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

2 files changed, 91 insertions, 12 deletions

diff --git a/src/backend/access/hash/hashfunc.c b/src/backend/access/hash/hashfunc.c
index e5f3d42e045..0bf15ae7236 100644
--- a/src/backend/access/hash/hashfunc.c
+++ b/src/backend/access/hash/hashfunc.c
@@ -27,8 +27,10 @@
 #include "postgres.h"
 
 #include "access/hash.h"
+#include "catalog/pg_collation.h"
 #include "utils/builtins.h"
 #include "utils/hashutils.h"
+#include "utils/pg_locale.h"
 
 /*
  * Datatype-specific hash functions.
@@ -243,15 +245,51 @@ Datum
 hashtext(PG_FUNCTION_ARGS)
 {
 	text	   *key = PG_GETARG_TEXT_PP(0);
+	Oid			collid = PG_GET_COLLATION();
+	pg_locale_t	mylocale = 0;
 	Datum		result;
 
-	/*
-	 * Note: this is currently identical in behavior to hashvarlena, but keep
-	 * it as a separate function in case we someday want to do something
-	 * different in non-C locales.  (See also hashbpchar, if so.)
-	 */
-	result = hash_any((unsigned char *) VARDATA_ANY(key),
-					  VARSIZE_ANY_EXHDR(key));
+	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.")));
+
+	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 *) VARDATA_ANY(key),
+						  VARSIZE_ANY_EXHDR(key));
+	}
+	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(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);
@@ -263,12 +301,52 @@ Datum
 hashtextextended(PG_FUNCTION_ARGS)
 {
 	text	   *key = PG_GETARG_TEXT_PP(0);
+	Oid			collid = PG_GET_COLLATION();
+	pg_locale_t	mylocale = 0;
 	Datum		result;
 
-	/* Same approach as hashtext */
-	result = hash_any_extended((unsigned char *) VARDATA_ANY(key),
-							   VARSIZE_ANY_EXHDR(key),
-							   PG_GETARG_INT64(1));
+	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.")));
+
+	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 *) VARDATA_ANY(key),
+								   VARSIZE_ANY_EXHDR(key),
+								   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);
 
diff --git a/src/backend/access/spgist/spgtextproc.c b/src/backend/access/spgist/spgtextproc.c
index 39cd391529c..d22998c54bf 100644
--- a/src/backend/access/spgist/spgtextproc.c
+++ b/src/backend/access/spgist/spgtextproc.c
@@ -630,7 +630,8 @@ spg_text_leaf_consistent(PG_FUNCTION_ARGS)
 			 * query (prefix) string, so we don't need to check it again.
 			 */
 			res = (level >= queryLen) ||
-				DatumGetBool(DirectFunctionCall2(text_starts_with,
+				DatumGetBool(DirectFunctionCall2Coll(text_starts_with,
+													 PG_GET_COLLATION(),
 												 out->leafValue,
 												 PointerGetDatum(query)));