Inline utf8_distance(), utf8_hop()

1 files changed, 56 insertions, 0 deletions

diff --git a/inline.h b/inline.h
index 85727f491e..5336746078 100644
--- a/inline.h
+++ b/inline.h
@@ -387,6 +387,62 @@ S_is_utf8_invariant_string(const U8* const s, const STRLEN len)
     return TRUE;
 }
 
+/*
+=for apidoc utf8_distance
+
+Returns the number of UTF-8 characters between the UTF-8 pointers C<a>
+and C<b>.
+
+WARNING: use only if you *know* that the pointers point inside the
+same UTF-8 buffer.
+
+=cut
+*/
+
+PERL_STATIC_INLINE IV
+Perl_utf8_distance(pTHX_ const U8 *a, const U8 *b)
+{
+    PERL_ARGS_ASSERT_UTF8_DISTANCE;
+
+    return (a < b) ? -1 * (IV) utf8_length(a, b) : (IV) utf8_length(b, a);
+}
+
+/*
+=for apidoc utf8_hop
+
+Return the UTF-8 pointer C<s> displaced by C<off> characters, either
+forward or backward.
+
+WARNING: do not use the following unless you *know* C<off> is within
+the UTF-8 data pointed to by C<s> *and* that on entry C<s> is aligned
+on the first byte of character or just after the last byte of a character.
+
+=cut
+*/
+
+PERL_STATIC_INLINE U8 *
+Perl_utf8_hop(const U8 *s, SSize_t off)
+{
+    PERL_ARGS_ASSERT_UTF8_HOP;
+
+    /* Note: cannot use UTF8_IS_...() too eagerly here since e.g
+     * the bitops (especially ~) can create illegal UTF-8.
+     * In other words: in Perl UTF-8 is not just for Unicode. */
+
+    if (off >= 0) {
+	while (off--)
+	    s += UTF8SKIP(s);
+    }
+    else {
+	while (off++) {
+	    s--;
+	    while (UTF8_IS_CONTINUATION(*s))
+		s--;
+	}
+    }
+    return (U8 *)s;
+}
+
 /* ------------------------------- perl.h ----------------------------- */
 
 /*