops	     17   ));
+DESCR("");
 
 #endif	 /* PG_OPCLASS_H */

src/include/catalog/pg_operator.h

@@ -8,7 +8,7 @@
  * Portions Copyright (c) 1996-2001, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $Id: pg_operator.h,v 1.91 2001/06/17 02:05:20 tgl Exp $
+ * $Id: pg_operator.h,v 1.92 2001/08/13 18:45:36 tgl Exp $
  *
  * NOTES
  *	  the genbki.sh script reads this file and generates .bki
@@ -809,6 +809,14 @@ DATA(insert OID = 1919 (  "+"	   PGUID 0 l t f   0  700 700	0   0   0   0 float4
 DATA(insert OID = 1920 (  "+"	   PGUID 0 l t f   0  701 701	0   0   0   0 float8up - - ));
 DATA(insert OID = 1921 (  "+"	   PGUID 0 l t f   0 1700 1700  0   0	0	0 numeric_uplus - - ));
 
+/* bytea operators */
+DATA(insert OID = 1955 ( "="	   PGUID 0 b t t 17 17	16 1955 1956 1957 1957 byteaeq eqsel eqjoinsel ));
+DATA(insert OID = 1956 ( "<>"	   PGUID 0 b t f 17 17	16 1956 1955  0 0 byteane neqsel neqjoinsel ));
+DATA(insert OID = 1957 ( "<"	   PGUID 0 b t f 17 17	16 1959 1960  0 0 bytealt scalarltsel scalarltjoinsel ));
+DATA(insert OID = 1958 ( "<="	   PGUID 0 b t f 17 17	16 1960 1959  0 0 byteale scalarltsel scalarltjoinsel ));
+DATA(insert OID = 1959 ( ">"	   PGUID 0 b t f 17 17	16 1957 1958  0 0 byteagt scalargtsel scalargtjoinsel ));
+DATA(insert OID = 1960 ( ">="	   PGUID 0 b t f 17 17	16 1958 1957  0 0 byteage scalargtsel scalargtjoinsel ));
+
 /*
  * function prototypes
  */

src/include/catalog/pg_proc.h

@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1996-2001, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $Id: pg_proc.h,v 1.202 2001/08/10 20:52:25 tgl Exp $
+ * $Id: pg_proc.h,v 1.203 2001/08/13 18:45:36 tgl Exp $
  *
  * NOTES
  *	  The script catalog/genbki.sh reads this file and generates .bki
@@ -2699,6 +2699,22 @@ DATA(insert OID = 1946 (  encode						PGUID 12 f t t t 2 f 25 "17 25" 100 0 0 10
 DESCR("Convert bytea value into some ascii-only text string");
 DATA(insert OID = 1947 (  decode						PGUID 12 f t t t 2 f 17 "25 25" 100 0 0 100	binary_decode - ));
 DESCR("Convert ascii-encoded text string into bytea value");
+
+DATA(insert OID = 1948 (  byteaeq		   PGUID 12 f t t t 2 f 16 "17 17" 100 0 0 100	byteaeq - ));
+DESCR("equal");
+DATA(insert OID = 1949 (  bytealt		   PGUID 12 f t t t 2 f 16 "17 17" 100 0 0 100	bytealt - ));
+DESCR("less-than");
+DATA(insert OID = 1950 (  byteale		   PGUID 12 f t t t 2 f 16 "17 17" 100 0 0 100	byteale - ));
+DESCR("less-than-or-equal");
+DATA(insert OID = 1951 (  byteagt		   PGUID 12 f t t t 2 f 16 "17 17" 100 0 0 100	byteagt - ));
+DESCR("greater-than");
+DATA(insert OID = 1952 (  byteage		   PGUID 12 f t t t 2 f 16 "17 17" 100 0 0 100	byteage - ));
+DESCR("greater-than-or-equal");
+DATA(insert OID = 1953 (  byteane		   PGUID 12 f t t t 2 f 16 "17 17" 100 0 0 100	byteane - ));
+DESCR("not equal");
+DATA(insert OID = 1954 (  byteacmp		   PGUID 12 f t t t 2 f 23 "17 17" 100 0 0 100	byteacmp - ));
+DESCR("less-equal-greater");
+
  
 /*
  * prototypes for functions pg_proc.c

src/include/utils/builtins.h

@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1996-2001, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $Id: builtins.h,v 1.159 2001/08/09 18:28:18 petere Exp $
+ * $Id: builtins.h,v 1.160 2001/08/13 18:45:36 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -412,6 +412,13 @@ extern Datum byteaSetByte(PG_FUNCTION_ARGS);
 extern Datum byteaSetBit(PG_FUNCTION_ARGS);
 extern Datum binary_encode(PG_FUNCTION_ARGS);
 extern Datum binary_decode(PG_FUNCTION_ARGS);
+extern Datum byteaeq(PG_FUNCTION_ARGS);
+extern Datum byteane(PG_FUNCTION_ARGS);
+extern Datum bytealt(PG_FUNCTION_ARGS);
+extern Datum byteale(PG_FUNCTION_ARGS);
+extern Datum byteagt(PG_FUNCTION_ARGS);
+extern Datum byteage(PG_FUNCTION_ARGS);
+extern Datum byteacmp(PG_FUNCTION_ARGS);
 
 /* version.c */
 extern Datum pgsql_version(PG_FUNCTION_ARGS);