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, 10 insertions, 0 deletions

diff --git a/src/include/nodes/execnodes.h b/src/include/nodes/execnodes.h
index 62eb1a06eef..869c303e157 100644
--- a/src/include/nodes/execnodes.h
+++ b/src/include/nodes/execnodes.h
@@ -693,6 +693,7 @@ typedef struct TupleHashTableData
 	AttrNumber *keyColIdx;		/* attr numbers of key columns */
 	FmgrInfo   *tab_hash_funcs; /* hash functions for table datatype(s) */
 	ExprState  *tab_eq_func;	/* comparator for table datatype(s) */
+	Oid		   *tab_collations;	/* collations for hash and comparison */
 	MemoryContext tablecxt;		/* memory context containing table */
 	MemoryContext tempcxt;		/* context for function evaluations */
 	Size		entrysize;		/* actual size to make each hash entry */
@@ -862,6 +863,7 @@ typedef struct SubPlanState
 	AttrNumber *keyColIdx;		/* control data for hash tables */
 	Oid		   *tab_eq_funcoids;	/* equality func oids for table
 									 * datatype(s) */
+	Oid		   *tab_collations;	/* collations for hash and comparison */
 	FmgrInfo   *tab_hash_funcs; /* hash functions for table datatype(s) */
 	FmgrInfo   *tab_eq_funcs;	/* equality functions for table datatype(s) */
 	FmgrInfo   *lhs_hash_funcs; /* hash functions for lefthand datatype(s) */
@@ -1872,6 +1874,7 @@ typedef struct HashJoinState
 	List	   *hj_OuterHashKeys;	/* list of ExprState nodes */
 	List	   *hj_InnerHashKeys;	/* list of ExprState nodes */
 	List	   *hj_HashOperators;	/* list of operator OIDs */
+	List	   *hj_Collations;
 	HashJoinTable hj_HashTable;
 	uint32		hj_CurHashValue;
 	int			hj_CurBucketNo;
diff --git a/src/include/nodes/plannodes.h b/src/include/nodes/plannodes.h
index d66a187a530..24740c31e3d 100644
--- a/src/include/nodes/plannodes.h
+++ b/src/include/nodes/plannodes.h
@@ -297,6 +297,7 @@ typedef struct RecursiveUnion
 								 * duplicate-ness */
 	AttrNumber *dupColIdx;		/* their indexes in the target list */
 	Oid		   *dupOperators;	/* equality operators to compare with */
+	Oid		   *dupCollations;
 	long		numGroups;		/* estimated number of groups in input */
 } RecursiveUnion;
 
@@ -773,6 +774,7 @@ typedef struct Group
 	int			numCols;		/* number of grouping columns */
 	AttrNumber *grpColIdx;		/* their indexes in the target list */
 	Oid		   *grpOperators;	/* equality operators to compare with */
+	Oid		   *grpCollations;
 } Group;
 
 /* ---------------
@@ -797,6 +799,7 @@ typedef struct Agg
 	int			numCols;		/* number of grouping columns */
 	AttrNumber *grpColIdx;		/* their indexes in the target list */
 	Oid		   *grpOperators;	/* equality operators to compare with */
+	Oid		   *grpCollations;
 	long		numGroups;		/* estimated number of groups in input */
 	Bitmapset  *aggParams;		/* IDs of Params used in Aggref inputs */
 	/* Note: planner provides numGroups & aggParams only in HASHED/MIXED case */
@@ -815,9 +818,11 @@ typedef struct WindowAgg
 	int			partNumCols;	/* number of columns in partition clause */
 	AttrNumber *partColIdx;		/* their indexes in the target list */
 	Oid		   *partOperators;	/* equality operators for partition columns */
+	Oid		   *partCollations;	/* collations for partition columns */
 	int			ordNumCols;		/* number of columns in ordering clause */
 	AttrNumber *ordColIdx;		/* their indexes in the target list */
 	Oid		   *ordOperators;	/* equality operators for ordering columns */
+	Oid		   *ordCollations;	/* collations for ordering columns */
 	int			frameOptions;	/* frame_clause options, see WindowDef */
 	Node	   *startOffset;	/* expression for starting bound, if any */
 	Node	   *endOffset;		/* expression for ending bound, if any */
@@ -839,6 +844,7 @@ typedef struct Unique
 	int			numCols;		/* number of columns to check for uniqueness */
 	AttrNumber *uniqColIdx;		/* their indexes in the target list */
 	Oid		   *uniqOperators;	/* equality operators to compare with */
+	Oid		   *uniqCollations;	/* collations for equality comparisons */
 } Unique;
 
 /* ------------
@@ -913,6 +919,7 @@ typedef struct SetOp
 								 * duplicate-ness */
 	AttrNumber *dupColIdx;		/* their indexes in the target list */
 	Oid		   *dupOperators;	/* equality operators to compare with */
+	Oid		   *dupCollations;
 	AttrNumber	flagColIdx;		/* where is the flag column, if any */
 	int			firstFlag;		/* flag value for first input relation */
 	long		numGroups;		/* estimated number of groups in input */