From bade53dd5d50ea0a4f2a2f62ebe2607dd290fcc7 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Petr=20P=C3=ADsa=C5=99?= <ppisar@redhat.com>
Date: Mon, 14 Sep 2020 14:12:34 +0200
Subject: [PATCH] Fix escaping test data

---
 ...n-tests-1-and-4-for-correct-Perl-beh.patch | 412 ++++++++++++++++++
 pcre2.spec                                    |   8 +-
 2 files changed, 419 insertions(+), 1 deletion(-)
 create mode 100644 pcre2-10.35-Fix-delimiters-in-tests-1-and-4-for-correct-Perl-beh.patch

diff --git a/pcre2-10.35-Fix-delimiters-in-tests-1-and-4-for-correct-Perl-beh.patch b/pcre2-10.35-Fix-delimiters-in-tests-1-and-4-for-correct-Perl-beh.patch
new file mode 100644
index 0000000..e85b066
--- /dev/null
+++ b/pcre2-10.35-Fix-delimiters-in-tests-1-and-4-for-correct-Perl-beh.patch
@@ -0,0 +1,412 @@
+From 0edcbc5e42409ea801908af0917ae11eb70a1435 Mon Sep 17 00:00:00 2001
+From: ph10 <ph10@6239d852-aaf2-0410-a92c-79f79f948069>
+Date: Sun, 13 Sep 2020 15:56:32 +0000
+Subject: [PATCH] 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).
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+git-svn-id: svn://vcs.exim.org/pcre2/code/trunk@1269 6239d852-aaf2-0410-a92c-79f79f948069
+Signed-off-by: Petr Písař <ppisar@redhat.com>
+---
+ perltest.sh          |  3 +++
+ testdata/testinput1  | 43 +++++++++++++++++----------------------
+ testdata/testinput2  | 16 +++++++++++++++
+ testdata/testinput4  |  8 ++++++--
+ testdata/testoutput1 | 48 ++++++++++++++++++--------------------------
+ testdata/testoutput2 | 20 ++++++++++++++++++
+ testdata/testoutput4 |  8 ++++++--
+
+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
+-- 
+2.25.4
+
diff --git a/pcre2.spec b/pcre2.spec
index 48768d9..2ea5125 100644
--- a/pcre2.spec
+++ b/pcre2.spec
@@ -9,7 +9,7 @@
 #%%global rcversion RC1
 Name:       pcre2
 Version:    10.35
-Release:    %{?rcversion:0.}4%{?rcversion:.%rcversion}%{?dist}.1
+Release:    %{?rcversion:0.}5%{?rcversion:.%rcversion}%{?dist}
 %global     myversion %{version}%{?rcversion:-%rcversion}
 Summary:    Perl-compatible regular expression library
 # the library:                          BSD with exceptions
@@ -67,6 +67,8 @@ Patch4:     pcre2-10.35-Fix-read-overflow-for-invalid-VERSION-test-with-one-.pat
 # Fix an early fail optimization with character ranges and a buffer overread
 # in JIT, upstream bug #2621, in upstream after 10.35
 Patch5:     pcre2-10.35-Fix-an-early-fail-optimization-issue-and-a-buffer-ov.patch
+# Fix escaping test data, upstream bug #2641, in upstream after 10.35
+Patch6:     pcre2-10.35-Fix-delimiters-in-tests-1-and-4-for-correct-Perl-beh.patch
 BuildRequires:  autoconf
 BuildRequires:  automake
 BuildRequires:  coreutils
@@ -163,6 +165,7 @@ Utilities demonstrating PCRE2 capabilities like pcre2grep or pcre2test.
 %patch3 -p1
 %patch4 -p1
 %patch5 -p1
+%patch6 -p1
 # Because of multilib patch
 libtoolize --copy --force
 autoreconf -vif
@@ -276,6 +279,9 @@ make %{?_smp_mflags} check VERBOSE=yes
 %{_mandir}/man1/pcre2test.*
 
 %changelog
+* Mon Sep 14 2020 Petr Pisar <ppisar@redhat.com> - 10.35-5
+- Fix escaping test data (upstream bug #2641)
+
 * Tue Jul 28 2020 Fedora Release Engineering <releng@fedoraproject.org> - 10.35-4.1
 - Rebuilt for https://fedoraproject.org/wiki/Fedora_33_Mass_Rebuild