Add reusable routine for making arrays unique.

Introduce qunique() and qunique_arg(), which can be used after qsort()
and qsort_arg() respectively to remove duplicate values.  Use it where
appropriate.

Author: Thomas Munro
Reviewed-by: Tom Lane (in an earlier version)
Discussion: https://postgr.es/m/CAEepm%3D2vmFTNpAmwbGGD2WaryM6T3hSDVKQPfUwjdD_5XY6vAA%40mail.gmail.com

3 files changed, 13 insertions, 36 deletions

diff --git a/contrib/hstore/hstore_io.c b/contrib/hstore/hstore_io.c
index be3cce4f740..10ec392775e 100644
--- a/contrib/hstore/hstore_io.c
+++ b/contrib/hstore/hstore_io.c
@@ -322,6 +322,11 @@ hstoreUniquePairs(Pairs *a, int32 l, int32 *buflen)
 	}
 
 	qsort((void *) a, l, sizeof(Pairs), comparePairs);
+
+	/*
+	 * We can't use qunique here because we have some clean-up code to run on
+	 * removed elements.
+	 */
 	ptr = a + 1;
 	res = a;
 	while (ptr - a < l)
diff --git a/contrib/intarray/_int_tool.c b/contrib/intarray/_int_tool.c
index efff81d77dc..e5f4bd40643 100644
--- a/contrib/intarray/_int_tool.c
+++ b/contrib/intarray/_int_tool.c
@@ -7,6 +7,7 @@
 
 #include "_int.h"
 #include "catalog/pg_type.h"
+#include "lib/qunique.h"
 
 /* arguments are assumed sorted & unique-ified */
 bool
@@ -308,23 +309,13 @@ internal_size(int *a, int len)
 ArrayType *
 _int_unique(ArrayType *r)
 {
-	int		   *tmp,
-			   *dr,
-			   *data;
 	int			num = ARRNELEMS(r);
+	bool		duplicates_found;	/* not used */
 
-	if (num < 2)
-		return r;
+	num = qunique_arg(ARRPTR(r), num, sizeof(int), isort_cmp,
+					  &duplicates_found);
 
-	data = tmp = dr = ARRPTR(r);
-	while (tmp - data < num)
-	{
-		if (*tmp != *dr)
-			*(++dr) = *tmp++;
-		else
-			tmp++;
-	}
-	return resize_intArrayType(r, dr + 1 - ARRPTR(r));
+	return resize_intArrayType(r, num);
 }
 
 void
diff --git a/contrib/pg_trgm/trgm_op.c b/contrib/pg_trgm/trgm_op.c
index 07a31803786..c9c8cbc7342 100644
--- a/contrib/pg_trgm/trgm_op.c
+++ b/contrib/pg_trgm/trgm_op.c
@@ -6,6 +6,7 @@
 #include <ctype.h>
 
 #include "catalog/pg_type.h"
+#include "lib/qunique.h"
 #include "trgm.h"
 #include "tsearch/ts_locale.h"
 #include "utils/lsyscache.h"
@@ -162,26 +163,6 @@ comp_trgm(const void *a, const void *b)
 	return CMPTRGM(a, b);
 }
 
-static int
-unique_array(trgm *a, int len)
-{
-	trgm	   *curend,
-			   *tmp;
-
-	curend = tmp = a;
-	while (tmp - a < len)
-		if (CMPTRGM(tmp, curend))
-		{
-			curend++;
-			CPTRGM(curend, tmp);
-			tmp++;
-		}
-		else
-			tmp++;
-
-	return curend + 1 - a;
-}
-
 /*
  * Finds first word in string, returns pointer to the word,
  * endword points to the character after word
@@ -394,7 +375,7 @@ generate_trgm(char *str, int slen)
 	if (len > 1)
 	{
 		qsort((void *) GETARR(trg), len, sizeof(trgm), comp_trgm);
-		len = unique_array(GETARR(trg), len);
+		len = qunique(GETARR(trg), len, sizeof(trgm), comp_trgm);
 	}
 
 	SET_VARSIZE(trg, CALCGTSIZE(ARRKEY, len));
@@ -942,7 +923,7 @@ generate_wildcard_trgm(const char *str, int slen)
 	if (len > 1)
 	{
 		qsort((void *) GETARR(trg), len, sizeof(trgm), comp_trgm);
-		len = unique_array(GETARR(trg), len);
+		len = qunique(GETARR(trg), len, sizeof(trgm), comp_trgm);
 	}
 
 	SET_VARSIZE(trg, CALCGTSIZE(ARRKEY, len));