More UTF-8 patches from Inaba Hiroto.

- The substr lval was still not okay.
- Now pp_stringify and sv_setsv copies source's UTF8 flag
  even if IN_BYTE.  pp_stringify is called from fold_constants
  at optimization phase and "\x{100}" was made SvUTF8_off under
  use bytes (the bytes pragma is for "byte semantics" and not
  for "do not produce UTF8 data")
- New `qu' operator to generate UTF8 string explicitly.
  Though I agree with the policy "0x00-0xff always produce bytes",
  sometimes want to such a string to be coded in UTF8.
  I can use pack"U0a*" but it requires more typing and has
  runtime overhead.
- Fix pp_regcomp bug uncovered by "0x00-0xff always produce bytes"
  change, the bug appears if a pm has PMdf_UTF8 flag but interpolated
  string is not UTF8_on and has char 0x80-0xff.

TODO: document and test qu.

p4raw-id: //depot/perl@8439

1 files changed, 7 insertions, 10 deletions

diff --git a/pp.c b/pp.c
index ba6c17a773..87e459e169 100644
--- a/pp.c
+++ b/pp.c
@@ -2792,6 +2792,8 @@ PP(pp_substr)
 	RETPUSHUNDEF;
     }
     else {
+	I32 upos = pos;
+	I32 urem = rem;
 	if (utfcurlen)
 	    sv_pos_u2b(sv, &pos, &rem);
 	tmps += pos;
@@ -2826,8 +2828,8 @@ PP(pp_substr)
 		    SvREFCNT_dec(LvTARG(TARG));
 		LvTARG(TARG) = SvREFCNT_inc(sv);
 	    }
-	    LvTARGOFF(TARG) = pos;
-	    LvTARGLEN(TARG) = rem;
+	    LvTARGOFF(TARG) = upos;
+	    LvTARGLEN(TARG) = urem;
 	}
     }
     SPAGAIN;
@@ -2970,11 +2972,9 @@ PP(pp_chr)
 
     (void)SvUPGRADE(TARG,SVt_PV);
 
-    if ((value > 255 && !IN_BYTE) ||
-	(UTF8_IS_CONTINUED(value) && (PL_hints & HINT_UTF8)) ) {
-	SvGROW(TARG, UTF8_MAXLEN+1);
-	tmps = SvPVX(TARG);
-	tmps = (char*)uv_to_utf8((U8*)tmps, (UV)value);
+    if (value > 255 && !IN_BYTE) {
+	SvGROW(TARG, UNISKIP(value)+1);
+	tmps = (char*)uv_to_utf8((U8*)SvPVX(TARG), value);
 	SvCUR_set(TARG, tmps - SvPVX(TARG));
 	*tmps = '\0';
 	(void)SvPOK_only(TARG);
@@ -2982,9 +2982,6 @@ PP(pp_chr)
 	XPUSHs(TARG);
 	RETURN;
     }
-    else {
-	SvUTF8_off(TARG);
-    }
 
     SvGROW(TARG,2);
     SvCUR_set(TARG, 1);