[PATCH v2] t4210: detect REG_ILLSEQ dynamically

["Carlo Marcelo Arenas Belón" <carenas@gmail.com>]

7187c7bbb8 (t4210: skip i18n tests that don't work on FreeBSD, 2019-11-27)
adds a REG_ILLSEQ prerequisite to avoid failures from the tests added with
4e2443b181 (log tests: test regex backends in "--encode=<enc>" tests,
2019-06-28), but hardcodes it to be only enabled for FreeBSD.

Instead of hardcoding the affected platform, add a test using test-tool to
make sure it can be dynamically detected in other affected systems (like
DragonFlyBSD or macOS), and while at it, enhance the tool so it can report
better on the cause of failure and be silent when needed.

To minimize changes, it is assumed the regcomp error is of the right type
since we control the only caller, and is also assumed to affect both basic
and extended syntax (only extended is tested, but both behave the same in
all three affected platforms).

The description of the first test which wasn't accurate has been corrected,
and unlike the original fix from 7187c7bbb8, that created a special case
for FreeBSD by adding REG_ILLSEQ to the common set in test-lib, this does
not need changes to test-lib and therefore had those reverted.

Only the affected engines will have their tests suppressed, which include
"fixed" if the PCRE optimization that uses LIBPCRE2 since b65abcafc7
(grep: use PCRE v2 for optimized fixed-string search, 2019-07-01) is not
available.

Helped-by: Eric Sunshine <sunshine@sunshineco.com>
Signed-off-by: Carlo Marcelo Arenas Belón <carenas@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
v2:
- address all suggestions from Eric
- reorder tests and add a helper functions (probably overly verbose) to
  clarify when the tests will be skipped (no prereq is used)

 t/helper/test-regex.c | 19 +++++++++---
 t/t4210-log-i18n.sh   | 70 ++++++++++++++++++++++++++++++++-----------
 t/test-lib.sh         |  6 ----
 3 files changed, 68 insertions(+), 27 deletions(-)

diff --git a/t/helper/test-regex.c b/t/helper/test-regex.c
index 10284cc56f..7a8ddce45b 100644
--- a/t/helper/test-regex.c
+++ b/t/helper/test-regex.c
@@ -41,16 +41,21 @@ int cmd__regex(int argc, const char **argv)
 {
 	const char *pat;
 	const char *str;
-	int flags = 0;
+	int ret, silent = 0, flags = 0;
 	regex_t r;
 	regmatch_t m[1];
+	char errbuf[64];
 
 	if (argc == 2 && !strcmp(argv[1], "--bug"))
 		return test_regex_bug();
 	else if (argc < 3)
 		usage("test-tool regex --bug\n"
-		      "test-tool regex <pattern> <string> [<options>]");
+		      "test-tool regex [--silent] <pattern> <string> [<options>]");
 
+	if (!strcmp(argv[1], "--silent")) {
+		silent = 1;
+		argv++;
+	}
 	argv++;
 	pat = *argv++;
 	str = *argv++;
@@ -67,8 +72,14 @@ int cmd__regex(int argc, const char **argv)
 	}
 	git_setup_gettext();
 
-	if (regcomp(&r, pat, flags))
-		die("failed regcomp() for pattern '%s'", pat);
+	ret = regcomp(&r, pat, flags);
+	if (ret) {
+		if (silent)
+			return 1;
+
+		regerror(ret, &r, errbuf, sizeof(errbuf));
+		die("failed regcomp() for pattern '%s' (%s)", pat, errbuf);
+	}
 	if (regexec(&r, str, 1, m, 0))
 		return 1;
 
diff --git a/t/t4210-log-i18n.sh b/t/t4210-log-i18n.sh
index c3792081e6..a89f456817 100755
--- a/t/t4210-log-i18n.sh
+++ b/t/t4210-log-i18n.sh
@@ -10,6 +10,12 @@ latin1_e=$(printf '\351')
 # invalid UTF-8
 invalid_e=$(printf '\303\50)') # ")" at end to close opening "("
 
+if test_have_prereq GETTEXT_LOCALE &&
+	! LC_ALL=$is_IS_locale test-tool regex --silent $latin1_e $latin1_e EXTENDED
+then
+	have_reg_illseq=1
+fi
+
 test_expect_success 'create commits in different encodings' '
 	test_tick &&
 	cat >msg <<-EOF &&
@@ -56,38 +62,68 @@ test_expect_success !MINGW 'log --grep does not find non-reencoded values (latin
 	test_must_be_empty actual
 '
 
+trigger_undefined_behaviour()
+{
+	local engine=$1
+
+	case $engine in
+	fixed)
+		if test -n "$have_reg_illseq" &&
+			! test_have_prereq LIBPCRE2
+		then
+			return 0
+		else
+			return 1
+		fi
+		;;
+	basic|extended)
+		if test -n "$have_reg_illseq"
+		then
+			return 0
+		else
+			return 1
+		fi
+		;;
+	perl)
+		return 1
+		;;
+	esac
+}
+
 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 &&
+		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 !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_must_be_empty actual
-	"
+	if ! trigger_undefined_behaviour $engine
+	then
+		test_expect_success !MINGW,GETTEXT_LOCALE,$prereq "-c grep.patternType=$engine log --grep searches in log output encoding (latin1 + locale)" "
+			cat >expect <<-\EOF &&
+			latin1
+			utf8
+			EOF
+			LC_ALL=$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=$engine log --grep does not die on invalid UTF-8 value (latin1 + locale + invalid needle)" "
+			LC_ALL=$is_IS_locale git -c grep.patternType=$engine log --encoding=ISO-8859-1 --format=%s --grep=\"$force_regex$invalid_e\" >actual &&
+			test_must_be_empty actual
+		"
+	fi
 done
 
 test_done
diff --git a/t/test-lib.sh b/t/test-lib.sh
index 0ea1e5a05e..81473fea1d 100644
--- a/t/test-lib.sh
+++ b/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
-- 
2.26.2.812.g046d49d455