Add pg_iswcased().

True if character has multiple case forms. Will be a useful
multibyte-aware replacement for char_is_cased().

Reviewed-by: Chao Li <li.evan.chao@gmail.com>
Reviewed-by: Peter Eisentraut <peter@eisentraut.org>
Discussion: https://postgr.es/m/450ceb6260cad30d7afdf155d991a9caafee7c0d.camel@j-davis.com

4 files changed, 42 insertions, 0 deletions

diff --git a/src/backend/utils/adt/pg_locale.c b/src/backend/utils/adt/pg_locale.c
index b00663b9585..70933ee3843 100644
--- a/src/backend/utils/adt/pg_locale.c
+++ b/src/backend/utils/adt/pg_locale.c
@@ -1588,6 +1588,17 @@ pg_iswxdigit(pg_wchar wc, pg_locale_t locale)
 		return locale->ctype->wc_isxdigit(wc, locale);
 }
 
+bool
+pg_iswcased(pg_wchar wc, pg_locale_t locale)
+{
+	/* for the C locale, Cased and Alpha are equivalent */
+	if (locale->ctype == NULL)
+		return (wc <= (pg_wchar) 127 &&
+				(pg_char_properties[wc] & PG_ISALPHA));
+	else
+		return locale->ctype->wc_iscased(wc, locale);
+}
+
 pg_wchar
 pg_towupper(pg_wchar wc, pg_locale_t locale)
 {
diff --git a/src/backend/utils/adt/pg_locale_builtin.c b/src/backend/utils/adt/pg_locale_builtin.c
index 1021e0d129b..0d4c754a267 100644
--- a/src/backend/utils/adt/pg_locale_builtin.c
+++ b/src/backend/utils/adt/pg_locale_builtin.c
@@ -186,6 +186,12 @@ wc_isxdigit_builtin(pg_wchar wc, pg_locale_t locale)
 }
 
 static bool
+wc_iscased_builtin(pg_wchar wc, pg_locale_t locale)
+{
+	return pg_u_prop_cased(to_char32(wc));
+}
+
+static bool
 char_is_cased_builtin(char ch, pg_locale_t locale)
 {
 	return IS_HIGHBIT_SET(ch) ||
@@ -220,6 +226,7 @@ static const struct ctype_methods ctype_methods_builtin = {
 	.wc_isspace = wc_isspace_builtin,
 	.wc_isxdigit = wc_isxdigit_builtin,
 	.char_is_cased = char_is_cased_builtin,
+	.wc_iscased = wc_iscased_builtin,
 	.wc_tolower = wc_tolower_builtin,
 	.wc_toupper = wc_toupper_builtin,
 };
diff --git a/src/backend/utils/adt/pg_locale_icu.c b/src/backend/utils/adt/pg_locale_icu.c
index f5a0cc8fe41..e8820666b2d 100644
--- a/src/backend/utils/adt/pg_locale_icu.c
+++ b/src/backend/utils/adt/pg_locale_icu.c
@@ -223,6 +223,12 @@ wc_isxdigit_icu(pg_wchar wc, pg_locale_t locale)
 	return u_isxdigit(wc);
 }
 
+static bool
+wc_iscased_icu(pg_wchar wc, pg_locale_t locale)
+{
+	return u_hasBinaryProperty(wc, UCHAR_CASED);
+}
+
 static const struct ctype_methods ctype_methods_icu = {
 	.strlower = strlower_icu,
 	.strtitle = strtitle_icu,
@@ -239,6 +245,7 @@ static const struct ctype_methods ctype_methods_icu = {
 	.wc_isspace = wc_isspace_icu,
 	.wc_isxdigit = wc_isxdigit_icu,
 	.char_is_cased = char_is_cased_icu,
+	.wc_iscased = wc_iscased_icu,
 	.wc_toupper = toupper_icu,
 	.wc_tolower = tolower_icu,
 };
diff --git a/src/backend/utils/adt/pg_locale_libc.c b/src/backend/utils/adt/pg_locale_libc.c
index fa871690e0c..3d841f818a5 100644
--- a/src/backend/utils/adt/pg_locale_libc.c
+++ b/src/backend/utils/adt/pg_locale_libc.c
@@ -185,6 +185,13 @@ wc_isxdigit_libc_sb(pg_wchar wc, pg_locale_t locale)
 }
 
 static bool
+wc_iscased_libc_sb(pg_wchar wc, pg_locale_t locale)
+{
+	return isupper_l((unsigned char) wc, locale->lt) ||
+		islower_l((unsigned char) wc, locale->lt);
+}
+
+static bool
 wc_isdigit_libc_mb(pg_wchar wc, pg_locale_t locale)
 {
 	return iswdigit_l((wint_t) wc, locale->lt);
@@ -249,6 +256,13 @@ wc_isxdigit_libc_mb(pg_wchar wc, pg_locale_t locale)
 }
 
 static bool
+wc_iscased_libc_mb(pg_wchar wc, pg_locale_t locale)
+{
+	return iswupper_l((wint_t) wc, locale->lt) ||
+		iswlower_l((wint_t) wc, locale->lt);
+}
+
+static bool
 char_is_cased_libc(char ch, pg_locale_t locale)
 {
 	bool		is_multibyte = pg_database_encoding_max_length() > 1;
@@ -332,6 +346,7 @@ static const struct ctype_methods ctype_methods_libc_sb = {
 	.wc_isspace = wc_isspace_libc_sb,
 	.wc_isxdigit = wc_isxdigit_libc_sb,
 	.char_is_cased = char_is_cased_libc,
+	.wc_iscased = wc_iscased_libc_sb,
 	.wc_toupper = toupper_libc_sb,
 	.wc_tolower = tolower_libc_sb,
 };
@@ -357,6 +372,7 @@ static const struct ctype_methods ctype_methods_libc_other_mb = {
 	.wc_isspace = wc_isspace_libc_sb,
 	.wc_isxdigit = wc_isxdigit_libc_sb,
 	.char_is_cased = char_is_cased_libc,
+	.wc_iscased = wc_iscased_libc_sb,
 	.wc_toupper = toupper_libc_sb,
 	.wc_tolower = tolower_libc_sb,
 };
@@ -378,6 +394,7 @@ static const struct ctype_methods ctype_methods_libc_utf8 = {
 	.wc_isspace = wc_isspace_libc_mb,
 	.wc_isxdigit = wc_isxdigit_libc_mb,
 	.char_is_cased = char_is_cased_libc,
+	.wc_iscased = wc_iscased_libc_mb,
 	.wc_toupper = toupper_libc_mb,
 	.wc_tolower = tolower_libc_mb,
 };