Remove lc_ctype_is_c().

Instead always fetch the locale and look at the ctype_is_c field.

hba.c relies on regexes working for the C locale without needing
catalog access, which worked before due to a special case for
C_COLLATION_OID in lc_ctype_is_c(). Move the special case to
pg_set_regex_collation() now that lc_ctype_is_c() is gone.

Author: Andreas Karlsson
Discussion: https://postgr.es/m/[email protected]

7 files changed, 39 insertions, 61 deletions

diff --git a/src/backend/regex/regc_pg_locale.c b/src/backend/regex/regc_pg_locale.c
index 35361c46a60..8f34948ad37 100644
--- a/src/backend/regex/regc_pg_locale.c
+++ b/src/backend/regex/regc_pg_locale.c
@@ -246,9 +246,13 @@ pg_set_regex_collation(Oid collation)
 				 errhint("Use the COLLATE clause to set the collation explicitly.")));
 	}
 
-	if (lc_ctype_is_c(collation))
+	if (collation == C_COLLATION_OID)
 	{
-		/* C/POSIX collations use this path regardless of database encoding */
+		/*
+		 * Some callers expect regexes to work for C_COLLATION_OID before
+		 * catalog access is available, so we can't call
+		 * pg_newlocale_from_collation().
+		 */
 		strategy = PG_REGEX_STRATEGY_C;
 		collation = C_COLLATION_OID;
 	}
@@ -261,7 +265,17 @@ pg_set_regex_collation(Oid collation)
 					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
 					 errmsg("nondeterministic collations are not supported for regular expressions")));
 
-		if (locale->provider == COLLPROVIDER_BUILTIN)
+		if (locale->ctype_is_c)
+		{
+			/*
+			 * C/POSIX collations use this path regardless of database
+			 * encoding
+			 */
+			strategy = PG_REGEX_STRATEGY_C;
+			locale = 0;
+			collation = C_COLLATION_OID;
+		}
+		else if (locale->provider == COLLPROVIDER_BUILTIN)
 		{
 			Assert(GetDatabaseEncoding() == PG_UTF8);
 			strategy = PG_REGEX_STRATEGY_BUILTIN;
@@ -274,6 +288,7 @@ pg_set_regex_collation(Oid collation)
 #endif
 		else
 		{
+			Assert(locale->provider == COLLPROVIDER_LIBC);
 			if (GetDatabaseEncoding() == PG_UTF8)
 				strategy = PG_REGEX_STRATEGY_LIBC_WIDE;
 			else
diff --git a/src/backend/utils/adt/formatting.c b/src/backend/utils/adt/formatting.c
index 33a810b008d..68fa89418ff 100644
--- a/src/backend/utils/adt/formatting.c
+++ b/src/backend/utils/adt/formatting.c
@@ -1636,6 +1636,7 @@ char *
 str_tolower(const char *buff, size_t nbytes, Oid collid)
 {
 	char	   *result;
+	pg_locale_t mylocale;
 
 	if (!buff)
 		return NULL;
@@ -1653,17 +1654,15 @@ str_tolower(const char *buff, size_t nbytes, Oid collid)
 				 errhint("Use the COLLATE clause to set the collation explicitly.")));
 	}
 
+	mylocale = pg_newlocale_from_collation(collid);
+
 	/* C/POSIX collations use this path regardless of database encoding */
-	if (lc_ctype_is_c(collid))
+	if (mylocale->ctype_is_c)
 	{
 		result = asc_tolower(buff, nbytes);
 	}
 	else
 	{
-		pg_locale_t mylocale;
-
-		mylocale = pg_newlocale_from_collation(collid);
-
 #ifdef USE_ICU
 		if (mylocale->provider == COLLPROVIDER_ICU)
 		{
@@ -1774,6 +1773,7 @@ char *
 str_toupper(const char *buff, size_t nbytes, Oid collid)
 {
 	char	   *result;
+	pg_locale_t mylocale;
 
 	if (!buff)
 		return NULL;
@@ -1791,17 +1791,15 @@ str_toupper(const char *buff, size_t nbytes, Oid collid)
 				 errhint("Use the COLLATE clause to set the collation explicitly.")));
 	}
 
+	mylocale = pg_newlocale_from_collation(collid);
+
 	/* C/POSIX collations use this path regardless of database encoding */
-	if (lc_ctype_is_c(collid))
+	if (mylocale->ctype_is_c)
 	{
 		result = asc_toupper(buff, nbytes);
 	}
 	else
 	{
-		pg_locale_t mylocale;
-
-		mylocale = pg_newlocale_from_collation(collid);
-
 #ifdef USE_ICU
 		if (mylocale->provider == COLLPROVIDER_ICU)
 		{
@@ -1954,6 +1952,7 @@ str_initcap(const char *buff, size_t nbytes, Oid collid)
 {
 	char	   *result;
 	int			wasalnum = false;
+	pg_locale_t mylocale;
 
 	if (!buff)
 		return NULL;
@@ -1971,17 +1970,15 @@ str_initcap(const char *buff, size_t nbytes, Oid collid)
 				 errhint("Use the COLLATE clause to set the collation explicitly.")));
 	}
 
+	mylocale = pg_newlocale_from_collation(collid);
+
 	/* C/POSIX collations use this path regardless of database encoding */
-	if (lc_ctype_is_c(collid))
+	if (mylocale->ctype_is_c)
 	{
 		result = asc_initcap(buff, nbytes);
 	}
 	else
 	{
-		pg_locale_t mylocale;
-
-		mylocale = pg_newlocale_from_collation(collid);
-
 #ifdef USE_ICU
 		if (mylocale->provider == COLLPROVIDER_ICU)
 		{
diff --git a/src/backend/utils/adt/like.c b/src/backend/utils/adt/like.c
index 131616fa6b8..f87675d7557 100644
--- a/src/backend/utils/adt/like.c
+++ b/src/backend/utils/adt/like.c
@@ -147,7 +147,7 @@ SB_lower_char(unsigned char c, pg_locale_t locale, bool locale_is_c)
 static inline int
 GenericMatchText(const char *s, int slen, const char *p, int plen, Oid collation)
 {
-	if (collation && !lc_ctype_is_c(collation))
+	if (collation)
 	{
 		pg_locale_t locale = pg_newlocale_from_collation(collation);
 
diff --git a/src/backend/utils/adt/like_support.c b/src/backend/utils/adt/like_support.c
index fb9291441d3..79c4ddc7573 100644
--- a/src/backend/utils/adt/like_support.c
+++ b/src/backend/utils/adt/like_support.c
@@ -100,7 +100,7 @@ static Selectivity regex_selectivity(const char *patt, int pattlen,
 									 bool case_insensitive,
 									 int fixed_prefix_len);
 static int	pattern_char_isalpha(char c, bool is_multibyte,
-								 pg_locale_t locale, bool locale_is_c);
+								 pg_locale_t locale);
 static Const *make_greater_string(const Const *str_const, FmgrInfo *ltproc,
 								  Oid collation);
 static Datum string_to_datum(const char *str, Oid datatype);
@@ -1000,7 +1000,6 @@ like_fixed_prefix(Const *patt_const, bool case_insensitive, Oid collation,
 				match_pos;
 	bool		is_multibyte = (pg_database_encoding_max_length() > 1);
 	pg_locale_t locale = 0;
-	bool		locale_is_c = false;
 
 	/* the right-hand const is type text or bytea */
 	Assert(typeid == BYTEAOID || typeid == TEXTOID);
@@ -1024,11 +1023,7 @@ like_fixed_prefix(Const *patt_const, bool case_insensitive, Oid collation,
 					 errhint("Use the COLLATE clause to set the collation explicitly.")));
 		}
 
-		/* If case-insensitive, we need locale info */
-		if (lc_ctype_is_c(collation))
-			locale_is_c = true;
-		else
-			locale = pg_newlocale_from_collation(collation);
+		locale = pg_newlocale_from_collation(collation);
 	}
 
 	if (typeid != BYTEAOID)
@@ -1065,7 +1060,7 @@ like_fixed_prefix(Const *patt_const, bool case_insensitive, Oid collation,
 
 		/* Stop if case-varying character (it's sort of a wildcard) */
 		if (case_insensitive &&
-			pattern_char_isalpha(patt[pos], is_multibyte, locale, locale_is_c))
+			pattern_char_isalpha(patt[pos], is_multibyte, locale))
 			break;
 
 		match[match_pos++] = patt[pos];
@@ -1499,16 +1494,16 @@ regex_selectivity(const char *patt, int pattlen, bool case_insensitive,
  */
 static int
 pattern_char_isalpha(char c, bool is_multibyte,
-					 pg_locale_t locale, bool locale_is_c)
+					 pg_locale_t locale)
 {
-	if (locale_is_c)
+	if (locale->ctype_is_c)
 		return (c >= 'A' && c <= 'Z') || (c >= 'a' && c <= 'z');
 	else if (is_multibyte && IS_HIGHBIT_SET(c))
 		return true;
-	else if (locale && locale->provider == COLLPROVIDER_ICU)
+	else if (locale->provider == COLLPROVIDER_ICU)
 		return IS_HIGHBIT_SET(c) ||
 			(c >= 'A' && c <= 'Z') || (c >= 'a' && c <= 'z');
-	else if (locale && locale->provider == COLLPROVIDER_LIBC)
+	else if (locale->provider == COLLPROVIDER_LIBC)
 		return isalpha_l((unsigned char) c, locale->info.lt);
 	else
 		return isalpha((unsigned char) c);
diff --git a/src/backend/utils/adt/pg_locale.c b/src/backend/utils/adt/pg_locale.c
index cb9f1b4f78e..a738da5674f 100644
--- a/src/backend/utils/adt/pg_locale.c
+++ b/src/backend/utils/adt/pg_locale.c
@@ -1266,32 +1266,6 @@ lookup_collation_cache(Oid collation)
 	return cache_entry;
 }
 
-/*
- * Detect whether collation's LC_CTYPE property is C
- */
-bool
-lc_ctype_is_c(Oid collation)
-{
-	/*
-	 * If we're asked about "collation 0", return false, so that the code will
-	 * go into the non-C path and report that the collation is bogus.
-	 */
-	if (!OidIsValid(collation))
-		return false;
-
-	/*
-	 * If we're asked about the built-in C/POSIX collations, we know that.
-	 */
-	if (collation == C_COLLATION_OID ||
-		collation == POSIX_COLLATION_OID)
-		return true;
-
-	/*
-	 * Otherwise, we have to consult pg_collation, but we cache that.
-	 */
-	return pg_newlocale_from_collation(collation)->ctype_is_c;
-}
-
 /* simple subroutine for reporting errors from newlocale() */
 static void
 report_newlocale_failure(const char *localename)
diff --git a/src/include/catalog/pg_collation.dat b/src/include/catalog/pg_collation.dat
index f1262012760..af5c9aa5824 100644
--- a/src/include/catalog/pg_collation.dat
+++ b/src/include/catalog/pg_collation.dat
@@ -19,8 +19,7 @@
   descr => 'standard C collation',
   collname => 'C', collprovider => 'c', collencoding => '-1',
   collcollate => 'C', collctype => 'C' },
-{ oid => '951', oid_symbol => 'POSIX_COLLATION_OID',
-  descr => 'standard POSIX collation',
+{ oid => '951', descr => 'standard POSIX collation',
   collname => 'POSIX', collprovider => 'c', collencoding => '-1',
   collcollate => 'POSIX', collctype => 'POSIX' },
 { oid => '962', descr => 'sorts by Unicode code point, C character semantics',
diff --git a/src/include/utils/pg_locale.h b/src/include/utils/pg_locale.h
index 8ec24437f4d..ab1c37a44b3 100644
--- a/src/include/utils/pg_locale.h
+++ b/src/include/utils/pg_locale.h
@@ -54,8 +54,6 @@ extern PGDLLIMPORT bool database_ctype_is_c;
 extern bool check_locale(int category, const char *locale, char **canonname);
 extern char *pg_perm_setlocale(int category, const char *locale);
 
-extern bool lc_ctype_is_c(Oid collation);
-
 /*
  * Return the POSIX lconv struct (contains number/money formatting
  * information) with locale information for all categories.