Collations with nondeterministic comparison

This adds a flag "deterministic" to collations.  If that is false,
such a collation disables various optimizations that assume that
strings are equal only if they are byte-wise equal.  That then allows
use cases such as case-insensitive or accent-insensitive comparisons
or handling of strings with different Unicode normal forms.

This functionality is only supported with the ICU provider.  At least
glibc doesn't appear to have any locales that work in a
nondeterministic way, so it's not worth supporting this for the libc
provider.

The term "deterministic comparison" in this context is from Unicode
Technical Standard #10
(https://unicode.org/reports/tr10/#Deterministic_Comparison).

This patch makes changes in three areas:

- CREATE COLLATION DDL changes and system catalog changes to support
  this new flag.

- Many executor nodes and auxiliary code are extended to track
  collations.  Previously, this code would just throw away collation
  information, because the eventually-called user-defined functions
  didn't use it since they only cared about equality, which didn't
  need collation information.

- String data type functions that do equality comparisons and hashing
  are changed to take the (non-)deterministic flag into account.  For
  comparison, this just means skipping various shortcuts and tie
  breakers that use byte-wise comparison.  For hashing, we first need
  to convert the input string to a canonical "sort key" using the ICU
  analogue of strxfrm().

Reviewed-by: Daniel Verite <daniel@manitou-mail.org>
Reviewed-by: Peter Geoghegan <pg@bowt.ie>
Discussion: https://www.postgresql.org/message-id/flat/1ccc668f-4cbc-0bef-af67-450b47cdfee7@2ndquadrant.com

11 files changed, 494 insertions, 170 deletions

diff --git a/src/backend/utils/adt/arrayfuncs.c b/src/backend/utils/adt/arrayfuncs.c
index a34605ac94a..9cef018c0b4 100644
--- a/src/backend/utils/adt/arrayfuncs.c
+++ b/src/backend/utils/adt/arrayfuncs.c
@@ -3957,7 +3957,7 @@ hash_array(PG_FUNCTION_ARGS)
 	 * apply the hash function to each array element.
 	 */
 	InitFunctionCallInfoData(*locfcinfo, &typentry->hash_proc_finfo, 1,
-							 InvalidOid, NULL, NULL);
+							 PG_GET_COLLATION(), NULL, NULL);
 
 	/* Loop over source data */
 	nitems = ArrayGetNItems(ndims, dims);
diff --git a/src/backend/utils/adt/like.c b/src/backend/utils/adt/like.c
index 853c9c01e92..704e5720cf5 100644
--- a/src/backend/utils/adt/like.c
+++ b/src/backend/utils/adt/like.c
@@ -45,7 +45,7 @@ static int UTF8_MatchText(const char *t, int tlen, const char *p, int plen,
 static int SB_IMatchText(const char *t, int tlen, const char *p, int plen,
 			  pg_locale_t locale, bool locale_is_c);
 
-static int	GenericMatchText(const char *s, int slen, const char *p, int plen);
+static int	GenericMatchText(const char *s, int slen, const char *p, int plen, Oid collation);
 static int	Generic_Text_IC_like(text *str, text *pat, Oid collation);
 
 /*--------------------
@@ -148,8 +148,18 @@ SB_lower_char(unsigned char c, pg_locale_t locale, bool locale_is_c)
 
 /* Generic for all cases not requiring inline case-folding */
 static inline int
-GenericMatchText(const char *s, int slen, const char *p, int plen)
+GenericMatchText(const char *s, int slen, const char *p, int plen, Oid collation)
 {
+	if (collation && !lc_ctype_is_c(collation) && collation != DEFAULT_COLLATION_OID)
+	{
+		pg_locale_t		locale = pg_newlocale_from_collation(collation);
+
+		if (locale && !locale->deterministic)
+			ereport(ERROR,
+					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+					 errmsg("nondeterministic collations are not supported for LIKE")));
+	}
+
 	if (pg_database_encoding_max_length() == 1)
 		return SB_MatchText(s, slen, p, plen, 0, true);
 	else if (GetDatabaseEncoding() == PG_UTF8)
@@ -184,6 +194,11 @@ Generic_Text_IC_like(text *str, text *pat, Oid collation)
 					 errhint("Use the COLLATE clause to set the collation explicitly.")));
 		}
 		locale = pg_newlocale_from_collation(collation);
+
+		if (locale && !locale->deterministic)
+			ereport(ERROR,
+					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+					 errmsg("nondeterministic collations are not supported for ILIKE")));
 	}
 
 	/*
@@ -240,7 +255,7 @@ namelike(PG_FUNCTION_ARGS)
 	p = VARDATA_ANY(pat);
 	plen = VARSIZE_ANY_EXHDR(pat);
 
-	result = (GenericMatchText(s, slen, p, plen) == LIKE_TRUE);
+	result = (GenericMatchText(s, slen, p, plen, PG_GET_COLLATION()) == LIKE_TRUE);
 
 	PG_RETURN_BOOL(result);
 }
@@ -261,7 +276,7 @@ namenlike(PG_FUNCTION_ARGS)
 	p = VARDATA_ANY(pat);
 	plen = VARSIZE_ANY_EXHDR(pat);
 
-	result = (GenericMatchText(s, slen, p, plen) != LIKE_TRUE);
+	result = (GenericMatchText(s, slen, p, plen, PG_GET_COLLATION()) != LIKE_TRUE);
 
 	PG_RETURN_BOOL(result);
 }
@@ -282,7 +297,7 @@ textlike(PG_FUNCTION_ARGS)
 	p = VARDATA_ANY(pat);
 	plen = VARSIZE_ANY_EXHDR(pat);
 
-	result = (GenericMatchText(s, slen, p, plen) == LIKE_TRUE);
+	result = (GenericMatchText(s, slen, p, plen, PG_GET_COLLATION()) == LIKE_TRUE);
 
 	PG_RETURN_BOOL(result);
 }
@@ -303,7 +318,7 @@ textnlike(PG_FUNCTION_ARGS)
 	p = VARDATA_ANY(pat);
 	plen = VARSIZE_ANY_EXHDR(pat);
 
-	result = (GenericMatchText(s, slen, p, plen) != LIKE_TRUE);
+	result = (GenericMatchText(s, slen, p, plen, PG_GET_COLLATION()) != LIKE_TRUE);
 
 	PG_RETURN_BOOL(result);
 }
diff --git a/src/backend/utils/adt/like_support.c b/src/backend/utils/adt/like_support.c
index 69509811ef7..a65e63736c4 100644
--- a/src/backend/utils/adt/like_support.c
+++ b/src/backend/utils/adt/like_support.c
@@ -258,6 +258,20 @@ match_pattern_prefix(Node *leftop,
 	patt = (Const *) rightop;
 
 	/*
+	 * Not supported if the expression collation is nondeterministic.  The
+	 * optimized equality or prefix tests use bytewise comparisons, which is
+	 * not consistent with nondeterministic collations.  The actual
+	 * pattern-matching implementation functions will later error out that
+	 * pattern-matching is not supported with nondeterministic collations.
+	 * (We could also error out here, but by doing it later we get more
+	 * precise error messages.)  (It should be possible to support at least
+	 * Pattern_Prefix_Exact, but no point as along as the actual
+	 * pattern-matching implementations don't support it.)
+	 */
+	if (!get_collation_isdeterministic(expr_coll))
+		return NIL;
+
+	/*
 	 * Try to extract a fixed prefix from the pattern.
 	 */
 	pstatus = pattern_fixed_prefix(patt, ptype, expr_coll,
diff --git a/src/backend/utils/adt/name.c b/src/backend/utils/adt/name.c
index 3a7887d4553..54425925edb 100644
--- a/src/backend/utils/adt/name.c
+++ b/src/backend/utils/adt/name.c
@@ -131,14 +131,26 @@ namesend(PG_FUNCTION_ARGS)
  * have a '\0' terminator.  Whatever might be past the terminator is not
  * considered relevant to comparisons.
  */
+static int
+namecmp(Name arg1, Name arg2, Oid collid)
+{
+	/* Fast path for common case used in system catalogs */
+	if (collid == C_COLLATION_OID)
+		return strncmp(NameStr(*arg1), NameStr(*arg2), NAMEDATALEN);
+
+	/* Else rely on the varstr infrastructure */
+	return varstr_cmp(NameStr(*arg1), strlen(NameStr(*arg1)),
+					  NameStr(*arg2), strlen(NameStr(*arg2)),
+					  collid);
+}
+
 Datum
 nameeq(PG_FUNCTION_ARGS)
 {
 	Name		arg1 = PG_GETARG_NAME(0);
 	Name		arg2 = PG_GETARG_NAME(1);
 
-	/* Collation doesn't matter: equal only if bitwise-equal */
-	PG_RETURN_BOOL(strncmp(NameStr(*arg1), NameStr(*arg2), NAMEDATALEN) == 0);
+	PG_RETURN_BOOL(namecmp(arg1, arg2, PG_GET_COLLATION()) == 0);
 }
 
 Datum
@@ -147,21 +159,7 @@ namene(PG_FUNCTION_ARGS)
 	Name		arg1 = PG_GETARG_NAME(0);
 	Name		arg2 = PG_GETARG_NAME(1);
 
-	/* Collation doesn't matter: equal only if bitwise-equal */
-	PG_RETURN_BOOL(strncmp(NameStr(*arg1), NameStr(*arg2), NAMEDATALEN) != 0);
-}
-
-static int
-namecmp(Name arg1, Name arg2, Oid collid)
-{
-	/* Fast path for common case used in system catalogs */
-	if (collid == C_COLLATION_OID)
-		return strncmp(NameStr(*arg1), NameStr(*arg2), NAMEDATALEN);
-
-	/* Else rely on the varstr infrastructure */
-	return varstr_cmp(NameStr(*arg1), strlen(NameStr(*arg1)),
-					  NameStr(*arg2), strlen(NameStr(*arg2)),
-					  collid);
+	PG_RETURN_BOOL(namecmp(arg1, arg2, PG_GET_COLLATION()) != 0);
 }
 
 Datum
diff --git a/src/backend/utils/adt/orderedsetaggs.c b/src/backend/utils/adt/orderedsetaggs.c
index 2d384a99447..4db2d0d0e17 100644
--- a/src/backend/utils/adt/orderedsetaggs.c
+++ b/src/backend/utils/adt/orderedsetaggs.c
@@ -1084,7 +1084,7 @@ mode_final(PG_FUNCTION_ARGS)
 			last_abbrev_val = abbrev_val;
 		}
 		else if (abbrev_val == last_abbrev_val &&
-				 DatumGetBool(FunctionCall2(equalfn, val, last_val)))
+				 DatumGetBool(FunctionCall2Coll(equalfn, PG_GET_COLLATION(), val, last_val)))
 		{
 			/* value equal to previous value, count it */
 			if (last_val_is_mode)
@@ -1345,6 +1345,7 @@ hypothetical_dense_rank_final(PG_FUNCTION_ARGS)
 											  numDistinctCols,
 											  sortColIdx,
 											  osastate->qstate->eqOperators,
+											  osastate->qstate->sortCollations,
 											  NULL);
 		MemoryContextSwitchTo(oldContext);
 		osastate->qstate->compareTuple = compareTuple;
diff --git a/src/backend/utils/adt/pg_locale.c b/src/backend/utils/adt/pg_locale.c
index 7fe10e284aa..6e33d653405 100644
--- a/src/backend/utils/adt/pg_locale.c
+++ b/src/backend/utils/adt/pg_locale.c
@@ -1312,6 +1312,7 @@ pg_newlocale_from_collation(Oid collid)
 		/* We'll fill in the result struct locally before allocating memory */
 		memset(&result, 0, sizeof(result));
 		result.provider = collform->collprovider;
+		result.deterministic = collform->collisdeterministic;
 
 		if (collform->collprovider == COLLPROVIDER_LIBC)
 		{
diff --git a/src/backend/utils/adt/ri_triggers.c b/src/backend/utils/adt/ri_triggers.c
index 6d443db7e2f..72f8a9d69cf 100644
--- a/src/backend/utils/adt/ri_triggers.c
+++ b/src/backend/utils/adt/ri_triggers.c
@@ -676,6 +676,8 @@ ri_restrict(TriggerData *trigdata, bool is_no_action)
 		{
 			Oid			pk_type = RIAttType(pk_rel, riinfo->pk_attnums[i]);
 			Oid			fk_type = RIAttType(fk_rel, riinfo->fk_attnums[i]);
+			Oid			pk_coll = RIAttCollation(pk_rel, riinfo->pk_attnums[i]);
+			Oid			fk_coll = RIAttCollation(fk_rel, riinfo->fk_attnums[i]);
 
 			quoteOneName(attname,
 						 RIAttName(fk_rel, riinfo->fk_attnums[i]));
@@ -684,6 +686,8 @@ ri_restrict(TriggerData *trigdata, bool is_no_action)
 							paramname, pk_type,
 							riinfo->pf_eq_oprs[i],
 							attname, fk_type);
+			if (pk_coll != fk_coll && !get_collation_isdeterministic(pk_coll))
+				ri_GenerateQualCollation(&querybuf, pk_coll);
 			querysep = "AND";
 			queryoids[i] = pk_type;
 		}
@@ -778,6 +782,8 @@ RI_FKey_cascade_del(PG_FUNCTION_ARGS)
 		{
 			Oid			pk_type = RIAttType(pk_rel, riinfo->pk_attnums[i]);
 			Oid			fk_type = RIAttType(fk_rel, riinfo->fk_attnums[i]);
+			Oid			pk_coll = RIAttCollation(pk_rel, riinfo->pk_attnums[i]);
+			Oid			fk_coll = RIAttCollation(fk_rel, riinfo->fk_attnums[i]);
 
 			quoteOneName(attname,
 						 RIAttName(fk_rel, riinfo->fk_attnums[i]));
@@ -786,6 +792,8 @@ RI_FKey_cascade_del(PG_FUNCTION_ARGS)
 							paramname, pk_type,
 							riinfo->pf_eq_oprs[i],
 							attname, fk_type);
+			if (pk_coll != fk_coll && !get_collation_isdeterministic(pk_coll))
+				ri_GenerateQualCollation(&querybuf, pk_coll);
 			querysep = "AND";
 			queryoids[i] = pk_type;
 		}
@@ -890,6 +898,8 @@ RI_FKey_cascade_upd(PG_FUNCTION_ARGS)
 		{
 			Oid			pk_type = RIAttType(pk_rel, riinfo->pk_attnums[i]);
 			Oid			fk_type = RIAttType(fk_rel, riinfo->fk_attnums[i]);
+			Oid			pk_coll = RIAttCollation(pk_rel, riinfo->pk_attnums[i]);
+			Oid			fk_coll = RIAttCollation(fk_rel, riinfo->fk_attnums[i]);
 
 			quoteOneName(attname,
 						 RIAttName(fk_rel, riinfo->fk_attnums[i]));
@@ -901,6 +911,8 @@ RI_FKey_cascade_upd(PG_FUNCTION_ARGS)
 							paramname, pk_type,
 							riinfo->pf_eq_oprs[i],
 							attname, fk_type);
+			if (pk_coll != fk_coll && !get_collation_isdeterministic(pk_coll))
+				ri_GenerateQualCollation(&querybuf, pk_coll);
 			querysep = ",";
 			qualsep = "AND";
 			queryoids[i] = pk_type;
@@ -1065,6 +1077,8 @@ ri_set(TriggerData *trigdata, bool is_set_null)
 		{
 			Oid			pk_type = RIAttType(pk_rel, riinfo->pk_attnums[i]);
 			Oid			fk_type = RIAttType(fk_rel, riinfo->fk_attnums[i]);
+			Oid			pk_coll = RIAttCollation(pk_rel, riinfo->pk_attnums[i]);
+			Oid			fk_coll = RIAttCollation(fk_rel, riinfo->fk_attnums[i]);
 
 			quoteOneName(attname,
 						 RIAttName(fk_rel, riinfo->fk_attnums[i]));
@@ -1077,6 +1091,8 @@ ri_set(TriggerData *trigdata, bool is_set_null)
 							paramname, pk_type,
 							riinfo->pf_eq_oprs[i],
 							attname, fk_type);
+			if (pk_coll != fk_coll && !get_collation_isdeterministic(pk_coll))
+				ri_GenerateQualCollation(&querybuf, pk_coll);
 			querysep = ",";
 			qualsep = "AND";
 			queryoids[i] = pk_type;
@@ -2496,11 +2512,20 @@ ri_AttributesEqual(Oid eq_opr, Oid typeid,
 	}
 
 	/*
-	 * Apply the comparison operator.  We assume it doesn't care about
-	 * collations.
+	 * Apply the comparison operator.
+	 *
+	 * Note: This function is part of a call stack that determines whether an
+	 * update to a row is significant enough that it needs checking or action
+	 * on the other side of a foreign-key constraint.  Therefore, the
+	 * comparison here would need to be done with the collation of the *other*
+	 * table.  For simplicity (e.g., we might not even have the other table
+	 * open), we'll just use the default collation here, which could lead to
+	 * some false negatives.  All this would break if we ever allow
+	 * database-wide collations to be nondeterministic.
 	 */
-	return DatumGetBool(FunctionCall2(&entry->eq_opr_finfo,
-									  oldvalue, newvalue));
+	return DatumGetBool(FunctionCall2Coll(&entry->eq_opr_finfo,
+										  DEFAULT_COLLATION_OID,
+										  oldvalue, newvalue));
 }
 
 /*
diff --git a/src/backend/utils/adt/varchar.c b/src/backend/utils/adt/varchar.c
index 440fc8ed663..4003631d8f5 100644
--- a/src/backend/utils/adt/varchar.c
+++ b/src/backend/utils/adt/varchar.c
@@ -23,6 +23,8 @@
 #include "utils/array.h"
 #include "utils/builtins.h"
 #include "utils/hashutils.h"
+#include "utils/lsyscache.h"
+#include "utils/pg_locale.h"
 #include "utils/varlena.h"
 #include "mb/pg_wchar.h"
 
@@ -717,6 +719,22 @@ bpcharoctetlen(PG_FUNCTION_ARGS)
  * need to be so careful.
  *****************************************************************************/
 
+static void
+check_collation_set(Oid collid)
+{
+	if (!OidIsValid(collid))
+	{
+		/*
+		 * This typically means that the parser could not resolve a conflict
+		 * of implicit collations, so report it that way.
+		 */
+		ereport(ERROR,
+				(errcode(ERRCODE_INDETERMINATE_COLLATION),
+				 errmsg("could not determine which collation to use for string comparison"),
+				 errhint("Use the COLLATE clause to set the collation explicitly.")));
+	}
+}
+
 Datum
 bpchareq(PG_FUNCTION_ARGS)
 {
@@ -725,18 +743,31 @@ bpchareq(PG_FUNCTION_ARGS)
 	int			len1,
 				len2;
 	bool		result;
+	Oid			collid = PG_GET_COLLATION();
+
+	check_collation_set(collid);
 
 	len1 = bcTruelen(arg1);
 	len2 = bcTruelen(arg2);
 
-	/*
-	 * Since we only care about equality or not-equality, we can avoid all the
-	 * expense of strcoll() here, and just do bitwise comparison.
-	 */
-	if (len1 != len2)
-		result = false;
+	if (lc_collate_is_c(collid) ||
+		collid == DEFAULT_COLLATION_OID ||
+		pg_newlocale_from_collation(collid)->deterministic)
+	{
+		/*
+		 * Since we only care about equality or not-equality, we can avoid all the
+		 * expense of strcoll() here, and just do bitwise comparison.
+		 */
+		if (len1 != len2)
+			result = false;
+		else
+			result = (memcmp(VARDATA_ANY(arg1), VARDATA_ANY(arg2), len1) == 0);
+	}
 	else
-		result = (memcmp(VARDATA_ANY(arg1), VARDATA_ANY(arg2), len1) == 0);
+	{
+		result = (varstr_cmp(VARDATA_ANY(arg1), len1, VARDATA_ANY(arg2), len2,
+							 collid) == 0);
+	}
 
 	PG_FREE_IF_COPY(arg1, 0);
 	PG_FREE_IF_COPY(arg2, 1);
@@ -752,18 +783,29 @@ bpcharne(PG_FUNCTION_ARGS)
 	int			len1,
 				len2;
 	bool		result;
+	Oid			collid = PG_GET_COLLATION();
 
 	len1 = bcTruelen(arg1);
 	len2 = bcTruelen(arg2);
 
-	/*
-	 * Since we only care about equality or not-equality, we can avoid all the
-	 * expense of strcoll() here, and just do bitwise comparison.
-	 */
-	if (len1 != len2)
-		result = true;
+	if (lc_collate_is_c(collid) ||
+		collid == DEFAULT_COLLATION_OID ||
+		pg_newlocale_from_collation(collid)->deterministic)
+	{
+		/*
+		 * Since we only care about equality or not-equality, we can avoid all the
+		 * expense of strcoll() here, and just do bitwise comparison.
+		 */
+		if (len1 != len2)
+			result = true;
+		else
+			result = (memcmp(VARDATA_ANY(arg1), VARDATA_ANY(arg2), len1) != 0);
+	}
 	else
-		result = (memcmp(VARDATA_ANY(arg1), VARDATA_ANY(arg2), len1) != 0);
+	{
+		result = (varstr_cmp(VARDATA_ANY(arg1), len1, VARDATA_ANY(arg2), len2,
+							 collid) != 0);
+	}
 
 	PG_FREE_IF_COPY(arg1, 0);
 	PG_FREE_IF_COPY(arg2, 1);
@@ -933,23 +975,60 @@ bpchar_smaller(PG_FUNCTION_ARGS)
 /*
  * bpchar needs a specialized hash function because we want to ignore
  * trailing blanks in comparisons.
- *
- * Note: currently there is no need for locale-specific behavior here,
- * but if we ever change the semantics of bpchar comparison to trust
- * strcoll() completely, we'd need to do something different in non-C locales.
  */
 Datum
 hashbpchar(PG_FUNCTION_ARGS)
 {
 	BpChar	   *key = PG_GETARG_BPCHAR_PP(0);
+	Oid			collid = PG_GET_COLLATION();
 	char	   *keydata;
 	int			keylen;
+	pg_locale_t	mylocale = 0;
 	Datum		result;
 
+	if (!collid)
+		ereport(ERROR,
+				(errcode(ERRCODE_INDETERMINATE_COLLATION),
+				 errmsg("could not determine which collation to use for string hashing"),
+				 errhint("Use the COLLATE clause to set the collation explicitly.")));
+
 	keydata = VARDATA_ANY(key);
 	keylen = bcTruelen(key);
 
-	result = hash_any((unsigned char *) keydata, keylen);
+	if (!lc_collate_is_c(collid) && collid != DEFAULT_COLLATION_OID)
+		mylocale = pg_newlocale_from_collation(collid);
+
+	if (!mylocale || mylocale->deterministic)
+	{
+		result = hash_any((unsigned char *) keydata, keylen);
+	}
+	else
+	{
+#ifdef USE_ICU
+		if (mylocale->provider == COLLPROVIDER_ICU)
+		{
+			int32_t		ulen = -1;
+			UChar	   *uchar = NULL;
+			Size		bsize;
+			uint8_t	   *buf;
+
+			ulen = icu_to_uchar(&uchar, keydata, keylen);
+
+			bsize = ucol_getSortKey(mylocale->info.icu.ucol,
+									uchar, ulen, NULL, 0);
+			buf = palloc(bsize);
+			ucol_getSortKey(mylocale->info.icu.ucol,
+							uchar, ulen, buf, bsize);
+
+			result = hash_any(buf, bsize);
+
+			pfree(buf);
+		}
+		else
+#endif
+			/* shouldn't happen */
+			elog(ERROR, "unsupported collprovider: %c", mylocale->provider);
+	}
 
 	/* Avoid leaking memory for toasted inputs */
 	PG_FREE_IF_COPY(key, 0);
@@ -961,15 +1040,56 @@ Datum
 hashbpcharextended(PG_FUNCTION_ARGS)
 {
 	BpChar	   *key = PG_GETARG_BPCHAR_PP(0);
+	Oid			collid = PG_GET_COLLATION();
 	char	   *keydata;
 	int			keylen;
+	pg_locale_t	mylocale = 0;
 	Datum		result;
 
+	if (!collid)
+		ereport(ERROR,
+				(errcode(ERRCODE_INDETERMINATE_COLLATION),
+				 errmsg("could not determine which collation to use for string hashing"),
+				 errhint("Use the COLLATE clause to set the collation explicitly.")));
+
 	keydata = VARDATA_ANY(key);
 	keylen = bcTruelen(key);
 
-	result = hash_any_extended((unsigned char *) keydata, keylen,
-							   PG_GETARG_INT64(1));
+	if (!lc_collate_is_c(collid) && collid != DEFAULT_COLLATION_OID)
+		mylocale = pg_newlocale_from_collation(collid);
+
+	if (!mylocale || mylocale->deterministic)
+	{
+		result = hash_any_extended((unsigned char *) keydata, keylen,
+								   PG_GETARG_INT64(1));
+	}
+	else
+	{
+#ifdef USE_ICU
+		if (mylocale->provider == COLLPROVIDER_ICU)
+		{
+			int32_t		ulen = -1;
+			UChar	   *uchar = NULL;
+			Size		bsize;
+			uint8_t	   *buf;
+
+			ulen = icu_to_uchar(&uchar, VARDATA_ANY(key), VARSIZE_ANY_EXHDR(key));
+
+			bsize = ucol_getSortKey(mylocale->info.icu.ucol,
+									uchar, ulen, NULL, 0);
+			buf = palloc(bsize);
+			ucol_getSortKey(mylocale->info.icu.ucol,
+							uchar, ulen, buf, bsize);
+
+			result = hash_any_extended(buf, bsize, PG_GETARG_INT64(1));
+
+			pfree(buf);
+		}
+		else
+#endif
+			/* shouldn't happen */
+			elog(ERROR, "unsupported collprovider: %c", mylocale->provider);
+	}
 
 	PG_FREE_IF_COPY(key, 0);
 
@@ -985,12 +1105,23 @@ hashbpcharextended(PG_FUNCTION_ARGS)
  */
 
 static int
-internal_bpchar_pattern_compare(BpChar *arg1, BpChar *arg2)
+internal_bpchar_pattern_compare(BpChar *arg1, BpChar *arg2, Oid collid)
 {
 	int			result;
 	int			len1,
 				len2;
 
+	check_collation_set(collid);
+
+	/*
+	 * see internal_text_pattern_compare()
+	 */
+	if (!get_collation_isdeterministic(collid))
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("nondeterministic collations are not supported for operator class \"%s\"",
+						"bpchar_pattern_ops")));
+
 	len1 = bcTruelen(arg1);
 	len2 = bcTruelen(arg2);
 
@@ -1013,7 +1144,7 @@ bpchar_pattern_lt(PG_FUNCTION_ARGS)
 	BpChar	   *arg2 = PG_GETARG_BPCHAR_PP(1);
 	int			result;
 
-	result = internal_bpchar_pattern_compare(arg1, arg2);
+	result = internal_bpchar_pattern_compare(arg1, arg2, PG_GET_COLLATION());
 
 	PG_FREE_IF_COPY(arg1, 0);
 	PG_FREE_IF_COPY(arg2, 1);
@@ -1029,7 +1160,7 @@ bpchar_pattern_le(PG_FUNCTION_ARGS)
 	BpChar	   *arg2 = PG_GETARG_BPCHAR_PP(1);
 	int			result;
 
-	result = internal_bpchar_pattern_compare(arg1, arg2);
+	result = internal_bpchar_pattern_compare(arg1, arg2, PG_GET_COLLATION());
 
 	PG_FREE_IF_COPY(arg1, 0);
 	PG_FREE_IF_COPY(arg2, 1);
@@ -1045,7 +1176,7 @@ bpchar_pattern_ge(PG_FUNCTION_ARGS)
 	BpChar	   *arg2 = PG_GETARG_BPCHAR_PP(1);
 	int			result;
 
-	result = internal_bpchar_pattern_compare(arg1, arg2);
+	result = internal_bpchar_pattern_compare(arg1, arg2, PG_GET_COLLATION());
 
 	PG_FREE_IF_COPY(arg1, 0);
 	PG_FREE_IF_COPY(arg2, 1);
@@ -1061,7 +1192,7 @@ bpchar_pattern_gt(PG_FUNCTION_ARGS)
 	BpChar	   *arg2 = PG_GETARG_BPCHAR_PP(1);
 	int			result;
 
-	result = internal_bpchar_pattern_compare(arg1, arg2);
+	result = internal_bpchar_pattern_compare(arg1, arg2, PG_GET_COLLATION());
 
 	PG_FREE_IF_COPY(arg1, 0);
 	PG_FREE_IF_COPY(arg2, 1);
@@ -1077,7 +1208,7 @@ btbpchar_pattern_cmp(PG_FUNCTION_ARGS)
 	BpChar	   *arg2 = PG_GETARG_BPCHAR_PP(1);
 	int			result;
 
-	result = internal_bpchar_pattern_compare(arg1, arg2);
+	result = internal_bpchar_pattern_compare(arg1, arg2, PG_GET_COLLATION());
 
 	PG_FREE_IF_COPY(arg1, 0);
 	PG_FREE_IF_COPY(arg2, 1);
@@ -1090,8 +1221,17 @@ Datum
 btbpchar_pattern_sortsupport(PG_FUNCTION_ARGS)
 {
 	SortSupport ssup = (SortSupport) PG_GETARG_POINTER(0);
+	Oid			collid = ssup->ssup_collation;
 	MemoryContext oldcontext;
 
+	check_collation_set(collid);
+
+	if (!get_collation_isdeterministic(collid))
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("nondeterministic collations are not supported for operator class \"%s\"",
+						"bpchar_pattern_ops")));
+
 	oldcontext = MemoryContextSwitchTo(ssup->ssup_cxt);
 
 	/* Use generic string SortSupport, forcing "C" collation */
diff --git a/src/backend/utils/adt/varlena.c b/src/backend/utils/adt/varlena.c
index 39c394331b6..68a6e49aeb4 100644
--- a/src/backend/utils/adt/varlena.c
+++ b/src/backend/utils/adt/varlena.c
@@ -122,13 +122,14 @@ static text *text_substring(Datum str,
 			   int32 length,
 			   bool length_not_specified);
 static text *text_overlay(text *t1, text *t2, int sp, int sl);
-static int	text_position(text *t1, text *t2);
-static void text_position_setup(text *t1, text *t2, TextPositionState *state);
+static int	text_position(text *t1, text *t2, Oid collid);
+static void text_position_setup(text *t1, text *t2, Oid collid, TextPositionState *state);
 static bool text_position_next(TextPositionState *state);
 static char *text_position_next_internal(char *start_ptr, TextPositionState *state);
 static char *text_position_get_match_ptr(TextPositionState *state);
 static int	text_position_get_match_pos(TextPositionState *state);
 static void text_position_cleanup(TextPositionState *state);
+static void check_collation_set(Oid collid);
 static int	text_cmp(text *arg1, text *arg2, Oid collid);
 static bytea *bytea_catenate(bytea *t1, bytea *t2);
 static bytea *bytea_substring(Datum str,
@@ -1094,7 +1095,7 @@ textpos(PG_FUNCTION_ARGS)
 	text	   *str = PG_GETARG_TEXT_PP(0);
 	text	   *search_str = PG_GETARG_TEXT_PP(1);
 
-	PG_RETURN_INT32((int32) text_position(str, search_str));
+	PG_RETURN_INT32((int32) text_position(str, search_str, PG_GET_COLLATION()));
 }
 
 /*
@@ -1112,7 +1113,7 @@ textpos(PG_FUNCTION_ARGS)
  *	functions.
  */
 static int
-text_position(text *t1, text *t2)
+text_position(text *t1, text *t2, Oid collid)
 {
 	TextPositionState state;
 	int			result;
@@ -1120,7 +1121,7 @@ text_position(text *t1, text *t2)
 	if (VARSIZE_ANY_EXHDR(t1) < 1 || VARSIZE_ANY_EXHDR(t2) < 1)
 		return 0;
 
-	text_position_setup(t1, t2, &state);
+	text_position_setup(t1, t2, collid, &state);
 	if (!text_position_next(&state))
 		result = 0;
 	else
@@ -1147,10 +1148,21 @@ text_position(text *t1, text *t2)
  */
 
 static void
-text_position_setup(text *t1, text *t2, TextPositionState *state)
+text_position_setup(text *t1, text *t2, Oid collid, TextPositionState *state)
 {
 	int			len1 = VARSIZE_ANY_EXHDR(t1);
 	int			len2 = VARSIZE_ANY_EXHDR(t2);
+	pg_locale_t	mylocale = 0;
+
+	check_collation_set(collid);
+
+	if (!lc_collate_is_c(collid) && collid != DEFAULT_COLLATION_OID)
+		mylocale = pg_newlocale_from_collation(collid);
+
+	if (mylocale && !mylocale->deterministic)
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("nondeterministic collations are not supported for substring searches")));
 
 	Assert(len1 > 0);
 	Assert(len2 > 0);
@@ -1429,6 +1441,22 @@ text_position_cleanup(TextPositionState *state)
 	/* no cleanup needed */
 }
 
+static void
+check_collation_set(Oid collid)
+{
+	if (!OidIsValid(collid))
+	{
+		/*
+		 * This typically means that the parser could not resolve a conflict
+		 * of implicit collations, so report it that way.
+		 */
+		ereport(ERROR,
+				(errcode(ERRCODE_INDETERMINATE_COLLATION),
+				 errmsg("could not determine which collation to use for string comparison"),
+				 errhint("Use the COLLATE clause to set the collation explicitly.")));
+	}
+}
+
 /* varstr_cmp()
  * Comparison function for text strings with given lengths.
  * Includes locale support, but must copy strings to temporary memory
@@ -1441,6 +1469,8 @@ varstr_cmp(const char *arg1, int len1, const char *arg2, int len2, Oid collid)
 {
 	int			result;
 
+	check_collation_set(collid);
+
 	/*
 	 * Unfortunately, there is no strncoll(), so in the non-C locale case we
 	 * have to do some memory copying.  This turns out to be significantly
@@ -1462,20 +1492,7 @@ varstr_cmp(const char *arg1, int len1, const char *arg2, int len2, Oid collid)
 		pg_locale_t mylocale = 0;
 
 		if (collid != DEFAULT_COLLATION_OID)
-		{
-			if (!OidIsValid(collid))
-			{
-				/*
-				 * This typically means that the parser could not resolve a
-				 * conflict of implicit collations, so report it that way.
-				 */
-				ereport(ERROR,
-						(errcode(ERRCODE_INDETERMINATE_COLLATION),
-						 errmsg("could not determine which collation to use for string comparison"),
-						 errhint("Use the COLLATE clause to set the collation explicitly.")));
-			}
 			mylocale = pg_newlocale_from_collation(collid);
-		}
 
 		/*
 		 * memcmp() can't tell us which of two unequal strings sorts first,
@@ -1558,13 +1575,9 @@ varstr_cmp(const char *arg1, int len1, const char *arg2, int len2, Oid collid)
 				ereport(ERROR,
 						(errmsg("could not compare Unicode strings: %m")));
 
-			/*
-			 * In some locales wcscoll() can claim that nonidentical strings
-			 * are equal.  Believing that would be bad news for a number of
-			 * reasons, so we follow Perl's lead and sort "equal" strings
-			 * according to strcmp (on the UTF-8 representation).
-			 */
-			if (result == 0)
+			/* Break tie if necessary. */
+			if (result == 0 &&
+				(!mylocale || mylocale->deterministic))
 			{
 				result = memcmp(arg1, arg2, Min(len1, len2));
 				if ((result == 0) && (len1 != len2))
@@ -1649,13 +1662,9 @@ varstr_cmp(const char *arg1, int len1, const char *arg2, int len2, Oid collid)
 		else
 			result = strcoll(a1p, a2p);
 
-		/*
-		 * In some locales strcoll() can claim that nonidentical strings are
-		 * equal.  Believing that would be bad news for a number of reasons,
-		 * so we follow Perl's lead and sort "equal" strings according to
-		 * strcmp().
-		 */
-		if (result == 0)
+		/* Break tie if necessary. */
+		if (result == 0 &&
+			(!mylocale || mylocale->deterministic))
 			result = strcmp(a1p, a2p);
 
 		if (a1p != a1buf)
@@ -1699,33 +1708,52 @@ text_cmp(text *arg1, text *arg2, Oid collid)
 Datum
 texteq(PG_FUNCTION_ARGS)
 {
-	Datum		arg1 = PG_GETARG_DATUM(0);
-	Datum		arg2 = PG_GETARG_DATUM(1);
+	Oid			collid = PG_GET_COLLATION();
 	bool		result;
-	Size		len1,
-				len2;
 
-	/*
-	 * Since we only care about equality or not-equality, we can avoid all the
-	 * expense of strcoll() here, and just do bitwise comparison.  In fact, we
-	 * don't even have to do a bitwise comparison if we can show the lengths
-	 * of the strings are unequal; which might save us from having to detoast
-	 * one or both values.
-	 */
-	len1 = toast_raw_datum_size(arg1);
-	len2 = toast_raw_datum_size(arg2);
-	if (len1 != len2)
-		result = false;
+	check_collation_set(collid);
+
+	if (lc_collate_is_c(collid) ||
+		collid == DEFAULT_COLLATION_OID ||
+		pg_newlocale_from_collation(collid)->deterministic)
+	{
+		Datum		arg1 = PG_GETARG_DATUM(0);
+		Datum		arg2 = PG_GETARG_DATUM(1);
+		Size		len1,
+					len2;
+
+		/*
+		 * Since we only care about equality or not-equality, we can avoid all the
+		 * expense of strcoll() here, and just do bitwise comparison.  In fact, we
+		 * don't even have to do a bitwise comparison if we can show the lengths
+		 * of the strings are unequal; which might save us from having to detoast
+		 * one or both values.
+		 */
+		len1 = toast_raw_datum_size(arg1);
+		len2 = toast_raw_datum_size(arg2);
+		if (len1 != len2)
+			result = false;
+		else
+		{
+			text	   *targ1 = DatumGetTextPP(arg1);
+			text	   *targ2 = DatumGetTextPP(arg2);
+
+			result = (memcmp(VARDATA_ANY(targ1), VARDATA_ANY(targ2),
+							 len1 - VARHDRSZ) == 0);
+
+			PG_FREE_IF_COPY(targ1, 0);
+			PG_FREE_IF_COPY(targ2, 1);
+		}
+	}
 	else
 	{
-		text	   *targ1 = DatumGetTextPP(arg1);
-		text	   *targ2 = DatumGetTextPP(arg2);
+		text	   *arg1 = PG_GETARG_TEXT_PP(0);
+		text	   *arg2 = PG_GETARG_TEXT_PP(1);
 
-		result = (memcmp(VARDATA_ANY(targ1), VARDATA_ANY(targ2),
-						 len1 - VARHDRSZ) == 0);
+		result = (text_cmp(arg1, arg2, collid) == 0);
 
-		PG_FREE_IF_COPY(targ1, 0);
-		PG_FREE_IF_COPY(targ2, 1);
+		PG_FREE_IF_COPY(arg1, 0);
+		PG_FREE_IF_COPY(arg2, 1);
 	}
 
 	PG_RETURN_BOOL(result);
@@ -1734,27 +1762,46 @@ texteq(PG_FUNCTION_ARGS)
 Datum
 textne(PG_FUNCTION_ARGS)
 {
-	Datum		arg1 = PG_GETARG_DATUM(0);
-	Datum		arg2 = PG_GETARG_DATUM(1);
+	Oid			collid = PG_GET_COLLATION();
 	bool		result;
-	Size		len1,
-				len2;
 
-	/* See comment in texteq() */
-	len1 = toast_raw_datum_size(arg1);
-	len2 = toast_raw_datum_size(arg2);
-	if (len1 != len2)
-		result = true;
+	check_collation_set(collid);
+
+	if (lc_collate_is_c(collid) ||
+		collid == DEFAULT_COLLATION_OID ||
+		pg_newlocale_from_collation(collid)->deterministic)
+	{
+		Datum		arg1 = PG_GETARG_DATUM(0);
+		Datum		arg2 = PG_GETARG_DATUM(1);
+		Size		len1,
+					len2;
+
+		/* See comment in texteq() */
+		len1 = toast_raw_datum_size(arg1);
+		len2 = toast_raw_datum_size(arg2);
+		if (len1 != len2)
+			result = true;
+		else
+		{
+			text	   *targ1 = DatumGetTextPP(arg1);
+			text	   *targ2 = DatumGetTextPP(arg2);
+
+			result = (memcmp(VARDATA_ANY(targ1), VARDATA_ANY(targ2),
+							 len1 - VARHDRSZ) != 0);
+
+			PG_FREE_IF_COPY(targ1, 0);
+			PG_FREE_IF_COPY(targ2, 1);
+		}
+	}
 	else
 	{
-		text	   *targ1 = DatumGetTextPP(arg1);
-		text	   *targ2 = DatumGetTextPP(arg2);
+		text	   *arg1 = PG_GETARG_TEXT_PP(0);
+		text	   *arg2 = PG_GETARG_TEXT_PP(1);
 
-		result = (memcmp(VARDATA_ANY(targ1), VARDATA_ANY(targ2),
-						 len1 - VARHDRSZ) != 0);
+		result = (text_cmp(arg1, arg2, collid) != 0);
 
-		PG_FREE_IF_COPY(targ1, 0);
-		PG_FREE_IF_COPY(targ2, 1);
+		PG_FREE_IF_COPY(arg1, 0);
+		PG_FREE_IF_COPY(arg2, 1);
 	}
 
 	PG_RETURN_BOOL(result);
@@ -1825,10 +1872,22 @@ text_starts_with(PG_FUNCTION_ARGS)
 {
 	Datum		arg1 = PG_GETARG_DATUM(0);
 	Datum		arg2 = PG_GETARG_DATUM(1);
+	Oid			collid = PG_GET_COLLATION();
+	pg_locale_t	mylocale = 0;
 	bool		result;
 	Size		len1,
 				len2;
 
+	check_collation_set(collid);
+
+	if (!lc_collate_is_c(collid) && collid != DEFAULT_COLLATION_OID)
+		mylocale = pg_newlocale_from_collation(collid);
+
+	if (mylocale && !mylocale->deterministic)
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("nondeterministic collations are not supported for substring searches")));
+
 	len1 = toast_raw_datum_size(arg1);
 	len2 = toast_raw_datum_size(arg2);
 	if (len2 > len1)
@@ -1898,6 +1957,8 @@ varstr_sortsupport(SortSupport ssup, Oid typid, Oid collid)
 	VarStringSortSupport *sss;
 	pg_locale_t locale = 0;
 
+	check_collation_set(collid);
+
 	/*
 	 * If possible, set ssup->comparator to a function which can be used to
 	 * directly compare two datums.  If we can do this, we'll avoid the
@@ -1934,20 +1995,7 @@ varstr_sortsupport(SortSupport ssup, Oid typid, Oid collid)
 		 * result.
 		 */
 		if (collid != DEFAULT_COLLATION_OID)
-		{
-			if (!OidIsValid(collid))
-			{
-				/*
-				 * This typically means that the parser could not resolve a
-				 * conflict of implicit collations, so report it that way.
-				 */
-				ereport(ERROR,
-						(errcode(ERRCODE_INDETERMINATE_COLLATION),
-						 errmsg("could not determine which collation to use for string comparison"),
-						 errhint("Use the COLLATE clause to set the collation explicitly.")));
-			}
 			locale = pg_newlocale_from_collation(collid);
-		}
 
 		/*
 		 * There is a further exception on Windows.  When the database
@@ -2328,12 +2376,9 @@ varstrfastcmp_locale(char *a1p, int len1, char *a2p, int len2, SortSupport ssup)
 	else
 		result = strcoll(sss->buf1, sss->buf2);
 
-	/*
-	 * In some locales strcoll() can claim that nonidentical strings are
-	 * equal. Believing that would be bad news for a number of reasons, so we
-	 * follow Perl's lead and sort "equal" strings according to strcmp().
-	 */
-	if (result == 0)
+	/* Break tie if necessary. */
+	if (result == 0 &&
+		(!sss->locale || sss->locale->deterministic))
 		result = strcmp(sss->buf1, sss->buf2);
 
 	/* Cache result, perhaps saving an expensive strcoll() call next time */
@@ -2760,10 +2805,18 @@ nameeqtext(PG_FUNCTION_ARGS)
 	text	   *arg2 = PG_GETARG_TEXT_PP(1);
 	size_t		len1 = strlen(NameStr(*arg1));
 	size_t		len2 = VARSIZE_ANY_EXHDR(arg2);
+	Oid			collid = PG_GET_COLLATION();
 	bool		result;
 
-	result = (len1 == len2 &&
-			  memcmp(NameStr(*arg1), VARDATA_ANY(arg2), len1) == 0);
+	check_collation_set(collid);
+
+	if (collid == C_COLLATION_OID)
+		result = (len1 == len2 &&
+				  memcmp(NameStr(*arg1), VARDATA_ANY(arg2), len1) == 0);
+	else
+		result = (varstr_cmp(NameStr(*arg1), len1,
+							 VARDATA_ANY(arg2), len2,
+							 collid) == 0);
 
 	PG_FREE_IF_COPY(arg2, 1);
 
@@ -2777,10 +2830,18 @@ texteqname(PG_FUNCTION_ARGS)
 	Name		arg2 = PG_GETARG_NAME(1);
 	size_t		len1 = VARSIZE_ANY_EXHDR(arg1);
 	size_t		len2 = strlen(NameStr(*arg2));
+	Oid			collid = PG_GET_COLLATION();
 	bool		result;
 
-	result = (len1 == len2 &&
-			  memcmp(VARDATA_ANY(arg1), NameStr(*arg2), len1) == 0);
+	check_collation_set(collid);
+
+	if (collid == C_COLLATION_OID)
+		result = (len1 == len2 &&
+				  memcmp(VARDATA_ANY(arg1), NameStr(*arg2), len1) == 0);
+	else
+		result = (varstr_cmp(VARDATA_ANY(arg1), len1,
+							 NameStr(*arg2), len2,
+							 collid) == 0);
 
 	PG_FREE_IF_COPY(arg1, 0);
 
@@ -2794,10 +2855,18 @@ namenetext(PG_FUNCTION_ARGS)
 	text	   *arg2 = PG_GETARG_TEXT_PP(1);
 	size_t		len1 = strlen(NameStr(*arg1));
 	size_t		len2 = VARSIZE_ANY_EXHDR(arg2);
+	Oid			collid = PG_GET_COLLATION();
 	bool		result;
 
-	result = !(len1 == len2 &&
-			   memcmp(NameStr(*arg1), VARDATA_ANY(arg2), len1) == 0);
+	check_collation_set(collid);
+
+	if (collid == C_COLLATION_OID)
+		result = !(len1 == len2 &&
+				   memcmp(NameStr(*arg1), VARDATA_ANY(arg2), len1) == 0);
+	else
+		result = !(varstr_cmp(NameStr(*arg1), len1,
+							  VARDATA_ANY(arg2), len2,
+							  collid) == 0);
 
 	PG_FREE_IF_COPY(arg2, 1);
 
@@ -2811,10 +2880,18 @@ textnename(PG_FUNCTION_ARGS)
 	Name		arg2 = PG_GETARG_NAME(1);
 	size_t		len1 = VARSIZE_ANY_EXHDR(arg1);
 	size_t		len2 = strlen(NameStr(*arg2));
+	Oid			collid = PG_GET_COLLATION();
 	bool		result;
 
-	result = !(len1 == len2 &&
-			   memcmp(VARDATA_ANY(arg1), NameStr(*arg2), len1) == 0);
+	check_collation_set(collid);
+
+	if (collid == C_COLLATION_OID)
+		result = !(len1 == len2 &&
+				   memcmp(VARDATA_ANY(arg1), NameStr(*arg2), len1) == 0);
+	else
+		result = !(varstr_cmp(VARDATA_ANY(arg1), len1,
+							  NameStr(*arg2), len2,
+							  collid) == 0);
 
 	PG_FREE_IF_COPY(arg1, 0);
 
@@ -2919,12 +2996,34 @@ textgename(PG_FUNCTION_ARGS)
  */
 
 static int
-internal_text_pattern_compare(text *arg1, text *arg2)
+internal_text_pattern_compare(text *arg1, text *arg2, Oid collid)
 {
 	int			result;
 	int			len1,
 				len2;
 
+	check_collation_set(collid);
+
+	/*
+	 * XXX We cannot use a text_pattern_ops index for nondeterministic
+	 * collations, because these operators intentionally ignore the collation.
+	 * However, the planner has no way to know that, so it might choose such
+	 * an index for an "=" clause, which would lead to wrong results.  This
+	 * check here doesn't prevent choosing the index, but it will at least
+	 * error out if the index is chosen.  A text_pattern_ops index on a column
+	 * with nondeterministic collation is pretty useless anyway, since LIKE
+	 * etc. won't work there either.  A future possibility would be to
+	 * annotate the operator class or its members in the catalog to avoid the
+	 * index.  Another alternative is to stay away from the *_pattern_ops
+	 * operator classes and prefer creating LIKE-supporting indexes with
+	 * COLLATE "C".
+	 */
+	if (!get_collation_isdeterministic(collid))
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("nondeterministic collations are not supported for operator class \"%s\"",
+						"text_pattern_ops")));
+
 	len1 = VARSIZE_ANY_EXHDR(arg1);
 	len2 = VARSIZE_ANY_EXHDR(arg2);
 
@@ -2947,7 +3046,7 @@ text_pattern_lt(PG_FUNCTION_ARGS)
 	text	   *arg2 = PG_GETARG_TEXT_PP(1);
 	int			result;
 
-	result = internal_text_pattern_compare(arg1, arg2);
+	result = internal_text_pattern_compare(arg1, arg2, PG_GET_COLLATION());
 
 	PG_FREE_IF_COPY(arg1, 0);
 	PG_FREE_IF_COPY(arg2, 1);
@@ -2963,7 +3062,7 @@ text_pattern_le(PG_FUNCTION_ARGS)
 	text	   *arg2 = PG_GETARG_TEXT_PP(1);
 	int			result;
 
-	result = internal_text_pattern_compare(arg1, arg2);
+	result = internal_text_pattern_compare(arg1, arg2, PG_GET_COLLATION());
 
 	PG_FREE_IF_COPY(arg1, 0);
 	PG_FREE_IF_COPY(arg2, 1);
@@ -2979,7 +3078,7 @@ text_pattern_ge(PG_FUNCTION_ARGS)
 	text	   *arg2 = PG_GETARG_TEXT_PP(1);
 	int			result;
 
-	result = internal_text_pattern_compare(arg1, arg2);
+	result = internal_text_pattern_compare(arg1, arg2, PG_GET_COLLATION());
 
 	PG_FREE_IF_COPY(arg1, 0);
 	PG_FREE_IF_COPY(arg2, 1);
@@ -2995,7 +3094,7 @@ text_pattern_gt(PG_FUNCTION_ARGS)
 	text	   *arg2 = PG_GETARG_TEXT_PP(1);
 	int			result;
 
-	result = internal_text_pattern_compare(arg1, arg2);
+	result = internal_text_pattern_compare(arg1, arg2, PG_GET_COLLATION());
 
 	PG_FREE_IF_COPY(arg1, 0);
 	PG_FREE_IF_COPY(arg2, 1);
@@ -3011,7 +3110,7 @@ bttext_pattern_cmp(PG_FUNCTION_ARGS)
 	text	   *arg2 = PG_GETARG_TEXT_PP(1);
 	int			result;
 
-	result = internal_text_pattern_compare(arg1, arg2);
+	result = internal_text_pattern_compare(arg1, arg2, PG_GET_COLLATION());
 
 	PG_FREE_IF_COPY(arg1, 0);
 	PG_FREE_IF_COPY(arg2, 1);
@@ -3024,8 +3123,17 @@ Datum
 bttext_pattern_sortsupport(PG_FUNCTION_ARGS)
 {
 	SortSupport ssup = (SortSupport) PG_GETARG_POINTER(0);
+	Oid			collid = ssup->ssup_collation;
 	MemoryContext oldcontext;
 
+	check_collation_set(collid);
+
+	if (!get_collation_isdeterministic(collid))
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("nondeterministic collations are not supported for operator class \"%s\"",
+						"text_pattern_ops")));
+
 	oldcontext = MemoryContextSwitchTo(ssup->ssup_cxt);
 
 	/* Use generic string SortSupport, forcing "C" collation */
@@ -4121,7 +4229,7 @@ replace_text(PG_FUNCTION_ARGS)
 		PG_RETURN_TEXT_P(src_text);
 	}
 
-	text_position_setup(src_text, from_sub_text, &state);
+	text_position_setup(src_text, from_sub_text, PG_GET_COLLATION(), &state);
 
 	found = text_position_next(&state);
 
@@ -4482,7 +4590,7 @@ split_text(PG_FUNCTION_ARGS)
 			PG_RETURN_TEXT_P(cstring_to_text(""));
 	}
 
-	text_position_setup(inputstring, fldsep, &state);
+	text_position_setup(inputstring, fldsep, PG_GET_COLLATION(), &state);
 
 	/* identify bounds of first field */
 	start_ptr = VARDATA_ANY(inputstring);
@@ -4538,11 +4646,12 @@ split_text(PG_FUNCTION_ARGS)
  * Convenience function to return true when two text params are equal.
  */
 static bool
-text_isequal(text *txt1, text *txt2)
+text_isequal(text *txt1, text *txt2, Oid collid)
 {
-	return DatumGetBool(DirectFunctionCall2(texteq,
-											PointerGetDatum(txt1),
-											PointerGetDatum(txt2)));
+	return DatumGetBool(DirectFunctionCall2Coll(texteq,
+												collid,
+												PointerGetDatum(txt1),
+												PointerGetDatum(txt2)));
 }
 
 /*
@@ -4633,7 +4742,7 @@ text_to_array_internal(PG_FUNCTION_ARGS)
 			int			lbs[1];
 
 			/* single element can be a NULL too */
-			is_null = null_string ? text_isequal(inputstring, null_string) : false;
+			is_null = null_string ? text_isequal(inputstring, null_string, PG_GET_COLLATION()) : false;
 
 			elems[0] = PointerGetDatum(inputstring);
 			nulls[0] = is_null;
@@ -4645,7 +4754,7 @@ text_to_array_internal(PG_FUNCTION_ARGS)
 													 TEXTOID, -1, false, 'i'));
 		}
 
-		text_position_setup(inputstring, fldsep, &state);
+		text_position_setup(inputstring, fldsep, PG_GET_COLLATION(), &state);
 
 		start_ptr = VARDATA_ANY(inputstring);
 
@@ -4673,7 +4782,7 @@ text_to_array_internal(PG_FUNCTION_ARGS)
 
 			/* must build a temp text datum to pass to accumArrayResult */
 			result_text = cstring_to_text_with_len(start_ptr, chunk_len);
-			is_null = null_string ? text_isequal(result_text, null_string) : false;
+			is_null = null_string ? text_isequal(result_text, null_string, PG_GET_COLLATION()) : false;
 
 			/* stash away this field */
 			astate = accumArrayResult(astate,
@@ -4715,7 +4824,7 @@ text_to_array_internal(PG_FUNCTION_ARGS)
 
 			/* must build a temp text datum to pass to accumArrayResult */
 			result_text = cstring_to_text_with_len(start_ptr, chunk_len);
-			is_null = null_string ? text_isequal(result_text, null_string) : false;
+			is_null = null_string ? text_isequal(result_text, null_string, PG_GET_COLLATION()) : false;
 
 			/* stash away this field */
 			astate = accumArrayResult(astate,
diff --git a/src/backend/utils/cache/catcache.c b/src/backend/utils/cache/catcache.c
index 07e1cd76962..d05930bc4cf 100644
--- a/src/backend/utils/cache/catcache.c
+++ b/src/backend/utils/cache/catcache.c
@@ -170,13 +170,18 @@ int4hashfast(Datum datum)
 static bool
 texteqfast(Datum a, Datum b)
 {
-	return DatumGetBool(DirectFunctionCall2(texteq, a, b));
+	/*
+	 * The use of DEFAULT_COLLATION_OID is fairly arbitrary here.  We just
+	 * want to take the fast "deterministic" path in texteq().
+	 */
+	return DatumGetBool(DirectFunctionCall2Coll(texteq, DEFAULT_COLLATION_OID, a, b));
 }
 
 static uint32
 texthashfast(Datum datum)
 {
-	return DatumGetInt32(DirectFunctionCall1(hashtext, datum));
+	/* analogously here as in texteqfast() */
+	return DatumGetInt32(DirectFunctionCall1Coll(hashtext, DEFAULT_COLLATION_OID, datum));
 }
 
 static bool
diff --git a/src/backend/utils/cache/lsyscache.c b/src/backend/utils/cache/lsyscache.c
index e88c45d268a..59e6bcd856c 100644
--- a/src/backend/utils/cache/lsyscache.c
+++ b/src/backend/utils/cache/lsyscache.c
@@ -908,6 +908,22 @@ get_collation_name(Oid colloid)
 		return NULL;
 }
 
+bool
+get_collation_isdeterministic(Oid colloid)
+{
+	HeapTuple	tp;
+	Form_pg_collation colltup;
+	bool		result;
+
+	tp = SearchSysCache1(COLLOID, ObjectIdGetDatum(colloid));
+	if (!HeapTupleIsValid(tp))
+		elog(ERROR, "cache lookup failed for collation %u", colloid);
+	colltup = (Form_pg_collation) GETSTRUCT(tp);
+	result = colltup->collisdeterministic;
+	ReleaseSysCache(tp);
+	return result;
+}
+
 /*				---------- CONSTRAINT CACHE ----------					 */
 
 /*