utf8.h: Add symbol for easing EBCDIC handling

This is then used in regcomp.c to avoid an #ifdef EBCDIC

2 files changed, 12 insertions, 5 deletions

diff --git a/regcomp.c b/regcomp.c
index b1148130d7..ced87a0416 100644
--- a/regcomp.c
+++ b/regcomp.c
@@ -19815,11 +19815,12 @@ S_optimize_regclass(pTHX_
          * invariant bytes, because they have the same bit patterns under UTF-8
          * as not. */
         PERL_UINT_FAST8_T inverted = 0;
-#ifdef EBCDIC
-        const PERL_UINT_FAST8_T max_permissible = 0xFF;
-#else
-        const PERL_UINT_FAST8_T max_permissible = 0x7F;
-#endif
+
+        /* Highest possible UTF-8 invariant is 7F on ASCII platforms; FF on
+         * EBCDIC */
+        const PERL_UINT_FAST8_T max_permissible
+                                    = nBIT_UMAX(7 + ONE_IF_EBCDIC_ZERO_IF_NOT);
+
         /* If doesn't fit the criteria for ANYOFM, invert and try again.  If
          * that works we will instead later generate an NANYOFM, and invert
          * back when through */
diff --git a/utf8.h b/utf8.h
index 4a4525ef11..1cb0b6855e 100644
--- a/utf8.h
+++ b/utf8.h
@@ -278,6 +278,12 @@ are in the character. */
 
 #endif /* EBCDIC vs ASCII */
 
+/* It turns out that in a number of cases, that handling ASCII vs EBCDIC is a
+ * matter of being off-by-one.  So this is a convenience macro, used to avoid
+ * some #ifdefs. */
+#define ONE_IF_EBCDIC_ZERO_IF_NOT                                           \
+ (UTF_CONTINUATION_BYTE_INFO_BITS == UTF_EBCDIC_CONTINUATION_BYTE_INFO_BITS)
+
 /* Since the significant bits in a continuation byte are stored in the
  * least-significant positions, we often find ourselves shifting by that
  * amount.  This is a clearer name in such situations */