selfuncs.c: use pg_strxfrm() instead of strxfrm().

jeff-davis · jeff-davis · commit a890ad214942 · 2024-08-06T12:25:12.000-07:00
pg_strxfrm() takes a pg_locale_t, so it works properly with all providers. This improves estimates for ICU when performing linear interpolation within a histogram bin. Previously, convert_string_datum() always used strxfrm() and relied on setlocale(). That did not produce good estimates for non-default or non-libc collations. Discussion: https://postgr.es/m/89475ee5487d795124f4e25118ea8f1853edb8cb.camel@j-davis.com
diff --git a/src/backend/utils/adt/pg_locale.c b/src/backend/utils/adt/pg_locale.c
@@ -2124,14 +2124,7 @@ pg_strxfrm_libc(char *dest, const char *src, size_t destsize,
 				pg_locale_t locale)
 {
 	Assert(locale->provider == COLLPROVIDER_LIBC);
-
-#ifdef TRUST_STRXFRM
 	return strxfrm_l(dest, src, destsize, locale->info.lt);
-#else
-	/* shouldn't happen */
-	PGLOCALE_SUPPORT_ERROR(locale->provider);
-	return 0;					/* keep compiler quiet */
-#endif
 }
 
 static size_t
@@ -2340,6 +2333,10 @@ pg_strxfrm_enabled(pg_locale_t locale)
  * The provided 'src' must be nul-terminated. If 'destsize' is zero, 'dest'
  * may be NULL.
  *
+ * Not all providers support pg_strxfrm() safely. The caller should check
+ * pg_strxfrm_enabled() first, otherwise this function may return wrong
+ * results or an error.
+ *
  * Returns the number of bytes needed (or more) to store the transformed
  * string, excluding the terminating nul byte. If the value returned is
  * 'destsize' or greater, the resulting contents of 'dest' are undefined.
@@ -2372,6 +2369,10 @@ pg_strxfrm(char *dest, const char *src, size_t destsize, pg_locale_t locale)
  * 'src' does not need to be nul-terminated. If 'destsize' is zero, 'dest' may
  * be NULL.
  *
+ * Not all providers support pg_strnxfrm() safely. The caller should check
+ * pg_strxfrm_enabled() first, otherwise this function may return wrong
+ * results or an error.
+ *
  * Returns the number of bytes needed (or more) to store the transformed
  * string, excluding the terminating nul byte. If the value returned is
  * 'destsize' or greater, the resulting contents of 'dest' are undefined.
@@ -2426,6 +2427,10 @@ pg_strxfrm_prefix_enabled(pg_locale_t locale)
  *
  * The provided 'src' must be nul-terminated.
  *
+ * Not all providers support pg_strxfrm_prefix() safely. The caller should
+ * check pg_strxfrm_prefix_enabled() first, otherwise this function may return
+ * wrong results or an error.
+ *
  * If destsize is not large enough to hold the resulting byte sequence, stores
  * only the first destsize bytes in 'dest'. Returns the number of bytes
  * actually copied to 'dest'.
@@ -2455,6 +2460,10 @@ pg_strxfrm_prefix(char *dest, const char *src, size_t destsize,
  *
  * The provided 'src' must be nul-terminated.
  *
+ * Not all providers support pg_strnxfrm_prefix() safely. The caller should
+ * check pg_strxfrm_prefix_enabled() first, otherwise this function may return
+ * wrong results or an error.
+ *
  * If destsize is not large enough to hold the resulting byte sequence, stores
  * only the first destsize bytes in 'dest'. Returns the number of bytes
  * actually copied to 'dest'.
diff --git a/src/backend/utils/adt/selfuncs.c b/src/backend/utils/adt/selfuncs.c
@@ -4639,7 +4639,7 @@ convert_one_string_to_scalar(char *value, int rangelo, int rangehi)
  * On failure (e.g., unsupported typid), set *failure to true;
  * otherwise, that variable is not changed.  (We'll return NULL on failure.)
  *
- * When using a non-C locale, we must pass the string through strxfrm()
+ * When using a non-C locale, we must pass the string through pg_strxfrm()
  * before continuing, so as to generate correct locale-specific results.
  */
 static char *
@@ -4673,20 +4673,25 @@ convert_string_datum(Datum value, Oid typid, Oid collid, bool *failure)
 
 	if (!lc_collate_is_c(collid))
 	{
+		pg_locale_t mylocale = pg_newlocale_from_collation(collid);
 		char	   *xfrmstr;
 		size_t		xfrmlen;
 		size_t		xfrmlen2 PG_USED_FOR_ASSERTS_ONLY;
 
 		/*
 		 * XXX: We could guess at a suitable output buffer size and only call
-		 * strxfrm twice if our guess is too small.
+		 * pg_strxfrm() twice if our guess is too small.
 		 *
 		 * XXX: strxfrm doesn't support UTF-8 encoding on Win32, it can return
 		 * bogus data or set an error. This is not really a problem unless it
 		 * crashes since it will only give an estimation error and nothing
 		 * fatal.
+		 *
+		 * XXX: we do not check pg_strxfrm_enabled(). On some platforms and in
+		 * some cases, libc strxfrm() may return the wrong results, but that
+		 * will only lead to an estimation error.
 		 */
-		xfrmlen = strxfrm(NULL, val, 0);
+		xfrmlen = pg_strxfrm(NULL, val, 0, mylocale);
 #ifdef WIN32
 
 		/*
@@ -4698,7 +4703,7 @@ convert_string_datum(Datum value, Oid typid, Oid collid, bool *failure)
 			return val;
 #endif
 		xfrmstr = (char *) palloc(xfrmlen + 1);
-		xfrmlen2 = strxfrm(xfrmstr, val, xfrmlen + 1);
+		xfrmlen2 = pg_strxfrm(xfrmstr, val, xfrmlen + 1, mylocale);
 
 		/*
 		 * Some systems (e.g., glibc) can return a smaller value from the
