sv.h: Document SVt_INVLIST fields

[perl5.git] / regcomp.c

diff --git a/regcomp.c b/regcomp.c
index c673274..3d4d348 100644 (file)
--- a/regcomp.c
+++ b/regcomp.c
@@ -5750,7 +5750,7 @@ S_concat_pat(pTHX_ RExC_state_t * const pRExC_state,
             if (oplist) {
                 assert(oplist->op_type == OP_PADAV
                     || oplist->op_type == OP_RV2AV);
-                oplist = oplist->op_sibling;;
+                oplist = OP_SIBLING(oplist);
             }
 
             if (SvRMAGICAL(av)) {
@@ -5797,10 +5797,10 @@ S_concat_pat(pTHX_ RExC_state_t * const pRExC_state,
                 pRExC_state->code_blocks[n].src_regex = NULL;
                 n++;
                 code = 1;
-                oplist = oplist->op_sibling; /* skip CONST */
+                oplist = OP_SIBLING(oplist); /* skip CONST */
                 assert(oplist);
             }
-            oplist = oplist->op_sibling;;
+            oplist = OP_SIBLING(oplist);;
         }
 
        /* apply magic and QR overloading to arg */
@@ -6298,7 +6298,7 @@ Perl_re_op_compile(pTHX_ SV ** const patternp, int pat_count,
        OP *o;
        int ncode = 0;
 
-       for (o = cLISTOPx(expr)->op_first; o; o = o->op_sibling)
+       for (o = cLISTOPx(expr)->op_first; o; o = OP_SIBLING(o))
            if (o->op_type == OP_NULL && (o->op_flags & OPf_SPECIAL))
                ncode++; /* count of DO blocks */
        if (ncode) {
@@ -6319,7 +6319,7 @@ Perl_re_op_compile(pTHX_ SV ** const patternp, int pat_count,
         if (expr->op_type == OP_CONST)
             n = 1;
         else
-            for (o = cLISTOPx(expr)->op_first; o; o = o->op_sibling) {
+            for (o = cLISTOPx(expr)->op_first; o; o = OP_SIBLING(o)) {
                 if (o->op_type == OP_CONST)
                     n++;
             }
@@ -6335,7 +6335,7 @@ Perl_re_op_compile(pTHX_ SV ** const patternp, int pat_count,
         if (expr->op_type == OP_CONST)
             new_patternp[n] = cSVOPx_sv(expr);
         else
-            for (o = cLISTOPx(expr)->op_first; o; o = o->op_sibling) {
+            for (o = cLISTOPx(expr)->op_first; o; o = OP_SIBLING(o)) {
                 if (o->op_type == OP_CONST)
                     new_patternp[n++] = cSVOPo_sv;
             }
@@ -6355,7 +6355,7 @@ Perl_re_op_compile(pTHX_ SV ** const patternp, int pat_count,
             assert(   expr->op_type == OP_PUSHMARK
                    || (expr->op_type == OP_NULL && expr->op_targ == OP_PUSHMARK)
                    || expr->op_type == OP_PADRANGE);
-            expr = expr->op_sibling;
+            expr = OP_SIBLING(expr);
     }
 
     pat = S_concat_pat(aTHX_ pRExC_state, NULL, new_patternp, pat_count,
@@ -13197,9 +13197,10 @@ S_add_above_Latin1_folds(pTHX_ RExC_state_t *pRExC_state, const U8 cp, SV** invl
      * disk to find the possible matches.
      *
      * This should be called only for a Latin1-range code points, cp, which is
-     * known to be involved in a fold with other code points above Latin1.  It
-     * would give false results if /aa has been specified.  Multi-char folds
-     * are outside the scope of this, and must be handled specially.
+     * known to be involved in a simple fold with other code points above
+     * Latin1.  It would give false results if /aa has been specified.
+     * Multi-char folds are outside the scope of this, and must be handled
+     * specially.
      *
      * XXX It would be better to generate these via regen, in case a new
      * version of the Unicode standard adds new mappings, though that is not
@@ -13208,6 +13209,8 @@ S_add_above_Latin1_folds(pTHX_ RExC_state_t *pRExC_state, const U8 cp, SV** invl
 
     PERL_ARGS_ASSERT_ADD_ABOVE_LATIN1_FOLDS;
 
+    assert(HAS_NONLATIN1_SIMPLE_FOLD_CLOSURE(cp));
+
     switch (cp) {
         case 'k':
         case 'K':
@@ -13233,22 +13236,6 @@ S_add_above_Latin1_folds(pTHX_ RExC_state_t *pRExC_state, const U8 cp, SV** invl
         case LATIN_SMALL_LETTER_SHARP_S:
           *invlist = add_cp_to_invlist(*invlist, LATIN_CAPITAL_LETTER_SHARP_S);
             break;
-        case 'F': case 'f':
-        case 'I': case 'i':
-        case 'L': case 'l':
-        case 'T': case 't':
-        case 'A': case 'a':
-        case 'H': case 'h':
-        case 'J': case 'j':
-        case 'N': case 'n':
-        case 'W': case 'w':
-        case 'Y': case 'y':
-            /* These all are targets of multi-character folds from code points
-             * that require UTF8 to express, so they can't match unless the
-             * target string is in UTF-8, so no action here is necessary, as
-             * regexec.c properly handles the general case for UTF-8 matching
-             * and multi-char folds */
-            break;
         default:
             /* Use deprecated warning to increase the chances of this being
              * output */