Optimize sorting and deduplicating trigrams

Use templated qsort() so that the comparison function can be
inlined. To speed up qunique(), use a specialized comparison function
that only checks for equality.

Author: David Geier <geidav.pg@gmail.com>
Reviewed-by: Kirill Reshke <reshkekirill@gmail.com>
Discussion: https://www.postgresql.org/message-id/2a76b5ef-4b12-4023-93a1-eed6e64968f3@gmail.com

diff --git a/contrib/pg_trgm/trgm_op.c b/contrib/pg_trgm/trgm_op.c
index ee89e548d16cd767f2ab2f5811597cc0b70ecddd..0aca9b5826f23cfc69031660219b1013cfcaf247 100644 (file)
--- a/contrib/pg_trgm/trgm_op.c
+++ b/contrib/pg_trgm/trgm_op.c
@@ -226,6 +226,55 @@ CMPTRGM_CHOOSE(const void *a, const void *b)
        return CMPTRGM(a, b);
 }
 
+#define ST_SORT trigram_qsort_signed
+#define ST_ELEMENT_TYPE_VOID
+#define ST_COMPARE(a, b) CMPTRGM_SIGNED(a, b)
+#define ST_SCOPE static
+#define ST_DEFINE
+#define ST_DECLARE
+#include "lib/sort_template.h"
+
+#define ST_SORT trigram_qsort_unsigned
+#define ST_ELEMENT_TYPE_VOID
+#define ST_COMPARE(a, b) CMPTRGM_UNSIGNED(a, b)
+#define ST_SCOPE static
+#define ST_DEFINE
+#define ST_DECLARE
+#include "lib/sort_template.h"
+
+/* Sort an array of trigrams, handling signedess correctly */
+static void
+trigram_qsort(trgm *array, size_t n)
+{
+       if (GetDefaultCharSignedness())
+               trigram_qsort_signed(array, n, sizeof(trgm));
+       else
+               trigram_qsort_unsigned(array, n, sizeof(trgm));
+}
+
+
+/*
+ * Compare two trigrams for equality.  This has the same signature as
+ * comparison functions used for sorting, so that this can be used with
+ * qunique().  This doesn't need separate versions for "signed char" and "
+ * unsigned char" because equality is the same for both.
+ */
+static inline int
+CMPTRGM_EQ(const void *a, const void *b)
+{
+       char       *aa = (char *) a;
+       char       *bb = (char *) b;
+
+       return aa[0] != bb[0] || aa[1] != bb[1] || aa[2] != bb[2] ? 1 : 0;
+}
+
+/* Deduplicate an array of trigrams */
+static size_t
+trigram_qunique(trgm *array, size_t n)
+{
+       return qunique(array, n, sizeof(trgm), CMPTRGM_EQ);
+}
+
 /*
  * Deprecated function.
  * Use "pg_trgm.similarity_threshold" GUC variable instead of this function.
@@ -281,12 +330,6 @@ show_limit(PG_FUNCTION_ARGS)
        PG_RETURN_FLOAT4(similarity_threshold);
 }
 
-static int
-comp_trgm(const void *a, const void *b)
-{
-       return CMPTRGM(a, b);
-}
-
 /*
  * Finds first word in string, returns pointer to the word,
  * endword points to the character after word
@@ -569,8 +612,8 @@ generate_trgm(char *str, int slen)
         */
        if (len > 1)
        {
-               qsort(GETARR(trg), len, sizeof(trgm), comp_trgm);
-               len = qunique(GETARR(trg), len, sizeof(trgm), comp_trgm);
+               trigram_qsort(GETARR(trg), len);
+               len = trigram_qunique(GETARR(trg), len);
        }
 
        SET_VARSIZE(trg, CALCGTSIZE(ARRKEY, len));
@@ -1100,8 +1143,8 @@ generate_wildcard_trgm(const char *str, int slen)
        len = arr.length;
        if (len > 1)
        {
-               qsort(GETARR(trg), len, sizeof(trgm), comp_trgm);
-               len = qunique(GETARR(trg), len, sizeof(trgm), comp_trgm);
+               trigram_qsort(GETARR(trg), len);
+               len = trigram_qunique(GETARR(trg), len);
        }
 
        trg->flag = ARRKEY;