From: Heikki Linnakangas Date: Wed, 12 Mar 2014 15:13:22 +0000 (+0200) Subject: Allow opclasses to provide tri-valued GIN consistent functions. X-Git-Tag: REL9_4_BETA1~351 X-Git-Url: https://granicus.if.org/sourcecode?a=commitdiff_plain;h=c5608ea26a1f51998ad3cf987c3f0bda643c87a8;p=postgresql Allow opclasses to provide tri-valued GIN consistent functions. With the GIN "fast scan" feature, GIN can skip items without fetching all the keys for them, if it can prove that they don't match regardless of those keys. So far, it has done the proving by calling the boolean consistent function with all combinations of TRUE/FALSE for the unfetched keys, but since that's O(n^2), it becomes unfeasible with more than a few keys. We can avoid calling consistent with all the combinations, if we can tell the operator class implementation directly which keys are unknown. This commit includes a triConsistent function for the built-in array and tsvector opclasses. Alexander Korotkov, with some changes by me. --- diff --git a/doc/src/sgml/gin.sgml b/doc/src/sgml/gin.sgml index 9ffa8be7bc..0bd759220f 100644 --- a/doc/src/sgml/gin.sgml +++ b/doc/src/sgml/gin.sgml @@ -74,15 +74,15 @@ All it takes to get a GIN access method working is to - implement four (or five) user-defined methods, which define the behavior of + implement a few user-defined methods, which define the behavior of keys in the tree and the relationships between keys, indexed items, and indexable queries. In short, GIN combines extensibility with generality, code reuse, and a clean interface. - The four methods that an operator class for - GIN must provide are: + There are three methods that an operator class for + GIN must provide: @@ -190,7 +190,18 @@ + + + An operator class must also provide a function to check if an indexed item + matches the query. It comes in two flavors, a boolean consistent + function, and a ternary triConsistent function. + triConsistent covers the functionality of both, so providing + triConsistent alone is sufficient. However, if the boolean variant is + significantly cheaper to calculate, it can be advantegous to provide both. + If only the boolean variant is provided, some optimizations that depend on + refuting index items before fetching all the keys are disabled. + bool consistent(bool check[], StrategyNumber n, Datum query, int32 nkeys, Pointer extra_data[], bool *recheck, @@ -241,10 +252,38 @@ + + + GinLogicValue triConsistent(GinLogicValue check[], StrategyNumber n, Datum query, + int32 nkeys, Pointer extra_data[], + Datum queryKeys[], bool nullFlags[]) + + + triConsistent is similar to consistent, + but instead of a boolean check[], there are three possible + values for each key: GIN_TRUE, GIN_FALSE and + GIN_MAYBE. GIN_FALSE and GIN_TRUE + have the same meaning as regular boolean values. + GIN_MAYBE means that the presence of that key is not known. + When GIN_MAYBE values are present, the function should only + return GIN_TRUE if the item matches whether or not the index item + contains the corresponding query keys. Likewise, the function must + return GIN_FALSE only if the item does not match, whether or not it + contains the GIN_MAYBE keys. If the result depends on the GIN_MAYBE + entries, ie. the match cannot be confirmed or refuted based on the + known query keys, the function must return GIN_MAYBE. + + + When there are no GIN_MAYBE values in the check vector, + GIN_MAYBE return value is equivalent of setting + recheck flag in the boolean consistent function. + + + - Optionally, an operator class for - GIN can supply a fifth method: + Optionally, an operator class for GIN can supply the + following method: @@ -282,8 +321,9 @@ above vary depending on the operator class. The item values passed to extractValue are always of the operator class's input type, and all key values must be of the class's STORAGE type. The type of - the query argument passed to extractQuery and - consistent is whatever is specified as the right-hand input + the query argument passed to extractQuery, + consistent and triConsistent is whatever is + specified as the right-hand input type of the class member operator identified by the strategy number. This need not be the same as the item type, so long as key values of the correct type can be extracted from it. diff --git a/doc/src/sgml/xindex.sgml b/doc/src/sgml/xindex.sgml index 806b35824e..0fe97ba4b5 100644 --- a/doc/src/sgml/xindex.sgml +++ b/doc/src/sgml/xindex.sgml @@ -567,7 +567,10 @@ consistent - determine whether value matches query condition + + determine whether value matches query condition (boolean variant) + (optional if support function 6 is present) + 4 @@ -580,6 +583,14 @@ 5 + + triConsistent + + determine whether value matches query condition (ternary variant) + (optional if support function 4 is present) + + 6 + diff --git a/src/backend/access/gin/ginarrayproc.c b/src/backend/access/gin/ginarrayproc.c index e02a91b82d..d04b851e3c 100644 --- a/src/backend/access/gin/ginarrayproc.c +++ b/src/backend/access/gin/ginarrayproc.c @@ -218,3 +218,87 @@ ginarrayconsistent(PG_FUNCTION_ARGS) PG_RETURN_BOOL(res); } + +/* + * triconsistent support function + */ +Datum +ginarraytriconsistent(PG_FUNCTION_ARGS) +{ + GinLogicValue *check = (GinLogicValue *) PG_GETARG_POINTER(0); + StrategyNumber strategy = PG_GETARG_UINT16(1); + + /* ArrayType *query = PG_GETARG_ARRAYTYPE_P(2); */ + int32 nkeys = PG_GETARG_INT32(3); + + /* Pointer *extra_data = (Pointer *) PG_GETARG_POINTER(4); */ + /* Datum *queryKeys = (Datum *) PG_GETARG_POINTER(5); */ + bool *nullFlags = (bool *) PG_GETARG_POINTER(6); + GinLogicValue res; + int32 i; + + switch (strategy) + { + case GinOverlapStrategy: + /* must have a match for at least one non-null element */ + res = GIN_FALSE; + for (i = 0; i < nkeys; i++) + { + if (!nullFlags[i]) + { + if (check[i] == GIN_TRUE) + { + res = GIN_TRUE; + break; + } + else if (check[i] == GIN_MAYBE && res == GIN_FALSE) + { + res = GIN_MAYBE; + } + } + } + break; + case GinContainsStrategy: + /* must have all elements in check[] true, and no nulls */ + res = GIN_TRUE; + for (i = 0; i < nkeys; i++) + { + if (check[i] == GIN_FALSE || nullFlags[i]) + { + res = GIN_FALSE; + break; + } + if (check[i] == GIN_MAYBE) + { + res = GIN_MAYBE; + } + } + break; + case GinContainedStrategy: + /* can't do anything else useful here */ + res = GIN_MAYBE; + break; + case GinEqualStrategy: + /* + * Must have all elements in check[] true; no discrimination + * against nulls here. This is because array_contain_compare and + * array_eq handle nulls differently ... + */ + res = GIN_MAYBE; + for (i = 0; i < nkeys; i++) + { + if (check[i] == GIN_FALSE) + { + res = GIN_FALSE; + break; + } + } + break; + default: + elog(ERROR, "ginarrayconsistent: unknown strategy number: %d", + strategy); + res = false; + } + + PG_RETURN_GIN_LOGIC_VALUE(res); +} diff --git a/src/backend/access/gin/ginlogic.c b/src/backend/access/gin/ginlogic.c index dc8e6304a2..4c8d706361 100644 --- a/src/backend/access/gin/ginlogic.c +++ b/src/backend/access/gin/ginlogic.c @@ -61,7 +61,7 @@ trueTriConsistentFn(GinScanKey key) * A helper function for calling a regular, binary logic, consistent function. */ static bool -normalBoolConsistentFn(GinScanKey key) +directBoolConsistentFn(GinScanKey key) { /* * Initialize recheckCurItem in case the consistentFn doesn't know it @@ -81,6 +81,53 @@ normalBoolConsistentFn(GinScanKey key) PointerGetDatum(key->queryCategories))); } +/* + * A helper function for calling a native ternary logic consistent function. + */ +static GinLogicValue +directTriConsistentFn(GinScanKey key) +{ + return DatumGetGinLogicValue(FunctionCall7Coll(key->triConsistentFmgrInfo, + key->collation, + PointerGetDatum(key->entryRes), + UInt16GetDatum(key->strategy), + key->query, + UInt32GetDatum(key->nuserentries), + PointerGetDatum(key->extra_data), + PointerGetDatum(key->queryValues), + PointerGetDatum(key->queryCategories))); +} + +/* + * This function implements a binary logic consistency check, using a ternary + * logic consistent function provided by the opclass. GIN_MAYBE return value + * is interpreted as true with recheck flag. + */ +static bool +shimBoolConsistentFn(GinScanKey key) +{ + GinLogicValue result; + result = DatumGetGinLogicValue(FunctionCall7Coll(key->triConsistentFmgrInfo, + key->collation, + PointerGetDatum(key->entryRes), + UInt16GetDatum(key->strategy), + key->query, + UInt32GetDatum(key->nuserentries), + PointerGetDatum(key->extra_data), + PointerGetDatum(key->queryValues), + PointerGetDatum(key->queryCategories))); + if (result == GIN_MAYBE) + { + key->recheckCurItem = true; + return true; + } + else + { + key->recheckCurItem = false; + return result; + } +} + /* * This function implements a tri-state consistency check, using a boolean * consistent function provided by the opclass. @@ -124,12 +171,12 @@ shimTriConsistentFn(GinScanKey key) * function as is. */ if (nmaybe == 0) - return normalBoolConsistentFn(key); + return directBoolConsistentFn(key); /* First call consistent function with all the maybe-inputs set FALSE */ for (i = 0; i < nmaybe; i++) key->entryRes[maybeEntries[i]] = GIN_FALSE; - curResult = normalBoolConsistentFn(key); + curResult = directBoolConsistentFn(key); for (;;) { @@ -147,7 +194,7 @@ shimTriConsistentFn(GinScanKey key) if (i == nmaybe) break; - boolResult = normalBoolConsistentFn(key); + boolResult = directBoolConsistentFn(key); recheck |= key->recheckCurItem; if (curResult != boolResult) @@ -175,8 +222,17 @@ ginInitConsistentFunction(GinState *ginstate, GinScanKey key) else { key->consistentFmgrInfo = &ginstate->consistentFn[key->attnum - 1]; + key->triConsistentFmgrInfo = &ginstate->triConsistentFn[key->attnum - 1]; key->collation = ginstate->supportCollation[key->attnum - 1]; - key->boolConsistentFn = normalBoolConsistentFn; - key->triConsistentFn = shimTriConsistentFn; + + if (OidIsValid(ginstate->consistentFn[key->attnum - 1].fn_oid)) + key->boolConsistentFn = directBoolConsistentFn; + else + key->boolConsistentFn = shimBoolConsistentFn; + + if (OidIsValid(ginstate->triConsistentFn[key->attnum - 1].fn_oid)) + key->triConsistentFn = directTriConsistentFn; + else + key->triConsistentFn = shimTriConsistentFn; } } diff --git a/src/backend/access/gin/ginutil.c b/src/backend/access/gin/ginutil.c index 486f2ef1f1..4dadb50dca 100644 --- a/src/backend/access/gin/ginutil.c +++ b/src/backend/access/gin/ginutil.c @@ -67,9 +67,31 @@ initGinState(GinState *state, Relation index) fmgr_info_copy(&(state->extractQueryFn[i]), index_getprocinfo(index, i + 1, GIN_EXTRACTQUERY_PROC), CurrentMemoryContext); - fmgr_info_copy(&(state->consistentFn[i]), - index_getprocinfo(index, i + 1, GIN_CONSISTENT_PROC), - CurrentMemoryContext); + /* + * Check opclass capability to do tri-state or binary logic consistent + * check. + */ + if (index_getprocid(index, i + 1, GIN_TRICONSISTENT_PROC) != InvalidOid) + { + fmgr_info_copy(&(state->triConsistentFn[i]), + index_getprocinfo(index, i + 1, GIN_TRICONSISTENT_PROC), + CurrentMemoryContext); + } + + if (index_getprocid(index, i + 1, GIN_CONSISTENT_PROC) != InvalidOid) + { + fmgr_info_copy(&(state->consistentFn[i]), + index_getprocinfo(index, i + 1, GIN_CONSISTENT_PROC), + CurrentMemoryContext); + } + + if (state->consistentFn[i].fn_oid == InvalidOid && + state->triConsistentFn[i].fn_oid == InvalidOid) + { + elog(ERROR, "missing GIN support function (%d or %d) for attribute %d of index \"%s\"", + GIN_CONSISTENT_PROC, GIN_TRICONSISTENT_PROC, + i + 1, RelationGetRelationName(index)); + } /* * Check opclass capability to do partial match. diff --git a/src/backend/utils/adt/tsginidx.c b/src/backend/utils/adt/tsginidx.c index 9f6e8e9fd5..47685e8b93 100644 --- a/src/backend/utils/adt/tsginidx.c +++ b/src/backend/utils/adt/tsginidx.c @@ -15,6 +15,7 @@ #include "access/gin.h" #include "access/skey.h" +#include "miscadmin.h" #include "tsearch/ts_type.h" #include "tsearch/ts_utils.h" #include "utils/builtins.h" @@ -172,12 +173,12 @@ gin_extract_tsquery(PG_FUNCTION_ARGS) typedef struct { QueryItem *first_item; - bool *check; + GinLogicValue *check; int *map_item_operand; bool *need_recheck; } GinChkVal; -static bool +static GinLogicValue checkcondition_gin(void *checkval, QueryOperand *val) { GinChkVal *gcv = (GinChkVal *) checkval; @@ -194,6 +195,66 @@ checkcondition_gin(void *checkval, QueryOperand *val) return gcv->check[j]; } +/* + * Evaluate tsquery boolean expression using ternary logic. + * + * chkcond is a callback function used to evaluate each VAL node in the query. + * checkval can be used to pass information to the callback. TS_execute doesn't + * do anything with it. + */ +static GinLogicValue +TS_execute_ternary(QueryItem *curitem, void *checkval, + GinLogicValue (*chkcond) (void *checkval, QueryOperand *val)) +{ + GinLogicValue val1, val2, result; + /* since this function recurses, it could be driven to stack overflow */ + check_stack_depth(); + + if (curitem->type == QI_VAL) + return chkcond(checkval, (QueryOperand *) curitem); + + switch (curitem->qoperator.oper) + { + case OP_NOT: + result = TS_execute_ternary(curitem + 1, checkval, chkcond); + if (result == GIN_MAYBE) + return result; + return !result; + + case OP_AND: + val1 = TS_execute_ternary(curitem + curitem->qoperator.left, + checkval, chkcond); + if (val1 == GIN_FALSE) + return GIN_FALSE; + val2 = TS_execute_ternary(curitem + 1, checkval, chkcond); + if (val2 == GIN_FALSE) + return GIN_FALSE; + if (val1 == GIN_TRUE && val2 == GIN_TRUE) + return GIN_TRUE; + else + return GIN_MAYBE; + + case OP_OR: + val1 = TS_execute_ternary(curitem + curitem->qoperator.left, + checkval, chkcond); + if (val1 == GIN_TRUE) + return GIN_TRUE; + val2 = TS_execute_ternary(curitem + 1, checkval, chkcond); + if (val2 == GIN_TRUE) + return GIN_TRUE; + if (val1 == GIN_FALSE && val2 == GIN_FALSE) + return GIN_FALSE; + else + return GIN_MAYBE; + + default: + elog(ERROR, "unrecognized operator: %d", curitem->qoperator.oper); + } + + /* not reachable, but keep compiler quiet */ + return false; +} + Datum gin_tsquery_consistent(PG_FUNCTION_ARGS) { @@ -233,6 +294,45 @@ gin_tsquery_consistent(PG_FUNCTION_ARGS) PG_RETURN_BOOL(res); } +Datum +gin_tsquery_triconsistent(PG_FUNCTION_ARGS) +{ + GinLogicValue *check = (GinLogicValue *) PG_GETARG_POINTER(0); + + /* StrategyNumber strategy = PG_GETARG_UINT16(1); */ + TSQuery query = PG_GETARG_TSQUERY(2); + + /* int32 nkeys = PG_GETARG_INT32(3); */ + Pointer *extra_data = (Pointer *) PG_GETARG_POINTER(4); + GinLogicValue res = GIN_FALSE; + bool recheck; + + /* The query requires recheck only if it involves weights */ + if (query->size > 0) + { + QueryItem *item; + GinChkVal gcv; + + /* + * check-parameter array has one entry for each value (operand) in the + * query. + */ + gcv.first_item = item = GETQUERY(query); + gcv.check = check; + gcv.map_item_operand = (int *) (extra_data[0]); + gcv.need_recheck = &recheck; + + res = TS_execute_ternary(GETQUERY(query), + &gcv, + checkcondition_gin); + + if (res == GIN_TRUE && recheck) + res = GIN_MAYBE; + } + + PG_RETURN_GIN_LOGIC_VALUE(res); +} + /* * Formerly, gin_extract_tsvector had only two arguments. Now it has three, * but we still need a pg_proc entry with two args to support reloading diff --git a/src/include/access/gin.h b/src/include/access/gin.h index 03e58c9b1c..75a86c4319 100644 --- a/src/include/access/gin.h +++ b/src/include/access/gin.h @@ -23,7 +23,8 @@ #define GIN_EXTRACTQUERY_PROC 3 #define GIN_CONSISTENT_PROC 4 #define GIN_COMPARE_PARTIAL_PROC 5 -#define GINNProcs 5 +#define GIN_TRICONSISTENT_PROC 6 +#define GINNProcs 6 /* * searchMode settings for extractQueryFn. @@ -46,6 +47,21 @@ typedef struct GinStatsData int32 ginVersion; } GinStatsData; +/* ginlogic.c */ +enum +{ + GIN_FALSE = 0, /* item is present / matches */ + GIN_TRUE = 1, /* item is not present / does not match */ + GIN_MAYBE = 2 /* don't know if item is present / don't know if + * matches */ +} GinLogicValueEnum; + +typedef char GinLogicValue; + +#define DatumGetGinLogicValue(X) ((GinLogicValue)(X)) +#define GinLogicValueGetDatum(X) ((Datum)(X)) +#define PG_RETURN_GIN_LOGIC_VALUE(x) return GinLogicValueGetDatum(x) + /* GUC parameter */ extern PGDLLIMPORT int GinFuzzySearchLimit; diff --git a/src/include/access/gin_private.h b/src/include/access/gin_private.h index 2cf042a766..009927282f 100644 --- a/src/include/access/gin_private.h +++ b/src/include/access/gin_private.h @@ -348,6 +348,7 @@ typedef struct GinState FmgrInfo extractValueFn[INDEX_MAX_KEYS]; FmgrInfo extractQueryFn[INDEX_MAX_KEYS]; FmgrInfo consistentFn[INDEX_MAX_KEYS]; + FmgrInfo triConsistentFn[INDEX_MAX_KEYS]; FmgrInfo comparePartialFn[INDEX_MAX_KEYS]; /* optional method */ /* canPartialMatch[i] is true if comparePartialFn[i] is valid */ bool canPartialMatch[INDEX_MAX_KEYS]; @@ -762,8 +763,9 @@ typedef struct GinScanKeyData /* array of check flags, reported to consistentFn */ bool *entryRes; bool (*boolConsistentFn) (GinScanKey key); - bool (*triConsistentFn) (GinScanKey key); + GinLogicValue (*triConsistentFn) (GinScanKey key); FmgrInfo *consistentFmgrInfo; + FmgrInfo *triConsistentFmgrInfo; Oid collation; /* other data needed for calling consistentFn */ @@ -850,17 +852,6 @@ extern void ginNewScanKey(IndexScanDesc scan); extern Datum gingetbitmap(PG_FUNCTION_ARGS); /* ginlogic.c */ - -enum -{ - GIN_FALSE = 0, /* item is present / matches */ - GIN_TRUE = 1, /* item is not present / does not match */ - GIN_MAYBE = 2 /* don't know if item is present / don't know if - * matches */ -} GinLogicValueEnum; - -typedef char GinLogicValue; - extern void ginInitConsistentFunction(GinState *ginstate, GinScanKey key); /* ginvacuum.c */ diff --git a/src/include/catalog/catversion.h b/src/include/catalog/catversion.h index 047039a417..60f78d24a9 100644 --- a/src/include/catalog/catversion.h +++ b/src/include/catalog/catversion.h @@ -53,6 +53,6 @@ */ /* yyyymmddN */ -#define CATALOG_VERSION_NO 201403041 +#define CATALOG_VERSION_NO 201403121 #endif diff --git a/src/include/catalog/pg_am.h b/src/include/catalog/pg_am.h index 4f46dddcff..759ea70570 100644 --- a/src/include/catalog/pg_am.h +++ b/src/include/catalog/pg_am.h @@ -126,7 +126,7 @@ DESCR("hash index access method"); DATA(insert OID = 783 ( gist 0 8 f t f f t t f t t t f 0 gistinsert gistbeginscan gistgettuple gistgetbitmap gistrescan gistendscan gistmarkpos gistrestrpos gistbuild gistbuildempty gistbulkdelete gistvacuumcleanup - gistcostestimate gistoptions )); DESCR("GiST index access method"); #define GIST_AM_OID 783 -DATA(insert OID = 2742 ( gin 0 5 f f f f t t f f t f f 0 gininsert ginbeginscan - gingetbitmap ginrescan ginendscan ginmarkpos ginrestrpos ginbuild ginbuildempty ginbulkdelete ginvacuumcleanup - gincostestimate ginoptions )); +DATA(insert OID = 2742 ( gin 0 6 f f f f t t f f t f f 0 gininsert ginbeginscan - gingetbitmap ginrescan ginendscan ginmarkpos ginrestrpos ginbuild ginbuildempty ginbulkdelete ginvacuumcleanup - gincostestimate ginoptions )); DESCR("GIN index access method"); #define GIN_AM_OID 2742 DATA(insert OID = 4000 ( spgist 0 5 f f f f f t f t f f f 0 spginsert spgbeginscan spggettuple spggetbitmap spgrescan spgendscan spgmarkpos spgrestrpos spgbuild spgbuildempty spgbulkdelete spgvacuumcleanup spgcanreturn spgcostestimate spgoptions )); diff --git a/src/include/catalog/pg_amproc.h b/src/include/catalog/pg_amproc.h index 66bd76505a..e3773e9759 100644 --- a/src/include/catalog/pg_amproc.h +++ b/src/include/catalog/pg_amproc.h @@ -235,127 +235,158 @@ DATA(insert ( 2745 1007 1007 1 351 )); DATA(insert ( 2745 1007 1007 2 2743 )); DATA(insert ( 2745 1007 1007 3 2774 )); DATA(insert ( 2745 1007 1007 4 2744 )); +DATA(insert ( 2745 1007 1007 6 3920 )); DATA(insert ( 2745 1009 1009 1 360 )); DATA(insert ( 2745 1009 1009 2 2743 )); DATA(insert ( 2745 1009 1009 3 2774 )); DATA(insert ( 2745 1009 1009 4 2744 )); +DATA(insert ( 2745 1009 1009 6 3920 )); DATA(insert ( 2745 1015 1015 1 360 )); DATA(insert ( 2745 1015 1015 2 2743 )); DATA(insert ( 2745 1015 1015 3 2774 )); DATA(insert ( 2745 1015 1015 4 2744 )); +DATA(insert ( 2745 1015 1015 6 3920 )); DATA(insert ( 2745 1023 1023 1 357 )); DATA(insert ( 2745 1023 1023 2 2743 )); DATA(insert ( 2745 1023 1023 3 2774 )); DATA(insert ( 2745 1023 1023 4 2744 )); +DATA(insert ( 2745 1023 1023 6 3920 )); DATA(insert ( 2745 1561 1561 1 1596 )); DATA(insert ( 2745 1561 1561 2 2743 )); DATA(insert ( 2745 1561 1561 3 2774 )); DATA(insert ( 2745 1561 1561 4 2744 )); +DATA(insert ( 2745 1561 1561 6 3920 )); DATA(insert ( 2745 1000 1000 1 1693 )); DATA(insert ( 2745 1000 1000 2 2743 )); DATA(insert ( 2745 1000 1000 3 2774 )); DATA(insert ( 2745 1000 1000 4 2744 )); +DATA(insert ( 2745 1000 1000 6 3920 )); DATA(insert ( 2745 1014 1014 1 1078 )); DATA(insert ( 2745 1014 1014 2 2743 )); DATA(insert ( 2745 1014 1014 3 2774 )); DATA(insert ( 2745 1014 1014 4 2744 )); +DATA(insert ( 2745 1014 1014 6 3920 )); DATA(insert ( 2745 1001 1001 1 1954 )); DATA(insert ( 2745 1001 1001 2 2743 )); DATA(insert ( 2745 1001 1001 3 2774 )); DATA(insert ( 2745 1001 1001 4 2744 )); +DATA(insert ( 2745 1001 1001 6 3920 )); DATA(insert ( 2745 1002 1002 1 358 )); DATA(insert ( 2745 1002 1002 2 2743 )); DATA(insert ( 2745 1002 1002 3 2774 )); DATA(insert ( 2745 1002 1002 4 2744 )); +DATA(insert ( 2745 1002 1002 6 3920 )); DATA(insert ( 2745 1182 1182 1 1092 )); DATA(insert ( 2745 1182 1182 2 2743 )); DATA(insert ( 2745 1182 1182 3 2774 )); DATA(insert ( 2745 1182 1182 4 2744 )); +DATA(insert ( 2745 1182 1182 6 3920 )); DATA(insert ( 2745 1021 1021 1 354 )); DATA(insert ( 2745 1021 1021 2 2743 )); DATA(insert ( 2745 1021 1021 3 2774 )); DATA(insert ( 2745 1021 1021 4 2744 )); +DATA(insert ( 2745 1021 1021 6 3920 )); DATA(insert ( 2745 1022 1022 1 355 )); DATA(insert ( 2745 1022 1022 2 2743 )); DATA(insert ( 2745 1022 1022 3 2774 )); DATA(insert ( 2745 1022 1022 4 2744 )); +DATA(insert ( 2745 1022 1022 6 3920 )); DATA(insert ( 2745 1041 1041 1 926 )); DATA(insert ( 2745 1041 1041 2 2743 )); DATA(insert ( 2745 1041 1041 3 2774 )); DATA(insert ( 2745 1041 1041 4 2744 )); +DATA(insert ( 2745 1041 1041 6 3920 )); DATA(insert ( 2745 651 651 1 926 )); DATA(insert ( 2745 651 651 2 2743 )); DATA(insert ( 2745 651 651 3 2774 )); DATA(insert ( 2745 651 651 4 2744 )); +DATA(insert ( 2745 651 651 6 3920 )); DATA(insert ( 2745 1005 1005 1 350 )); DATA(insert ( 2745 1005 1005 2 2743 )); DATA(insert ( 2745 1005 1005 3 2774 )); DATA(insert ( 2745 1005 1005 4 2744 )); +DATA(insert ( 2745 1005 1005 6 3920 )); DATA(insert ( 2745 1016 1016 1 842 )); DATA(insert ( 2745 1016 1016 2 2743 )); DATA(insert ( 2745 1016 1016 3 2774 )); DATA(insert ( 2745 1016 1016 4 2744 )); +DATA(insert ( 2745 1016 1016 6 3920 )); DATA(insert ( 2745 1187 1187 1 1315 )); DATA(insert ( 2745 1187 1187 2 2743 )); DATA(insert ( 2745 1187 1187 3 2774 )); DATA(insert ( 2745 1187 1187 4 2744 )); +DATA(insert ( 2745 1187 1187 6 3920 )); DATA(insert ( 2745 1040 1040 1 836 )); DATA(insert ( 2745 1040 1040 2 2743 )); DATA(insert ( 2745 1040 1040 3 2774 )); DATA(insert ( 2745 1040 1040 4 2744 )); +DATA(insert ( 2745 1040 1040 6 3920 )); DATA(insert ( 2745 1003 1003 1 359 )); DATA(insert ( 2745 1003 1003 2 2743 )); DATA(insert ( 2745 1003 1003 3 2774 )); DATA(insert ( 2745 1003 1003 4 2744 )); +DATA(insert ( 2745 1003 1003 6 3920 )); DATA(insert ( 2745 1231 1231 1 1769 )); DATA(insert ( 2745 1231 1231 2 2743 )); DATA(insert ( 2745 1231 1231 3 2774 )); DATA(insert ( 2745 1231 1231 4 2744 )); +DATA(insert ( 2745 1231 1231 6 3920 )); DATA(insert ( 2745 1028 1028 1 356 )); DATA(insert ( 2745 1028 1028 2 2743 )); DATA(insert ( 2745 1028 1028 3 2774 )); DATA(insert ( 2745 1028 1028 4 2744 )); +DATA(insert ( 2745 1028 1028 6 3920 )); DATA(insert ( 2745 1013 1013 1 404 )); DATA(insert ( 2745 1013 1013 2 2743 )); DATA(insert ( 2745 1013 1013 3 2774 )); DATA(insert ( 2745 1013 1013 4 2744 )); +DATA(insert ( 2745 1013 1013 6 3920 )); DATA(insert ( 2745 1183 1183 1 1107 )); DATA(insert ( 2745 1183 1183 2 2743 )); DATA(insert ( 2745 1183 1183 3 2774 )); DATA(insert ( 2745 1183 1183 4 2744 )); +DATA(insert ( 2745 1183 1183 6 3920 )); DATA(insert ( 2745 1185 1185 1 1314 )); DATA(insert ( 2745 1185 1185 2 2743 )); DATA(insert ( 2745 1185 1185 3 2774 )); DATA(insert ( 2745 1185 1185 4 2744 )); +DATA(insert ( 2745 1185 1185 6 3920 )); DATA(insert ( 2745 1270 1270 1 1358 )); DATA(insert ( 2745 1270 1270 2 2743 )); DATA(insert ( 2745 1270 1270 3 2774 )); DATA(insert ( 2745 1270 1270 4 2744 )); +DATA(insert ( 2745 1270 1270 6 3920 )); DATA(insert ( 2745 1563 1563 1 1672 )); DATA(insert ( 2745 1563 1563 2 2743 )); DATA(insert ( 2745 1563 1563 3 2774 )); DATA(insert ( 2745 1563 1563 4 2744 )); +DATA(insert ( 2745 1563 1563 6 3920 )); DATA(insert ( 2745 1115 1115 1 2045 )); DATA(insert ( 2745 1115 1115 2 2743 )); DATA(insert ( 2745 1115 1115 3 2774 )); DATA(insert ( 2745 1115 1115 4 2744 )); +DATA(insert ( 2745 1115 1115 6 3920 )); DATA(insert ( 2745 791 791 1 377 )); DATA(insert ( 2745 791 791 2 2743 )); DATA(insert ( 2745 791 791 3 2774 )); DATA(insert ( 2745 791 791 4 2744 )); +DATA(insert ( 2745 791 791 6 3920 )); DATA(insert ( 2745 1024 1024 1 380 )); DATA(insert ( 2745 1024 1024 2 2743 )); DATA(insert ( 2745 1024 1024 3 2774 )); DATA(insert ( 2745 1024 1024 4 2744 )); +DATA(insert ( 2745 1024 1024 6 3920 )); DATA(insert ( 2745 1025 1025 1 381 )); DATA(insert ( 2745 1025 1025 2 2743 )); DATA(insert ( 2745 1025 1025 3 2774 )); DATA(insert ( 2745 1025 1025 4 2744 )); +DATA(insert ( 2745 1025 1025 6 3920 )); DATA(insert ( 3659 3614 3614 1 3724 )); DATA(insert ( 3659 3614 3614 2 3656 )); DATA(insert ( 3659 3614 3614 3 3657 )); DATA(insert ( 3659 3614 3614 4 3658 )); DATA(insert ( 3659 3614 3614 5 2700 )); +DATA(insert ( 3659 3614 3614 6 3921 )); /* sp-gist */ diff --git a/src/include/catalog/pg_proc.h b/src/include/catalog/pg_proc.h index bde018d957..4bd23fc5fd 100644 --- a/src/include/catalog/pg_proc.h +++ b/src/include/catalog/pg_proc.h @@ -3991,6 +3991,8 @@ DATA(insert OID = 2774 ( ginqueryarrayextract PGNSP PGUID 12 1 0 0 0 f f f f t DESCR("GIN array support"); DATA(insert OID = 2744 ( ginarrayconsistent PGNSP PGUID 12 1 0 0 0 f f f f t f i 8 0 16 "2281 21 2277 23 2281 2281 2281 2281" _null_ _null_ _null_ _null_ ginarrayconsistent _null_ _null_ _null_ )); DESCR("GIN array support"); +DATA(insert OID = 3920 ( ginarraytriconsistent PGNSP PGUID 12 1 0 0 0 f f f f t f i 7 0 16 "2281 21 2277 23 2281 2281 2281" _null_ _null_ _null_ _null_ ginarraytriconsistent _null_ _null_ _null_ )); +DESCR("GIN array support"); DATA(insert OID = 3076 ( ginarrayextract PGNSP PGUID 12 1 0 0 0 f f f f t f i 2 0 2281 "2277 2281" _null_ _null_ _null_ _null_ ginarrayextract_2args _null_ _null_ _null_ )); DESCR("GIN array support (obsolete)"); @@ -4334,6 +4336,8 @@ DATA(insert OID = 3657 ( gin_extract_tsquery PGNSP PGUID 12 1 0 0 0 f f f f t f DESCR("GIN tsvector support"); DATA(insert OID = 3658 ( gin_tsquery_consistent PGNSP PGUID 12 1 0 0 0 f f f f t f i 8 0 16 "2281 21 3615 23 2281 2281 2281 2281" _null_ _null_ _null_ _null_ gin_tsquery_consistent _null_ _null_ _null_ )); DESCR("GIN tsvector support"); +DATA(insert OID = 3921 ( gin_tsquery_triconsistent PGNSP PGUID 12 1 0 0 0 f f f f t f i 7 0 16 "2281 21 3615 23 2281 2281 2281" _null_ _null_ _null_ _null_ gin_tsquery_triconsistent _null_ _null_ _null_ )); +DESCR("GIN tsvector support"); DATA(insert OID = 3724 ( gin_cmp_tslexeme PGNSP PGUID 12 1 0 0 0 f f f f t f i 2 0 23 "25 25" _null_ _null_ _null_ _null_ gin_cmp_tslexeme _null_ _null_ _null_ )); DESCR("GIN tsvector support"); DATA(insert OID = 2700 ( gin_cmp_prefix PGNSP PGUID 12 1 0 0 0 f f f f t f i 4 0 23 "25 25 21 2281" _null_ _null_ _null_ _null_ gin_cmp_prefix _null_ _null_ _null_ )); diff --git a/src/include/tsearch/ts_utils.h b/src/include/tsearch/ts_utils.h index 974e58cb52..2ffb3fb429 100644 --- a/src/include/tsearch/ts_utils.h +++ b/src/include/tsearch/ts_utils.h @@ -149,6 +149,7 @@ extern Datum gin_cmp_tslexeme(PG_FUNCTION_ARGS); extern Datum gin_cmp_prefix(PG_FUNCTION_ARGS); extern Datum gin_extract_tsquery(PG_FUNCTION_ARGS); extern Datum gin_tsquery_consistent(PG_FUNCTION_ARGS); +extern Datum gin_tsquery_triconsistent(PG_FUNCTION_ARGS); extern Datum gin_extract_tsvector_2args(PG_FUNCTION_ARGS); extern Datum gin_extract_tsquery_5args(PG_FUNCTION_ARGS); extern Datum gin_tsquery_consistent_6args(PG_FUNCTION_ARGS); diff --git a/src/include/utils/builtins.h b/src/include/utils/builtins.h index b90d88d3da..031a43a7e7 100644 --- a/src/include/utils/builtins.h +++ b/src/include/utils/builtins.h @@ -1161,6 +1161,7 @@ extern Datum ginarrayextract(PG_FUNCTION_ARGS); extern Datum ginarrayextract_2args(PG_FUNCTION_ARGS); extern Datum ginqueryarrayextract(PG_FUNCTION_ARGS); extern Datum ginarrayconsistent(PG_FUNCTION_ARGS); +extern Datum ginarraytriconsistent(PG_FUNCTION_ARGS); /* access/transam/twophase.c */ extern Datum pg_prepared_xact(PG_FUNCTION_ARGS); diff --git a/src/test/regress/expected/opr_sanity.out b/src/test/regress/expected/opr_sanity.out index 26abe8abc3..5627b4a426 100644 --- a/src/test/regress/expected/opr_sanity.out +++ b/src/test/regress/expected/opr_sanity.out @@ -1297,46 +1297,49 @@ WHERE p1.amprocfamily = p3.oid AND p3.opfmethod = p2.oid AND -- Detect missing pg_amproc entries: should have as many support functions -- as AM expects for each datatype combination supported by the opfamily. --- btree/GiST/GIN each allow one optional support function, though. -SELECT p1.amname, p2.opfname, p3.amproclefttype, p3.amprocrighttype -FROM pg_am AS p1, pg_opfamily AS p2, pg_amproc AS p3 -WHERE p2.opfmethod = p1.oid AND p3.amprocfamily = p2.oid AND - (SELECT count(*) FROM pg_amproc AS p4 - WHERE p4.amprocfamily = p2.oid AND - p4.amproclefttype = p3.amproclefttype AND - p4.amprocrighttype = p3.amprocrighttype) - NOT BETWEEN - (CASE WHEN p1.amname IN ('btree', 'gist', 'gin') THEN p1.amsupport - 1 - ELSE p1.amsupport END) - AND p1.amsupport; - amname | opfname | amproclefttype | amprocrighttype ---------+---------+----------------+----------------- +SELECT * FROM ( + SELECT p1.amname, p2.opfname, p3.amproclefttype, p3.amprocrighttype, + array_agg(p3.amprocnum ORDER BY amprocnum) AS procnums + FROM pg_am AS p1, pg_opfamily AS p2, pg_amproc AS p3 + WHERE p2.opfmethod = p1.oid AND p3.amprocfamily = p2.oid + GROUP BY p1.amname, p2.opfname, p3.amproclefttype, p3.amprocrighttype +) AS t +WHERE NOT ( + -- btree has one mandatory and one optional support function. + -- hash has one support function, which is mandatory. + -- GiST has eight support functions, one of which is optional. + -- GIN has six support functions. 1-3 are mandatory, 5 is optional, and + -- at least one of 4 and 6 must be given. + -- SP-GiST has five support functions, all mandatory + amname = 'btree' AND procnums @> '{1}' OR + amname = 'hash' AND procnums = '{1}' OR + amname = 'gist' AND procnums @> '{1, 2, 3, 4, 5, 6, 7}' OR + amname = 'gin' AND (procnums @> '{1, 2, 3}' AND (procnums && '{4, 6}')) OR + amname = 'spgist' AND procnums = '{1, 2, 3, 4, 5}' +); + amname | opfname | amproclefttype | amprocrighttype | procnums +--------+---------+----------------+-----------------+---------- (0 rows) -- Also, check if there are any pg_opclass entries that don't seem to have --- pg_amproc support. Again, opclasses with an optional support proc have --- to be checked specially. -SELECT amname, opcname, count(*) -FROM pg_am am JOIN pg_opclass op ON opcmethod = am.oid - LEFT JOIN pg_amproc p ON amprocfamily = opcfamily AND - amproclefttype = amprocrighttype AND amproclefttype = opcintype -WHERE am.amname <> 'btree' AND am.amname <> 'gist' AND am.amname <> 'gin' -GROUP BY amname, amsupport, opcname, amprocfamily -HAVING count(*) != amsupport OR amprocfamily IS NULL; - amname | opcname | count ---------+---------+------- -(0 rows) - -SELECT amname, opcname, count(*) -FROM pg_am am JOIN pg_opclass op ON opcmethod = am.oid - LEFT JOIN pg_amproc p ON amprocfamily = opcfamily AND - amproclefttype = amprocrighttype AND amproclefttype = opcintype -WHERE am.amname = 'btree' OR am.amname = 'gist' OR am.amname = 'gin' -GROUP BY amname, amsupport, opcname, amprocfamily -HAVING (count(*) != amsupport AND count(*) != amsupport - 1) - OR amprocfamily IS NULL; - amname | opcname | count ---------+---------+------- +-- pg_amproc support. +SELECT * FROM ( + SELECT amname, opcname, array_agg(amprocnum ORDER BY amprocnum) as procnums + FROM pg_am am JOIN pg_opclass op ON opcmethod = am.oid + LEFT JOIN pg_amproc p ON amprocfamily = opcfamily AND + amproclefttype = amprocrighttype AND amproclefttype = opcintype + GROUP BY amname, opcname, amprocfamily +) AS t +WHERE NOT ( + -- same per-AM rules as above + amname = 'btree' AND procnums @> '{1}' OR + amname = 'hash' AND procnums = '{1}' OR + amname = 'gist' AND procnums @> '{1, 2, 3, 4, 5, 6, 7}' OR + amname = 'gin' AND (procnums @> '{1, 2, 3}' AND (procnums && '{4, 6}')) OR + amname = 'spgist' AND procnums = '{1, 2, 3, 4, 5}' +); + amname | opcname | procnums +--------+---------+---------- (0 rows) -- Unfortunately, we can't check the amproc link very well because the diff --git a/src/test/regress/sql/opr_sanity.sql b/src/test/regress/sql/opr_sanity.sql index 40e1be2178..ad37178924 100644 --- a/src/test/regress/sql/opr_sanity.sql +++ b/src/test/regress/sql/opr_sanity.sql @@ -992,40 +992,46 @@ WHERE p1.amprocfamily = p3.oid AND p3.opfmethod = p2.oid AND -- Detect missing pg_amproc entries: should have as many support functions -- as AM expects for each datatype combination supported by the opfamily. --- btree/GiST/GIN each allow one optional support function, though. - -SELECT p1.amname, p2.opfname, p3.amproclefttype, p3.amprocrighttype -FROM pg_am AS p1, pg_opfamily AS p2, pg_amproc AS p3 -WHERE p2.opfmethod = p1.oid AND p3.amprocfamily = p2.oid AND - (SELECT count(*) FROM pg_amproc AS p4 - WHERE p4.amprocfamily = p2.oid AND - p4.amproclefttype = p3.amproclefttype AND - p4.amprocrighttype = p3.amprocrighttype) - NOT BETWEEN - (CASE WHEN p1.amname IN ('btree', 'gist', 'gin') THEN p1.amsupport - 1 - ELSE p1.amsupport END) - AND p1.amsupport; + +SELECT * FROM ( + SELECT p1.amname, p2.opfname, p3.amproclefttype, p3.amprocrighttype, + array_agg(p3.amprocnum ORDER BY amprocnum) AS procnums + FROM pg_am AS p1, pg_opfamily AS p2, pg_amproc AS p3 + WHERE p2.opfmethod = p1.oid AND p3.amprocfamily = p2.oid + GROUP BY p1.amname, p2.opfname, p3.amproclefttype, p3.amprocrighttype +) AS t +WHERE NOT ( + -- btree has one mandatory and one optional support function. + -- hash has one support function, which is mandatory. + -- GiST has eight support functions, one of which is optional. + -- GIN has six support functions. 1-3 are mandatory, 5 is optional, and + -- at least one of 4 and 6 must be given. + -- SP-GiST has five support functions, all mandatory + amname = 'btree' AND procnums @> '{1}' OR + amname = 'hash' AND procnums = '{1}' OR + amname = 'gist' AND procnums @> '{1, 2, 3, 4, 5, 6, 7}' OR + amname = 'gin' AND (procnums @> '{1, 2, 3}' AND (procnums && '{4, 6}')) OR + amname = 'spgist' AND procnums = '{1, 2, 3, 4, 5}' +); -- Also, check if there are any pg_opclass entries that don't seem to have --- pg_amproc support. Again, opclasses with an optional support proc have --- to be checked specially. - -SELECT amname, opcname, count(*) -FROM pg_am am JOIN pg_opclass op ON opcmethod = am.oid - LEFT JOIN pg_amproc p ON amprocfamily = opcfamily AND - amproclefttype = amprocrighttype AND amproclefttype = opcintype -WHERE am.amname <> 'btree' AND am.amname <> 'gist' AND am.amname <> 'gin' -GROUP BY amname, amsupport, opcname, amprocfamily -HAVING count(*) != amsupport OR amprocfamily IS NULL; - -SELECT amname, opcname, count(*) -FROM pg_am am JOIN pg_opclass op ON opcmethod = am.oid - LEFT JOIN pg_amproc p ON amprocfamily = opcfamily AND - amproclefttype = amprocrighttype AND amproclefttype = opcintype -WHERE am.amname = 'btree' OR am.amname = 'gist' OR am.amname = 'gin' -GROUP BY amname, amsupport, opcname, amprocfamily -HAVING (count(*) != amsupport AND count(*) != amsupport - 1) - OR amprocfamily IS NULL; +-- pg_amproc support. + +SELECT * FROM ( + SELECT amname, opcname, array_agg(amprocnum ORDER BY amprocnum) as procnums + FROM pg_am am JOIN pg_opclass op ON opcmethod = am.oid + LEFT JOIN pg_amproc p ON amprocfamily = opcfamily AND + amproclefttype = amprocrighttype AND amproclefttype = opcintype + GROUP BY amname, opcname, amprocfamily +) AS t +WHERE NOT ( + -- same per-AM rules as above + amname = 'btree' AND procnums @> '{1}' OR + amname = 'hash' AND procnums = '{1}' OR + amname = 'gist' AND procnums @> '{1, 2, 3, 4, 5, 6, 7}' OR + amname = 'gin' AND (procnums @> '{1, 2, 3}' AND (procnums && '{4, 6}')) OR + amname = 'spgist' AND procnums = '{1, 2, 3, 4, 5}' +); -- Unfortunately, we can't check the amproc link very well because the -- signature of the function may be different for different support routines