Create internal _is_utf8_mark()

This is so we can deprecate non-core use of the existing one in a future
commit.  XS coders should be using the macros in handy.h instead of
calling such functions directly.  A future commit will deprecate all of
them, but first the core uses of this one must change so they don't
generate deprecation messages.  I will not have a chance to look for
some time, but I suspect that most uses of this function in the core
should be changed to use something else, but in the meantime, the
non-core uses can be deprecated.

diff --git a/embed.fnc b/embed.fnc
index 170d15962f93b5825fa8ff636d1c42dc39bca4d0..0ec56cd38b3fa81c5d7b480dcc312c1661fd33a3 100644 (file)
--- a/embed.fnc
+++ b/embed.fnc
@@ -681,6 +681,7 @@ AMpR        |bool   |is_utf8_print  |NN const U8 *p
 AMpR   |bool   |is_utf8_punct  |NN const U8 *p
 ADMpR  |bool   |is_utf8_xdigit |NN const U8 *p
 AMpR   |bool   |is_utf8_mark   |NN const U8 *p
+AMpR   |bool   |_is_utf8_mark  |NN const U8 *p
 : Used in perly.y
 p      |OP*    |jmaybe         |NN OP *o
 : Used in pp.c 

diff --git a/embed.h b/embed.h
index 6c0eaa70c60c29696de71ecf7b4883f7eacd4aa4..89dca3c19d2a226f5b877956ced4b9086e14221b 100644 (file)
--- a/embed.h
+++ b/embed.h
@@ -30,6 +30,7 @@
 #define _is_uni_FOO(a,b)       Perl__is_uni_FOO(aTHX_ a,b)
 #define _is_uni_perl_idstart(a)        Perl__is_uni_perl_idstart(aTHX_ a)
 #define _is_utf8_FOO(a,b)      Perl__is_utf8_FOO(aTHX_ a,b)
+#define _is_utf8_mark(a)       Perl__is_utf8_mark(aTHX_ a)
 #define _is_utf8_perl_idstart(a)       Perl__is_utf8_perl_idstart(aTHX_ a)
 #define _to_uni_fold_flags(a,b,c,d)    Perl__to_uni_fold_flags(aTHX_ a,b,c,d)
 #define _to_utf8_fold_flags(a,b,c,d,e) Perl__to_utf8_fold_flags(aTHX_ a,b,c,d,e)

diff --git a/pp.c b/pp.c
index 33943e44c761af1925f8933631290756090fd88a..4a55e02195c2c1ab9a080fdc660ee3518a87a4a6 100644 (file)
--- a/pp.c
+++ b/pp.c
@@ -3757,7 +3757,7 @@ PP(pp_uc)
            STRLEN u;
            STRLEN ulen;
            UV uv;
-           if (in_iota_subscript && ! is_utf8_mark(s)) {
+           if (in_iota_subscript && ! _is_utf8_mark(s)) {
 
                /* A non-mark.  Time to output the iota subscript */
 #define GREEK_CAPITAL_LETTER_IOTA 0x0399

diff --git a/proto.h b/proto.h
index ae3e254ca437bbaf9e424fe035f4ebd3270887af..e07eacd2ae590c048b4a0addc68a4fef08b46ef2 100644 (file)
--- a/proto.h
+++ b/proto.h
@@ -44,6 +44,12 @@ PERL_CALLCONV bool   Perl__is_utf8_FOO(pTHX_ const U8 classnum, const U8 *p)
 #define PERL_ARGS_ASSERT__IS_UTF8_FOO  \
        assert(p)
 
+PERL_CALLCONV bool     Perl__is_utf8_mark(pTHX_ const U8 *p)
+                       __attribute__warn_unused_result__
+                       __attribute__nonnull__(pTHX_1);
+#define PERL_ARGS_ASSERT__IS_UTF8_MARK \
+       assert(p)
+
 PERL_CALLCONV bool     Perl__is_utf8_perl_idstart(pTHX_ const U8 *p)
                        __attribute__warn_unused_result__
                        __attribute__nonnull__(pTHX_1);

diff --git a/toke.c b/toke.c
index d9d6f93875ebb38a54bc5f6c9fff52f0cf3bb959..4f671cccc8a390766b7a25ff362f40d9baa9e9cb 100644 (file)
--- a/toke.c
+++ b/toke.c
@@ -8076,7 +8076,7 @@ Perl_yylex(pTHX)
                for (d = s; isALNUM_lazy_if(d,UTF);) {
                    d += UTF ? UTF8SKIP(d) : 1;
                     if (UTF) {
-                        while (UTF8_IS_CONTINUED(*d) && is_utf8_mark((U8*)d)) {
+                        while (UTF8_IS_CONTINUED(*d) && _is_utf8_mark((U8*)d)) {
                             d += UTF ? UTF8SKIP(d) : 1;
                         }
                     }
@@ -9187,7 +9187,7 @@ S_scan_word(pTHX_ char *s, char *dest, STRLEN destlen, int allow_package, STRLEN
        else if (UTF && UTF8_IS_START(*s) && isALNUM_utf8((U8*)s)) {
            char *t = s + UTF8SKIP(s);
            size_t len;
-           while (UTF8_IS_CONTINUED(*t) && is_utf8_mark((U8*)t))
+           while (UTF8_IS_CONTINUED(*t) && _is_utf8_mark((U8*)t))
                t += UTF8SKIP(t);
            len = t - s;
            if (d + len > e)
@@ -9241,7 +9241,7 @@ S_scan_ident(pTHX_ char *s, const char *send, char *dest, STRLEN destlen, I32 ck
            }
            else if (UTF && UTF8_IS_START(*s) && isALNUM_utf8((U8*)s)) {
                char *t = s + UTF8SKIP(s);
-               while (UTF8_IS_CONTINUED(*t) && is_utf8_mark((U8*)t))
+               while (UTF8_IS_CONTINUED(*t) && _is_utf8_mark((U8*)t))
                    t += UTF8SKIP(t);
                if (d + (t - s) > e)
                    Perl_croak(aTHX_ ident_too_long);
@@ -9304,7 +9304,7 @@ S_scan_ident(pTHX_ char *s, const char *send, char *dest, STRLEN destlen, I32 ck
                char *end = s;
                while ((end < send && isALNUM_lazy_if(end,UTF)) || *end == ':') {
                    end += UTF8SKIP(end);
-                   while (end < send && UTF8_IS_CONTINUED(*end) && is_utf8_mark((U8*)end))
+                   while (end < send && UTF8_IS_CONTINUED(*end) && _is_utf8_mark((U8*)end))
                        end += UTF8SKIP(end);
                }
                Copy(s, d, end - s, char);

diff --git a/utf8.c b/utf8.c
index b6ca4876d839fb011daddb064ebc6c9e962a0dde..930b14841924d424738f355293fd815b353a6777 100644 (file)
--- a/utf8.c
+++ b/utf8.c
@@ -2287,6 +2287,17 @@ Perl_is_utf8_xdigit(pTHX_ const U8 *p)
     return is_XDIGIT_utf8(p);
 }
 
+bool
+Perl__is_utf8_mark(pTHX_ const U8 *p)
+{
+    dVAR;
+
+    PERL_ARGS_ASSERT__IS_UTF8_MARK;
+
+    return is_utf8_common(p, &PL_utf8_mark, "IsM");
+}
+
+
 bool
 Perl_is_utf8_mark(pTHX_ const U8 *p)
 {
@@ -2294,7 +2305,7 @@ Perl_is_utf8_mark(pTHX_ const U8 *p)
 
     PERL_ARGS_ASSERT_IS_UTF8_MARK;
 
-    return is_utf8_common(p, &PL_utf8_mark, "IsM");
+    return _is_utf8_mark(p);
 }
 
 /*