diff mbox series

[v8,27/30] t/lib-unicode-nfc-nfd: helper prereqs for testing unicode nfc/nfd

Message ID 25c6066eddc725c7d4c233620fca82d3638b394e.1653490853.git.gitgitgadget@gmail.com (mailing list archive)
State Superseded
Headers show
Series Builtin FSMonitor Part 3 | expand

Commit Message

Jeff Hostetler May 25, 2022, 3 p.m. UTC
From: Jeff Hostetler <jeffhost@microsoft.com>

Create a set of prereqs to help understand how file names
are handled by the filesystem when they contain NFC and NFD
Unicode characters.

Signed-off-by: Jeff Hostetler <jeffhost@microsoft.com>
---
 t/lib-unicode-nfc-nfd.sh | 162 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 162 insertions(+)
 create mode 100755 t/lib-unicode-nfc-nfd.sh
diff mbox series

Patch

diff --git a/t/lib-unicode-nfc-nfd.sh b/t/lib-unicode-nfc-nfd.sh
new file mode 100755
index 00000000000..22232247efc
--- /dev/null
+++ b/t/lib-unicode-nfc-nfd.sh
@@ -0,0 +1,162 @@ 
+# Help detect how Unicode NFC and NFD are handled on the filesystem.
+
+# A simple character that has a NFD form.
+#
+# NFC:       U+00e9 LATIN SMALL LETTER E WITH ACUTE
+# UTF8(NFC): \xc3 \xa9
+#
+# NFD:       U+0065 LATIN SMALL LETTER E
+#            U+0301 COMBINING ACUTE ACCENT
+# UTF8(NFD): \x65  +  \xcc \x81
+#
+utf8_nfc=$(printf "\xc3\xa9")
+utf8_nfd=$(printf "\x65\xcc\x81")
+
+# Is the OS or the filesystem "Unicode composition sensitive"?
+#
+# That is, does the OS or the filesystem allow files to exist with
+# both the NFC and NFD spellings?  Or, does the OS/FS lie to us and
+# tell us that the NFC and NFD forms are equivalent.
+#
+# This is or may be independent of what type of filesystem we have,
+# since it might be handled by the OS at a layer above the FS.
+# Testing shows on MacOS using APFS, HFS+, and FAT32 reports a
+# collision, for example.
+#
+# This does not tell us how the Unicode pathname will be spelled
+# on disk, but rather only that the two spelling "collide".  We
+# will examine the actual on disk spelling in a later prereq.
+#
+test_lazy_prereq UNICODE_COMPOSITION_SENSITIVE '
+	mkdir trial_${utf8_nfc} &&
+	mkdir trial_${utf8_nfd}
+'
+
+# Is the spelling of an NFC pathname preserved on disk?
+#
+# On MacOS with HFS+ and FAT32, NFC paths are converted into NFD
+# and on APFS, NFC paths are preserved.  As we have established
+# above, this is independent of "composition sensitivity".
+#
+test_lazy_prereq UNICODE_NFC_PRESERVED '
+	mkdir c_${utf8_nfc} &&
+	ls | test-tool hexdump >dump &&
+	grep "63 5f c3 a9" dump
+'
+
+# Is the spelling of an NFD pathname preserved on disk?
+#
+test_lazy_prereq UNICODE_NFD_PRESERVED '
+	mkdir d_${utf8_nfd} &&
+	ls | test-tool hexdump >dump &&
+	grep "64 5f 65 cc 81" dump
+'
+
+# The following _DOUBLE_ forms are more for my curiosity,
+# but there may be quirks lurking when there are multiple
+# combining characters in non-canonical order.
+
+# Unicode also allows multiple combining characters
+# that can be decomposed in pieces.
+#
+# NFC:        U+1f67 GREEK SMALL LETTER OMEGA WITH DASIA AND PERISPOMENI
+# UTF8(NFC):  \xe1 \xbd \xa7
+#
+# NFD1:       U+1f61 GREEK SMALL LETTER OMEGA WITH DASIA
+#             U+0342 COMBINING GREEK PERISPOMENI
+# UTF8(NFD1): \xe1 \xbd \xa1  +  \xcd \x82
+#
+# But U+1f61 decomposes into
+# NFD2:       U+03c9 GREEK SMALL LETTER OMEGA
+#             U+0314 COMBINING REVERSED COMMA ABOVE
+# UTF8(NFD2): \xcf \x89  +  \xcc \x94
+#
+# Yielding:   \xcf \x89  +  \xcc \x94  +  \xcd \x82
+#
+# Note that I've used the canonical ordering of the
+# combinining characters.  It is also possible to
+# swap them.  My testing shows that that non-standard
+# ordering also causes a collision in mkdir.  However,
+# the resulting names don't draw correctly on the
+# terminal (implying that the on-disk format also has
+# them out of order).
+#
+greek_nfc=$(printf "\xe1\xbd\xa7")
+greek_nfd1=$(printf "\xe1\xbd\xa1\xcd\x82")
+greek_nfd2=$(printf "\xcf\x89\xcc\x94\xcd\x82")
+
+# See if a double decomposition also collides.
+#
+test_lazy_prereq UNICODE_DOUBLE_COMPOSITION_SENSITIVE '
+	mkdir trial_${greek_nfc} &&
+	mkdir trial_${greek_nfd2}
+'
+
+# See if the NFC spelling appears on the disk.
+#
+test_lazy_prereq UNICODE_DOUBLE_NFC_PRESERVED '
+	mkdir c_${greek_nfc} &&
+	ls | test-tool hexdump >dump &&
+	grep "63 5f e1 bd a7" dump
+'
+
+# See if the NFD spelling appears on the disk.
+#
+test_lazy_prereq UNICODE_DOUBLE_NFD_PRESERVED '
+	mkdir d_${greek_nfd2} &&
+	ls | test-tool hexdump >dump &&
+	grep "64 5f cf 89 cc 94 cd 82" dump
+'
+
+# The following is for debugging. I found it useful when
+# trying to understand the various (OS, FS) quirks WRT
+# Unicode and how composition/decomposition is handled.
+# For example, when trying to understand how (macOS, APFS)
+# and (macOS, HFS) and (macOS, FAT32) compare.
+#
+# It is rather noisy, so it is disabled by default.
+#
+if test "$unicode_debug" = "true"
+then
+	if test_have_prereq UNICODE_COMPOSITION_SENSITIVE
+	then
+		echo NFC and NFD are distinct on this OS/filesystem.
+	else
+		echo NFC and NFD are aliases on this OS/filesystem.
+	fi
+
+	if test_have_prereq UNICODE_NFC_PRESERVED
+	then
+		echo NFC maintains original spelling.
+	else
+		echo NFC is modified.
+	fi
+
+	if test_have_prereq UNICODE_NFD_PRESERVED
+	then
+		echo NFD maintains original spelling.
+	else
+		echo NFD is modified.
+	fi
+
+	if test_have_prereq UNICODE_DOUBLE_COMPOSITION_SENSITIVE
+	then
+		echo DOUBLE NFC and NFD are distinct on this OS/filesystem.
+	else
+		echo DOUBLE NFC and NFD are aliases on this OS/filesystem.
+	fi
+
+	if test_have_prereq UNICODE_DOUBLE_NFC_PRESERVED
+	then
+		echo Double NFC maintains original spelling.
+	else
+		echo Double NFC is modified.
+	fi
+
+	if test_have_prereq UNICODE_DOUBLE_NFD_PRESERVED
+	then
+		echo Double NFD maintains original spelling.
+	else
+		echo Double NFD is modified.
+	fi
+fi