Allow regexp-to-pvlv assignment

Since the xpvlv and regexp structs conflict, we have to find somewhere
else to put the regexp struct.

I was going to sneak it in SvPVX, allocating a buffer large
enough to fit the regexp struct followed by the string, and have
SvPVX - sizeof(regexp) point to the struct.  But that would make all
regexp flag-checking macros fatter, and those are used in hot code.

So I came up with another method.  Regexp stringification is not
speed-critical.  So we can move the regexp stringification out of
re->sv_u and put it in the regexp struct.  Then the regexp struct
itself can be pointed to by re->sv_u.  So SVt_REGEXPs will have
re->sv_any and re->sv_u pointing to the same spot.  PVLVs can then
have sv->sv_any point to the xpvlv body as usual, but have sv->sv_u
point to a regexp struct.  All regexp member access can go through
sv_u instead of sv_any, which will be no slower than before.

Regular expressions will no longer be SvPOK, so we give sv_2pv spec-
ial logic for regexps.  We don’t need to make the regexp struct
larger, as SvLEN is currently always 0 iff mother_re is set.  So we
can replace the SvLEN field with the pv.

SvFAKE is never used without SvPOK or SvSCREAM also set.  So we can
use that to identify regexps.

1 files changed, 15 insertions, 6 deletions

diff --git a/dump.c b/dump.c
index 72f7c4e469..4eadad08b2 100644
--- a/dump.c
+++ b/dump.c
@@ -1612,7 +1612,10 @@ Perl_do_sv_dump(pTHX_ I32 level, PerlIO *file, SV *sv, I32 nest, I32 maxnest, bo
     }
 
     if (type <= SVt_PVLV && !isGV_with_GP(sv)) {
-	if (SvPVX_const(sv)) {
+	const bool re = isREGEXP(sv);
+	const char * const ptr =
+	    re ? RX_WRAPPED((REGEXP*)sv) : SvPVX_const(sv);
+	if (ptr) {
 	    STRLEN delta;
 	    if (SvOOK(sv)) {
 		SvOOK_offset(sv, delta);
@@ -1621,18 +1624,22 @@ Perl_do_sv_dump(pTHX_ I32 level, PerlIO *file, SV *sv, I32 nest, I32 maxnest, bo
 	    } else {
 		delta = 0;
 	    }
-	    Perl_dump_indent(aTHX_ level, file,"  PV = 0x%"UVxf" ", PTR2UV(SvPVX_const(sv)));
+	    Perl_dump_indent(aTHX_ level, file,"  PV = 0x%"UVxf" ", PTR2UV(ptr));
 	    if (SvOOK(sv)) {
 		PerlIO_printf(file, "( %s . ) ",
-			      pv_display(d, SvPVX_const(sv) - delta, delta, 0,
+			      pv_display(d, ptr - delta, delta, 0,
 					 pvlim));
 	    }
-	    PerlIO_printf(file, "%s", pv_display(d, SvPVX_const(sv), SvCUR(sv), SvLEN(sv), pvlim));
+	    PerlIO_printf(file, "%s", pv_display(d, ptr, SvCUR(sv),
+						 re ? 0 : SvLEN(sv),
+						 pvlim));
 	    if (SvUTF8(sv)) /* the 6?  \x{....} */
 	        PerlIO_printf(file, " [UTF8 \"%s\"]", sv_uni_display(d, sv, 6 * SvCUR(sv), UNI_DISPLAY_QQ));
 	    PerlIO_printf(file, "\n");
 	    Perl_dump_indent(aTHX_ level, file, "  CUR = %"IVdf"\n", (IV)SvCUR(sv));
-	    Perl_dump_indent(aTHX_ level, file, "  LEN = %"IVdf"\n", (IV)SvLEN(sv));
+	    if (!re)
+		Perl_dump_indent(aTHX_ level, file, "  LEN = %"IVdf"\n",
+				       (IV)SvLEN(sv));
 	}
 	else
 	    Perl_dump_indent(aTHX_ level, file, "  PV = 0\n");
@@ -1958,6 +1965,7 @@ Perl_do_sv_dump(pTHX_ I32 level, PerlIO *file, SV *sv, I32 nest, I32 maxnest, bo
 		do_sv_dump(level+1, file, LvTARG(sv), nest+1, maxnest,
 		    dumpops, pvlim);
 	}
+	if (isREGEXP(sv)) goto dumpregexp;
 	if (!isGV_with_GP(sv))
 	    break;
 	Perl_dump_indent(aTHX_ level, file, "  NAME = \"%s\"\n", GvNAME(sv));
@@ -2026,8 +2034,9 @@ Perl_do_sv_dump(pTHX_ I32 level, PerlIO *file, SV *sv, I32 nest, I32 maxnest, bo
 	Perl_dump_indent(aTHX_ level, file, "  FLAGS = 0x%"UVxf"\n", (UV)IoFLAGS(sv));
 	break;
     case SVt_REGEXP:
+      dumpregexp:
 	{
-	    struct regexp * const r = (struct regexp *)SvANY(sv);
+	    struct regexp * const r = ReANY((REGEXP*)sv);
 	    flags = RX_EXTFLAGS((REGEXP*)sv);
 	    sv_setpv(d,"");
 	    append_flags(d, flags, regexp_flags_names);