v2-0003-alternative-approach.patch

From 280929ad8f70106be7bc4d59d90957ecf86a421c Mon Sep 17 00:00:00 2001
From: Jeff Davis <jeff@j-davis.com>
Date: Tue, 15 Apr 2025 15:49:44 -0700
Subject: [PATCH v2 3/3] alternative approach

---
 src/backend/regex/regc_pg_locale.c | 60 +++++++++++++++++++++++++-----
 1 file changed, 50 insertions(+), 10 deletions(-)

diff --git a/src/backend/regex/regc_pg_locale.c b/src/backend/regex/regc_pg_locale.c
index 7377f459607..ec9bb8e460b 100644
--- a/src/backend/regex/regc_pg_locale.c
+++ b/src/backend/regex/regc_pg_locale.c
@@ -64,6 +64,8 @@ typedef enum
 {
 	PG_REGEX_STRATEGY_C,		/* C locale (encoding independent) */
 	PG_REGEX_STRATEGY_BUILTIN,	/* built-in Unicode semantics */
+	PG_REGEX_STRATEGY_DEF_WIDE,	/* libc default, locale_t <wctype.h> functions */
+	PG_REGEX_STRATEGY_DEF_1BYTE,	/* libc default, locale_t <ctype.h> functions */
 	PG_REGEX_STRATEGY_LIBC_WIDE,	/* Use locale_t <wctype.h> functions */
 	PG_REGEX_STRATEGY_LIBC_1BYTE,	/* Use locale_t <ctype.h> functions */
 	PG_REGEX_STRATEGY_ICU,		/* Use ICU uchar.h functions */
@@ -285,9 +287,19 @@ pg_set_regex_collation(Oid collation)
 		{
 			Assert(locale->provider == COLLPROVIDER_LIBC);
 			if (GetDatabaseEncoding() == PG_UTF8)
-				strategy = PG_REGEX_STRATEGY_LIBC_WIDE;
+			{
+				if (locale->is_default)
+					strategy = PG_REGEX_STRATEGY_DEF_WIDE;
+				else
+					strategy = PG_REGEX_STRATEGY_LIBC_WIDE;
+			}
 			else
-				strategy = PG_REGEX_STRATEGY_LIBC_1BYTE;
+			{
+				if (locale->is_default)
+					strategy = PG_REGEX_STRATEGY_DEF_1BYTE;
+				else
+					strategy = PG_REGEX_STRATEGY_LIBC_1BYTE;
+			}
 		}
 	}
 
@@ -305,10 +317,12 @@ pg_wc_isdigit(pg_wchar c)
 					(pg_char_properties[c] & PG_ISDIGIT));
 		case PG_REGEX_STRATEGY_BUILTIN:
 			return pg_u_isdigit(c, !pg_regex_locale->info.builtin.casemap_full);
+		case PG_REGEX_STRATEGY_DEF_WIDE:
 		case PG_REGEX_STRATEGY_LIBC_WIDE:
 			if (sizeof(wchar_t) >= 4 || c <= (pg_wchar) 0xFFFF)
 				return iswdigit_l((wint_t) c, pg_regex_locale->info.lt);
 			/* FALL THRU */
+		case PG_REGEX_STRATEGY_DEF_1BYTE:
 		case PG_REGEX_STRATEGY_LIBC_1BYTE:
 			return (c <= (pg_wchar) UCHAR_MAX &&
 					isdigit_l((unsigned char) c, pg_regex_locale->info.lt));
@@ -332,10 +346,12 @@ pg_wc_isalpha(pg_wchar c)
 					(pg_char_properties[c] & PG_ISALPHA));
 		case PG_REGEX_STRATEGY_BUILTIN:
 			return pg_u_isalpha(c);
+		case PG_REGEX_STRATEGY_DEF_WIDE:
 		case PG_REGEX_STRATEGY_LIBC_WIDE:
 			if (sizeof(wchar_t) >= 4 || c <= (pg_wchar) 0xFFFF)
 				return iswalpha_l((wint_t) c, pg_regex_locale->info.lt);
 			/* FALL THRU */
+		case PG_REGEX_STRATEGY_DEF_1BYTE:
 		case PG_REGEX_STRATEGY_LIBC_1BYTE:
 			return (c <= (pg_wchar) UCHAR_MAX &&
 					isalpha_l((unsigned char) c, pg_regex_locale->info.lt));
@@ -359,10 +375,12 @@ pg_wc_isalnum(pg_wchar c)
 					(pg_char_properties[c] & PG_ISALNUM));
 		case PG_REGEX_STRATEGY_BUILTIN:
 			return pg_u_isalnum(c, !pg_regex_locale->info.builtin.casemap_full);
+		case PG_REGEX_STRATEGY_DEF_WIDE:
 		case PG_REGEX_STRATEGY_LIBC_WIDE:
 			if (sizeof(wchar_t) >= 4 || c <= (pg_wchar) 0xFFFF)
 				return iswalnum_l((wint_t) c, pg_regex_locale->info.lt);
 			/* FALL THRU */
+		case PG_REGEX_STRATEGY_DEF_1BYTE:
 		case PG_REGEX_STRATEGY_LIBC_1BYTE:
 			return (c <= (pg_wchar) UCHAR_MAX &&
 					isalnum_l((unsigned char) c, pg_regex_locale->info.lt));
@@ -395,10 +413,12 @@ pg_wc_isupper(pg_wchar c)
 					(pg_char_properties[c] & PG_ISUPPER));
 		case PG_REGEX_STRATEGY_BUILTIN:
 			return pg_u_isupper(c);
+		case PG_REGEX_STRATEGY_DEF_WIDE:
 		case PG_REGEX_STRATEGY_LIBC_WIDE:
 			if (sizeof(wchar_t) >= 4 || c <= (pg_wchar) 0xFFFF)
 				return iswupper_l((wint_t) c, pg_regex_locale->info.lt);
 			/* FALL THRU */
+		case PG_REGEX_STRATEGY_DEF_1BYTE:
 		case PG_REGEX_STRATEGY_LIBC_1BYTE:
 			return (c <= (pg_wchar) UCHAR_MAX &&
 					isupper_l((unsigned char) c, pg_regex_locale->info.lt));
@@ -422,10 +442,12 @@ pg_wc_islower(pg_wchar c)
 					(pg_char_properties[c] & PG_ISLOWER));
 		case PG_REGEX_STRATEGY_BUILTIN:
 			return pg_u_islower(c);
+		case PG_REGEX_STRATEGY_DEF_WIDE:
 		case PG_REGEX_STRATEGY_LIBC_WIDE:
 			if (sizeof(wchar_t) >= 4 || c <= (pg_wchar) 0xFFFF)
 				return iswlower_l((wint_t) c, pg_regex_locale->info.lt);
 			/* FALL THRU */
+		case PG_REGEX_STRATEGY_DEF_1BYTE:
 		case PG_REGEX_STRATEGY_LIBC_1BYTE:
 			return (c <= (pg_wchar) UCHAR_MAX &&
 					islower_l((unsigned char) c, pg_regex_locale->info.lt));
@@ -449,10 +471,12 @@ pg_wc_isgraph(pg_wchar c)
 					(pg_char_properties[c] & PG_ISGRAPH));
 		case PG_REGEX_STRATEGY_BUILTIN:
 			return pg_u_isgraph(c);
+		case PG_REGEX_STRATEGY_DEF_WIDE:
 		case PG_REGEX_STRATEGY_LIBC_WIDE:
 			if (sizeof(wchar_t) >= 4 || c <= (pg_wchar) 0xFFFF)
 				return iswgraph_l((wint_t) c, pg_regex_locale->info.lt);
 			/* FALL THRU */
+		case PG_REGEX_STRATEGY_DEF_1BYTE:
 		case PG_REGEX_STRATEGY_LIBC_1BYTE:
 			return (c <= (pg_wchar) UCHAR_MAX &&
 					isgraph_l((unsigned char) c, pg_regex_locale->info.lt));
@@ -476,10 +500,12 @@ pg_wc_isprint(pg_wchar c)
 					(pg_char_properties[c] & PG_ISPRINT));
 		case PG_REGEX_STRATEGY_BUILTIN:
 			return pg_u_isprint(c);
+		case PG_REGEX_STRATEGY_DEF_WIDE:
 		case PG_REGEX_STRATEGY_LIBC_WIDE:
 			if (sizeof(wchar_t) >= 4 || c <= (pg_wchar) 0xFFFF)
 				return iswprint_l((wint_t) c, pg_regex_locale->info.lt);
 			/* FALL THRU */
+		case PG_REGEX_STRATEGY_DEF_1BYTE:
 		case PG_REGEX_STRATEGY_LIBC_1BYTE:
 			return (c <= (pg_wchar) UCHAR_MAX &&
 					isprint_l((unsigned char) c, pg_regex_locale->info.lt));
@@ -503,10 +529,12 @@ pg_wc_ispunct(pg_wchar c)
 					(pg_char_properties[c] & PG_ISPUNCT));
 		case PG_REGEX_STRATEGY_BUILTIN:
 			return pg_u_ispunct(c, !pg_regex_locale->info.builtin.casemap_full);
+		case PG_REGEX_STRATEGY_DEF_WIDE:
 		case PG_REGEX_STRATEGY_LIBC_WIDE:
 			if (sizeof(wchar_t) >= 4 || c <= (pg_wchar) 0xFFFF)
 				return iswpunct_l((wint_t) c, pg_regex_locale->info.lt);
 			/* FALL THRU */
+		case PG_REGEX_STRATEGY_DEF_1BYTE:
 		case PG_REGEX_STRATEGY_LIBC_1BYTE:
 			return (c <= (pg_wchar) UCHAR_MAX &&
 					ispunct_l((unsigned char) c, pg_regex_locale->info.lt));
@@ -530,10 +558,12 @@ pg_wc_isspace(pg_wchar c)
 					(pg_char_properties[c] & PG_ISSPACE));
 		case PG_REGEX_STRATEGY_BUILTIN:
 			return pg_u_isspace(c);
+		case PG_REGEX_STRATEGY_DEF_WIDE:
 		case PG_REGEX_STRATEGY_LIBC_WIDE:
 			if (sizeof(wchar_t) >= 4 || c <= (pg_wchar) 0xFFFF)
 				return iswspace_l((wint_t) c, pg_regex_locale->info.lt);
 			/* FALL THRU */
+		case PG_REGEX_STRATEGY_DEF_1BYTE:
 		case PG_REGEX_STRATEGY_LIBC_1BYTE:
 			return (c <= (pg_wchar) UCHAR_MAX &&
 					isspace_l((unsigned char) c, pg_regex_locale->info.lt));
@@ -558,17 +588,21 @@ pg_wc_toupper(pg_wchar c)
 			return c;
 		case PG_REGEX_STRATEGY_BUILTIN:
 			return unicode_uppercase_simple(c);
-		case PG_REGEX_STRATEGY_LIBC_WIDE:
+		case PG_REGEX_STRATEGY_DEF_WIDE:
 			/* force C behavior for ASCII characters, per comments above */
-			if (pg_regex_locale->is_default && c <= (pg_wchar) 127)
+			if (c <= (pg_wchar) 127)
 				return pg_ascii_toupper((unsigned char) c);
+			/* FALL THRU */
+		case PG_REGEX_STRATEGY_LIBC_WIDE:
 			if (sizeof(wchar_t) >= 4 || c <= (pg_wchar) 0xFFFF)
 				return towupper_l((wint_t) c, pg_regex_locale->info.lt);
 			/* FALL THRU */
-		case PG_REGEX_STRATEGY_LIBC_1BYTE:
+		case PG_REGEX_STRATEGY_DEF_1BYTE:
 			/* force C behavior for ASCII characters, per comments above */
-			if (pg_regex_locale->is_default && c <= (pg_wchar) 127)
+			if (c <= (pg_wchar) 127)
 				return pg_ascii_toupper((unsigned char) c);
+			/* FALL THRU */
+		case PG_REGEX_STRATEGY_LIBC_1BYTE:
 			if (c <= (pg_wchar) UCHAR_MAX)
 				return toupper_l((unsigned char) c, pg_regex_locale->info.lt);
 			return c;
@@ -592,17 +626,21 @@ pg_wc_tolower(pg_wchar c)
 			return c;
 		case PG_REGEX_STRATEGY_BUILTIN:
 			return unicode_lowercase_simple(c);
-		case PG_REGEX_STRATEGY_LIBC_WIDE:
+		case PG_REGEX_STRATEGY_DEF_WIDE:
 			/* force C behavior for ASCII characters, per comments above */
-			if (pg_regex_locale->is_default && c <= (pg_wchar) 127)
+			if (c <= (pg_wchar) 127)
 				return pg_ascii_tolower((unsigned char) c);
+			/* FALL THRU */
+		case PG_REGEX_STRATEGY_LIBC_WIDE:
 			if (sizeof(wchar_t) >= 4 || c <= (pg_wchar) 0xFFFF)
 				return towlower_l((wint_t) c, pg_regex_locale->info.lt);
 			/* FALL THRU */
-		case PG_REGEX_STRATEGY_LIBC_1BYTE:
+		case PG_REGEX_STRATEGY_DEF_1BYTE:
 			/* force C behavior for ASCII characters, per comments above */
-			if (pg_regex_locale->is_default && c <= (pg_wchar) 127)
+			if (c <= (pg_wchar) 127)
 				return pg_ascii_tolower((unsigned char) c);
+			/* FALL THRU */
+		case PG_REGEX_STRATEGY_LIBC_1BYTE:
 			if (c <= (pg_wchar) UCHAR_MAX)
 				return tolower_l((unsigned char) c, pg_regex_locale->info.lt);
 			return c;
@@ -751,9 +789,11 @@ pg_ctype_get_cache(pg_wc_probefunc probefunc, int cclasscode)
 		case PG_REGEX_STRATEGY_BUILTIN:
 			max_chr = (pg_wchar) MAX_SIMPLE_CHR;
 			break;
+		case PG_REGEX_STRATEGY_DEF_WIDE:
 		case PG_REGEX_STRATEGY_LIBC_WIDE:
 			max_chr = (pg_wchar) MAX_SIMPLE_CHR;
 			break;
+		case PG_REGEX_STRATEGY_DEF_1BYTE:
 		case PG_REGEX_STRATEGY_LIBC_1BYTE:
 #if MAX_SIMPLE_CHR >= UCHAR_MAX
 			max_chr = (pg_wchar) UCHAR_MAX;
-- 
2.34.1