From 3458a2e2cda4c46f2238aa67d46a2ff2635c8646 Mon Sep 17 00:00:00 2001
From: "Philip.Hazel" <Philip.Hazel@gmail.com>
Date: Tue, 12 Dec 2017 16:23:01 +0000
Subject: [PATCH] Fix infelicity in not finding a first character inside a
 non-assertive group within a positive assertion.

---
 ChangeLog            |  8 ++++++++
 src/pcre2_compile.c  | 12 ++++++------
 testdata/testoutput2 |  2 +-
 3 files changed, 15 insertions(+), 7 deletions(-)

diff --git a/ChangeLog b/ChangeLog
index 7af58de..e74a6bf 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -70,6 +70,14 @@ pattern, apart from assertions, an incorrect first matching character could be
 recorded. For example, for the pattern /(?=(a))\1?b/, "b" was incorrectly set 
 as the first character of a match.
 
+18. Characters in a leading positive assertion are considered for recording a
+first character of a match when the rest of the pattern does not provide one.
+However, a character in a non-assertive group within a leading assertion such
+as in the pattern /(?=(a))\1?b/ caused this process to fail. This was an 
+infelicity rather than an outright bug, because it did not affect the result of 
+a match, just its speed. (In fact, in this case, the starting 'a' was 
+subsequently picked up in the study.)
+
 
 Version 10.30 14-August-2017
 ----------------------------
diff --git a/src/pcre2_compile.c b/src/pcre2_compile.c
index ad17338..1e06040 100644
--- a/src/pcre2_compile.c
+++ b/src/pcre2_compile.c
@@ -8106,13 +8106,13 @@ REQ_NONE in the flags.
 Arguments:
   code       points to start of compiled pattern
   flags      points to the first code unit flags
-  inassert   TRUE if in an assertion
+  inassert   non-zero if in an assertion
 
 Returns:     the fixed first code unit, or 0 with REQ_NONE in flags
 */
 
 static uint32_t
-find_firstassertedcu(PCRE2_SPTR code, int32_t *flags, BOOL inassert)
+find_firstassertedcu(PCRE2_SPTR code, int32_t *flags, uint32_t inassert)
 {
 uint32_t c = 0;
 int cflags = REQ_NONE;
@@ -8139,7 +8139,7 @@ do {
      case OP_SCBRAPOS:
      case OP_ASSERT:
      case OP_ONCE:
-     d = find_firstassertedcu(scode, &dflags, op == OP_ASSERT);
+     d = find_firstassertedcu(scode, &dflags, inassert + ((op==OP_ASSERT)?1:0));
      if (dflags < 0)
        return 0;
      if (cflags < 0) { c = d; cflags = dflags; }
@@ -8154,7 +8154,7 @@ do {
      case OP_PLUS:
      case OP_MINPLUS:
      case OP_POSPLUS:
-     if (!inassert) return 0;
+     if (inassert == 0) return 0;
      if (cflags < 0) { c = scode[1]; cflags = 0; }
        else if (c != scode[1]) return 0;
      break;
@@ -8167,7 +8167,7 @@ do {
      case OP_PLUSI:
      case OP_MINPLUSI:
      case OP_POSPLUSI:
-     if (!inassert) return 0;
+     if (inassert == 0) return 0;
      if (cflags < 0) { c = scode[1]; cflags = REQ_CASELESS; }
        else if (c != scode[1]) return 0;
      break;
@@ -9674,7 +9674,7 @@ if ((re->overall_options & PCRE2_NO_START_OPTIMIZE) == 0)
   actual literals that follow). */
 
   if (firstcuflags < 0)
-    firstcu = find_firstassertedcu(codestart, &firstcuflags, FALSE);
+    firstcu = find_firstassertedcu(codestart, &firstcuflags, 0);
 
   /* Save the data for a first code unit. */
 
diff --git a/testdata/testoutput2 b/testdata/testoutput2
index 31ccfbe..ee9cde9 100644
--- a/testdata/testoutput2
+++ b/testdata/testoutput2
@@ -16358,7 +16358,7 @@ Subject length lower bound = 1
 "(?=(a))\1?b"I
 Capturing subpattern count = 1
 Max back reference = 1
-Starting code units: a 
+First code unit = 'a'
 Last code unit = 'b'
 Subject length lower bound = 1
     ab