Merge branch 'cb/t4210-illseq-auto-detect'

As FreeBSD is not the only platform whose regexp library reports
a REG_ILLSEQ error when fed invalid UTF-8, add logic to detect that
automatically and skip the affected tests.

* cb/t4210-illseq-auto-detect:
  t4210: detect REG_ILLSEQ dynamically and skip affected tests
  t/helper: teach test-regex to report pattern errors (like REG_ILLSEQ)

t/helper/test-regex.c

@@ -1,5 +1,4 @@
 #include "test-tool.h"
-#include "git-compat-util.h"
 #include "gettext.h"
 
 struct reg_flag {
@@ -8,12 +7,13 @@ struct reg_flag {
 };
 
 static struct reg_flag reg_flags[] = {
-	{ "EXTENDED",	 REG_EXTENDED	},
+	{ "EXTENDED",	REG_EXTENDED	},
-	{ "NEWLINE",	 REG_NEWLINE	},
+	{ "NEWLINE",	REG_NEWLINE	},
-	{ "ICASE",	 REG_ICASE	},
+	{ "ICASE",	REG_ICASE	},
-	{ "NOTBOL",	 REG_NOTBOL	},
+	{ "NOTBOL",	REG_NOTBOL	},
+	{ "NOTEOL",	REG_NOTEOL	},
 #ifdef REG_STARTEND
-	{ "STARTEND",	 REG_STARTEND	},
+	{ "STARTEND",	REG_STARTEND	},
 #endif
 	{ NULL, 0 }
 };
@@ -41,36 +41,74 @@ 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>]");
 
 	argv++;
-	pat = *argv++;
+	argc--;
-	str = *argv++;
+
-	while (*argv) {
+	if (!argc)
-		struct reg_flag *rf;
+		goto usage;
-		for (rf = reg_flags; rf->name; rf++)
+
-			if (!strcmp(*argv, rf->name)) {
+	if (!strcmp(*argv, "--bug")) {
-				flags |= rf->flag;
+		if (argc == 1)
-				break;
+			return test_regex_bug();
-			}
+		else
-		if (!rf->name)
+			goto usage;
-			die("do not recognize %s", *argv);
+	}
+	if (!strcmp(*argv, "--silent")) {
+		silent = 1;
 		argv++;
+		argc--;
+	}
+	if (!argc)
+		goto usage;
+
+	pat = *argv++;
+	if (argc == 1)
+		str = NULL;
+	else {
+		str = *argv++;
+		while (*argv) {
+			struct reg_flag *rf;
+			for (rf = reg_flags; rf->name; rf++)
+				if (!strcmp(*argv, rf->name)) {
+					flags |= rf->flag;
+					break;
+				}
+			if (!rf->name)
+				die("do not recognize flag %s", *argv);
+			argv++;
+		}
 	}
 	git_setup_gettext();
 
-	if (regcomp(&r, pat, flags))
+	ret = regcomp(&r, pat, flags);
-		die("failed regcomp() for pattern '%s'", pat);
+	if (ret) {
-	if (regexec(&r, str, 1, m, 0))
+		if (silent)
-		return 1;
+			return ret;
+
+		regerror(ret, &r, errbuf, sizeof(errbuf));
+		die("failed regcomp() for pattern '%s' (%s)", pat, errbuf);
+	}
+	if (!str)
+		return 0;
+
+	ret = regexec(&r, str, 1, m, 0);
+	if (ret) {
+		if (silent || ret == REG_NOMATCH)
+			return ret;
+
+		regerror(ret, &r, errbuf, sizeof(errbuf));
+		die("failed regexec() for subject '%s' (%s)", str, errbuf);
+	}
 
 	return 0;
+usage:
+	usage("\ttest-tool regex --bug\n"
+	      "\ttest-tool regex [--silent] <pattern>\n"
+	      "\ttest-tool regex [--silent] <pattern> <string> [<options>]");
+	return -1;
 }

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"
+		prereq=PCRE
-	else
-		prereq=""
 	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 &&
+	test_expect_success $prereq "config grep.patternType=$engine" "
-		latin1
+		git config grep.patternType $engine
-		utf8
-		EOF
-		LC_ALL=\"$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)" "
+	test_expect_success GETTEXT_LOCALE,$prereq "log --grep does not find non-reencoded values (latin1 + locale)" "
-		LC_ALL=\"$is_IS_locale\" git -c grep.patternType=$engine log --encoding=ISO-8859-1 --format=%s --grep=\"$force_regex$utf8_e\" >actual &&
+		mismatched_git_log '$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)" "
+	if ! triggers_undefined_behaviour $engine
-		LC_ALL=\"$is_IS_locale\" git -c grep.patternType=$engine log --encoding=ISO-8859-1 --format=%s --grep=\"$force_regex$invalid_e\" >actual &&
+	then
-		test_must_be_empty actual
+		test_expect_success !MINGW,GETTEXT_LOCALE,$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

@@ -1489,12 +1489,6 @@ 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