Fix patternsel() and callers to do the right thing for NOT LIKE and the other

negated-match operators.  patternsel had been using the supplied operator as
though it were a positive-match operator, and thus obtaining a wrong result,
which was even more wrong after the caller subtracted it from 1.  Seems
cleanest to give patternsel an explicit "negate" argument so that it knows
what's going on.  Also install the same factorization scheme for pattern
join selectivity estimators; even though they are just stubs at the
moment, this may keep someone from making the same type of mistake when
they get filled out.  Per report from Greg Mullane.

Backpatch to 8.2 --- previous releases do not show the problem because
patternsel() doesn't actually use the operator directly.

diff --git a/src/backend/utils/adt/selfuncs.c b/src/backend/utils/adt/selfuncs.c
index 56248a93b6ad742fcaf8c408a3b6091ae72a7769..f1a83b0875b232a1d33368a6efca9d77c410dd34 100644 (file)
--- a/src/backend/utils/adt/selfuncs.c
+++ b/src/backend/utils/adt/selfuncs.c
@@ -15,7 +15,7 @@
  *
  *
  * IDENTIFICATION
- *       $PostgreSQL: pgsql/src/backend/utils/adt/selfuncs.c,v 1.214.2.6 2007/08/31 23:35:29 tgl Exp $
+ *       $PostgreSQL: pgsql/src/backend/utils/adt/selfuncs.c,v 1.214.2.7 2007/11/07 21:00:44 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -900,7 +900,7 @@ scalargtsel(PG_FUNCTION_ARGS)
  * patternsel                  - Generic code for pattern-match selectivity.
  */
 static double
-patternsel(PG_FUNCTION_ARGS, Pattern_Type ptype)
+patternsel(PG_FUNCTION_ARGS, Pattern_Type ptype, bool negate)
 {
        PlannerInfo *root = (PlannerInfo *) PG_GETARG_POINTER(0);
        Oid                     operator = PG_GETARG_OID(1);
@@ -920,23 +920,40 @@ patternsel(PG_FUNCTION_ARGS, Pattern_Type ptype)
        Const      *rest = NULL;
        double          result;
 
+       /*
+        * If this is for a NOT LIKE or similar operator, get the corresponding
+        * positive-match operator and work with that.  Set result to the
+        * correct default estimate, too.
+        */
+       if (negate)
+       {
+               operator = get_negator(operator);
+               if (!OidIsValid(operator))
+                       elog(ERROR, "patternsel called for operator without a negator");
+               result = 1.0 - DEFAULT_MATCH_SEL;
+       }
+       else
+       {
+               result = DEFAULT_MATCH_SEL;
+       }
+
        /*
         * If expression is not variable op constant, then punt and return a
         * default estimate.
         */
        if (!get_restriction_variable(root, args, varRelid,
                                                                  &vardata, &other, &varonleft))
-               return DEFAULT_MATCH_SEL;
+               return result;
        if (!varonleft || !IsA(other, Const))
        {
                ReleaseVariableStats(vardata);
-               return DEFAULT_MATCH_SEL;
+               return result;
        }
        variable = (Node *) linitial(args);
 
        /*
         * If the constant is NULL, assume operator is strict and return zero, ie,
-        * operator will never return TRUE.
+        * operator will never return TRUE.  (It's zero even for a negator op.)
         */
        if (((Const *) other)->constisnull)
        {
@@ -955,7 +972,7 @@ patternsel(PG_FUNCTION_ARGS, Pattern_Type ptype)
        if (consttype != TEXTOID && consttype != BYTEAOID)
        {
                ReleaseVariableStats(vardata);
-               return DEFAULT_MATCH_SEL;
+               return result;
        }
 
        /*
@@ -990,7 +1007,7 @@ patternsel(PG_FUNCTION_ARGS, Pattern_Type ptype)
                        break;
                default:
                        ReleaseVariableStats(vardata);
-                       return DEFAULT_MATCH_SEL;
+                       return result;
        }
 
        /* divide pattern into fixed prefix and remainder */
@@ -1019,7 +1036,7 @@ patternsel(PG_FUNCTION_ARGS, Pattern_Type ptype)
                                elog(ERROR, "unrecognized consttype: %u",
                                         prefix->consttype);
                                ReleaseVariableStats(vardata);
-                               return DEFAULT_MATCH_SEL;
+                               return result;
                }
                prefix = string_to_const(prefixstr, vartype);
                pfree(prefixstr);
@@ -1126,7 +1143,7 @@ patternsel(PG_FUNCTION_ARGS, Pattern_Type ptype)
 
        ReleaseVariableStats(vardata);
 
-       return result;
+       return negate ? (1.0 - result) : result;
 }
 
 /*
@@ -1135,7 +1152,7 @@ patternsel(PG_FUNCTION_ARGS, Pattern_Type ptype)
 Datum
 regexeqsel(PG_FUNCTION_ARGS)
 {
-       PG_RETURN_FLOAT8(patternsel(fcinfo, Pattern_Type_Regex));
+       PG_RETURN_FLOAT8(patternsel(fcinfo, Pattern_Type_Regex, false));
 }
 
 /*
@@ -1144,7 +1161,7 @@ regexeqsel(PG_FUNCTION_ARGS)
 Datum
 icregexeqsel(PG_FUNCTION_ARGS)
 {
-       PG_RETURN_FLOAT8(patternsel(fcinfo, Pattern_Type_Regex_IC));
+       PG_RETURN_FLOAT8(patternsel(fcinfo, Pattern_Type_Regex_IC, false));
 }
 
 /*
@@ -1153,7 +1170,7 @@ icregexeqsel(PG_FUNCTION_ARGS)
 Datum
 likesel(PG_FUNCTION_ARGS)
 {
-       PG_RETURN_FLOAT8(patternsel(fcinfo, Pattern_Type_Like));
+       PG_RETURN_FLOAT8(patternsel(fcinfo, Pattern_Type_Like, false));
 }
 
 /*
@@ -1162,7 +1179,7 @@ likesel(PG_FUNCTION_ARGS)
 Datum
 iclikesel(PG_FUNCTION_ARGS)
 {
-       PG_RETURN_FLOAT8(patternsel(fcinfo, Pattern_Type_Like_IC));
+       PG_RETURN_FLOAT8(patternsel(fcinfo, Pattern_Type_Like_IC, false));
 }
 
 /*
@@ -1171,11 +1188,7 @@ iclikesel(PG_FUNCTION_ARGS)
 Datum
 regexnesel(PG_FUNCTION_ARGS)
 {
-       double          result;
-
-       result = patternsel(fcinfo, Pattern_Type_Regex);
-       result = 1.0 - result;
-       PG_RETURN_FLOAT8(result);
+       PG_RETURN_FLOAT8(patternsel(fcinfo, Pattern_Type_Regex, true));
 }
 
 /*
@@ -1184,11 +1197,7 @@ regexnesel(PG_FUNCTION_ARGS)
 Datum
 icregexnesel(PG_FUNCTION_ARGS)
 {
-       double          result;
-
-       result = patternsel(fcinfo, Pattern_Type_Regex_IC);
-       result = 1.0 - result;
-       PG_RETURN_FLOAT8(result);
+       PG_RETURN_FLOAT8(patternsel(fcinfo, Pattern_Type_Regex_IC, true));
 }
 
 /*
@@ -1197,11 +1206,7 @@ icregexnesel(PG_FUNCTION_ARGS)
 Datum
 nlikesel(PG_FUNCTION_ARGS)
 {
-       double          result;
-
-       result = patternsel(fcinfo, Pattern_Type_Like);
-       result = 1.0 - result;
-       PG_RETURN_FLOAT8(result);
+       PG_RETURN_FLOAT8(patternsel(fcinfo, Pattern_Type_Like, true));
 }
 
 /*
@@ -1210,11 +1215,7 @@ nlikesel(PG_FUNCTION_ARGS)
 Datum
 icnlikesel(PG_FUNCTION_ARGS)
 {
-       double          result;
-
-       result = patternsel(fcinfo, Pattern_Type_Like_IC);
-       result = 1.0 - result;
-       PG_RETURN_FLOAT8(result);
+       PG_RETURN_FLOAT8(patternsel(fcinfo, Pattern_Type_Like_IC, true));
 }
 
 /*
@@ -2109,13 +2110,23 @@ scalargtjoinsel(PG_FUNCTION_ARGS)
        PG_RETURN_FLOAT8(DEFAULT_INEQ_SEL);
 }
 
+/*
+ * patternjoinsel              - Generic code for pattern-match join selectivity.
+ */
+static double
+patternjoinsel(PG_FUNCTION_ARGS, Pattern_Type ptype, bool negate)
+{
+       /* For the moment we just punt. */
+       return negate ? (1.0 - DEFAULT_MATCH_SEL) : DEFAULT_MATCH_SEL;
+}
+
 /*
  *             regexeqjoinsel  - Join selectivity of regular-expression pattern match.
  */
 Datum
 regexeqjoinsel(PG_FUNCTION_ARGS)
 {
-       PG_RETURN_FLOAT8(DEFAULT_MATCH_SEL);
+       PG_RETURN_FLOAT8(patternjoinsel(fcinfo, Pattern_Type_Regex, false));
 }
 
 /*
@@ -2124,7 +2135,7 @@ regexeqjoinsel(PG_FUNCTION_ARGS)
 Datum
 icregexeqjoinsel(PG_FUNCTION_ARGS)
 {
-       PG_RETURN_FLOAT8(DEFAULT_MATCH_SEL);
+       PG_RETURN_FLOAT8(patternjoinsel(fcinfo, Pattern_Type_Regex_IC, false));
 }
 
 /*
@@ -2133,7 +2144,7 @@ icregexeqjoinsel(PG_FUNCTION_ARGS)
 Datum
 likejoinsel(PG_FUNCTION_ARGS)
 {
-       PG_RETURN_FLOAT8(DEFAULT_MATCH_SEL);
+       PG_RETURN_FLOAT8(patternjoinsel(fcinfo, Pattern_Type_Like, false));
 }
 
 /*
@@ -2142,7 +2153,7 @@ likejoinsel(PG_FUNCTION_ARGS)
 Datum
 iclikejoinsel(PG_FUNCTION_ARGS)
 {
-       PG_RETURN_FLOAT8(DEFAULT_MATCH_SEL);
+       PG_RETURN_FLOAT8(patternjoinsel(fcinfo, Pattern_Type_Like_IC, false));
 }
 
 /*
@@ -2151,11 +2162,7 @@ iclikejoinsel(PG_FUNCTION_ARGS)
 Datum
 regexnejoinsel(PG_FUNCTION_ARGS)
 {
-       float8          result;
-
-       result = DatumGetFloat8(regexeqjoinsel(fcinfo));
-       result = 1.0 - result;
-       PG_RETURN_FLOAT8(result);
+       PG_RETURN_FLOAT8(patternjoinsel(fcinfo, Pattern_Type_Regex, true));
 }
 
 /*
@@ -2164,11 +2171,7 @@ regexnejoinsel(PG_FUNCTION_ARGS)
 Datum
 icregexnejoinsel(PG_FUNCTION_ARGS)
 {
-       float8          result;
-
-       result = DatumGetFloat8(icregexeqjoinsel(fcinfo));
-       result = 1.0 - result;
-       PG_RETURN_FLOAT8(result);
+       PG_RETURN_FLOAT8(patternjoinsel(fcinfo, Pattern_Type_Regex_IC, true));
 }
 
 /*
@@ -2177,11 +2180,7 @@ icregexnejoinsel(PG_FUNCTION_ARGS)
 Datum
 nlikejoinsel(PG_FUNCTION_ARGS)
 {
-       float8          result;
-
-       result = DatumGetFloat8(likejoinsel(fcinfo));
-       result = 1.0 - result;
-       PG_RETURN_FLOAT8(result);
+       PG_RETURN_FLOAT8(patternjoinsel(fcinfo, Pattern_Type_Like, true));
 }
 
 /*
@@ -2190,11 +2189,7 @@ nlikejoinsel(PG_FUNCTION_ARGS)
 Datum
 icnlikejoinsel(PG_FUNCTION_ARGS)
 {
-       float8          result;
-
-       result = DatumGetFloat8(iclikejoinsel(fcinfo));
-       result = 1.0 - result;
-       PG_RETURN_FLOAT8(result);
+       PG_RETURN_FLOAT8(patternjoinsel(fcinfo, Pattern_Type_Like_IC, true));
 }
 
 /*