t4210: detect REG_ILLSEQ dynamically and skip affected tests

7187c7b (t4210: skip i18n tests that don't work on FreeBSD, 2019-11-27)
adds a REG_ILLSEQ prerequisite, and to do that copies the common branch in
test-lib and expands it to include it in a special case for FreeBSD.

Instead; test for it using a previously added extension to test-tool and
use that, together with a function that identifies when regcomp/regexec
will be called with broken patterns to avoid any test that would otherwise
rely on undefined behaviour.

The description of the first test which wasn't accurate has been corrected,
and the test rearranged for clarity, including a helper function that avoids
overly long lines.

Only the affected engines will have their tests suppressed, also including
"fixed" if the PCRE optimization that uses LIBPCRE2 since b65abca
(grep: use PCRE v2 for optimized fixed-string search, 2019-07-01) is not
available.

Helped-by: Eric Sunshine <[email protected]>
Signed-off-by: Carlo Marcelo Arenas Belón <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: carenas

t/t4210-log-i18n.sh

@@ -10,6 +10,13 @@ latin1_e=$(printf '\351')
 # invalid UTF-8
 invalid_e=$(printf '\303\50)') # ")" at end to close opening "("
 
+have_reg_illseq=
+if test_have_prereq GETTEXT_LOCALE &&
+	! LC_ALL=$is_IS_locale test-tool regex --silent $latin1_e
+then
+	have_reg_illseq=1
+fi
+
 test_expect_success 'create commits in different encodings' '
 	test_tick &&
 	cat >msg <<-EOF &&
@@ -51,43 +58,77 @@ test_expect_success !MINGW 'log --grep does not find non-reencoded values (utf8)
 	test_must_be_empty actual
 '
 
-test_expect_success !MINGW 'log --grep does not find non-reencoded values (latin1)' '
+test_expect_success 'log --grep does not find non-reencoded values (latin1)' '
 	git log --encoding=ISO-8859-1 --format=%s --grep=$utf8_e >actual &&
 	test_must_be_empty actual
 '
 
+triggers_undefined_behaviour () {
+	local engine=$1
+
+	case $engine in
+	fixed)
+		if test -n "$have_reg_illseq" &&
+			! test_have_prereq LIBPCRE2
+		then
+			return 0
+		fi
+		;;
+	basic|extended)
+		if test -n "$have_reg_illseq"
+		then
+			return 0
+		fi
+		;;
+	esac
+	return 1
+}
+
+mismatched_git_log () {
+	local pattern=$1
+
+	LC_ALL=$is_IS_locale git log --encoding=ISO-8859-1 --format=%s \
+		--grep=$pattern
+}
+
 for engine in fixed basic extended perl
 do
 	prereq=
 	if test $engine = "perl"
 	then
-		prereq="PCRE"
-	else
-		prereq=""
+		prereq=PCRE
 	fi
 	force_regex=
 	if test $engine != "fixed"
 	then
-	    force_regex=.*
+		force_regex='.*'
 	fi
-	test_expect_success !MINGW,!REGEX_ILLSEQ,GETTEXT_LOCALE,$prereq "-c grep.patternType=$engine log --grep does not find non-reencoded values (latin1 + locale)" "
-		cat >expect <<-\EOF &&
-		latin1
-		utf8
-		EOF
-		LC_ALL=\"$is_IS_locale\" git -c grep.patternType=$engine log --encoding=ISO-8859-1 --format=%s --grep=\"$force_regex$latin1_e\" >actual &&
-		test_cmp expect actual
-	"
 
-	test_expect_success !MINGW,GETTEXT_LOCALE,$prereq "-c grep.patternType=$engine log --grep does not find non-reencoded values (latin1 + locale)" "
-		LC_ALL=\"$is_IS_locale\" git -c grep.patternType=$engine log --encoding=ISO-8859-1 --format=%s --grep=\"$force_regex$utf8_e\" >actual &&
-		test_must_be_empty actual
+	test_expect_success $prereq "config grep.patternType=$engine" "
+		git config grep.patternType $engine
 	"
 
-	test_expect_success !MINGW,!REGEX_ILLSEQ,GETTEXT_LOCALE,$prereq "-c grep.patternType=$engine log --grep does not die on invalid UTF-8 value (latin1 + locale + invalid needle)" "
-		LC_ALL=\"$is_IS_locale\" git -c grep.patternType=$engine log --encoding=ISO-8859-1 --format=%s --grep=\"$force_regex$invalid_e\" >actual &&
+	test_expect_success GETTEXT_LOCALE,$prereq "log --grep does not find non-reencoded values (latin1 + locale)" "
+		mismatched_git_log '$force_regex$utf8_e' >actual &&
 		test_must_be_empty actual
 	"
+
+	if ! triggers_undefined_behaviour $engine
+	then
+		test_expect_success !MINGW,GETTEXT_LOCALE,$prereq "log --grep searches in log output encoding (latin1 + locale)" "
+			cat >expect <<-\EOF &&
+			latin1
+			utf8
+			EOF
+			mismatched_git_log '$force_regex$latin1_e' >actual &&
+			test_cmp expect actual
+		"
+
+		test_expect_success GETTEXT_LOCALE,$prereq "log --grep does not die on invalid UTF-8 value (latin1 + locale + invalid needle)" "
+			mismatched_git_log '$force_regex$invalid_e' >actual &&
+			test_must_be_empty actual
+		"
+	fi
 done
 
 test_done

t/test-lib.sh

@@ -1454,12 +1454,6 @@ case $uname_s in
 	test_set_prereq SED_STRIPS_CR
 	test_set_prereq GREP_STRIPS_CR
 	;;
-FreeBSD)
-	test_set_prereq REGEX_ILLSEQ
-	test_set_prereq POSIXPERM
-	test_set_prereq BSLASHPSPEC
-	test_set_prereq EXECKEEPSPID
-	;;
 *)
 	test_set_prereq POSIXPERM
 	test_set_prereq BSLASHPSPEC