Fix PCRE2_ENDANCHORED behaviour in recursion in pcre2_match(). Fixes #331.

Author: PhilipHazel

ChangeLog

@@ -146,6 +146,10 @@ restrictions on POSIX classes.
 pcre2_dfa_match() misbehaved. PCRE2_FIRSTLINE is now ignored for anchored 
 patterns.
 
+38. If PCRE2_ENDANCHORED was set and the end of the pattern was reached during 
+a recursion, pcre2_match() misbehaved and gave the wrong match. For example, 
+the pattern /|a(?0)/ matched against "aaaa".
+
 
 Version 10.42 11-December-2022
 ------------------------------

src/pcre2_match.c

@@ -833,6 +833,18 @@ fprintf(stderr, "++ op=%d\n", *Fecode);
     case OP_ACCEPT:
     case OP_END:
 
+    /* Fail if PCRE2_ENDANCHORED is set and the end of the match is not
+    the end of the subject. After (*ACCEPT) we fail the entire match (at this
+    position) but backtrack if we've reached the end of the pattern. This
+    applies whether or not we are in a recursion. */
+
+    if (Feptr < mb->end_subject &&
+        ((mb->moptions | mb->poptions) & PCRE2_ENDANCHORED) != 0)
+      {
+      if (Fop == OP_END) RRETURN(MATCH_NOMATCH);
+      return MATCH_NOMATCH;   /* (*ACCEPT) */
+      }
+
     /* Handle end of a recursion. */
 
     if (Fcurrent_recurse != RECURSE_UNSET)
@@ -871,17 +883,6 @@ fprintf(stderr, "++ op=%d\n", *Fecode);
              Fstart_match == mb->start_subject + mb->start_offset)))
       RRETURN(MATCH_NOMATCH);
 
-    /* Also fail if PCRE2_ENDANCHORED is set and the end of the match is not
-    the end of the subject. After (*ACCEPT) we fail the entire match (at this
-    position) but backtrack on reaching the end of the pattern. */
-
-    if (Feptr < mb->end_subject &&
-        ((mb->moptions | mb->poptions) & PCRE2_ENDANCHORED) != 0)
-      {
-      if (Fop == OP_END) RRETURN(MATCH_NOMATCH);
-      return MATCH_NOMATCH;
-      }
-
     /* We have a successful match of the whole pattern. Record the result and
     then do a direct return from the function. If there is space in the offset
     vector, set any pairs that follow the highest-numbered captured string but

testdata/testinput2

@@ -6041,4 +6041,7 @@ a)"xI
     \x0a
     abc\x0adef
 
+/|a(?0)/endanchored
+    aaaa
+
 # End of testinput2

testdata/testinput6

@@ -5039,4 +5039,7 @@
     \x0a
     abc\x0adef
 
+/|a(?0)/endanchored
+    aaaa
+
 # End of testinput6

testdata/testoutput2

@@ -17918,6 +17918,10 @@ No match
     abc\x0adef
  0: \x0a
 
+/|a(?0)/endanchored
+    aaaa
+ 0: aaaa
+
 # End of testinput2
 Error -70: PCRE2_ERROR_BADDATA (unknown error number)
 Error -62: bad serialized data

testdata/testoutput6

@@ -7912,4 +7912,12 @@ Partial match:
     abc\x0adef
  0: \x0a
 
+/|a(?0)/endanchored
+    aaaa
+ 0: aaaa
+ 1: aaa
+ 2: aa
+ 3: a
+ 4: 
+
 # End of testinput6