Remove atomic restriction on capture groups containing recursive back

references, as since 10.30 it has been unnecessary.


git-svn-id: svn://vcs.exim.org/pcre2/code/trunk@1193 6239d852-aaf2-0410-a92c-79f79f948069

7 files changed, 236 insertions, 237 deletions

diff --git a/testdata/testinput1 b/testdata/testinput1
index f5159d6..109de29 100644
--- a/testdata/testinput1
+++ b/testdata/testinput1
@@ -6386,4 +6386,11 @@ ef) x/x,mark
 /^(?<A>a)(?(<A>)b)((?<=b).*)$/
     abc
 
+/^(a\1?){4}$/
+    aaaa
+    aaaaaa
+
+/^((\1+)|\d)+133X$/
+    111133X
+
 # End of testinput1 
diff --git a/testdata/testinput2 b/testdata/testinput2
index 655e519..b700d9e 100644
--- a/testdata/testinput2
+++ b/testdata/testinput2
@@ -324,16 +324,7 @@
 \= Expect no match
     fooabar
 
-# This one is here because Perl behaves differently; see also the following.
-
-/^(a\1?){4}$/I
-\= Expect no match
-    aaaa
-    aaaaaa
-
-# Perl does not fail these two for the final subjects. Neither did PCRE until
-# release 8.01. The problem is in backtracking into a subpattern that contains
-# a recursive reference to itself. PCRE has now made these into atomic patterns.
+# Perl does not fail these two for the final subjects.
 
 /^(xa|=?\1a){2}$/
     xa=xaa
@@ -5772,4 +5763,13 @@ a)"xI
 /(a)?a/I
     manm
 
+/^(?|(\*)(*napla:\S*_(\2?+.+))|(\w)(?=\S*_(\2?+\1)))+_\2$/
+    *abc_12345abc
+
+/^(?|(\*)(*napla:\S*_(\3?+.+))|(\w)(?=\S*_((\2?+\1))))+_\2$/
+    *abc_12345abc
+
+/^((\1+)(?C)|\d)+133X$/
+    111133X\=callout_capture
+
 # End of testinput2
diff --git a/testdata/testoutput1 b/testdata/testoutput1
index ad2175b..c425ed4 100644
--- a/testdata/testoutput1
+++ b/testdata/testoutput1
@@ -10112,4 +10112,18 @@ No match
  1: a
  2: c
 
+/^(a\1?){4}$/
+    aaaa
+ 0: aaaa
+ 1: a
+    aaaaaa
+ 0: aaaaaa
+ 1: aa
+
+/^((\1+)|\d)+133X$/
+    111133X
+ 0: 111133X
+ 1: 11
+ 2: 11
+
 # End of testinput1 
diff --git a/testdata/testoutput2 b/testdata/testoutput2
index c733c12..df2f230 100644
--- a/testdata/testoutput2
+++ b/testdata/testoutput2
@@ -809,24 +809,7 @@ Subject length lower bound = 3
     fooabar
 No match
 
-# This one is here because Perl behaves differently; see also the following.
-
-/^(a\1?){4}$/I
-Capture group count = 1
-Max back reference = 1
-Compile options: <none>
-Overall options: anchored
-First code unit = 'a'
-Subject length lower bound = 4
-\= Expect no match
-    aaaa
-No match
-    aaaaaa
-No match
-
-# Perl does not fail these two for the final subjects. Neither did PCRE until
-# release 8.01. The problem is in backtracking into a subpattern that contains
-# a recursive reference to itself. PCRE has now made these into atomic patterns.
+# Perl does not fail these two for the final subjects.
 
 /^(xa|=?\1a){2}$/
     xa=xaa
@@ -10060,7 +10043,6 @@ No match
 ------------------------------------------------------------------
         Bra
         ^
-        Once
         CBra 1
         ab
         CBra 2
@@ -10071,8 +10053,6 @@ No match
         Alt
         x
         Ket
-        Ket
-        Once
         CBra 1
         ab
         CBra 2
@@ -10083,7 +10063,6 @@ No match
         Alt
         x
         Ket
-        Ket
         $
         Ket
         End
@@ -10479,27 +10458,23 @@ Failed: error 168 at offset 3: \c must be followed by a printable ASCII characte
 /(?P<abn>(?P=abn)xxx)/B
 ------------------------------------------------------------------
         Bra
-        Once
         CBra 1
         \1
         xxx
         Ket
         Ket
-        Ket
         End
 ------------------------------------------------------------------
 
 /(a\1z)/B
 ------------------------------------------------------------------
         Bra
-        Once
         CBra 1
         a
         \1
         z
         Ket
         Ket
-        Ket
         End
 ------------------------------------------------------------------
 
@@ -11299,27 +11274,23 @@ No match
 /(?P<abn>(?P=abn)xxx)/B
 ------------------------------------------------------------------
         Bra
-        Once
         CBra 1
         \1
         xxx
         Ket
         Ket
-        Ket
         End
 ------------------------------------------------------------------
 
 /(a\1z)/B
 ------------------------------------------------------------------
         Bra
-        Once
         CBra 1
         a
         \1
         z
         Ket
         Ket
-        Ket
         End
 ------------------------------------------------------------------
 
@@ -13319,7 +13290,6 @@ Failed: error 144 at offset 5: subpattern name must start with a non-digit
         Bra
         Brazero
         SCBra 1
-        Once
         CBra 2
         CBra 3
         a
@@ -13331,7 +13301,6 @@ Failed: error 144 at offset 5: subpattern name must start with a non-digit
         Ket
         Recurse
         Ket
-        Ket
         KetRmax
         a?+
         Ket
@@ -13999,7 +13968,6 @@ Matched, but too many substrings
 /((?+1)(\1))/B
 ------------------------------------------------------------------
         Bra
-        Once
         CBra 1
         Recurse
         CBra 2
@@ -14007,7 +13975,6 @@ Matched, but too many substrings
         Ket
         Ket
         Ket
-        Ket
         End
 ------------------------------------------------------------------
 
@@ -14425,7 +14392,6 @@ Subject length lower bound = 1
 ------------------------------------------------------------------
         Bra
         Any
-        Once
         CBra 1
         Recurse
         Recurse
@@ -14434,7 +14400,6 @@ Subject length lower bound = 1
         Alt
         $
         Ket
-        Ket
         CBra 2
         Ket
         Ket
@@ -14445,7 +14410,6 @@ Subject length lower bound = 1
 ------------------------------------------------------------------
         Bra
         Any
-        Once
         CBra 1
         Recurse
         Recurse
@@ -14457,7 +14421,6 @@ Subject length lower bound = 1
         Alt
         $
         Ket
-        Ket
         CBra 3
         Ket
         Ket
@@ -17435,6 +17398,45 @@ Subject length lower bound = 1
     manm
  0: a
 
+/^(?|(\*)(*napla:\S*_(\2?+.+))|(\w)(?=\S*_(\2?+\1)))+_\2$/
+    *abc_12345abc
+ 0: *abc_12345abc
+ 1: c
+ 2: 12345abc
+
+/^(?|(\*)(*napla:\S*_(\3?+.+))|(\w)(?=\S*_((\2?+\1))))+_\2$/
+    *abc_12345abc
+ 0: *abc_12345abc
+ 1: c
+ 2: 12345abc
+ 3: 12345abc
+
+/^((\1+)(?C)|\d)+133X$/
+    111133X\=callout_capture
+Callout 0: last capture = 2
+ 1: 1
+ 2: 111
+--->111133X
+    ^   ^       |
+Callout 0: last capture = 2
+ 1: 3
+ 2: 3
+--->111133X
+    ^     ^     |
+Callout 0: last capture = 2
+ 1: 1
+ 2: 11
+--->111133X
+    ^  ^        |
+Callout 0: last capture = 2
+ 1: 3
+ 2: 3
+--->111133X
+    ^     ^     |
+ 0: 111133X
+ 1: 11
+ 2: 11
+
 # End of testinput2
 Error -70: PCRE2_ERROR_BADDATA (unknown error number)
 Error -62: bad serialized data
diff --git a/testdata/testoutput8-16-2 b/testdata/testoutput8-16-2
index ff3474b..569a860 100644
--- a/testdata/testoutput8-16-2
+++ b/testdata/testoutput8-16-2
@@ -720,41 +720,37 @@ Memory allocation (code space): 14
 
 /(((a\2)|(a*)\g<-1>))*a?/
 ------------------------------------------------------------------
-  0  39 Bra
+  0  35 Bra
   2     Brazero
-  3  32 SCBra 1
-  6  27 Once
-  8  12 CBra 2
- 11   7 CBra 3
- 14     a
- 16     \2
- 18   7 Ket
- 20  11 Alt
- 22   5 CBra 4
- 25     a*
- 27   5 Ket
- 29  22 Recurse
- 31  23 Ket
- 33  27 Ket
- 35  32 KetRmax
- 37     a?+
- 39  39 Ket
- 41     End
+  3  28 SCBra 1
+  6  12 CBra 2
+  9   7 CBra 3
+ 12     a
+ 14     \2
+ 16   7 Ket
+ 18  11 Alt
+ 20   5 CBra 4
+ 23     a*
+ 25   5 Ket
+ 27  20 Recurse
+ 29  23 Ket
+ 31  28 KetRmax
+ 33     a?+
+ 35  35 Ket
+ 37     End
 ------------------------------------------------------------------
 
 /((?+1)(\1))/
 ------------------------------------------------------------------
-  0  20 Bra
-  2  16 Once
-  4  12 CBra 1
-  7   9 Recurse
-  9   5 CBra 2
- 12     \1
- 14   5 Ket
- 16  12 Ket
- 18  16 Ket
- 20  20 Ket
- 22     End
+  0  16 Bra
+  2  12 CBra 1
+  5   7 Recurse
+  7   5 CBra 2
+ 10     \1
+ 12   5 Ket
+ 14  12 Ket
+ 16  16 Ket
+ 18     End
 ------------------------------------------------------------------
 
 "(?1)(?#?'){2}(a)"
@@ -771,45 +767,41 @@ Memory allocation (code space): 14
 
 /.((?2)(?R)|\1|$)()/
 ------------------------------------------------------------------
-  0  28 Bra
+  0  24 Bra
   2     Any
-  3  18 Once
-  5   7 CBra 1
-  8  23 Recurse
- 10   0 Recurse
- 12   4 Alt
- 14     \1
- 16   3 Alt
- 18     $
- 19  14 Ket
- 21  18 Ket
- 23   3 CBra 2
- 26   3 Ket
- 28  28 Ket
- 30     End
+  3   7 CBra 1
+  6  19 Recurse
+  8   0 Recurse
+ 10   4 Alt
+ 12     \1
+ 14   3 Alt
+ 16     $
+ 17  14 Ket
+ 19   3 CBra 2
+ 22   3 Ket
+ 24  24 Ket
+ 26     End
 ------------------------------------------------------------------
 
 /.((?3)(?R)()(?2)|\1|$)()/
 ------------------------------------------------------------------
-  0  35 Bra
+  0  31 Bra
   2     Any
-  3  25 Once
-  5  14 CBra 1
-  8  30 Recurse
- 10   0 Recurse
- 12   3 CBra 2
- 15   3 Ket
- 17  12 Recurse
- 19   4 Alt
- 21     \1
- 23   3 Alt
- 25     $
- 26  21 Ket
- 28  25 Ket
- 30   3 CBra 3
- 33   3 Ket
- 35  35 Ket
- 37     End
+  3  14 CBra 1
+  6  26 Recurse
+  8   0 Recurse
+ 10   3 CBra 2
+ 13   3 Ket
+ 15  10 Recurse
+ 17   4 Alt
+ 19     \1
+ 21   3 Alt
+ 23     $
+ 24  21 Ket
+ 26   3 CBra 3
+ 29   3 Ket
+ 31  31 Ket
+ 33     End
 ------------------------------------------------------------------
 
 /(?1)()((((((\1++))\x85)+)|))/
diff --git a/testdata/testoutput8-32-2 b/testdata/testoutput8-32-2
index 7d1c931..91d96c9 100644
--- a/testdata/testoutput8-32-2
+++ b/testdata/testoutput8-32-2
@@ -720,41 +720,37 @@ Memory allocation (code space): 28
 
 /(((a\2)|(a*)\g<-1>))*a?/
 ------------------------------------------------------------------
-  0  39 Bra
+  0  35 Bra
   2     Brazero
-  3  32 SCBra 1
-  6  27 Once
-  8  12 CBra 2
- 11   7 CBra 3
- 14     a
- 16     \2
- 18   7 Ket
- 20  11 Alt
- 22   5 CBra 4
- 25     a*
- 27   5 Ket
- 29  22 Recurse
- 31  23 Ket
- 33  27 Ket
- 35  32 KetRmax
- 37     a?+
- 39  39 Ket
- 41     End
+  3  28 SCBra 1
+  6  12 CBra 2
+  9   7 CBra 3
+ 12     a
+ 14     \2
+ 16   7 Ket
+ 18  11 Alt
+ 20   5 CBra 4
+ 23     a*
+ 25   5 Ket
+ 27  20 Recurse
+ 29  23 Ket
+ 31  28 KetRmax
+ 33     a?+
+ 35  35 Ket
+ 37     End
 ------------------------------------------------------------------
 
 /((?+1)(\1))/
 ------------------------------------------------------------------
-  0  20 Bra
-  2  16 Once
-  4  12 CBra 1
-  7   9 Recurse
-  9   5 CBra 2
- 12     \1
- 14   5 Ket
- 16  12 Ket
- 18  16 Ket
- 20  20 Ket
- 22     End
+  0  16 Bra
+  2  12 CBra 1
+  5   7 Recurse
+  7   5 CBra 2
+ 10     \1
+ 12   5 Ket
+ 14  12 Ket
+ 16  16 Ket
+ 18     End
 ------------------------------------------------------------------
 
 "(?1)(?#?'){2}(a)"
@@ -771,45 +767,41 @@ Memory allocation (code space): 28
 
 /.((?2)(?R)|\1|$)()/
 ------------------------------------------------------------------
-  0  28 Bra
+  0  24 Bra
   2     Any
-  3  18 Once
-  5   7 CBra 1
-  8  23 Recurse
- 10   0 Recurse
- 12   4 Alt
- 14     \1
- 16   3 Alt
- 18     $
- 19  14 Ket
- 21  18 Ket
- 23   3 CBra 2
- 26   3 Ket
- 28  28 Ket
- 30     End
+  3   7 CBra 1
+  6  19 Recurse
+  8   0 Recurse
+ 10   4 Alt
+ 12     \1
+ 14   3 Alt
+ 16     $
+ 17  14 Ket
+ 19   3 CBra 2
+ 22   3 Ket
+ 24  24 Ket
+ 26     End
 ------------------------------------------------------------------
 
 /.((?3)(?R)()(?2)|\1|$)()/
 ------------------------------------------------------------------
-  0  35 Bra
+  0  31 Bra
   2     Any
-  3  25 Once
-  5  14 CBra 1
-  8  30 Recurse
- 10   0 Recurse
- 12   3 CBra 2
- 15   3 Ket
- 17  12 Recurse
- 19   4 Alt
- 21     \1
- 23   3 Alt
- 25     $
- 26  21 Ket
- 28  25 Ket
- 30   3 CBra 3
- 33   3 Ket
- 35  35 Ket
- 37     End
+  3  14 CBra 1
+  6  26 Recurse
+  8   0 Recurse
+ 10   3 CBra 2
+ 13   3 Ket
+ 15  10 Recurse
+ 17   4 Alt
+ 19     \1
+ 21   3 Alt
+ 23     $
+ 24  21 Ket
+ 26   3 CBra 3
+ 29   3 Ket
+ 31  31 Ket
+ 33     End
 ------------------------------------------------------------------
 
 /(?1)()((((((\1++))\x85)+)|))/
diff --git a/testdata/testoutput8-8-2 b/testdata/testoutput8-8-2
index 4c4e6a8..8393d5c 100644
--- a/testdata/testoutput8-8-2
+++ b/testdata/testoutput8-8-2
@@ -720,41 +720,37 @@ Memory allocation (code space): 10
 
 /(((a\2)|(a*)\g<-1>))*a?/
 ------------------------------------------------------------------
-  0  57 Bra
+  0  51 Bra
   3     Brazero
-  4  48 SCBra 1
-  9  40 Once
- 12  18 CBra 2
- 17  10 CBra 3
- 22     a
- 24     \2
- 27  10 Ket
- 30  16 Alt
- 33   7 CBra 4
- 38     a*
- 40   7 Ket
- 43  33 Recurse
- 46  34 Ket
- 49  40 Ket
- 52  48 KetRmax
- 55     a?+
- 57  57 Ket
- 60     End
+  4  42 SCBra 1
+  9  18 CBra 2
+ 14  10 CBra 3
+ 19     a
+ 21     \2
+ 24  10 Ket
+ 27  16 Alt
+ 30   7 CBra 4
+ 35     a*
+ 37   7 Ket
+ 40  30 Recurse
+ 43  34 Ket
+ 46  42 KetRmax
+ 49     a?+
+ 51  51 Ket
+ 54     End
 ------------------------------------------------------------------
 
 /((?+1)(\1))/
 ------------------------------------------------------------------
-  0  31 Bra
-  3  25 Once
-  6  19 CBra 1
- 11  14 Recurse
- 14   8 CBra 2
- 19     \1
- 22   8 Ket
- 25  19 Ket
- 28  25 Ket
- 31  31 Ket
- 34     End
+  0  25 Bra
+  3  19 CBra 1
+  8  11 Recurse
+ 11   8 CBra 2
+ 16     \1
+ 19   8 Ket
+ 22  19 Ket
+ 25  25 Ket
+ 28     End
 ------------------------------------------------------------------
 
 "(?1)(?#?'){2}(a)"
@@ -771,45 +767,41 @@ Memory allocation (code space): 10
 
 /.((?2)(?R)|\1|$)()/
 ------------------------------------------------------------------
-  0  42 Bra
+  0  36 Bra
   3     Any
-  4  27 Once
-  7  11 CBra 1
- 12  34 Recurse
- 15   0 Recurse
- 18   6 Alt
- 21     \1
- 24   4 Alt
- 27     $
- 28  21 Ket
- 31  27 Ket
- 34   5 CBra 2
- 39   5 Ket
- 42  42 Ket
- 45     End
+  4  11 CBra 1
+  9  28 Recurse
+ 12   0 Recurse
+ 15   6 Alt
+ 18     \1
+ 21   4 Alt
+ 24     $
+ 25  21 Ket
+ 28   5 CBra 2
+ 33   5 Ket
+ 36  36 Ket
+ 39     End
 ------------------------------------------------------------------
 
 /.((?3)(?R)()(?2)|\1|$)()/
 ------------------------------------------------------------------
-  0  53 Bra
+  0  47 Bra
   3     Any
-  4  38 Once
-  7  22 CBra 1
- 12  45 Recurse
- 15   0 Recurse
- 18   5 CBra 2
- 23   5 Ket
- 26  18 Recurse
- 29   6 Alt
- 32     \1
- 35   4 Alt
- 38     $
- 39  32 Ket
- 42  38 Ket
- 45   5 CBra 3
- 50   5 Ket
- 53  53 Ket
- 56     End
+  4  22 CBra 1
+  9  39 Recurse
+ 12   0 Recurse
+ 15   5 CBra 2
+ 20   5 Ket
+ 23  15 Recurse
+ 26   6 Alt
+ 29     \1
+ 32   4 Alt
+ 35     $
+ 36  32 Ket
+ 39   5 CBra 3
+ 44   5 Ket
+ 47  47 Ket
+ 50     End
 ------------------------------------------------------------------
 
 /(?1)()((((((\1++))\x85)+)|))/