handy.h: isIDFIRST_utf8() changed to use XIDStart

Previously this used a home-grown definition of an identifier start,
stemming from a bug in some early Unicode versions.  This led to some
problems, fixed by #74022.

But the home-grown solution did not track Unicode, and allowed for
characters, like marks, to begin words when they shouldn't.  This change
brings this macro into compliance with Unicode going-forward.

1 files changed, 25 insertions, 0 deletions

diff --git a/utf8.c b/utf8.c
index b5d853188b..808d9a80a7 100644
--- a/utf8.c
+++ b/utf8.c
@@ -1501,6 +1501,19 @@ Perl_is_utf8_idfirst(pTHX_ const U8 *p) /* The naming is historical. */
 }
 
 bool
+Perl_is_utf8_xidfirst(pTHX_ const U8 *p) /* The naming is historical. */
+{
+    dVAR;
+
+    PERL_ARGS_ASSERT_IS_UTF8_XIDFIRST;
+
+    if (*p == '_')
+	return TRUE;
+    /* is_utf8_idstart would be more logical. */
+    return is_utf8_common(p, &PL_utf8_xidstart, "XIdStart");
+}
+
+bool
 Perl_is_utf8_idcont(pTHX_ const U8 *p)
 {
     dVAR;
@@ -1513,6 +1526,18 @@ Perl_is_utf8_idcont(pTHX_ const U8 *p)
 }
 
 bool
+Perl_is_utf8_xidcont(pTHX_ const U8 *p)
+{
+    dVAR;
+
+    PERL_ARGS_ASSERT_IS_UTF8_XIDCONT;
+
+    if (*p == '_')
+	return TRUE;
+    return is_utf8_common(p, &PL_utf8_idcont, "XIdContinue");
+}
+
+bool
 Perl_is_utf8_alpha(pTHX_ const U8 *p)
 {
     dVAR;