tests: replace mingw_test_cmp with a helper in C

This helper is slightly more performant than the script with MSYS2's
Bash. And a lot more readable.

To accommodate t1050, which wants to compare files weighing in with 3MB
(falling outside of t1050's malloc limit of 1.5MB), we simply lift the
allocation limit by setting the environment variable GIT_ALLOC_LIMIT to
zero when calling the helper.

Signed-off-by: Johannes Schindelin <[email protected]>

Author: dscho

Makefile

@@ -693,6 +693,7 @@ PROGRAMS += $(patsubst %.o,git-%$X,$(PROGRAM_OBJS))
 TEST_BUILTINS_OBJS += test-advise.o
 TEST_BUILTINS_OBJS += test-bloom.o
 TEST_BUILTINS_OBJS += test-chmtime.o
+TEST_BUILTINS_OBJS += test-cmp.o
 TEST_BUILTINS_OBJS += test-config.o
 TEST_BUILTINS_OBJS += test-ctype.o
 TEST_BUILTINS_OBJS += test-date.o

t/helper/test-cmp.c

@@ -0,0 +1,73 @@
+#include "test-tool.h"
+#include "git-compat-util.h"
+#include "strbuf.h"
+#include "gettext.h"
+#include "parse-options.h"
+#include "run-command.h"
+
+#ifdef WIN32
+#define NO_SUCH_DIR "\\\\.\\GLOBALROOT\\invalid"
+#else
+#define NO_SUCH_DIR "/dev/null"
+#endif
+
+static int run_diff(const char *path1, const char *path2)
+{
+	const char *argv[] = {
+		"diff", "--no-index", NULL, NULL, NULL
+	};
+	const char *env[] = {
+		"GIT_PAGER=cat",
+		"GIT_DIR=" NO_SUCH_DIR,
+		"HOME=" NO_SUCH_DIR,
+		NULL
+	};
+
+	argv[2] = path1;
+	argv[3] = path2;
+	return run_command_v_opt_cd_env(argv,
+					RUN_COMMAND_NO_STDIN | RUN_GIT_CMD,
+					NULL, env);
+}
+
+int cmd__cmp(int argc, const char **argv)
+{
+	FILE *f0, *f1;
+	struct strbuf b0 = STRBUF_INIT, b1 = STRBUF_INIT;
+
+	if (argc != 3)
+		die("Require exactly 2 arguments, got %d", argc);
+
+	if (!(f0 = !strcmp(argv[1], "-") ? stdin : fopen(argv[1], "r")))
+		return error_errno("could not open '%s'", argv[1]);
+	if (!(f1 = !strcmp(argv[2], "-") ? stdin : fopen(argv[2], "r"))) {
+		fclose(f0);
+		return error_errno("could not open '%s'", argv[2]);
+	}
+
+	for (;;) {
+		int r0 = strbuf_getline(&b0, f0);
+		int r1 = strbuf_getline(&b1, f1);
+
+		if (r0 == EOF) {
+			fclose(f0);
+			fclose(f1);
+			strbuf_release(&b0);
+			strbuf_release(&b1);
+			if (r1 == EOF)
+				return 0;
+cmp_failed:
+			if (!run_diff(argv[1], argv[2]))
+				die("Huh? 'diff --no-index %s %s' succeeded",
+				    argv[1], argv[2]);
+			return 1;
+		}
+		if (r1 == EOF || strbuf_cmp(&b0, &b1)) {
+			fclose(f0);
+			fclose(f1);
+			strbuf_release(&b0);
+			strbuf_release(&b1);
+			goto cmp_failed;
+		}
+	}
+}

t/helper/test-tool.c

@@ -17,6 +17,7 @@ static struct test_cmd cmds[] = {
 	{ "advise", cmd__advise_if_enabled },
 	{ "bloom", cmd__bloom },
 	{ "chmtime", cmd__chmtime },
+	{ "cmp", cmd__cmp },
 	{ "config", cmd__config },
 	{ "ctype", cmd__ctype },
 	{ "date", cmd__date },

t/helper/test-tool.h

@@ -7,6 +7,7 @@
 int cmd__advise_if_enabled(int argc, const char **argv);
 int cmd__bloom(int argc, const char **argv);
 int cmd__chmtime(int argc, const char **argv);
+int cmd__cmp(int argc, const char **argv);
 int cmd__config(int argc, const char **argv);
 int cmd__ctype(int argc, const char **argv);
 int cmd__date(int argc, const char **argv);

t/test-lib-functions.sh

@@ -952,13 +952,7 @@ test_expect_code () {
 # - not all diff versions understand "-u"
 
 test_cmp() {
-	test $# -eq 2 || BUG "test_cmp requires two arguments"
-	if ! eval "$GIT_TEST_CMP" '"$@"'
-	then
-		test "x$1" = x- || test -e "$1" || BUG "test_cmp '$1' missing"
-		test "x$2" = x- || test -e "$2" || BUG "test_cmp '$2' missing"
-		return 1
-	fi
+	GIT_ALLOC_LIMIT=0 eval "$GIT_TEST_CMP" '"$@"'
 }
 
 # Check that the given config key has the expected value.
@@ -1289,72 +1283,6 @@ test_skip_or_die () {
 	error "$2"
 }
 
-# The following mingw_* functions obey POSIX shell syntax, but are actually
-# bash scripts, and are meant to be used only with bash on Windows.
-
-# A test_cmp function that treats LF and CRLF equal and avoids to fork
-# diff when possible.
-mingw_test_cmp () {
-	# Read text into shell variables and compare them. If the results
-	# are different, use regular diff to report the difference.
-	local test_cmp_a= test_cmp_b=
-
-	# When text came from stdin (one argument is '-') we must feed it
-	# to diff.
-	local stdin_for_diff=
-
-	# Since it is difficult to detect the difference between an
-	# empty input file and a failure to read the files, we go straight
-	# to diff if one of the inputs is empty.
-	if test -s "$1" && test -s "$2"
-	then
-		# regular case: both files non-empty
-		mingw_read_file_strip_cr_ test_cmp_a <"$1"
-		mingw_read_file_strip_cr_ test_cmp_b <"$2"
-	elif test -s "$1" && test "$2" = -
-	then
-		# read 2nd file from stdin
-		mingw_read_file_strip_cr_ test_cmp_a <"$1"
-		mingw_read_file_strip_cr_ test_cmp_b
-		stdin_for_diff='<<<"$test_cmp_b"'
-	elif test "$1" = - && test -s "$2"
-	then
-		# read 1st file from stdin
-		mingw_read_file_strip_cr_ test_cmp_a
-		mingw_read_file_strip_cr_ test_cmp_b <"$2"
-		stdin_for_diff='<<<"$test_cmp_a"'
-	fi
-	test -n "$test_cmp_a" &&
-	test -n "$test_cmp_b" &&
-	test "$test_cmp_a" = "$test_cmp_b" ||
-	eval "diff -u \"\$@\" $stdin_for_diff"
-}
-
-# $1 is the name of the shell variable to fill in
-mingw_read_file_strip_cr_ () {
-	# Read line-wise using LF as the line separator
-	# and use IFS to strip CR.
-	local line
-	while :
-	do
-		if IFS=$'\r' read -r -d $'\n' line
-		then
-			# good
-			line=$line$'\n'
-		else
-			# we get here at EOF, but also if the last line
-			# was not terminated by LF; in the latter case,
-			# some text was read
-			if test -z "$line"
-			then
-				# EOF, really
-				break
-			fi
-		fi
-		eval "$1=\$$1\$line"
-	done
-}
-
 # Like "env FOO=BAR some-program", but run inside a subshell, which means
 # it also works for shell functions (though those functions cannot impact
 # the environment outside of the test_env invocation).

t/test-lib.sh

@@ -1482,7 +1482,7 @@ case $uname_s in
 	test_set_prereq NATIVE_CRLF
 	test_set_prereq SED_STRIPS_CR
 	test_set_prereq GREP_STRIPS_CR
-	GIT_TEST_CMP=mingw_test_cmp
+	GIT_TEST_CMP="test-tool cmp"
 	;;
 *CYGWIN*)
 	test_set_prereq POSIXPERM