Create a selectivity estimation function for the text search @@ operator.

Jan Urbanski

doc/src/sgml/catalogs.sgml

@@ -1,4 +1,4 @@
-<!-- $PostgreSQL: pgsql/doc/src/sgml/catalogs.sgml,v 2.174 2008/09/15 18:43:41 tgl Exp $ -->
+<!-- $PostgreSQL: pgsql/doc/src/sgml/catalogs.sgml,v 2.175 2008/09/19 19:03:40 tgl Exp $ -->
 <!--
  Documentation of the system catalogs, directed toward PostgreSQL developers
  -->
@@ -6664,6 +6664,9 @@
        A list of the frequencies of the most common values or elements,
        i.e., number of occurrences of each divided by total number of rows.
        (NULL when <structfield>most_common_vals</structfield> is.)
+       For some datatypes such as <type>tsvector</>, it can also store some
+       additional information, making it longer than the
+       <structfield>most_common_vals</> array.
       </entry>
      </row>
 

src/backend/tsearch/Makefile

@@ -4,7 +4,7 @@
 #
 # Copyright (c) 2006-2008, PostgreSQL Global Development Group
 #
-# $PostgreSQL: pgsql/src/backend/tsearch/Makefile,v 1.7 2008/07/14 00:51:45 tgl Exp $
+# $PostgreSQL: pgsql/src/backend/tsearch/Makefile,v 1.8 2008/09/19 19:03:40 tgl Exp $
 #
 #-------------------------------------------------------------------------
 subdir = src/backend/tsearch
@@ -19,7 +19,7 @@ DICTFILES=synonym_sample.syn thesaurus_sample.ths hunspell_sample.affix \
 OBJS = ts_locale.o ts_parse.o wparser.o wparser_def.o dict.o \
 	dict_simple.o dict_synonym.o dict_thesaurus.o \
 	dict_ispell.o regis.o spell.o \
-	to_tsany.o ts_typanalyze.o ts_utils.o
+	to_tsany.o ts_selfuncs.o ts_typanalyze.o ts_utils.o
 
 include $(top_srcdir)/src/backend/common.mk
 

src/backend/tsearch/ts_selfuncs.c

@@ -0,0 +1,363 @@
+/*-------------------------------------------------------------------------
+ *
+ * ts_selfuncs.c
+ *	  Selectivity estimation functions for text search operators.
+ *
+ * Portions Copyright (c) 1996-2008, PostgreSQL Global Development Group
+ *
+ *
+ * IDENTIFICATION
+ *	  $PostgreSQL: pgsql/src/backend/tsearch/ts_selfuncs.c,v 1.1 2008/09/19 19:03:40 tgl Exp $
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "postgres.h"
+
+#include "catalog/pg_statistic.h"
+#include "catalog/pg_type.h"
+#include "miscadmin.h"
+#include "nodes/nodes.h"
+#include "tsearch/ts_type.h"
+#include "utils/lsyscache.h"
+#include "utils/selfuncs.h"
+#include "utils/syscache.h"
+
+
+/*
+ * The default text search selectivity is chosen to be small enough to
+ * encourage indexscans for typical table densities.  See selfuncs.h and
+ * DEFAULT_EQ_SEL for details.
+ */
+#define DEFAULT_TS_MATCH_SEL 0.005
+
+/* lookup table type for binary searching through MCELEMs */
+typedef struct
+{
+	text   *element;
+	float4	frequency;
+} TextFreq;
+
+/* type of keys for bsearch'ing through an array of TextFreqs */
+typedef struct
+{
+	char	*lexeme;
+	int		length;
+} LexemeKey;
+
+static Selectivity tsquerysel(VariableStatData *vardata, Datum constval);
+static Selectivity mcelem_tsquery_selec(TSQuery query,
+										Datum *mcelem, int nmcelem,
+										float4 *numbers, int nnumbers);
+static Selectivity tsquery_opr_selec(QueryItem *item, char *operand,
+								 TextFreq *lookup, int length, float4 minfreq);
+static int	compare_lexeme_textfreq(const void *e1, const void *e2);
+
+
+/*
+ *	tsmatchsel -- Selectivity of "@@"
+ *
+ * restriction selectivity function for tsvector @@ tsquery and
+ * tsquery @@ tsvector
+ */
+Datum
+tsmatchsel(PG_FUNCTION_ARGS)
+{
+	PlannerInfo *root = (PlannerInfo *) PG_GETARG_POINTER(0);
+#ifdef NOT_USED
+	Oid			operator = PG_GETARG_OID(1);
+#endif
+	List	   *args = (List *) PG_GETARG_POINTER(2);
+	int			varRelid = PG_GETARG_INT32(3);
+	VariableStatData vardata;
+	Node	   *other;
+	bool		varonleft;
+	Selectivity	selec;
+
+	/*
+	 * If expression is not variable = something or something = variable, then
+	 * punt and return a default estimate.
+	 */
+	if (!get_restriction_variable(root, args, varRelid,
+								  &vardata, &other, &varonleft))
+		PG_RETURN_FLOAT8(DEFAULT_TS_MATCH_SEL);
+
+	/*
+	 * Can't do anything useful if the something is not a constant, either.
+	 */
+	if (!IsA(other, Const))
+	{
+		ReleaseVariableStats(vardata);
+		PG_RETURN_FLOAT8(DEFAULT_TS_MATCH_SEL);
+	}
+
+	/*
+	 * The "@@" operator is strict, so we can cope with NULL right away
+	 */
+	if (((Const *) other)->constisnull)
+	{
+		ReleaseVariableStats(vardata);
+		PG_RETURN_FLOAT8(0.0);
+	}
+
+	/*
+	 * OK, there's a Var and a Const we're dealing with here. We need the Var
+	 * to be a TSVector (or else we don't have any useful statistic for it).
+	 * We have to check this because the Var might be the TSQuery not the
+	 * TSVector.
+	 */
+	if (vardata.vartype == TSVECTOROID)
+	{
+		/* tsvector @@ tsquery or the other way around */
+		Assert(((Const *) other)->consttype == TSQUERYOID);
+
+		selec = tsquerysel(&vardata, ((Const *) other)->constvalue);
+	}
+	else
+	{
+		/* The Var is something we don't have useful statistics for */
+		selec = DEFAULT_TS_MATCH_SEL;
+	}
+
+	ReleaseVariableStats(vardata);
+
+	CLAMP_PROBABILITY(selec);
+
+	PG_RETURN_FLOAT8((float8) selec);
+}
+
+
+/*
+ *	tsmatchjoinsel -- join selectivity of "@@"
+ *
+ * join selectivity function for tsvector @@ tsquery and tsquery @@ tsvector
+ */
+Datum
+tsmatchjoinsel(PG_FUNCTION_ARGS)
+{
+	/* for the moment we just punt */
+	PG_RETURN_FLOAT8(DEFAULT_TS_MATCH_SEL);
+}
+
+
+/*
+ * @@ selectivity for tsvector var vs tsquery constant
+ */
+static Selectivity
+tsquerysel(VariableStatData *vardata, Datum constval)
+{
+	Selectivity			selec;
+
+	if (HeapTupleIsValid(vardata->statsTuple))
+	{
+		TSQuery				query;
+		Form_pg_statistic	stats;
+		Datum				*values;
+		int					nvalues;
+		float4				*numbers;
+		int					nnumbers;
+
+		/* The caller made sure the const is a TSQuery, so get it now */
+		query = DatumGetTSQuery(constval);
+
+		stats = (Form_pg_statistic) GETSTRUCT(vardata->statsTuple);
+
+		/* MCELEM will be an array of TEXT elements for a tsvector column */
+		if (get_attstatsslot(vardata->statsTuple,
+							 TEXTOID, -1,
+							 STATISTIC_KIND_MCELEM, InvalidOid,
+							 &values, &nvalues,
+							 &numbers, &nnumbers))
+		{
+			/*
+			 * There is a most-common-elements slot for the tsvector Var, so
+			 * use that.
+			 */
+			selec = mcelem_tsquery_selec(query, values, nvalues,
+										 numbers, nnumbers);
+			free_attstatsslot(TEXTOID, values, nvalues, numbers, nnumbers);
+		}
+		else
+		{
+			/* No most-common-elements info, so we must punt */
+			selec = (Selectivity) DEFAULT_TS_MATCH_SEL;
+		}
+	}
+	else
+	{
+		/* No stats at all, so we must punt */
+		selec = (Selectivity) DEFAULT_TS_MATCH_SEL;
+	}
+
+	return selec;
+}
+
+/*
+ * Extract data from the pg_statistic arrays into useful format.
+ */
+static Selectivity
+mcelem_tsquery_selec(TSQuery query, Datum *mcelem, int nmcelem,
+					 float4 *numbers, int nnumbers)
+{
+	float4			minfreq;
+	TextFreq		*lookup;
+	Selectivity		selec;
+	int				i;
+
+	/*
+	 * There should be two more Numbers than Values, because the last two
+	 * cells are taken for minimal and maximal frequency.  Punt if not.
+	 */
+	if (nnumbers != nmcelem + 2)
+		return DEFAULT_TS_MATCH_SEL;
+
+	/*
+	 * Transpose the data into a single array so we can use bsearch().
+	 */
+	lookup = (TextFreq *) palloc(sizeof(TextFreq) * nmcelem);
+	for (i = 0; i < nmcelem; i++)
+	{
+		/*
+		 * The text Datums came from an array, so it cannot be compressed
+		 * or stored out-of-line -- it's safe to use VARSIZE_ANY*.
+		 */
+		Assert(!VARATT_IS_COMPRESSED(mcelem[i]) && !VARATT_IS_EXTERNAL(mcelem[i]));
+		lookup[i].element = (text *) DatumGetPointer(mcelem[i]);
+		lookup[i].frequency = numbers[i];
+	}
+
+	/*
+	 * Grab the lowest frequency. compute_tsvector_stats() stored it for us in
+	 * the one before the last cell of the Numbers array. See ts_typanalyze.c
+	 */
+	minfreq = numbers[nnumbers - 2];
+
+	selec = tsquery_opr_selec(GETQUERY(query), GETOPERAND(query), lookup,
+							  nmcelem, minfreq);
+
+	pfree(lookup);
+
+	return selec;
+}
+
+/*
+ * Traverse the tsquery in preorder, calculating selectivity as:
+ *
+ *   selec(left_oper) * selec(right_oper) in AND nodes,
+ *
+ *   selec(left_oper) + selec(right_oper) -
+ *      selec(left_oper) * selec(right_oper) in OR nodes,
+ *
+ *   1 - select(oper) in NOT nodes
+ *
+ *   freq[val] in VAL nodes, if the value is in MCELEM
+ *   min(freq[MCELEM]) / 2 in VAL nodes, if it is not
+ *
+ *
+ * The MCELEM array is already sorted (see ts_typanalyze.c), so we can use
+ * binary search for determining freq[MCELEM].
+ */
+static Selectivity
+tsquery_opr_selec(QueryItem *item, char *operand,
+				  TextFreq *lookup, int length, float4 minfreq)
+{
+	LexemeKey	key;
+	TextFreq	*searchres;
+	Selectivity	selec, s1, s2;
+
+	/* since this function recurses, it could be driven to stack overflow */
+	check_stack_depth();
+
+	if (item->type == QI_VAL)
+	{
+		QueryOperand *oper = (QueryOperand *) item;
+
+		/*
+		 * Prepare the key for bsearch().
+		 */
+		key.lexeme = operand + oper->distance;
+		key.length = oper->length;
+
+		searchres = (TextFreq *) bsearch(&key, lookup, length,
+										 sizeof(TextFreq),
+										 compare_lexeme_textfreq);
+
+		if (searchres)
+		{
+			/*
+			 * The element is in MCELEM. Return precise selectivity (or at
+			 * least as precise as ANALYZE could find out).
+			 */
+			return (Selectivity) searchres->frequency;
+		}
+		else
+		{
+			/*
+			 * The element is not in MCELEM. Punt, but assert that the
+			 * selectivity cannot be more than minfreq / 2.
+			 */
+			return (Selectivity) Min(DEFAULT_TS_MATCH_SEL, minfreq / 2);
+		}
+	}
+
+	/* Current TSQuery node is an operator */
+	switch (item->operator.oper)
+	{
+		case OP_NOT:
+			selec =  1.0 - tsquery_opr_selec(item + 1, operand,
+											 lookup, length, minfreq);
+			break;
+
+		case OP_AND:
+			s1 = tsquery_opr_selec(item + 1, operand,
+									 lookup, length, minfreq);
+			s2 = tsquery_opr_selec(item + item->operator.left, operand,
+								   lookup, length, minfreq);
+			selec = s1 * s2;
+			break;
+
+		case OP_OR:
+			s1 = tsquery_opr_selec(item + 1, operand,
+								   lookup, length, minfreq);
+			s2 = tsquery_opr_selec(item + item->operator.left, operand,
+								   lookup, length, minfreq);
+			selec = s1 + s2 - s1 * s2;
+			break;
+
+		default:
+			elog(ERROR, "unrecognized operator: %d", item->operator.oper);
+			selec = 0;			/* keep compiler quiet */
+			break;
+	}
+
+	/* Clamp intermediate results to stay sane despite roundoff error */
+	CLAMP_PROBABILITY(selec);
+
+	return selec;
+}
+
+/*
+ * bsearch() comparator for a lexeme (non-NULL terminated string with length)
+ * and a TextFreq. Use length, then byte-for-byte comparison, because that's
+ * how ANALYZE code sorted data before storing it in a statistic tuple.
+ * See ts_typanalyze.c for details.
+ */
+static int
+compare_lexeme_textfreq(const void *e1, const void *e2)
+{
+	const LexemeKey	*key = (const LexemeKey *) e1;
+	const TextFreq	*t = (const TextFreq *) e2;
+	int				len1,
+					len2;
+
+	len1 = key->length;
+	len2 = VARSIZE_ANY_EXHDR(t->element);
+
+	/* Compare lengths first, possibly avoiding a strncmp call */
+	if (len1 > len2)
+		return 1;
+	else if (len1 < len2)
+		return -1;
+
+	/* Fall back on byte-for-byte comparison */
+	return strncmp(key->lexeme, VARDATA_ANY(t->element), len1);
+}

src/backend/tsearch/ts_typanalyze.c

@@ -7,7 +7,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/tsearch/ts_typanalyze.c,v 1.1 2008/07/14 00:51:45 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/tsearch/ts_typanalyze.c,v 1.2 2008/09/19 19:03:40 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -43,7 +43,9 @@ static void compute_tsvector_stats(VacAttrStats *stats,
 static void prune_lexemes_hashtable(HTAB *lexemes_tab, int b_current);
 static uint32 lexeme_hash(const void *key, Size keysize);
 static int lexeme_match(const void *key1, const void *key2, Size keysize);
-static int trackitem_compare_desc(const void *e1, const void *e2);
+static int lexeme_compare(const void *key1, const void *key2);
+static int trackitem_compare_frequencies_desc(const void *e1, const void *e2);
+static int trackitem_compare_lexemes(const void *e1, const void *e2);
 
 
 /*
@@ -247,6 +249,7 @@ compute_tsvector_stats(VacAttrStats *stats,
 		int			i;
 		TrackItem	**sort_table;
 		int			track_len;
+		int			minfreq, maxfreq;
 
 		stats->stats_valid = true;
 		/* Do the simple null-frac and average width stats */
@@ -273,7 +276,7 @@ compute_tsvector_stats(VacAttrStats *stats,
 		Assert(i == track_len);
 
 		qsort(sort_table, track_len, sizeof(TrackItem *),
-			  trackitem_compare_desc);
+			  trackitem_compare_frequencies_desc);
 
 		/* Suppress any single-occurrence items */
 		while (track_len > 0)
@@ -287,6 +290,26 @@ compute_tsvector_stats(VacAttrStats *stats,
 		if (num_mcelem > track_len)
 			num_mcelem = track_len;
 
+		/* Grab the minimal and maximal frequencies that will get stored */
+		minfreq = sort_table[num_mcelem - 1]->frequency;
+		maxfreq = sort_table[0]->frequency;
+
+		/*
+		 * We want to store statistics sorted on the lexeme value using first
+		 * length, then byte-for-byte comparison. The reason for doing length
+		 * comparison first is that we don't care about the ordering so long
+		 * as it's consistent, and comparing lengths first gives us a chance
+		 * to avoid a strncmp() call.
+		 *
+		 * This is different from what we do with scalar statistics -- they get
+		 * sorted on frequencies. The rationale is that we usually search
+		 * through most common elements looking for a specific value, so we can
+		 * grab its frequency.  When values are presorted we can employ binary
+		 * search for that.  See ts_selfuncs.c for a real usage scenario.
+		 */
+		qsort(sort_table, num_mcelem, sizeof(TrackItem *),
+			  trackitem_compare_lexemes);
+
 		/* Generate MCELEM slot entry */
 		if (num_mcelem > 0)
 		{
@@ -296,8 +319,15 @@ compute_tsvector_stats(VacAttrStats *stats,
 
 			/* Must copy the target values into anl_context */
 			old_context = MemoryContextSwitchTo(stats->anl_context);
+
+			/*
+			 * We sorted statistics on the lexeme value, but we want to be
+			 * able to find out the minimal and maximal frequency without
+			 * going through all the values.  We keep those two extra
+			 * frequencies in two extra cells in mcelem_freqs.
+			 */
 			mcelem_values = (Datum *) palloc(num_mcelem * sizeof(Datum));
-			mcelem_freqs = (float4 *) palloc(num_mcelem * sizeof(float4));
+			mcelem_freqs = (float4 *) palloc((num_mcelem + 2) * sizeof(float4));
 
 			for (i = 0; i < num_mcelem; i++)
 			{
@@ -308,12 +338,15 @@ compute_tsvector_stats(VacAttrStats *stats,
 															 item->key.length));
 				mcelem_freqs[i] = (double) item->frequency / (double) nonnull_cnt;
 			}
+			mcelem_freqs[i++] = (double) minfreq / (double) nonnull_cnt;
+			mcelem_freqs[i] = (double) maxfreq / (double) nonnull_cnt;
 			MemoryContextSwitchTo(old_context);
 
 			stats->stakind[0] = STATISTIC_KIND_MCELEM;
 			stats->staop[0] = TextEqualOperator;
 			stats->stanumbers[0] = mcelem_freqs;
-			stats->numnumbers[0] = num_mcelem;
+			/* See above comment about two extra frequency fields */
+			stats->numnumbers[0] = num_mcelem + 2;
 			stats->stavalues[0] = mcelem_values;
 			stats->numvalues[0] = num_mcelem;
 			/* We are storing text values */
@@ -379,25 +412,48 @@ lexeme_hash(const void *key, Size keysize)
 static int
 lexeme_match(const void *key1, const void *key2, Size keysize)
 {
-	const LexemeHashKey *d1 = (const LexemeHashKey *) key1;
+	/* The keysize parameter is superfluous, the keys store their lengths */
-	const LexemeHashKey *d2 = (const LexemeHashKey *) key2;
+	return lexeme_compare(key1, key2);
-
-	/* The lexemes need to have the same length, and be memcmp-equal */
-	if (d1->length == d2->length &&
-		memcmp(d1->lexeme, d2->lexeme, d1->length) == 0)
-		return 0;
-	else
-		return 1;
 }
 
 /*
- *	qsort() comparator for TrackItems - LC style (descending sort)
+ *	Comparison function for lexemes.
  */
 static int
-trackitem_compare_desc(const void *e1, const void *e2)
+lexeme_compare(const void *key1, const void *key2)
+{
+	const LexemeHashKey	*d1 = (const LexemeHashKey *) key1;
+	const LexemeHashKey	*d2 = (const LexemeHashKey *) key2;
+
+	/* First, compare by length */
+	if (d1->length > d2->length)
+		return 1;
+	else if (d1->length < d2->length)
+		return -1;
+	/* Lengths are equal, do a byte-by-byte comparison */
+	return strncmp(d1->lexeme, d2->lexeme, d1->length);
+}
+
+/*
+ *	qsort() comparator for sorting TrackItems on frequencies (descending sort)
+ */
+static int
+trackitem_compare_frequencies_desc(const void *e1, const void *e2)
 {
 	const TrackItem * const *t1 = (const TrackItem * const *) e1;
 	const TrackItem * const *t2 = (const TrackItem * const *) e2;
 
 	return (*t2)->frequency - (*t1)->frequency;
 }
+
+/*
+ *	qsort() comparator for sorting TrackItems on lexemes
+ */
+static int
+trackitem_compare_lexemes(const void *e1, const void *e2)
+{
+	const TrackItem * const *t1 = (const TrackItem * const *) e1;
+	const TrackItem * const *t2 = (const TrackItem * const *) e2;
+
+	return lexeme_compare(&(*t1)->key, &(*t2)->key);
+}

src/include/catalog/catversion.h

@@ -37,7 +37,7 @@
  * Portions Copyright (c) 1996-2008, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/catalog/catversion.h,v 1.486 2008/09/15 18:43:41 tgl Exp $
+ * $PostgreSQL: pgsql/src/include/catalog/catversion.h,v 1.487 2008/09/19 19:03:40 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -53,6 +53,6 @@
  */
 
 /*							yyyymmddN */
-#define CATALOG_VERSION_NO	200809151
+#define CATALOG_VERSION_NO	200809191
 
 #endif

src/include/catalog/pg_operator.h

@@ -8,7 +8,7 @@
  * Portions Copyright (c) 1996-2008, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/catalog/pg_operator.h,v 1.162 2008/08/16 00:01:37 tgl Exp $
+ * $PostgreSQL: pgsql/src/include/catalog/pg_operator.h,v 1.163 2008/09/19 19:03:40 tgl Exp $
  *
  * NOTES
  *	  the genbki.sh script reads this file and generates .bki
@@ -915,10 +915,10 @@ DATA(insert OID = 3630 (  "<>"	   PGNSP PGUID b f f 3614	 3614	 16 3630 3629	 ts
 DATA(insert OID = 3631 (  ">="	   PGNSP PGUID b f f 3614	 3614	 16 3628 3627	 tsvector_ge scalargtsel scalargtjoinsel ));
 DATA(insert OID = 3632 (  ">"	   PGNSP PGUID b f f 3614	 3614	 16 3627 3628	 tsvector_gt scalargtsel scalargtjoinsel ));
 DATA(insert OID = 3633 (  "||"	   PGNSP PGUID b f f 3614	 3614	 3614  0	0	 tsvector_concat   -	-	  ));
-DATA(insert OID = 3636 (  "@@"	   PGNSP PGUID b f f 3614	 3615	 16 3637	0	 ts_match_vq   contsel	   contjoinsel	 ));
+DATA(insert OID = 3636 (  "@@"	   PGNSP PGUID b f f 3614	 3615	 16 3637	0	 ts_match_vq   tsmatchsel tsmatchjoinsel ));
-DATA(insert OID = 3637 (  "@@"	   PGNSP PGUID b f f 3615	 3614	 16 3636	0	 ts_match_qv   contsel	   contjoinsel	 ));
+DATA(insert OID = 3637 (  "@@"	   PGNSP PGUID b f f 3615	 3614	 16 3636	0	 ts_match_qv   tsmatchsel tsmatchjoinsel ));
-DATA(insert OID = 3660 (  "@@@"    PGNSP PGUID b f f 3614	 3615	 16 3661	0	 ts_match_vq   contsel	   contjoinsel	 ));
+DATA(insert OID = 3660 (  "@@@"    PGNSP PGUID b f f 3614	 3615	 16 3661	0	 ts_match_vq   tsmatchsel tsmatchjoinsel ));
-DATA(insert OID = 3661 (  "@@@"    PGNSP PGUID b f f 3615	 3614	 16 3660	0	 ts_match_qv   contsel	   contjoinsel	 ));
+DATA(insert OID = 3661 (  "@@@"    PGNSP PGUID b f f 3615	 3614	 16 3660	0	 ts_match_qv   tsmatchsel tsmatchjoinsel ));
 DATA(insert OID = 3674 (  "<"	   PGNSP PGUID b f f 3615	 3615	 16 3679 3678	 tsquery_lt scalarltsel scalarltjoinsel ));
 DATA(insert OID = 3675 (  "<="	   PGNSP PGUID b f f 3615	 3615	 16 3678 3679	 tsquery_le scalarltsel scalarltjoinsel ));
 DATA(insert OID = 3676 (  "="	   PGNSP PGUID b t f 3615	 3615	 16 3676 3677	 tsquery_eq eqsel eqjoinsel ));

src/include/catalog/pg_proc.h

@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1996-2008, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/catalog/pg_proc.h,v 1.514 2008/09/10 18:09:20 alvherre Exp $
+ * $PostgreSQL: pgsql/src/include/catalog/pg_proc.h,v 1.515 2008/09/19 19:03:40 tgl Exp $
  *
  * NOTES
  *	  The script catalog/genbki.sh reads this file and generates .bki
@@ -4434,7 +4434,11 @@ DESCR("GiST tsquery support");
 DATA(insert OID = 3701 (  gtsquery_consistent			PGNSP PGUID 12 1 0 0 f f t f i 5 16 "2281 2281 23 26 2281" _null_ _null_ _null_ gtsquery_consistent _null_ _null_ _null_ ));
 DESCR("GiST tsquery support");
 
-DATA(insert OID = 3688 (  ts_typanalyze	PGNSP PGUID 12 1 0 0 f f t f s 1 16 "2281" _null_ _null_ _null_ ts_typanalyze _null_ _null_ _null_ ));
+DATA(insert OID = 3686 (  tsmatchsel		PGNSP PGUID 12 1 0 0 f f t f s 4 701 "2281 26 2281 23" _null_ _null_ _null_ tsmatchsel _null_ _null_ _null_ ));
+DESCR("restriction selectivity of tsvector @@ tsquery");
+DATA(insert OID = 3687 (  tsmatchjoinsel	PGNSP PGUID 12 1 0 0 f f t f s 5 701 "2281 26 2281 21 2281" _null_ _null_ _null_ tsmatchjoinsel _null_ _null_ _null_ ));
+DESCR("join selectivity of tsvector @@ tsquery");
+DATA(insert OID = 3688 (  ts_typanalyze		PGNSP PGUID 12 1 0 0 f f t f s 1 16 "2281" _null_ _null_ _null_ ts_typanalyze _null_ _null_ _null_ ));
 DESCR("tsvector typanalyze");
 
 DATA(insert OID = 3689 (  ts_stat		PGNSP PGUID 12 10 10000 0 f f t t v 1 2249 "25" "{25,25,23,23}" "{i,o,o,o}" "{query,word,ndoc,nentry}" ts_stat1 _null_ _null_ _null_ ));

src/include/catalog/pg_statistic.h

@@ -8,7 +8,7 @@
  * Portions Copyright (c) 1996-2008, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/catalog/pg_statistic.h,v 1.36 2008/07/14 00:51:45 tgl Exp $
+ * $PostgreSQL: pgsql/src/include/catalog/pg_statistic.h,v 1.37 2008/09/19 19:03:41 tgl Exp $
  *
  * NOTES
  *	  the genbki.sh script reads this file and generates .bki
@@ -243,8 +243,12 @@ typedef FormData_pg_statistic *Form_pg_statistic;
  * values.  This is useful when the column datatype is an array or some other
  * type with identifiable elements (for instance, tsvector).  staop contains
  * the equality operator appropriate to the element type.  stavalues contains
- * the most common element values, and stanumbers their frequencies, with the
+ * the most common element values, and stanumbers their frequencies.  Unlike
- * same rules as for MCV slots.
+ * MCV slots, the values are sorted into order (to support binary search
+ * for a particular value).  Since this puts the minimum and maximum
+ * frequencies at unpredictable spots in stanumbers, there are two extra
+ * members of stanumbers, holding copies of the minimum and maximum
+ * frequencies.
  *
  * Note: in current usage for tsvector columns, the stavalues elements are of
  * type text, even though their representation within tsvector is not

src/include/tsearch/ts_type.h

@@ -5,7 +5,7 @@
  *
  * Copyright (c) 1998-2008, PostgreSQL Global Development Group
  *
- * $PostgreSQL: pgsql/src/include/tsearch/ts_type.h,v 1.13 2008/07/14 00:51:45 tgl Exp $
+ * $PostgreSQL: pgsql/src/include/tsearch/ts_type.h,v 1.14 2008/09/19 19:03:41 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -153,6 +153,9 @@ extern Datum ts_rankcd_wtt(PG_FUNCTION_ARGS);
 extern Datum ts_rankcd_ttf(PG_FUNCTION_ARGS);
 extern Datum ts_rankcd_wttf(PG_FUNCTION_ARGS);
 
+extern Datum tsmatchsel(PG_FUNCTION_ARGS);
+extern Datum tsmatchjoinsel(PG_FUNCTION_ARGS);
+
 extern Datum ts_typanalyze(PG_FUNCTION_ARGS);