From 3be538015bf4ab00becbb601f22cdc24af4222dc Mon Sep 17 00:00:00 2001
From: "Philip.Hazel" <Philip.Hazel@gmail.com>
Date: Mon, 24 Feb 2020 17:29:00 +0000
Subject: [PATCH] Fix bad lookbehind compilation when preceded by a DEFINE
 group.

---
 ChangeLog            | 5 +++++
 src/pcre2_compile.c  | 5 +++++
 testdata/testinput1  | 3 +++
 testdata/testoutput1 | 4 ++++
 4 files changed, 17 insertions(+)

diff --git a/ChangeLog b/ChangeLog
index 9f493be..95e0123 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -77,6 +77,11 @@ low surrogate. This caused incorrect behaviour, for example when
 PCRE2_MATCH_INVALID_UTF was set and a match started immediately following the
 invalid high surrogate, such as /aa/ matching "\x{d800}aa".
 
+20. If a DEFINE group immediately preceded a lookbehind assertion, the pattern 
+could be mis-compiled and therefore not match correctly. This is the example 
+that found this: /(?(DEFINE)(?<foo>bar))(?<![-a-z0-9])word/ which failed to 
+match "word" because the "move back" value was set to zero.
+
 
 Version 10.34 21-November-2019
 ------------------------------
diff --git a/src/pcre2_compile.c b/src/pcre2_compile.c
index 515f2aa..13769a0 100644
--- a/src/pcre2_compile.c
+++ b/src/pcre2_compile.c
@@ -8019,6 +8019,7 @@ and skip over the pattern offset. */
 lookbehind = *code == OP_ASSERTBACK ||
              *code == OP_ASSERTBACK_NOT ||
              *code == OP_ASSERTBACK_NA;
+
 if (lookbehind)
   {
   lookbehindlength = META_DATA(pptr[-1]);
@@ -9553,6 +9554,10 @@ for (; *pptr != META_END; pptr++)
     break;
 
     case META_COND_DEFINE:
+    pptr += SIZEOFFSET;
+    nestlevel++;
+    break;
+
     case META_COND_NAME:
     case META_COND_NUMBER:
     case META_COND_RNAME:
diff --git a/testdata/testinput1 b/testdata/testinput1
index c6b3647..8d952e2 100644
--- a/testdata/testinput1
+++ b/testdata/testinput1
@@ -6424,4 +6424,7 @@ ef) x/x,mark
 "(?<=X(?(DEFINE)(Y))(?1))."
     AXYZ
 
+"(?(DEFINE)(?<foo>bar))(?<![-a-z0-9])word"
+    word
+
 # End of testinput1 
diff --git a/testdata/testoutput1 b/testdata/testoutput1
index 4c43caa..470e412 100644
--- a/testdata/testoutput1
+++ b/testdata/testoutput1
@@ -10182,4 +10182,8 @@ No match
     AXYZ
  0: Z
 
+"(?(DEFINE)(?<foo>bar))(?<![-a-z0-9])word"
+    word
+ 0: word
+
 # End of testinput1