Refactor to add pg_strcoll(), pg_strxfrm(), and variants.

Offers a generally better separation of responsibilities for collation
code. Also, a step towards multi-lib ICU, which should be based on a
clean separation of the routines required for collation providers.

Callers with NUL-terminated strings should call pg_strcoll() or
pg_strxfrm(); callers with strings and their length should call the
variants pg_strncoll() or pg_strnxfrm().

Reviewed-by: Peter Eisentraut, Peter Geoghegan
Discussion: https://postgr.es/m/a581136455c940d7bd0ff482d3a2bd51af25a94f.camel%40j-davis.com

1 files changed, 34 insertions, 27 deletions

diff --git a/src/backend/access/hash/hashfunc.c b/src/backend/access/hash/hashfunc.c
index e3e40d6c21a..2deba44abd3 100644
--- a/src/backend/access/hash/hashfunc.c
+++ b/src/backend/access/hash/hashfunc.c
@@ -292,21 +292,24 @@ hashtext(PG_FUNCTION_ARGS)
 #ifdef USE_ICU
 		if (mylocale->provider == COLLPROVIDER_ICU)
 		{
-			int32_t		ulen = -1;
-			UChar	   *uchar = NULL;
-			Size		bsize;
-			uint8_t    *buf;
+			Size		bsize, rsize;
+			char	   *buf;
+			const char *keydata = VARDATA_ANY(key);
+			size_t		keylen = VARSIZE_ANY_EXHDR(key);
 
-			ulen = icu_to_uchar(&uchar, VARDATA_ANY(key), VARSIZE_ANY_EXHDR(key));
+			bsize = pg_strnxfrm(NULL, 0, keydata, keylen, mylocale);
+			buf = palloc(bsize + 1);
 
-			bsize = ucol_getSortKey(mylocale->info.icu.ucol,
-									uchar, ulen, NULL, 0);
-			buf = palloc(bsize);
-			ucol_getSortKey(mylocale->info.icu.ucol,
-							uchar, ulen, buf, bsize);
-			pfree(uchar);
+			rsize = pg_strnxfrm(buf, bsize + 1, keydata, keylen, mylocale);
+			if (rsize != bsize)
+				elog(ERROR, "pg_strnxfrm() returned unexpected result");
 
-			result = hash_any(buf, bsize);
+			/*
+			 * In principle, there's no reason to include the terminating NUL
+			 * character in the hash, but it was done before and the behavior
+			 * must be preserved.
+			 */
+			result = hash_any((uint8_t *) buf, bsize + 1);
 
 			pfree(buf);
 		}
@@ -350,21 +353,25 @@ hashtextextended(PG_FUNCTION_ARGS)
 #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);
-			pfree(uchar);
-
-			result = hash_any_extended(buf, bsize, PG_GETARG_INT64(1));
+			Size		bsize, rsize;
+			char	   *buf;
+			const char *keydata = VARDATA_ANY(key);
+			size_t		keylen = VARSIZE_ANY_EXHDR(key);
+
+			bsize = pg_strnxfrm(NULL, 0, keydata, keylen, mylocale);
+			buf = palloc(bsize + 1);
+
+			rsize = pg_strnxfrm(buf, bsize + 1, keydata, keylen, mylocale);
+			if (rsize != bsize)
+				elog(ERROR, "pg_strnxfrm() returned unexpected result");
+
+			/*
+			 * In principle, there's no reason to include the terminating NUL
+			 * character in the hash, but it was done before and the behavior
+			 * must be preserved.
+			 */
+			result = hash_any_extended((uint8_t *) buf, bsize + 1,
+									   PG_GETARG_INT64(1));
 
 			pfree(buf);
 		}