v1-0001-Another-unintentional-behavior-change-in-commit-e.patch

From e8a68f42f5802d138ba04043b25b7d42862be29d Mon Sep 17 00:00:00 2001
From: Jeff Davis <jeff@j-davis.com>
Date: Mon, 14 Apr 2025 11:34:11 -0700
Subject: [PATCH v1] Another unintentional behavior change in commit
 e9931bfb75.

Reported-by: Noah Misch <noah@leadboat.com>
Discussion: https://postgr.es/m/20250412123430.8c.nmisch@google.com
---
 src/backend/regex/regc_pg_locale.c | 24 +++++++++++++++++++-----
 1 file changed, 19 insertions(+), 5 deletions(-)

diff --git a/src/backend/regex/regc_pg_locale.c b/src/backend/regex/regc_pg_locale.c
index ed7411df83d..41b993ad773 100644
--- a/src/backend/regex/regc_pg_locale.c
+++ b/src/backend/regex/regc_pg_locale.c
@@ -21,9 +21,10 @@
 #include "utils/pg_locale.h"
 
 /*
- * To provide as much functionality as possible on a variety of platforms,
- * without going so far as to implement everything from scratch, we use
- * several implementation strategies depending on the situation:
+ * For the libc provider, to provide as much functionality as possible on a
+ * variety of platforms without going so far as to implement everything from
+ * scratch, we use several implementation strategies depending on the
+ * situation:
  *
  * 1. In C/POSIX collations, we use hard-wired code.  We can't depend on
  * the <ctype.h> functions since those will obey LC_CTYPE.  Note that these
@@ -33,8 +34,9 @@
  *
  * 2a. When working in UTF8 encoding, we use the <wctype.h> functions.
  * This assumes that every platform uses Unicode codepoints directly
- * as the wchar_t representation of Unicode.  On some platforms
- * wchar_t is only 16 bits wide, so we have to punt for codepoints > 0xFFFF.
+ * as the wchar_t representation of Unicode.  (XXX: This could be a problem
+ * for ICU in non-UTF8 encodings.)  On some platforms wchar_t is only 16 bits
+ * wide, so we have to punt for codepoints > 0xFFFF.
  *
  * 2b. In all other encodings, we use the <ctype.h> functions for pg_wchar
  * values up to 255, and punt for values above that.  This is 100% correct
@@ -562,10 +564,16 @@ pg_wc_toupper(pg_wchar c)
 		case PG_REGEX_STRATEGY_BUILTIN:
 			return unicode_uppercase_simple(c);
 		case PG_REGEX_STRATEGY_LIBC_WIDE:
+			/* force C behavior for ASCII characters, per comments above */
+			if (pg_regex_locale->is_default && c <= (pg_wchar) 127)
+				return pg_ascii_toupper((unsigned char) c);
 			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:
+			/* force C behavior for ASCII characters, per comments above */
+			if (pg_regex_locale->is_default && c <= (pg_wchar) 127)
+				return pg_ascii_toupper((unsigned char) c);
 			if (c <= (pg_wchar) UCHAR_MAX)
 				return toupper_l((unsigned char) c, pg_regex_locale->info.lt);
 			return c;
@@ -590,10 +598,16 @@ pg_wc_tolower(pg_wchar c)
 		case PG_REGEX_STRATEGY_BUILTIN:
 			return unicode_lowercase_simple(c);
 		case PG_REGEX_STRATEGY_LIBC_WIDE:
+			/* force C behavior for ASCII characters, per comments above */
+			if (pg_regex_locale->is_default && c <= (pg_wchar) 127)
+				return pg_ascii_tolower((unsigned char) c);
 			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:
+			/* force C behavior for ASCII characters, per comments above */
+			if (pg_regex_locale->is_default && c <= (pg_wchar) 127)
+				return pg_ascii_tolower((unsigned char) c);
 			if (c <= (pg_wchar) UCHAR_MAX)
 				return tolower_l((unsigned char) c, pg_regex_locale->info.lt);
 			return c;
-- 
2.34.1