Carthago delenda est

[perl5.git] / regexec.c

diff --git a/regexec.c b/regexec.c
index 73178b3..05675ad 100644 (file)
--- a/regexec.c
+++ b/regexec.c
@@ -126,13 +126,16 @@ static const char* const non_utf8_target_but_utf8_required
                     (U8*)(off >= 0 ? reginfo->strend : reginfo->strbeg)) \
            : (U8*)(pos + off))
 
-#define HOPBACKc(pos, off) \
-       (char*)(reginfo->is_utf8_target \
-           ? reghopmaybe3((U8*)pos, (SSize_t)0-off, (U8*)(reginfo->strbeg)) \
-           : (pos - off >= reginfo->strbeg)    \
-               ? (U8*)pos - off                \
+/* like HOPMAYBE3 but backwards. lim must be +ve. Returns NULL on overshoot */
+#define HOPBACK3(pos, off, lim) \
+       (reginfo->is_utf8_target                          \
+           ? reghopmaybe3((U8*)pos, (SSize_t)0-off, (U8*)(lim)) \
+           : (pos - off >= lim)                                 \
+               ? (U8*)pos - off                                 \
                : NULL)
 
+#define HOPBACKc(pos, off) ((char*)HOPBACK3(pos, off, reginfo->strbeg))
+
 #define HOP3(pos,off,lim) (reginfo->is_utf8_target  ? reghop3((U8*)(pos), off, (U8*)(lim)) : (U8*)(pos + off))
 #define HOP3c(pos,off,lim) ((char*)HOP3(pos,off,lim))
 
@@ -884,7 +887,9 @@ Perl_re_intuit_start(pTHX_
                 (IV)prog->check_end_shift);
         });
         
-        end_point = HOP3(strend, -end_shift, strbeg);
+        end_point = HOPBACK3(strend, end_shift, rx_origin);
+        if (!end_point)
+            goto fail_finish;
         start_point = HOPMAYBE3(rx_origin, start_shift, end_point);
         if (!start_point)
             goto fail_finish;
@@ -4340,7 +4345,7 @@ S_isGCB(pTHX_ const GCB_enum before, const GCB_enum after, const U8 * const strb
                 /* Do not break within emoji flag sequences. That is, do not
                  * break between regional indicator (RI) symbols if there is an
                  * odd number of RI characters before the break point.
-                 *  GB12     ^ (RI RI)* RI × RI
+                 *  GB12   sot (RI RI)* RI × RI
                  *  GB13 [^RI] (RI RI)* RI × RI */
 
                 while (backup_one_GCB(strbeg,
@@ -4632,7 +4637,7 @@ S_isLB(pTHX_ LB_enum before,
                  * only if there are an even number of regional indicators
                  * preceding the position of the break.
                  *
-                 *  sot (RI RI)* RI × RI
+                 *    sot (RI RI)* RI × RI
                  *  [^RI] (RI RI)* RI × RI */
 
                 while (backup_one_LB(strbeg,
@@ -5162,7 +5167,7 @@ S_isWB(pTHX_ WB_enum previous,
                  * odd number of RI characters before the potential break
                  * point.
                  *
-                 * WB15     ^ (RI RI)* RI × RI
+                 * WB15   sot (RI RI)* RI × RI
                  * WB16 [^RI] (RI RI)* RI × RI */
 
                 while (backup_one_WB(&previous,
@@ -5593,6 +5598,7 @@ S_regmatch(pTHX_ regmatch_info *reginfo, char *startpos, regnode *prog)
                 if (scan->flags == EXACTL || scan->flags == EXACTFLU8) {
                     _CHECK_AND_WARN_PROBLEMATIC_LOCALE;
                     if (utf8_target
+                        && nextchr >= 0 /* guard against negative EOS value in nextchr */
                         && UTF8_IS_ABOVE_LATIN1(nextchr)
                         && scan->flags == EXACTL)
                     {
@@ -6838,7 +6844,7 @@ S_regmatch(pTHX_ regmatch_info *reginfo, char *startpos, regnode *prog)
                 /* Some notes about MULTICALL and the context and save stacks.
                  *
                  * In something like
-                 *   /...(?{ my $x)}...(?{ my $z)}...(?{ my $z)}.../
+                 *   /...(?{ my $x)}...(?{ my $y)}...(?{ my $z)}.../
                  * since codeblocks don't introduce a new scope (so that
                  * local() etc accumulate), at the end of a successful
                  * match there will be a SAVEt_CLEARSV on the savestack
@@ -6873,7 +6879,7 @@ S_regmatch(pTHX_ regmatch_info *reginfo, char *startpos, regnode *prog)
                  * *everything* SAVEd by this function is undone and then
                  * the context popped, rather than e.g., popping the
                  * context (and restoring the original PL_comppad) then
-                 * popping more of the savestack and restoiring a bad
+                 * popping more of the savestack and restoring a bad
                  * PL_comppad.
                  */
 
@@ -7603,11 +7609,11 @@ NULL
            CACHEsayNO;
            NOT_REACHED; /* NOTREACHED */
 
-       case WHILEM_A_min_fail: /* just failed to match A in a minimal match */
-           /* FALLTHROUGH */
        case WHILEM_A_pre_fail: /* just failed to match even minimal A */
            REGCP_UNWIND(ST.lastcp);
             regcppop(rex, &maxopenparen);
+           /* FALLTHROUGH */
+       case WHILEM_A_min_fail: /* just failed to match A in a minimal match */
            cur_curlyx->u.curlyx.lastloc = ST.save_lastloc;
            cur_curlyx->u.curlyx.count--;
            CACHEsayNO;
@@ -7661,9 +7667,6 @@ NULL
            );
            /* Try grabbing another A and see if it helps. */
            cur_curlyx->u.curlyx.lastloc = locinput;
-            ST.cp = regcppush(rex, cur_curlyx->u.curlyx.parenfloor,
-                            maxopenparen);
-           REGCP_SET(ST.lastcp);
            PUSH_STATE_GOTO(WHILEM_A_min,
                /*A*/ NEXTOPER(ST.save_curlyx->u.curlyx.me) + EXTRA_STEP_2ARGS,
                 locinput);
@@ -9752,6 +9755,8 @@ S_to_byte_substr(pTHX_ regexp *prog)
     return TRUE;
 }
 
+#ifndef PERL_IN_XSUB_RE
+
 bool
 Perl__is_grapheme(pTHX_ const U8 * strbeg, const U8 * s, const U8 * strend, const UV cp)
 {
@@ -9807,6 +9812,7 @@ Perl__is_grapheme(pTHX_ const U8 * strbeg, const U8 * s, const U8 * strend, cons
     return isGCB(cp_gcb_val, next_cp_gcb_val, strbeg, s, TRUE);
 }
 
+#endif