From af164f31b9f5f00561d5831a72ab91cfe091f92e Mon Sep 17 00:00:00 2001
From: Jeff Davis <jdavis@postgresql.org>
Date: Wed, 15 Oct 2025 12:54:01 -0700
Subject: Add pg_iswalpha() and related functions.

Per-character pg_locale_t APIs. Useful for tsearch parsing and
potentially other places.

Significant overlap with the regc_wc_isalpha() and related functions
in regc_pg_locale.c, but this change leaves those intact for
now.

Discussion: https://postgr.es/m/0151ad01239e2cc7b3139644358cf8f7b9622ff7.camel@j-davis.com
---
 src/backend/utils/adt/pg_locale.c | 124 ++++++++++++++++++++++++++++++++++++++
 1 file changed, 124 insertions(+)

(limited to 'src/backend/utils/adt')

diff --git a/src/backend/utils/adt/pg_locale.c b/src/backend/utils/adt/pg_locale.c
index 97c2ac1faf9..50b25445f7a 100644
--- a/src/backend/utils/adt/pg_locale.c
+++ b/src/backend/utils/adt/pg_locale.c
@@ -45,6 +45,7 @@
 #include "utils/lsyscache.h"
 #include "utils/memutils.h"
 #include "utils/pg_locale.h"
+#include "utils/pg_locale_c.h"
 #include "utils/relcache.h"
 #include "utils/syscache.h"
 
@@ -1149,6 +1150,13 @@ init_database_collation(void)
 		PGLOCALE_SUPPORT_ERROR(dbform->datlocprovider);
 
 	result->is_default = true;
+
+	Assert((result->collate_is_c && result->collate == NULL) ||
+		   (!result->collate_is_c && result->collate != NULL));
+
+	Assert((result->ctype_is_c && result->ctype == NULL) ||
+		   (!result->ctype_is_c && result->ctype != NULL));
+
 	ReleaseSysCache(tup);
 
 	default_locale = result;
@@ -1395,6 +1403,122 @@ pg_strnxfrm_prefix(char *dest, size_t destsize, const char *src,
 	return locale->collate->strnxfrm_prefix(dest, destsize, src, srclen, locale);
 }
 
+bool
+pg_iswdigit(pg_wchar wc, pg_locale_t locale)
+{
+	if (locale->ctype == NULL)
+		return (wc <= (pg_wchar) 127 &&
+				(pg_char_properties[wc] & PG_ISDIGIT));
+	else
+		return locale->ctype->wc_isdigit(wc, locale);
+}
+
+bool
+pg_iswalpha(pg_wchar wc, pg_locale_t locale)
+{
+	if (locale->ctype == NULL)
+		return (wc <= (pg_wchar) 127 &&
+				(pg_char_properties[wc] & PG_ISALPHA));
+	else
+		return locale->ctype->wc_isalpha(wc, locale);
+}
+
+bool
+pg_iswalnum(pg_wchar wc, pg_locale_t locale)
+{
+	if (locale->ctype == NULL)
+		return (wc <= (pg_wchar) 127 &&
+				(pg_char_properties[wc] & PG_ISALNUM));
+	else
+		return locale->ctype->wc_isalnum(wc, locale);
+}
+
+bool
+pg_iswupper(pg_wchar wc, pg_locale_t locale)
+{
+	if (locale->ctype == NULL)
+		return (wc <= (pg_wchar) 127 &&
+				(pg_char_properties[wc] & PG_ISUPPER));
+	else
+		return locale->ctype->wc_isupper(wc, locale);
+}
+
+bool
+pg_iswlower(pg_wchar wc, pg_locale_t locale)
+{
+	if (locale->ctype == NULL)
+		return (wc <= (pg_wchar) 127 &&
+				(pg_char_properties[wc] & PG_ISLOWER));
+	else
+		return locale->ctype->wc_islower(wc, locale);
+}
+
+bool
+pg_iswgraph(pg_wchar wc, pg_locale_t locale)
+{
+	if (locale->ctype == NULL)
+		return (wc <= (pg_wchar) 127 &&
+				(pg_char_properties[wc] & PG_ISGRAPH));
+	else
+		return locale->ctype->wc_isgraph(wc, locale);
+}
+
+bool
+pg_iswprint(pg_wchar wc, pg_locale_t locale)
+{
+	if (locale->ctype == NULL)
+		return (wc <= (pg_wchar) 127 &&
+				(pg_char_properties[wc] & PG_ISPRINT));
+	else
+		return locale->ctype->wc_isprint(wc, locale);
+}
+
+bool
+pg_iswpunct(pg_wchar wc, pg_locale_t locale)
+{
+	if (locale->ctype == NULL)
+		return (wc <= (pg_wchar) 127 &&
+				(pg_char_properties[wc] & PG_ISPUNCT));
+	else
+		return locale->ctype->wc_ispunct(wc, locale);
+}
+
+bool
+pg_iswspace(pg_wchar wc, pg_locale_t locale)
+{
+	if (locale->ctype == NULL)
+		return (wc <= (pg_wchar) 127 &&
+				(pg_char_properties[wc] & PG_ISSPACE));
+	else
+		return locale->ctype->wc_isspace(wc, locale);
+}
+
+pg_wchar
+pg_towupper(pg_wchar wc, pg_locale_t locale)
+{
+	if (locale->ctype == NULL)
+	{
+		if (wc <= (pg_wchar) 127)
+			return pg_ascii_toupper((unsigned char) wc);
+		return wc;
+	}
+	else
+		return locale->ctype->wc_toupper(wc, locale);
+}
+
+pg_wchar
+pg_towlower(pg_wchar wc, pg_locale_t locale)
+{
+	if (locale->ctype == NULL)
+	{
+		if (wc <= (pg_wchar) 127)
+			return pg_ascii_tolower((unsigned char) wc);
+		return wc;
+	}
+	else
+		return locale->ctype->wc_tolower(wc, locale);
+}
+
 /*
  * char_is_cased()
  *
-- 
cgit v1.2.3