[Pcre-svn] [1303] code/trunk/src/pcre2_jit_compile.c: Prefer…

Revision: 1303

          http://www.exim.org/viewvc/pcre2?view=rev&revision=1303
Author:   zherczeg
Date:     2021-02-19 11:58:36 +0000 (Fri, 19 Feb 2021)
Log Message:
-----------
Prefer single character optimization over bracket repetition in JIT.

Modified Paths:
--------------
    code/trunk/src/pcre2_jit_compile.c

Modified: code/trunk/src/pcre2_jit_compile.c
===================================================================
--- code/trunk/src/pcre2_jit_compile.c    2021-02-19 09:20:37 UTC (rev 1302)
+++ code/trunk/src/pcre2_jit_compile.c    2021-02-19 11:58:36 UTC (rev 1303)
@@ -1238,6 +1238,7 @@
 */
 static int detect_early_fail(compiler_common *common, PCRE2_SPTR cc, int *private_data_start, sljit_s32 depth, int start)
 {
+PCRE2_SPTR begin = cc;
 PCRE2_SPTR next_alt;
 PCRE2_SPTR end;
 PCRE2_SPTR accelerated_start;
@@ -1475,31 +1476,19 @@
       case OP_CBRA:
       end = cc + GET(cc, 1);

-      if (*end == OP_KET && PRIVATE_DATA(end) == 0)
-        {
-        if (*cc == OP_CBRA)
-          {
-          if (common->optimized_cbracket[GET2(cc, 1 + LINK_SIZE)] == 0)
-            break;
-          cc += IMM2_SIZE;
-          }
-
-        cc += 1 + LINK_SIZE;
-        continue;
-        }
-
       fast_forward_allowed = FALSE;
       if (depth >= 4)
         break;

       end = bracketend(cc) - (1 + LINK_SIZE);
-      if (*end != OP_KET || PRIVATE_DATA(end) != 0)
+      if (*end != OP_KET || (*cc == OP_CBRA && common->optimized_cbracket[GET2(cc, 1 + LINK_SIZE)] == 0))
         break;

-      if (*cc == OP_CBRA && common->optimized_cbracket[GET2(cc, 1 + LINK_SIZE)] == 0)
-        break;
+      count = detect_early_fail(common, cc, private_data_start, depth + 1, count);

-      count = detect_early_fail(common, cc, private_data_start, depth + 1, count);
+      if (PRIVATE_DATA(cc) != 0)
+        common->private_data_ptrs[begin - common->start] = 1;
+
       if (count < EARLY_FAIL_ENHANCE_MAX)
         {
         cc = end + (1 + LINK_SIZE);
@@ -1555,6 +1544,8 @@
           return EARLY_FAIL_ENHANCE_MAX;
         }

+      /* Cannot be part of a repeat. */
+      common->private_data_ptrs[begin - common->start] = 1;
       count++;

       if (count < EARLY_FAIL_ENHANCE_MAX)
@@ -1620,11 +1611,12 @@
 sljit_s32 min, max, i;

/* Detect fixed iterations first. */
-if (end[-(1 + LINK_SIZE)] != OP_KET)
+if (end[-(1 + LINK_SIZE)] != OP_KET || PRIVATE_DATA(begin) != 0)
return FALSE;

-/* Already detected repeat. */
-if (common->private_data_ptrs[end - common->start - LINK_SIZE] != 0)
+/* /(?:AB){4,6}/ is currently converted to /(?:AB){3}(?AB){1,3}/
+ * Skip the check of the second part. */
+if (PRIVATE_DATA(end - LINK_SIZE) == 0)
return TRUE;

 next = end;
@@ -1763,6 +1755,7 @@
   if (private_data_ptr > SLJIT_MAX_LOCAL_SIZE)
     break;

+  /* When the bracket is prefixed by a zero iteration, skip the repeat check (at this point). */
   if (repeat_check && (*cc == OP_ONCE || *cc == OP_BRA || *cc == OP_CBRA || *cc == OP_COND))
     {
     if (detect_repeat(common, cc))
@@ -1813,6 +1806,7 @@

     case OP_COND:
     /* Might be a hidden SCOND. */
+    common->private_data_ptrs[cc - common->start] = 0;
     alternative = cc + GET(cc, 1);
     if (*alternative == OP_KETRMAX || *alternative == OP_KETRMIN)
       {
@@ -13661,10 +13655,12 @@
 memset(common->private_data_ptrs, 0, total_length * sizeof(sljit_s32));

private_data_size = common->cbra_ptr + (re->top_bracket + 1) * sizeof(sljit_sw);
-set_private_data_ptrs(common, &private_data_size, ccend);
+
if ((re->overall_options & PCRE2_ANCHORED) == 0 && (re->overall_options & PCRE2_NO_START_OPTIMIZE) == 0 && !common->has_skip_in_assert_back)
detect_early_fail(common, common->start, &private_data_size, 0, 0);

+set_private_data_ptrs(common, &private_data_size, ccend);
+
SLJIT_ASSERT(common->early_fail_start_ptr <= common->early_fail_end_ptr);

if (private_data_size > SLJIT_MAX_LOCAL_SIZE)