Introduce t_isalnum() to replace t_isalpha() || t_isdigit() tests.

tglsfdc · tglsfdc · commit ca71131eebba · 2022-10-06T11:08:56.000-04:00
ts_locale.c omitted support for "isalnum" tests, perhaps on the grounds that there were initially no use-cases for that. However, both ltree and pg_trgm need such tests, and we do also have one use-case now in the core backend. The workaround of testing isalpha and isdigit separately seems quite inefficient, especially when dealing with multibyte characters; so let's fill in the missing support. Discussion: https://postgr.es/m/2548310.1664999615@sss.pgh.pa.us
diff --git a/contrib/ltree/ltree.h b/contrib/ltree/ltree.h
@@ -126,7 +126,7 @@ typedef struct
 
 #define LQUERY_HASNOT		0x01
 
-#define ISALNUM(x)	( t_isalpha(x) || t_isdigit(x)	|| ( pg_mblen(x) == 1 && t_iseq((x), '_') ) )
+#define ISALNUM(x)	( t_isalnum(x) || ( pg_mblen(x) == 1 && t_iseq((x), '_') ) )
 
 /* full text query */
 
diff --git a/contrib/pg_trgm/trgm.h b/contrib/pg_trgm/trgm.h
@@ -52,7 +52,7 @@ typedef char trgm[3];
 } while(0)
 
 #ifdef KEEPONLYALNUM
-#define ISWORDCHR(c)	(t_isalpha(c) || t_isdigit(c))
+#define ISWORDCHR(c)	(t_isalnum(c))
 #define ISPRINTABLECHAR(a)	( isascii( *(unsigned char*)(a) ) && (isalnum( *(unsigned char*)(a) ) || *(unsigned char*)(a)==' ') )
 #else
 #define ISWORDCHR(c)	(!t_isspace(c))
diff --git a/src/backend/tsearch/ts_locale.c b/src/backend/tsearch/ts_locale.c
@@ -81,6 +81,22 @@ t_isalpha(const char *ptr)
 	return iswalpha((wint_t) character[0]);
 }
 
+int
+t_isalnum(const char *ptr)
+{
+	int			clen = pg_mblen(ptr);
+	wchar_t		character[WC_BUF_LEN];
+	Oid			collation = DEFAULT_COLLATION_OID;	/* TODO */
+	pg_locale_t mylocale = 0;	/* TODO */
+
+	if (clen == 1 || lc_ctype_is_c(collation))
+		return isalnum(TOUCHAR(ptr));
+
+	char2wchar(character, WC_BUF_LEN, ptr, clen, mylocale);
+
+	return iswalnum((wint_t) character[0]);
+}
+
 int
 t_isprint(const char *ptr)
 {
diff --git a/src/backend/utils/adt/tsquery.c b/src/backend/utils/adt/tsquery.c
@@ -248,7 +248,7 @@ parse_or_operator(TSQueryParserState pstate)
 		return false;
 
 	/* it shouldn't be a part of any word */
-	if (t_iseq(ptr, '-') || t_iseq(ptr, '_') || t_isalpha(ptr) || t_isdigit(ptr))
+	if (t_iseq(ptr, '-') || t_iseq(ptr, '_') || t_isalnum(ptr))
 		return false;
 
 	for (;;)
diff --git a/src/include/tsearch/ts_locale.h b/src/include/tsearch/ts_locale.h
@@ -42,6 +42,7 @@ typedef struct
 extern int	t_isdigit(const char *ptr);
 extern int	t_isspace(const char *ptr);
 extern int	t_isalpha(const char *ptr);
+extern int	t_isalnum(const char *ptr);
 extern int	t_isprint(const char *ptr);
 
 extern char *lowerstr(const char *str);
