Fix delimiters in tests 1 and 4 for correct Perl behaviour (Bugzilla #2641).

Also move \K in lookaround tests to test 2 (Perl no longer supports).


git-svn-id: svn://vcs.exim.org/pcre2/code/trunk@1269 6239d852-aaf2-0410-a92c-79f79f948069

8 files changed, 99 insertions, 58 deletions

diff --git a/ChangeLog b/ChangeLog
index 680d7f1..4f7bb89 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -52,6 +52,17 @@ buffer overflow). Fixes ClusterFuzz 23779.
 handled by an optimization in JIT. Furthermore a wrong offset was used to
 read a value from a buffer which could lead to memory overread.
 
+10. Unnoticed for many years was the fact that delimiters other than / in the 
+testinput1 and testinput4 files could cause incorrect behaviour when these 
+files were processed by perltest.sh. There were several tests that used quotes 
+as delimiters, and it was just luck that they didn't go wrong with perltest.sh.
+All the patterns in testinput1 and testinput4 now use / as their delimiter. 
+This fixes Bugzilla #2641.
+
+11. Perl has started to give an error for \K within lookarounds (though there 
+are cases where it doesn't). PCRE2 still allows this, so the tests that include 
+this case have been moved from test 1 to test 2.
+
 
 Version 10.35 09-May-2020
 ---------------------------
diff --git a/perltest.sh b/perltest.sh
index 8368781..31406c5 100755
--- a/perltest.sh
+++ b/perltest.sh
@@ -68,6 +68,9 @@ fi
 # #newline_default commands, which are needed in the relevant pcre2test files,
 # are ignored. Any other #-command is ignored, with a warning message.
 #
+# The pattern lines should use only / as the delimiter. The other characters
+# that pcre2test supports cause problems with this script.
+#
 # The data lines must not have any pcre2test modifiers. Unless
 # "subject_literal" is on the pattern, data lines are processed as
 # Perl double-quoted strings, so if they contain " $ or @ characters, these
diff --git a/testdata/testinput1 b/testdata/testinput1
index 8d952e2..8a50cfa 100644
--- a/testdata/testinput1
+++ b/testdata/testinput1
@@ -1,6 +1,10 @@
 # This set of tests is for features that are compatible with all versions of
 # Perl >= 5.10, in non-UTF mode. It should run clean for the 8-bit, 16-bit, and
 # 32-bit PCRE libraries, and also using the perltest.sh script.
+
+# WARNING: Use only / as the pattern delimiter. Although pcre2test supports
+# a number of delimiters, all those other than / give problems with the
+# perltest.sh script.
     
 #forbid_utf
 #newline_default lf any anycrlf
@@ -1957,7 +1961,7 @@
     abc\nzzz
     qqq\nabc\nzzz
 
-"(?>.*/)foo"
+/(?>.*\/)foo/
     /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/and/foo
 \= Expect no match     
     /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/it/you/see/
@@ -3831,12 +3835,13 @@
 /(?-x: )/x
     A\x20B
     
-"(?x)(?-x: \s*#\s*)"
+/(?x)(?-x: \s*#\s*)/
     A # B
 \= Expect no match
     #  
+    A s#s B
 
-"(?x-is)(?:(?-ixs) \s*#\s*) include"
+/(?x-is)(?:(?-ixs) \s*#\s*) include/
     A #include
 \= Expect no match
     A#include  
@@ -5232,11 +5237,11 @@ name)/mark
     alphabetabcd
     endingwxyz 
 
-"(?>.*)foo"
+/(?>.*)foo/
 \= Expect no match
     abcdfooxyz
     
-"(?>.*?)foo"
+/(?>.*?)foo/
     abcdfooxyz
 
 /(?:(a(*PRUNE)b)){0}(?:(?1)|ac)/
@@ -5423,18 +5428,6 @@ name)/mark
 \= Expect no match
     a
 
-/(?=a\Kb)ab/
-    ab 
-
-/(?!a\Kb)ac/
-    ac 
-    
-/^abc(?<=b\Kc)d/
-    abcd
-
-/^abc(?<!b\Kq)d/
-    abcd
-
 /A(*PRUNE:A)A+(*SKIP:A)(B|Z) | AC/x,mark
 \= Expect no match
     AAAC
@@ -5727,9 +5720,9 @@ name)/mark
 
 /(\2)(\1)/
 
-"Z*(|d*){216}"
+/Z*(|d*){216}/
 
-"(?1)(?#?'){8}(a)"
+/(?1)(?#?'){8}(a)/
     baaaaaaaaac
 
 /((((((((((((x))))))))))))\12/
@@ -5741,7 +5734,7 @@ name)/mark
 /(?1)()((((((\1++))\x85)+)|))/
     \x85\x85
 
-"(?|(\k'Pm')|(?'Pm'))"
+/(?|(\k'Pm')|(?'Pm'))/
     abcd
 
 /(?|(aaa)|(b))\g{1}/
@@ -6411,20 +6404,20 @@ ef) x/x,mark
     Hackdaws love my big sphinx of quartz.
     Pack my fox with five dozen liquor jugs.
 
-"(?<=X(?(DEFINE)(A)))X(*F)"
+/(?<=X(?(DEFINE)(A)))X(*F)/
 \= Expect no match
     AXYZ
 
-"(?<=X(?(DEFINE)(A)))."
+/(?<=X(?(DEFINE)(A)))./
     AXYZ
 
-"(?<=X(?(DEFINE)(.*))Y)."
+/(?<=X(?(DEFINE)(.*))Y)./
     AXYZ
 
-"(?<=X(?(DEFINE)(Y))(?1))."
+/(?<=X(?(DEFINE)(Y))(?1))./
     AXYZ
 
-"(?(DEFINE)(?<foo>bar))(?<![-a-z0-9])word"
+/(?(DEFINE)(?<foo>bar))(?<![-a-z0-9])word/
     word
 
 # End of testinput1 
diff --git a/testdata/testinput2 b/testdata/testinput2
index 47320eb..14ad824 100644
--- a/testdata/testinput2
+++ b/testdata/testinput2
@@ -5866,4 +5866,20 @@ a)"xI
 
 /(?(VERSION=0.0/
 
+# Perl has made \K in lookarounds an error. At the moment PCRE2 still accepts.
+
+/(?=a\Kb)ab/
+    ab 
+
+/(?!a\Kb)ac/
+    ac 
+    
+/^abc(?<=b\Kc)d/
+    abcd
+
+/^abc(?<!b\Kq)d/
+    abcd
+    
+# --------- 
+
 # End of testinput2
diff --git a/testdata/testinput4 b/testdata/testinput4
index 0bdac57..4e2a0ab 100644
--- a/testdata/testinput4
+++ b/testdata/testinput4
@@ -3,6 +3,10 @@
 # some of the property tests may differ because of different versions of
 # Unicode in use by PCRE2 and Perl.
 
+# WARNING: Use only / as the pattern delimiter. Although pcre2test supports
+# a number of delimiters, all those other than / give problems with the
+# perltest.sh script.
+    
 #newline_default lf anycrlf any
 #perltest
 
@@ -476,7 +480,7 @@
 /^\ሴ/utf
     ሴ
 
-"(?s)(.{1,5})"utf
+/(?s)(.{1,5})/utf
     abcdefg
     ab
 
@@ -2220,7 +2224,7 @@
 /[A-`]/i,utf
     abcdefghijklmno
 
-"[\S\V\H]"utf
+/[\S\V\H]/utf
 
 /[^\p{Any}]*+x/utf
     x
diff --git a/testdata/testoutput1 b/testdata/testoutput1
index 470e412..47d42ee 100644
--- a/testdata/testoutput1
+++ b/testdata/testoutput1
@@ -1,6 +1,10 @@
 # This set of tests is for features that are compatible with all versions of
 # Perl >= 5.10, in non-UTF mode. It should run clean for the 8-bit, 16-bit, and
 # 32-bit PCRE libraries, and also using the perltest.sh script.
+
+# WARNING: Use only / as the pattern delimiter. Although pcre2test supports
+# a number of delimiters, all those other than / give problems with the
+# perltest.sh script.
     
 #forbid_utf
 #newline_default lf any anycrlf
@@ -2949,7 +2953,7 @@ No match
     qqq\nabc\nzzz
 No match
 
-"(?>.*/)foo"
+/(?>.*\/)foo/
     /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/and/foo
  0: /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/and/foo
 \= Expect no match     
@@ -6081,14 +6085,16 @@ No match
     A\x20B
  0:  
     
-"(?x)(?-x: \s*#\s*)"
+/(?x)(?-x: \s*#\s*)/
     A # B
  0:  # 
 \= Expect no match
     #  
 No match
+    A s#s B
+No match
 
-"(?x-is)(?:(?-ixs) \s*#\s*) include"
+/(?x-is)(?:(?-ixs) \s*#\s*) include/
     A #include
  0:  #include
 \= Expect no match
@@ -8402,12 +8408,12 @@ No match
  1: <unset>
  2: wxyz
 
-"(?>.*)foo"
+/(?>.*)foo/
 \= Expect no match
     abcdfooxyz
 No match
     
-"(?>.*?)foo"
+/(?>.*?)foo/
     abcdfooxyz
  0: foo
 
@@ -8648,22 +8654,6 @@ No match
     a
 No match
 
-/(?=a\Kb)ab/
-    ab 
- 0: b
-
-/(?!a\Kb)ac/
-    ac 
- 0: ac
-    
-/^abc(?<=b\Kc)d/
-    abcd
- 0: cd
-
-/^abc(?<!b\Kq)d/
-    abcd
- 0: abcd
-
 /A(*PRUNE:A)A+(*SKIP:A)(B|Z) | AC/x,mark
 \= Expect no match
     AAAC
@@ -9128,9 +9118,9 @@ No match
 
 /(\2)(\1)/
 
-"Z*(|d*){216}"
+/Z*(|d*){216}/
 
-"(?1)(?#?'){8}(a)"
+/(?1)(?#?'){8}(a)/
     baaaaaaaaac
  0: aaaaaaaaa
  1: a
@@ -9166,7 +9156,7 @@ No match
  6: 
  7: 
 
-"(?|(\k'Pm')|(?'Pm'))"
+/(?|(\k'Pm')|(?'Pm'))/
     abcd
  0: 
  1: 
@@ -10165,24 +10155,24 @@ No match
     Pack my fox with five dozen liquor jugs.
 No match
 
-"(?<=X(?(DEFINE)(A)))X(*F)"
+/(?<=X(?(DEFINE)(A)))X(*F)/
 \= Expect no match
     AXYZ
 No match
 
-"(?<=X(?(DEFINE)(A)))."
+/(?<=X(?(DEFINE)(A)))./
     AXYZ
  0: Y
 
-"(?<=X(?(DEFINE)(.*))Y)."
+/(?<=X(?(DEFINE)(.*))Y)./
     AXYZ
  0: Z
 
-"(?<=X(?(DEFINE)(Y))(?1))."
+/(?<=X(?(DEFINE)(Y))(?1))./
     AXYZ
  0: Z
 
-"(?(DEFINE)(?<foo>bar))(?<![-a-z0-9])word"
+/(?(DEFINE)(?<foo>bar))(?<![-a-z0-9])word/
     word
  0: word
 
diff --git a/testdata/testoutput2 b/testdata/testoutput2
index c06363a..d0592d3 100644
--- a/testdata/testoutput2
+++ b/testdata/testoutput2
@@ -17624,6 +17624,26 @@ MK: >\x00<
 /(?(VERSION=0.0/
 Failed: error 179 at offset 14: syntax error or number too big in (?(VERSION condition
 
+# Perl has made \K in lookarounds an error. At the moment PCRE2 still accepts.
+
+/(?=a\Kb)ab/
+    ab 
+ 0: b
+
+/(?!a\Kb)ac/
+    ac 
+ 0: ac
+    
+/^abc(?<=b\Kc)d/
+    abcd
+ 0: cd
+
+/^abc(?<!b\Kq)d/
+    abcd
+ 0: abcd
+    
+# --------- 
+
 # End of testinput2
 Error -70: PCRE2_ERROR_BADDATA (unknown error number)
 Error -62: bad serialized data
diff --git a/testdata/testoutput4 b/testdata/testoutput4
index 245a036..f43d940 100644
--- a/testdata/testoutput4
+++ b/testdata/testoutput4
@@ -3,6 +3,10 @@
 # some of the property tests may differ because of different versions of
 # Unicode in use by PCRE2 and Perl.
 
+# WARNING: Use only / as the pattern delimiter. Although pcre2test supports
+# a number of delimiters, all those other than / give problems with the
+# perltest.sh script.
+    
 #newline_default lf anycrlf any
 #perltest
 
@@ -795,7 +799,7 @@ No match
     ሴ
  0: \x{1234}
 
-"(?s)(.{1,5})"utf
+/(?s)(.{1,5})/utf
     abcdefg
  0: abcde
  1: abcde
@@ -3596,7 +3600,7 @@ No match
     abcdefghijklmno
  0: a
 
-"[\S\V\H]"utf
+/[\S\V\H]/utf
 
 /[^\p{Any}]*+x/utf
     x