Merge branch 'ab/grep-preparatory-cleanup' into sb/submodule-blanket-recursive

* ab/grep-preparatory-cleanup: (31 commits)
  grep: assert that threading is enabled when calling grep_{lock,unlock}
  grep: given --threads with NO_PTHREADS=YesPlease, warn
  pack-objects: fix buggy warning about threads
  pack-objects & index-pack: add test for --threads warning
  test-lib: add a PTHREADS prerequisite
  grep: move is_fixed() earlier to avoid forward declaration
  grep: change internal *pcre* variable & function names to be *pcre1*
  grep: change the internal PCRE macro names to be PCRE1
  grep: factor test for \0 in grep patterns into a function
  grep: remove redundant regflags assignments
  grep: catch a missing enum in switch statement
  perf: add a comparison test of log --grep regex engines with -F
  perf: add a comparison test of log --grep regex engines
  perf: add a comparison test of grep regex engines with -F
  perf: add a comparison test of grep regex engines
  perf: emit progress output when unpacking & building
  perf: add a GIT_PERF_MAKE_COMMAND for when *_MAKE_OPTS won't do
  grep: add tests to fix blind spots with \0 patterns
  grep: prepare for testing binary regexes containing rx metacharacters
  grep: add a test helper function for less verbose -f \0 tests
  ...

1 files changed, 103 insertions, 32 deletions

diff --git a/t/t7008-grep-binary.sh b/t/t7008-grep-binary.sh
index 9c9c378119..615e7e0162 100755
--- a/t/t7008-grep-binary.sh
+++ b/t/t7008-grep-binary.sh
@@ -4,8 +4,43 @@ 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 'binaryQfile' | q_to_nul >a &&
+	echo 'binaryQfileQm[*]cQ*æQð' | q_to_nul >a &&
 	git add a &&
 	git commit -m.
 "
@@ -69,35 +104,71 @@ test_expect_failure 'git grep .fi a' '
 	git grep .fi a
 '
 
-test_expect_success 'git grep -F y<NUL>f a' "
-	printf 'yQf' | q_to_nul >f &&
-	git grep -f f -F a
-"
-
-test_expect_success 'git grep -F y<NUL>x a' "
-	printf 'yQx' | q_to_nul >f &&
-	test_must_fail git grep -f f -F a
-"
-
-test_expect_success 'git grep -Fi Y<NUL>f a' "
-	printf 'YQf' | q_to_nul >f &&
-	git grep -f f -Fi a
-"
-
-test_expect_success 'git grep -Fi Y<NUL>x a' "
-	printf 'YQx' | q_to_nul >f &&
-	test_must_fail git grep -f f -Fi a
-"
-
-test_expect_success 'git grep y<NUL>f a' "
-	printf 'yQf' | q_to_nul >f &&
-	git grep -f f a
-"
-
-test_expect_success 'git grep y<NUL>x a' "
-	printf 'yQx' | q_to_nul >f &&
-	test_must_fail git grep -f f 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 &&
@@ -162,7 +233,7 @@ test_expect_success 'grep does not honor textconv' '
 '
 
 test_expect_success 'grep --textconv honors textconv' '
-	echo "a:binaryQfile" >expect &&
+	echo "a:binaryQfileQm[*]cQ*æQð" >expect &&
 	git grep --textconv Qfile >actual &&
 	test_cmp expect actual
 '
@@ -172,7 +243,7 @@ test_expect_success 'grep --no-textconv does not honor textconv' '
 '
 
 test_expect_success 'grep --textconv blob honors textconv' '
-	echo "HEAD:a:binaryQfile" >expect &&
+	echo "HEAD:a:binaryQfileQm[*]cQ*æQð" >expect &&
 	git grep --textconv Qfile HEAD:a >actual &&
 	test_cmp expect actual
 '