Refactor is_CNTRL_utf8(), is_utf8_cntrl()

All controls will always be in the Latin1 range by Unicode's stability
policy.  This means that we don't have to call is_utf8_cntrl() when the
input to the is_CNTRL_utf8() macro is above Latin1; we can just fail.
And that means that Perl_is_utf8_cntrl() can just use the macro.

diff --git a/handy.h b/handy.h
index 0f50d8b..613129e 100644 (file)
--- a/handy.h
+++ b/handy.h
@@ -1008,7 +1008,7 @@ EXTCONST U32 PL_charclass[];
 /* Because ASCII is invariant under utf8, the non-utf8 macro works */
 #define isASCII_utf8(p)         isASCII(*p)
 
-#define isCNTRL_utf8(p)         _generic_utf8(_CC_CNTRL, is_utf8_cntrl, p)
+#define isCNTRL_utf8(p)         _generic_utf8_utf8(_CC_CNTRL, p, 0)
 #define isGRAPH_utf8(p)         _generic_utf8(_CC_GRAPH, is_utf8_graph, p)
 #define isPRINT_utf8(p)         _generic_utf8(_CC_PRINT, is_utf8_print, p)
 #define isPUNCT_utf8(p)         _generic_utf8(_CC_PUNCT, is_utf8_punct, p)

diff --git a/utf8.c b/utf8.c
index 76d0331..cc38b0f 100644 (file)
--- a/utf8.c
+++ b/utf8.c
@@ -2147,15 +2147,7 @@ Perl_is_utf8_cntrl(pTHX_ const U8 *p)
 
     PERL_ARGS_ASSERT_IS_UTF8_CNTRL;
 
-    if (isASCII(*p)) {
-       return isCNTRL_A(*p);
-    }
-
-    /* All controls are in Latin1 */
-    if (! UTF8_IS_DOWNGRADEABLE_START(*p)) {
-       return 0;
-    }
-    return isCNTRL_L1(TWO_BYTE_UTF8_TO_UNI(*p, *(p+1)));
+    return isCNTRL_utf8(p);
 }
 
 bool