[v2,26/27] t7527: test Unicode NFC/NFD handling on MacOS

Commit Message

Jeff Hostetler March 8, 2022, 10:15 p.m. UTC

From: Jeff Hostetler <[e-mail]>

Confirm that the daemon reports events using the on-disk
spelling for Unicode NFC/NFD characters.  On APFS we still
have Unicode aliasing, so we cannot create two files that
only differ by NFC/NFD, but the on-disk format preserves
the spelling used to create the file.  On HFS+ we also
have aliasing, but the path is always stored on disk in
NFD.

Signed-off-by: Jeff Hostetler <[e-mail]>
---
 t/t7527-builtin-fsmonitor.sh | 54 ++++++++++++++++++++++++++++++++++++
 1 file changed, 54 insertions(+)

Patch

diff --git a/t/t7527-builtin-fsmonitor.sh b/t/t7527-builtin-fsmonitor.sh
index a41e37236b5..48c9125d8da 100755
--- a/t/t7527-builtin-fsmonitor.sh
+++ b/t/t7527-builtin-fsmonitor.sh
@@ -861,4 +861,58 @@  test_expect_success CASE_INSENSITIVE_FS 'case insensitive+preserving' '
 	egrep "^event: abc/def/xyz$" ./insensitive.trace
 '
 
+unicode_debug=0
+. "$TEST_DIRECTORY/lib-unicode-nfc-nfd.sh"
+
+# See if the OS or filesystem does NFC/NFD aliasing/munging.
+#
+# The daemon should err on the side of caution and send BOTH the
+# NFC and NFD forms.  It does not know the original spelling of
+# the pathname (how the user thinks it should be spelled), so
+# emit both and let the client decide (when necessary).  This is
+# similar to "core.precomposeUnicode".
+#
+test_expect_success !UNICODE_COMPOSITION_SENSITIVE 'Unicode nfc/nfd' '
+	test_when_finished "stop_daemon_delete_repo test_unicode" &&
+
+	git init test_unicode &&
+	(
+		GIT_TRACE_FSMONITOR="$(pwd)/unicode.trace" &&
+		export GIT_TRACE_FSMONITOR &&
+
+		start_daemon test_unicode
+	) &&
+
+	# Create a directory using an NFC spelling.
+	#
+	mkdir test_unicode/nfc &&
+	mkdir test_unicode/nfc/c_${utf8_nfc} &&
+
+	# Create a directory using an NFD spelling.
+	#
+	mkdir test_unicode/nfd &&
+	mkdir test_unicode/nfd/d_${utf8_nfd} &&
+
+	git -C test_unicode fsmonitor--daemon stop &&
+
+	if test_have_prereq UNICODE_NFC_PRESERVED
+	then
+		# We should have seen NFC event from OS.
+		# We should not have synthesized an NFD event.
+		egrep    "^event: nfc/c_${utf8_nfc}/?$" ./unicode.trace &&
+		egrep -v "^event: nfc/c_${utf8_nfd}/?$" ./unicode.trace
+	else
+		# We should have seen NFD event from OS.
+		# We should have synthesized an NFC event.
+		egrep "^event: nfc/c_${utf8_nfd}/?$" ./unicode.trace &&
+		egrep "^event: nfc/c_${utf8_nfc}/?$" ./unicode.trace
+	fi &&
+
+	# We assume UNICODE_NFD_PRESERVED.
+	# We should have seen explicit NFD from OS.
+	# We should have synthesized an NFC event.
+	egrep "^event: nfd/d_${utf8_nfd}/?$" ./unicode.trace &&
+	egrep "^event: nfd/d_${utf8_nfc}/?$" ./unicode.trace
+'
+
 test_done