Control collation behavior with a method table.

Previously, behavior branched based on the provider. A method table is
less error-prone and more flexible.

The ctype behavior will be addressed in an upcoming commit.

Reviewed-by: Andreas Karlsson
Discussion: https://postgr.es/m/2830211e1b6e6a2e26d845780b03e125281ea17b.camel%40j-davis.com

Author: jeff-davis

src/backend/utils/adt/pg_locale.c

@@ -92,27 +92,12 @@ extern char *get_collation_actual_version_builtin(const char *collcollate);
 /* pg_locale_icu.c */
 #ifdef USE_ICU
 extern UCollator *pg_ucol_open(const char *loc_str);
-extern int	strncoll_icu(const char *arg1, ssize_t len1,
-						 const char *arg2, ssize_t len2,
-						 pg_locale_t locale);
-extern size_t strnxfrm_icu(char *dest, size_t destsize,
-						   const char *src, ssize_t srclen,
-						   pg_locale_t locale);
-extern size_t strnxfrm_prefix_icu(char *dest, size_t destsize,
-								  const char *src, ssize_t srclen,
-								  pg_locale_t locale);
 extern char *get_collation_actual_version_icu(const char *collcollate);
 #endif
 extern pg_locale_t create_pg_locale_icu(Oid collid, MemoryContext context);
 
 /* pg_locale_libc.c */
 extern pg_locale_t create_pg_locale_libc(Oid collid, MemoryContext context);
-extern int	strncoll_libc(const char *arg1, ssize_t len1,
-						  const char *arg2, ssize_t len2,
-						  pg_locale_t locale);
-extern size_t strnxfrm_libc(char *dest, size_t destsize,
-							const char *src, ssize_t srclen,
-							pg_locale_t locale);
 extern char *get_collation_actual_version_libc(const char *collcollate);
 
 extern size_t strlower_builtin(char *dst, size_t dstsize, const char *src,
@@ -1244,6 +1229,9 @@ create_pg_locale(Oid collid, MemoryContext context)
 
 	result->is_default = false;
 
+	Assert((result->collate_is_c && result->collate == NULL) ||
+		   (!result->collate_is_c && result->collate != NULL));
+
 	datum = SysCacheGetAttr(COLLOID, tp, Anum_pg_collation_collversion,
 							&isnull);
 	if (!isnull)
@@ -1467,19 +1455,7 @@ pg_strupper(char *dst, size_t dstsize, const char *src, ssize_t srclen,
 int
 pg_strcoll(const char *arg1, const char *arg2, pg_locale_t locale)
 {
-	int			result;
-
-	if (locale->provider == COLLPROVIDER_LIBC)
-		result = strncoll_libc(arg1, -1, arg2, -1, locale);
-#ifdef USE_ICU
-	else if (locale->provider == COLLPROVIDER_ICU)
-		result = strncoll_icu(arg1, -1, arg2, -1, locale);
-#endif
-	else
-		/* shouldn't happen */
-		PGLOCALE_SUPPORT_ERROR(locale->provider);
-
-	return result;
+	return locale->collate->strncoll(arg1, -1, arg2, -1, locale);
 }
 
 /*
@@ -1500,51 +1476,25 @@ int
 pg_strncoll(const char *arg1, ssize_t len1, const char *arg2, ssize_t len2,
 			pg_locale_t locale)
 {
-	int			result;
-
-	if (locale->provider == COLLPROVIDER_LIBC)
-		result = strncoll_libc(arg1, len1, arg2, len2, locale);
-#ifdef USE_ICU
-	else if (locale->provider == COLLPROVIDER_ICU)
-		result = strncoll_icu(arg1, len1, arg2, len2, locale);
-#endif
-	else
-		/* shouldn't happen */
-		PGLOCALE_SUPPORT_ERROR(locale->provider);
-
-	return result;
+	return locale->collate->strncoll(arg1, len1, arg2, len2, locale);
 }
 
 /*
  * Return true if the collation provider supports pg_strxfrm() and
  * pg_strnxfrm(); otherwise false.
  *
- * Unfortunately, it seems that strxfrm() for non-C collations is broken on
- * many common platforms; testing of multiple versions of glibc reveals that,
- * for many locales, strcoll() and strxfrm() do not return consistent
- * results. While no other libc other than Cygwin has so far been shown to
- * have a problem, we take the conservative course of action for right now and
- * disable this categorically.  (Users who are certain this isn't a problem on
- * their system can define TRUST_STRXFRM.)
  *
  * No similar problem is known for the ICU provider.
  */
 bool
 pg_strxfrm_enabled(pg_locale_t locale)
 {
-	if (locale->provider == COLLPROVIDER_LIBC)
-#ifdef TRUST_STRXFRM
-		return true;
-#else
-		return false;
-#endif
-	else if (locale->provider == COLLPROVIDER_ICU)
-		return true;
-	else
-		/* shouldn't happen */
-		PGLOCALE_SUPPORT_ERROR(locale->provider);
-
-	return false;				/* keep compiler quiet */
+	/*
+	 * locale->collate->strnxfrm is still a required method, even if it may
+	 * have the wrong behavior, because the planner uses it for estimates in
+	 * some cases.
+	 */
+	return locale->collate->strxfrm_is_safe;
 }
 
 /*
@@ -1555,19 +1505,7 @@ pg_strxfrm_enabled(pg_locale_t locale)
 size_t
 pg_strxfrm(char *dest, const char *src, size_t destsize, pg_locale_t locale)
 {
-	size_t		result = 0;		/* keep compiler quiet */
-
-	if (locale->provider == COLLPROVIDER_LIBC)
-		result = strnxfrm_libc(dest, destsize, src, -1, locale);
-#ifdef USE_ICU
-	else if (locale->provider == COLLPROVIDER_ICU)
-		result = strnxfrm_icu(dest, destsize, src, -1, locale);
-#endif
-	else
-		/* shouldn't happen */
-		PGLOCALE_SUPPORT_ERROR(locale->provider);
-
-	return result;
+	return locale->collate->strnxfrm(dest, destsize, src, -1, locale);
 }
 
 /*
@@ -1593,19 +1531,7 @@ size_t
 pg_strnxfrm(char *dest, size_t destsize, const char *src, ssize_t srclen,
 			pg_locale_t locale)
 {
-	size_t		result = 0;		/* keep compiler quiet */
-
-	if (locale->provider == COLLPROVIDER_LIBC)
-		result = strnxfrm_libc(dest, destsize, src, srclen, locale);
-#ifdef USE_ICU
-	else if (locale->provider == COLLPROVIDER_ICU)
-		result = strnxfrm_icu(dest, destsize, src, srclen, locale);
-#endif
-	else
-		/* shouldn't happen */
-		PGLOCALE_SUPPORT_ERROR(locale->provider);
-
-	return result;
+	return locale->collate->strnxfrm(dest, destsize, src, srclen, locale);
 }
 
 /*
@@ -1615,15 +1541,7 @@ pg_strnxfrm(char *dest, size_t destsize, const char *src, ssize_t srclen,
 bool
 pg_strxfrm_prefix_enabled(pg_locale_t locale)
 {
-	if (locale->provider == COLLPROVIDER_LIBC)
-		return false;
-	else if (locale->provider == COLLPROVIDER_ICU)
-		return true;
-	else
-		/* shouldn't happen */
-		PGLOCALE_SUPPORT_ERROR(locale->provider);
-
-	return false;				/* keep compiler quiet */
+	return (locale->collate->strnxfrm_prefix != NULL);
 }
 
 /*
@@ -1635,7 +1553,7 @@ size_t
 pg_strxfrm_prefix(char *dest, const char *src, size_t destsize,
 				  pg_locale_t locale)
 {
-	return pg_strnxfrm_prefix(dest, destsize, src, -1, locale);
+	return locale->collate->strnxfrm_prefix(dest, destsize, src, -1, locale);
 }
 
 /*
@@ -1660,16 +1578,7 @@ size_t
 pg_strnxfrm_prefix(char *dest, size_t destsize, const char *src,
 				   ssize_t srclen, pg_locale_t locale)
 {
-	size_t		result = 0;		/* keep compiler quiet */
-
-#ifdef USE_ICU
-	if (locale->provider == COLLPROVIDER_ICU)
-		result = strnxfrm_prefix_icu(dest, destsize, src, -1, locale);
-	else
-#endif
-		PGLOCALE_SUPPORT_ERROR(locale->provider);
-
-	return result;
+	return locale->collate->strnxfrm_prefix(dest, destsize, src, srclen, locale);
 }
 
 /*