From 05206d66340341bef7a673108a855f594c148950 Mon Sep 17 00:00:00 2001
From: Philip Hazel <[email protected]>
Date: Sun, 19 Nov 2023 18:32:10 +0000
Subject: [PATCH] Fix \z behaviour when matching within invalid UTF

---
 src/pcre2_match.c        | 6 ++++--
 testdata/testinput10     | 3 +++
 testdata/testinput12     | 3 +++
 testdata/testoutput10    | 4 ++++
 testdata/testoutput12-16 | 4 ++++
 testdata/testoutput12-32 | 4 ++++
 6 files changed, 22 insertions(+), 2 deletions(-)

diff --git a/src/pcre2_match.c b/src/pcre2_match.c
index 2dcf8c4..ea03976 100644
--- a/src/pcre2_match.c
+++ b/src/pcre2_match.c
@@ -6076,10 +6076,12 @@ fprintf(stderr, "++ %2ld op=%3d %s\n", Fecode - mb->start_code, *Fecode,
     if ((mb->poptions & PCRE2_DOLLAR_ENDONLY) == 0) goto ASSERT_NL_OR_EOS;
 
     /* Fall through */
-    /* Unconditional end of subject assertion (\z) */
+    /* Unconditional end of subject assertion (\z). We must check NOTEOL
+    because it gets set for invalid UTF fragments. */
 
     case OP_EOD:
-    if (Feptr < mb->end_subject) RRETURN(MATCH_NOMATCH);
+    if (Feptr < mb->end_subject || (mb->moptions & PCRE2_NOTEOL) != 0)
+      RRETURN(MATCH_NOMATCH);
     if (mb->partial != 0)
       {
       mb->hitend = TRUE;
diff --git a/testdata/testinput10 b/testdata/testinput10
index c7618b1..e901d51 100644
--- a/testdata/testinput10
+++ b/testdata/testinput10
@@ -642,4 +642,7 @@
     qchq\=ph
     qchq\=ps
 
+/A\z/utf,match_invalid_utf
+    A\x80\x42\n
+
 # End of testinput10
diff --git a/testdata/testinput12 b/testdata/testinput12
index 1e552e6..5a2d8d2 100644
--- a/testdata/testinput12
+++ b/testdata/testinput12
@@ -464,6 +464,9 @@
 
 /aa/utf,ucp,match_invalid_utf,global
     \x{d800}aa
+    
+/A\z/utf,match_invalid_utf
+    A\x{df00}\n
 
 # ---------------------------------------------------- 
 
diff --git a/testdata/testoutput10 b/testdata/testoutput10
index 18dd9d2..8145891 100644
--- a/testdata/testoutput10
+++ b/testdata/testoutput10
@@ -1921,4 +1921,8 @@ Partial match:
     qchq\=ps
 Partial match: 
 
+/A\z/utf,match_invalid_utf
+    A\x80\x42\n
+No match
+
 # End of testinput10
diff --git a/testdata/testoutput12-16 b/testdata/testoutput12-16
index 8cbc13d..9ac403e 100644
--- a/testdata/testoutput12-16
+++ b/testdata/testoutput12-16
@@ -1607,6 +1607,10 @@ No match
 /aa/utf,ucp,match_invalid_utf,global
     \x{d800}aa
  0: aa
+    
+/A\z/utf,match_invalid_utf
+    A\x{df00}\n
+No match
 
 # ---------------------------------------------------- 
 
diff --git a/testdata/testoutput12-32 b/testdata/testoutput12-32
index 1a98b4b..9396305 100644
--- a/testdata/testoutput12-32
+++ b/testdata/testoutput12-32
@@ -1605,6 +1605,10 @@ No match
 /aa/utf,ucp,match_invalid_utf,global
     \x{d800}aa
  0: aa
+    
+/A\z/utf,match_invalid_utf
+    A\x{df00}\n
+No match
 
 # ---------------------------------------------------- 
 
-- 
2.33.0