grep tests: move binary pattern tests into their own file

Move the tests for "-f <file>" where "<file>" contains a NUL byte
pattern into their own file. I added most of these tests in
966be95549 ("grep: add tests to fix blind spots with \0 patterns",
2017-05-20).

Whether a regex engine supports matching binary content is very
different from whether it matches binary patterns. Since
2f8952250a ("regex: add regexec_buf() that can work on a non
NUL-terminated string", 2016-09-21) we've required REG_STARTEND of our
regex engines so we can match binary content, but only the PCRE v2
engine can sensibly match binary patterns.

Since 9eceddeec6 ("Use kwset in grep", 2011-08-21) we've been punting
patterns containing NUL-byte and considering them fixed, except in
cases where "--ignore-case" is provided and they're non-ASCII, see
5c1ebcca4d ("grep/icase: avoid kwsset on literal non-ascii strings",
2016-06-25). Subsequent commits will change this behavior.

Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

2 files changed, 114 insertions, 101 deletions

diff --git a/t/t7815-grep-binary.sh b/t/t7815-grep-binary.sh
index 2d87c49b75..90ebb64f46 100755
--- a/t/t7815-grep-binary.sh
+++ b/t/t7815-grep-binary.sh
@@ -4,41 +4,6 @@ test_description='git grep in binary files'
 
 . ./test-lib.sh
 
-nul_match () {
-	matches=$1
-	flags=$2
-	pattern=$3
-	pattern_human=$(echo "$pattern" | sed 's/Q/<NUL>/g')
-
-	if test "$matches" = 1
-	then
-		test_expect_success "git grep -f f $flags '$pattern_human' a" "
-			printf '$pattern' | q_to_nul >f &&
-			git grep -f f $flags a
-		"
-	elif test "$matches" = 0
-	then
-		test_expect_success "git grep -f f $flags '$pattern_human' a" "
-			printf '$pattern' | q_to_nul >f &&
-			test_must_fail git grep -f f $flags a
-		"
-	elif test "$matches" = T1
-	then
-		test_expect_failure "git grep -f f $flags '$pattern_human' a" "
-			printf '$pattern' | q_to_nul >f &&
-			git grep -f f $flags a
-		"
-	elif test "$matches" = T0
-	then
-		test_expect_failure "git grep -f f $flags '$pattern_human' a" "
-			printf '$pattern' | q_to_nul >f &&
-			test_must_fail git grep -f f $flags a
-		"
-	else
-		test_expect_success "PANIC: Test framework error. Unknown matches value $matches" 'false'
-	fi
-}
-
 test_expect_success 'setup' "
 	echo 'binaryQfileQm[*]cQ*æQð' | q_to_nul >a &&
 	git add a &&
@@ -102,72 +67,6 @@ test_expect_failure 'git grep .fi a' '
 	git grep .fi a
 '
 
-nul_match 1 '-F' 'yQf'
-nul_match 0 '-F' 'yQx'
-nul_match 1 '-Fi' 'YQf'
-nul_match 0 '-Fi' 'YQx'
-nul_match 1 '' 'yQf'
-nul_match 0 '' 'yQx'
-nul_match 1 '' 'æQð'
-nul_match 1 '-F' 'eQm[*]c'
-nul_match 1 '-Fi' 'EQM[*]C'
-
-# Regex patterns that would match but shouldn't with -F
-nul_match 0 '-F' 'yQ[f]'
-nul_match 0 '-F' '[y]Qf'
-nul_match 0 '-Fi' 'YQ[F]'
-nul_match 0 '-Fi' '[Y]QF'
-nul_match 0 '-F' 'æQ[ð]'
-nul_match 0 '-F' '[æ]Qð'
-nul_match 0 '-Fi' 'ÆQ[Ð]'
-nul_match 0 '-Fi' '[Æ]QÐ'
-
-# kwset is disabled on -i & non-ASCII. No way to match non-ASCII \0
-# patterns case-insensitively.
-nul_match T1 '-i' 'ÆQÐ'
-
-# \0 implicitly disables regexes. This is an undocumented internal
-# limitation.
-nul_match T1 '' 'yQ[f]'
-nul_match T1 '' '[y]Qf'
-nul_match T1 '-i' 'YQ[F]'
-nul_match T1 '-i' '[Y]Qf'
-nul_match T1 '' 'æQ[ð]'
-nul_match T1 '' '[æ]Qð'
-nul_match T1 '-i' 'ÆQ[Ð]'
-
-# ... because of \0 implicitly disabling regexes regexes that
-# should/shouldn't match don't do the right thing.
-nul_match T1 '' 'eQm.*cQ'
-nul_match T1 '-i' 'EQM.*cQ'
-nul_match T0 '' 'eQm[*]c'
-nul_match T0 '-i' 'EQM[*]C'
-
-# Due to the REG_STARTEND extension when kwset() is disabled on -i &
-# non-ASCII the string will be matched in its entirety, but the
-# pattern will be cut off at the first \0.
-nul_match 0 '-i' 'NOMATCHQð'
-nul_match T0 '-i' '[Æ]QNOMATCH'
-nul_match T0 '-i' '[æ]QNOMATCH'
-# Matches, but for the wrong reasons, just stops at [æ]
-nul_match 1 '-i' '[Æ]Qð'
-nul_match 1 '-i' '[æ]Qð'
-
-# Ensure that the matcher doesn't regress to something that stops at
-# \0
-nul_match 0 '-F' 'yQ[f]'
-nul_match 0 '-Fi' 'YQ[F]'
-nul_match 0 '' 'yQNOMATCH'
-nul_match 0 '' 'QNOMATCH'
-nul_match 0 '-i' 'YQNOMATCH'
-nul_match 0 '-i' 'QNOMATCH'
-nul_match 0 '-F' 'æQ[ð]'
-nul_match 0 '-Fi' 'ÆQ[Ð]'
-nul_match 0 '' 'yQNÓMATCH'
-nul_match 0 '' 'QNÓMATCH'
-nul_match 0 '-i' 'YQNÓMATCH'
-nul_match 0 '-i' 'QNÓMATCH'
-
 test_expect_success 'grep respects binary diff attribute' '
 	echo text >t &&
 	git add t &&
diff --git a/t/t7816-grep-binary-pattern.sh b/t/t7816-grep-binary-pattern.sh
new file mode 100755
index 0000000000..4060dbd679
--- /dev/null
+++ b/t/t7816-grep-binary-pattern.sh
@@ -0,0 +1,114 @@
+#!/bin/sh
+
+test_description='git grep with a binary pattern files'
+
+. ./test-lib.sh
+
+nul_match () {
+	matches=$1
+	flags=$2
+	pattern=$3
+	pattern_human=$(echo "$pattern" | sed 's/Q/<NUL>/g')
+
+	if test "$matches" = 1
+	then
+		test_expect_success "git grep -f f $flags '$pattern_human' a" "
+			printf '$pattern' | q_to_nul >f &&
+			git grep -f f $flags a
+		"
+	elif test "$matches" = 0
+	then
+		test_expect_success "git grep -f f $flags '$pattern_human' a" "
+			printf '$pattern' | q_to_nul >f &&
+			test_must_fail git grep -f f $flags a
+		"
+	elif test "$matches" = T1
+	then
+		test_expect_failure "git grep -f f $flags '$pattern_human' a" "
+			printf '$pattern' | q_to_nul >f &&
+			git grep -f f $flags a
+		"
+	elif test "$matches" = T0
+	then
+		test_expect_failure "git grep -f f $flags '$pattern_human' a" "
+			printf '$pattern' | q_to_nul >f &&
+			test_must_fail git grep -f f $flags a
+		"
+	else
+		test_expect_success "PANIC: Test framework error. Unknown matches value $matches" 'false'
+	fi
+}
+
+test_expect_success 'setup' "
+	echo 'binaryQfileQm[*]cQ*æQð' | q_to_nul >a &&
+	git add a &&
+	git commit -m.
+"
+
+nul_match 1 '-F' 'yQf'
+nul_match 0 '-F' 'yQx'
+nul_match 1 '-Fi' 'YQf'
+nul_match 0 '-Fi' 'YQx'
+nul_match 1 '' 'yQf'
+nul_match 0 '' 'yQx'
+nul_match 1 '' 'æQð'
+nul_match 1 '-F' 'eQm[*]c'
+nul_match 1 '-Fi' 'EQM[*]C'
+
+# Regex patterns that would match but shouldn't with -F
+nul_match 0 '-F' 'yQ[f]'
+nul_match 0 '-F' '[y]Qf'
+nul_match 0 '-Fi' 'YQ[F]'
+nul_match 0 '-Fi' '[Y]QF'
+nul_match 0 '-F' 'æQ[ð]'
+nul_match 0 '-F' '[æ]Qð'
+nul_match 0 '-Fi' 'ÆQ[Ð]'
+nul_match 0 '-Fi' '[Æ]QÐ'
+
+# kwset is disabled on -i & non-ASCII. No way to match non-ASCII \0
+# patterns case-insensitively.
+nul_match T1 '-i' 'ÆQÐ'
+
+# \0 implicitly disables regexes. This is an undocumented internal
+# limitation.
+nul_match T1 '' 'yQ[f]'
+nul_match T1 '' '[y]Qf'
+nul_match T1 '-i' 'YQ[F]'
+nul_match T1 '-i' '[Y]Qf'
+nul_match T1 '' 'æQ[ð]'
+nul_match T1 '' '[æ]Qð'
+nul_match T1 '-i' 'ÆQ[Ð]'
+
+# ... because of \0 implicitly disabling regexes regexes that
+# should/shouldn't match don't do the right thing.
+nul_match T1 '' 'eQm.*cQ'
+nul_match T1 '-i' 'EQM.*cQ'
+nul_match T0 '' 'eQm[*]c'
+nul_match T0 '-i' 'EQM[*]C'
+
+# Due to the REG_STARTEND extension when kwset() is disabled on -i &
+# non-ASCII the string will be matched in its entirety, but the
+# pattern will be cut off at the first \0.
+nul_match 0 '-i' 'NOMATCHQð'
+nul_match T0 '-i' '[Æ]QNOMATCH'
+nul_match T0 '-i' '[æ]QNOMATCH'
+# Matches, but for the wrong reasons, just stops at [æ]
+nul_match 1 '-i' '[Æ]Qð'
+nul_match 1 '-i' '[æ]Qð'
+
+# Ensure that the matcher doesn't regress to something that stops at
+# \0
+nul_match 0 '-F' 'yQ[f]'
+nul_match 0 '-Fi' 'YQ[F]'
+nul_match 0 '' 'yQNOMATCH'
+nul_match 0 '' 'QNOMATCH'
+nul_match 0 '-i' 'YQNOMATCH'
+nul_match 0 '-i' 'QNOMATCH'
+nul_match 0 '-F' 'æQ[ð]'
+nul_match 0 '-Fi' 'ÆQ[Ð]'
+nul_match 0 '' 'yQNÓMATCH'
+nul_match 0 '' 'QNÓMATCH'
+nul_match 0 '-i' 'YQNÓMATCH'
+nul_match 0 '-i' 'QNÓMATCH'
+
+test_done