tests/generic/453 - pub/scm/fs/xfs/xfstests-dev - Git at Google

 #! /bin/bash
 # SPDX-License-Identifier: GPL-2.0
 # Copyright (c) 2017, Oracle and/or its affiliates.  All Rights Reserved.
 #
 # FS QA Test No. 453
 #
 # Create a directory with multiple filenames that all appear the same
 # (in unicode, anyway) but point to different inodes.  In theory all
 # Linux filesystems should allow this (filenames are a sequence of
 # arbitrary bytes) even if the user implications are horrifying.
 #
 . ./common/preamble
 _begin_fstest auto quick dir

 # Import common functions.

 _require_scratch
 _require_names_are_bytes

 echo "Format and mount"
 _scratch_mkfs > $seqres.full 2>&1
 _scratch_mount >> $seqres.full 2>&1

 testdir="${SCRATCH_MNT}/test-${seq}"
 mkdir $testdir

 hexbytes() {
 	echo -n "$1" | od -tx1 -w99999 | head -n1 | sed -e 's/^0* //g'
 }

 setf() {
 	key="$(echo -e "$1")"
 	value="$2"

 	echo "${value}" > "${testdir}/${key}"
 	echo "Storing ${key} ($(hexbytes "${key}")) -> ${value}" >> $seqres.full
 }

 setchild() {
 	subdir="$1"
 	key="$(echo -e "$2")"

 	mkdir -p "${testdir}/${subdir}"
 	echo "$subdir" > "${testdir}/${subdir}/${key}"
 	echo "Storing ${subdir}/${key} ($(hexbytes "${key}")) -> ${subdir}" >> $seqres.full
 }

 setd() {
 	key="$(echo -e "$1")"
 	value="$2"

 	mkdir -p "${testdir}/${key}"
 	echo "${value}" > "${testdir}/${key}/value"
 	echo "Storing ${key} ($(hexbytes "${key}")) -> ${value}" >> $seqres.full
 }

 testf() {
 	key="$(echo -e "$1")"
 	value="$2"
 	fname="${testdir}/${key}"

 	echo "Testing ${key} ($(hexbytes "${key}")) -> ${value}" >> $seqres.full

 	if [ ! -e "${fname}" ]; then
 		echo "Key ${key} does not exist for ${value} test??"
 		return
 	fi

 	actual_value="$(cat "${fname}")"
 	if [ "${actual_value}" != "${value}" ]; then
 		echo "Key ${key} has value ${value}, expected ${actual_value}."
 	fi
 }

 testchild() {
 	subdir="$1"
 	key="$(echo -e "$2")"
 	fname="${testdir}/${subdir}/${key}"

 	echo "Testing ${subdir}/${key} ($(hexbytes "${key}")) -> ${subdir}" >> $seqres.full

 	if [ ! -e "${fname}" ]; then
 		echo "Key ${key} does not exist for ${subdir} test??"
 		return
 	fi

 	actual_value="$(cat "${fname}")"
 	if [ "${actual_value}" != "${subdir}" ]; then
 		echo "Key ${key} has value ${subdir}, expected ${actual_value}."
 	fi
 }

 testd() {
 	key="$(echo -e "$1")"
 	value="$2"
 	fname="${testdir}/${key}/value"

 	echo "Testing ${key} ($(hexbytes "${key}")) -> ${value}" >> $seqres.full

 	if [ ! -e "${fname}" ]; then
 		echo "Key ${key} does not exist for ${value} test??"
 		return
 	fi

 	actual_value="$(cat "${fname}")"
 	if [ "${actual_value}" != "${value}" ]; then
 		echo "Key ${key} has value ${value}, expected ${actual_value}."
 	fi
 }

 filter_scrub() {
 	grep 'Unicode' | sed -e 's/^.*Duplicate/Duplicate/g'
 }

 echo "Create files"
 # These two render the same
 setf "french_caf\xc3\xa9.txt" "NFC"
 setf "french_cafe\xcc\x81.txt" "NFD"

 # These two may have different widths
 setf "chinese_\xef\xbd\xb6.txt" "NFKC1"
 setf "chinese_\xe3\x82\xab.txt" "NFKC2"

 # Same point, different byte representations in NFC/NFD/NFKC/NFKD
 setf "greek_\xcf\x93.txt" "GREEK UPSILON WITH ACUTE AND HOOK SYMBOL, NFC"
 setf "greek_\xcf\x92\xcc\x81.txt" "GREEK UPSILON WITH ACUTE AND HOOK SYMBOL, NFD"
 setf "greek_\xce\x8e.txt" "GREEK UPSILON WITH ACUTE AND HOOK SYMBOL, NFKC"
 setf "greek_\xce\xa5\xcc\x81.txt" "GREEK UPSILON WITH ACUTE AND HOOK SYMBOL, NFKD"

 # Arabic code point can expand into a muuuch longer series
 setf "arabic_\xef\xb7\xba.txt" "ARABIC LIGATURE SALLALLAHOU ALAYHE WASALLAM, NFC"
 setf "arabic_\xd8\xb5\xd9\x84\xd9\x89\x20\xd8\xa7\xd9\x84\xd9\x84\xd9\x87\x20\xd8\xb9\xd9\x84\xd9\x8a\xd9\x87\x20\xd9\x88\xd8\xb3\xd9\x84\xd9\x85.txt" "ARABIC LIGATURE SALLALLAHOU ALAYHE WASALLAM, NFKC"

 # Fake slash?
 setf "urk\xc0\xafmoo" "FAKESLASH"

 # Emoji: octopus butterfly owl giraffe
 setf "emoji_\xf0\x9f\xa6\x91\xf0\x9f\xa6\x8b\xf0\x9f\xa6\x89\xf0\x9f\xa6\x92.txt" "octopus butterfly owl giraffe emoji"

 # Line draw characters, because why not?
 setf "\x6c\x69\x6e\x65\x64\x72\x61\x77\x5f\x0a\xe2\x95\x94\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x97\x0a\xe2\x95\x91\x20\x6d\x65\x74\x61\x74\x61\x62\x6c\x65\x20\xe2\x95\x91\x0a\xe2\x95\x9f\xe2\x94\x80\xe2\x94\x80\xe2\x94\x80\xe2\x94\x80\xe2\x94\x80\xe2\x94\x80\xe2\x94\x80\xe2\x94\x80\xe2\x94\x80\xe2\x94\x80\xe2\x94\x80\xe2\x95\xa2\x0a\xe2\x95\x91\x20\x5f\x5f\x69\x6e\x64\x65\x78\x20\x20\x20\xe2\x95\x91\x0a\xe2\x95\x9a\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x9d\x0a.txt" "ugly box because we can"

 # unicode rtl widgets too...
 setf "moo\xe2\x80\xaegnp.txt" "Well say hello,"
 setf "mootxt.png" "Harvey"

 # mixed-script confusables
 setf "mixed_t\xce\xbfp.txt" "greek omicron instead of o"
 setf "mixed_top.txt" "greek omicron instead of o"

 # single-script spoofing
 setf "hyphens_a\xe2\x80\x90b.txt" "hyphens"
 setf "hyphens_a-b.txt" "hyphens"

 setf "dz_digraph_dze.txt" "d-z digraph"
 setf "dz_digraph_\xca\xa3e.txt" "d-z digraph"

 # inadequate rendering
 setf "inadequate_al.txt" "is it l or is it 1"
 setf "inadequate_a1.txt" "is it l or is it 1"

 # symbols
 setf "prohibition_Rs.txt" "rupee symbol"
 setf "prohibition_\xe2\x82\xa8.txt" "rupee symbol"

 # zero width joiners
 setf "zerojoin_moocow.txt" "zero width joiners"
 setf "zerojoin_moo\xe2\x80\x8dcow.txt" "zero width joiners"

 # combining marks
 setf "combmark_\xe1\x80\x9c\xe1\x80\xad\xe1\x80\xaf.txt" "combining marks"
 setf "combmark_\xe1\x80\x9c\xe1\x80\xaf\xe1\x80\xad.txt" "combining marks"

 # fake dotdot entry
 setd ".\xe2\x80\x8d" "zero width joiners in dot entry"
 setd "..\xe2\x80\x8d" "zero width joiners in dotdot entry"

 # utf8 sequence mapping to a u32 unicode codepoint that can be confused
 setf "toilet_bowl.\xf0\x9f\x9a\xbd" "toilet emoji"
 setf "toilet_bow\xe2\x80\x8dl.\xf0\x9f\x9a\xbd" "toilet emoji with zero width joiner"

 # decoy file extensions used in 3cx malware attack, and similar ones
 setchild "one_dot_leader" "job offer\xe2\x80\xa4pdf"
 setchild "small_full_stop" "job offer\xef\xb9\x92pdf"
 setchild "fullwidth_full_stop" "job offer\xef\xbc\x8epdf"
 setchild "syriac_supralinear" "job offer\xdc\x81pdf"
 setchild "syriac_sublinear" "job offer\xdc\x82pdf"
 setchild "lisu_letter_tone" "job offer\xea\x93\xb8pdf"
 setchild "actual_period" "job offer.pdf"
 setchild "one_dot_leader_zero_width_space" "job offer\xe2\x80\xa4\xe2\x80\x8dpdf"

 # again, but this time all in the same directory to trip the confusable
 # detector
 setf "job offer\xe2\x80\xa4pdf" "one dot leader"
 setf "job offer\xef\xb9\x92pdf" "small full stop"
 setf "job offer\xef\xbc\x8epdf" "fullwidth full stop"
 setf "job offer\xdc\x81pdf" "syriac supralinear full stop"
 setf "job offer\xdc\x82pdf" "syriac sublinear full stop"
 setf "job offer\xea\x93\xb8pdf" "li_su letter tone mya ti"
 setf "job offer.pdf" "actual period"

 # encoding hidden tag characters in filenames to create confusing names
 setf "llamapirate\xf3\xa0\x80\x81\xf3\xa0\x81\x94\xf3\xa0\x81\xa8\xf3\xa0\x81\xa5\xf3\xa0\x80\xa0\xf3\xa0\x81\xb3\xf3\xa0\x81\xa1\xf3\xa0\x81\xac\xf3\xa0\x81\xa5\xf3\xa0\x81\xb3\xf3\xa0\x80\xa0\xf3\xa0\x81\xa6\xf3\xa0\x81\xaf\xf3\xa0\x81\xb2\xf3\xa0\x80\xa0\xf3\xa0\x81\x93\xf3\xa0\x81\xa5\xf3\xa0\x81\xa1\xf3\xa0\x81\xb4\xf3\xa0\x81\xb4\xf3\xa0\x81\xac\xf3\xa0\x81\xa5\xf3\xa0\x80\xa0\xf3\xa0\x81\xb7\xf3\xa0\x81\xa5\xf3\xa0\x81\xb2\xf3\xa0\x81\xa5\xf3\xa0\x80\xa0\xf3\xa0\x81\x95\xf3\xa0\x81\x93\xf3\xa0\x81\x84\xf3\xa0\x80\xa0\xf3\xa0\x80\xb1\xf3\xa0\x80\xb2\xf3\xa0\x80\xb0\xf3\xa0\x80\xb0\xf3\xa0\x80\xb0\xf3\xa0\x80\xb0\xf3\xa0\x81\xbf"
 setf "llamapirate"

 # colored heart emoji to check if casefolding whacks emoji
 setf "\xf0\x9f\x92\x9c" "purple"
 setf "\xf0\x9f\x92\x99" "blue"
 setf "\xf0\x9f\x92\x9a" "green"
 setf "\xf0\x9f\x92\x9b" "yellow"
 setf "\xf0\x9f\xab\x80" "heart"
 setf "\xe2\x9d\xa4\xef\xb8\x8f" "red"
 setf "\xf0\x9f\xa4\x8e" "brown"
 setf "\xf0\x9f\xa4\x8d" "white"
 setf "\xf0\x9f\x96\xa4" "black"
 setf "\xf0\x9f\xa7\xa1" "orange"
 setf "\xe2\x99\xa5\xef\xb8\x8f" "red suit"

 # zero width joiners exist in the middle of emoji sequences aren't supposed
 # to be normalized to nothing, but apparently this caused issues with
 # casefolding on ext4; also the mending heart caused a crash in xfs_scrub
 setf "\xf0\x9f\x92\x94" "broken heart"
 setf "\xe2\x9d\xa4\xef\xb8\x8f\xe2\x80\x8d\xf0\x9f\xa9\xb9" "mending heart"
 setf "\xf0\x9f\xa7\x91\xf0\x9f\x8f\xbb\xe2\x80\x8d\xe2\x9d\xa4\xef\xb8
 \x8f\xe2\x80\x8d\xf0\x9f\xa7\x91\xf0\x9f\x8f\xbc" "couple with heart"
 setf "\xf0\x9f\xa7\x91\xf0\x9f\x8f\xbb\xe2\x80\x8d\xe2\x9d\xa4\xef\xb8\x8f\xe2\x80\x8d\xf0\x9f\xa7\x91\xf0\x9f\x8f\xbf" "couple with heart, light and dark skin tone"

 # emoji heart hands with skin tone variations
 setf "\xf0\x9f\xab\xb6\xf0\x9f\x8f\xbf" "dark"
 setf "\xf0\x9f\xab\xb6\xf0\x9f\x8f\xbe" "medium dark"
 setf "\xf0\x9f\xab\xb6\xf0\x9f\x8f\xbd" "medium"
 setf "\xf0\x9f\xab\xb6\xf0\x9f\x8f\xbc" "medium light"
 setf "\xf0\x9f\xab\xb6\xf0\x9f\x8f\xbb" "light"
 setf "\xf0\x9f\xab\xb6" "neutral"

 ls -laR $testdir >> $seqres.full

 echo "Test files"
 testf "french_caf\xc3\xa9.txt" "NFC"
 testf "french_cafe\xcc\x81.txt" "NFD"

 testf "chinese_\xef\xbd\xb6.txt" "NFKC1"
 testf "chinese_\xe3\x82\xab.txt" "NFKC2"

 testf "greek_\xcf\x93.txt" "GREEK UPSILON WITH ACUTE AND HOOK SYMBOL, NFC"
 testf "greek_\xcf\x92\xcc\x81.txt" "GREEK UPSILON WITH ACUTE AND HOOK SYMBOL, NFD"
 testf "greek_\xce\x8e.txt" "GREEK UPSILON WITH ACUTE AND HOOK SYMBOL, NFKC"
 testf "greek_\xce\xa5\xcc\x81.txt" "GREEK UPSILON WITH ACUTE AND HOOK SYMBOL, NFKD"

 testf "arabic_\xef\xb7\xba.txt" "ARABIC LIGATURE SALLALLAHOU ALAYHE WASALLAM, NFC"
 testf "arabic_\xd8\xb5\xd9\x84\xd9\x89\x20\xd8\xa7\xd9\x84\xd9\x84\xd9\x87\x20\xd8\xb9\xd9\x84\xd9\x8a\xd9\x87\x20\xd9\x88\xd8\xb3\xd9\x84\xd9\x85.txt" "ARABIC LIGATURE SALLALLAHOU ALAYHE WASALLAM, NFKC"

 testf "urk\xc0\xafmoo" "FAKESLASH"

 testf "emoji_\xf0\x9f\xa6\x91\xf0\x9f\xa6\x8b\xf0\x9f\xa6\x89\xf0\x9f\xa6\x92.txt" "octopus butterfly owl giraffe emoji"

 testf "\x6c\x69\x6e\x65\x64\x72\x61\x77\x5f\x0a\xe2\x95\x94\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x97\x0a\xe2\x95\x91\x20\x6d\x65\x74\x61\x74\x61\x62\x6c\x65\x20\xe2\x95\x91\x0a\xe2\x95\x9f\xe2\x94\x80\xe2\x94\x80\xe2\x94\x80\xe2\x94\x80\xe2\x94\x80\xe2\x94\x80\xe2\x94\x80\xe2\x94\x80\xe2\x94\x80\xe2\x94\x80\xe2\x94\x80\xe2\x95\xa2\x0a\xe2\x95\x91\x20\x5f\x5f\x69\x6e\x64\x65\x78\x20\x20\x20\xe2\x95\x91\x0a\xe2\x95\x9a\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x9d\x0a.txt" "ugly box because we can"

 testf "moo\xe2\x80\xaegnp.txt" "Well say hello,"
 testf "mootxt.png" "Harvey"

 testf "mixed_t\xce\xbfp.txt" "greek omicron instead of o"
 testf "mixed_top.txt" "greek omicron instead of o"

 testf "hyphens_a\xe2\x80\x90b.txt" "hyphens"
 testf "hyphens_a-b.txt" "hyphens"

 testf "dz_digraph_dze.txt" "d-z digraph"
 testf "dz_digraph_\xca\xa3e.txt" "d-z digraph"

 testf "inadequate_al.txt" "is it l or is it 1"
 testf "inadequate_a1.txt" "is it l or is it 1"

 testf "prohibition_Rs.txt" "rupee symbol"
 testf "prohibition_\xe2\x82\xa8.txt" "rupee symbol"

 testf "zerojoin_moocow.txt" "zero width joiners"
 testf "zerojoin_moo\xe2\x80\x8dcow.txt" "zero width joiners"

 testf "combmark_\xe1\x80\x9c\xe1\x80\xad\xe1\x80\xaf.txt" "combining marks"
 testf "combmark_\xe1\x80\x9c\xe1\x80\xaf\xe1\x80\xad.txt" "combining marks"

 testd ".\xe2\x80\x8d" "zero width joiners in dot entry"
 testd "..\xe2\x80\x8d" "zero width joiners in dotdot entry"

 testf "toilet_bowl.\xf0\x9f\x9a\xbd" "toilet emoji"
 testf "toilet_bow\xe2\x80\x8dl.\xf0\x9f\x9a\xbd" "toilet emoji with zero width joiner"

 testchild "one_dot_leader" "job offer\xe2\x80\xa4pdf"
 testchild "small_full_stop" "job offer\xef\xb9\x92pdf"
 testchild "fullwidth_full_stop" "job offer\xef\xbc\x8epdf"
 testchild "syriac_supralinear" "job offer\xdc\x81pdf"
 testchild "syriac_sublinear" "job offer\xdc\x82pdf"
 testchild "lisu_letter_tone" "job offer\xea\x93\xb8pdf"
 testchild "actual_period" "job offer.pdf"
 testchild "one_dot_leader_zero_width_space" "job offer\xe2\x80\xa4\xe2\x80\x8dpdf"

 testf "job offer\xe2\x80\xa4pdf" "one dot leader"
 testf "job offer\xef\xb9\x92pdf" "small full stop"
 testf "job offer\xef\xbc\x8epdf" "fullwidth full stop"
 testf "job offer\xdc\x81pdf" "syriac supralinear full stop"
 testf "job offer\xdc\x82pdf" "syriac sublinear full stop"
 testf "job offer\xea\x93\xb8pdf" "li_su letter tone mya ti"
 testf "job offer.pdf" "actual period"

 testf "llamapirate\xf3\xa0\x80\x81\xf3\xa0\x81\x94\xf3\xa0\x81\xa8\xf3\xa0\x81\xa5\xf3\xa0\x80\xa0\xf3\xa0\x81\xb3\xf3\xa0\x81\xa1\xf3\xa0\x81\xac\xf3\xa0\x81\xa5\xf3\xa0\x81\xb3\xf3\xa0\x80\xa0\xf3\xa0\x81\xa6\xf3\xa0\x81\xaf\xf3\xa0\x81\xb2\xf3\xa0\x80\xa0\xf3\xa0\x81\x93\xf3\xa0\x81\xa5\xf3\xa0\x81\xa1\xf3\xa0\x81\xb4\xf3\xa0\x81\xb4\xf3\xa0\x81\xac\xf3\xa0\x81\xa5\xf3\xa0\x80\xa0\xf3\xa0\x81\xb7\xf3\xa0\x81\xa5\xf3\xa0\x81\xb2\xf3\xa0\x81\xa5\xf3\xa0\x80\xa0\xf3\xa0\x81\x95\xf3\xa0\x81\x93\xf3\xa0\x81\x84\xf3\xa0\x80\xa0\xf3\xa0\x80\xb1\xf3\xa0\x80\xb2\xf3\xa0\x80\xb0\xf3\xa0\x80\xb0\xf3\xa0\x80\xb0\xf3\xa0\x80\xb0\xf3\xa0\x81\xbf"
 testf "llamapirate"

 testf "\xf0\x9f\x92\x9c" "purple"
 testf "\xf0\x9f\x92\x99" "blue"
 testf "\xf0\x9f\x92\x9a" "green"
 testf "\xf0\x9f\x92\x9b" "yellow"
 testf "\xf0\x9f\xab\x80" "heart"
 testf "\xe2\x9d\xa4\xef\xb8\x8f" "red"
 testf "\xf0\x9f\xa4\x8e" "brown"
 testf "\xf0\x9f\xa4\x8d" "white"
 testf "\xf0\x9f\x96\xa4" "black"
 testf "\xf0\x9f\xa7\xa1" "orange"
 testf "\xe2\x99\xa5\xef\xb8\x8f" "red suit"

 testf "\xf0\x9f\x92\x94" "broken heart"
 testf "\xe2\x9d\xa4\xef\xb8\x8f\xe2\x80\x8d\xf0\x9f\xa9\xb9" "mending heart"
 testf "\xf0\x9f\xa7\x91\xf0\x9f\x8f\xbb\xe2\x80\x8d\xe2\x9d\xa4\xef\xb8
 \x8f\xe2\x80\x8d\xf0\x9f\xa7\x91\xf0\x9f\x8f\xbc" "couple with heart"
 testf "\xf0\x9f\xa7\x91\xf0\x9f\x8f\xbb\xe2\x80\x8d\xe2\x9d\xa4\xef\xb8\x8f\xe2\x80\x8d\xf0\x9f\xa7\x91\xf0\x9f\x8f\xbf" "couple with heart, light and dark skin tone"

 testf "\xf0\x9f\xab\xb6\xf0\x9f\x8f\xbf" "dark"
 testf "\xf0\x9f\xab\xb6\xf0\x9f\x8f\xbe" "medium dark"
 testf "\xf0\x9f\xab\xb6\xf0\x9f\x8f\xbd" "medium"
 testf "\xf0\x9f\xab\xb6\xf0\x9f\x8f\xbc" "medium light"
 testf "\xf0\x9f\xab\xb6\xf0\x9f\x8f\xbb" "light"
 testf "\xf0\x9f\xab\xb6" "neutral"

 echo "Uniqueness of inodes?"
 stat -c '%i' "${testdir}/"* | sort | uniq -c | while read nr inum; do
 	if [ "${nr}" -gt 1 ]; then
 		echo "${nr} ${inum}"
 	fi
 done

 echo "Test XFS online scrub, if applicable"

 if _check_xfs_scrub_does_unicode "$SCRATCH_MNT" "$SCRATCH_DEV"; then
 	LC_ALL="C.UTF-8" ${XFS_SCRUB_PROG} -v -n "${SCRATCH_MNT}" 2>&1 | filter_scrub > $tmp.scrub

 	grep -q "french_" $tmp.scrub || echo "No complaints about french e accent?"
 	grep -q "greek_" $tmp.scrub || echo "No complaints about greek letter mess?"
 	grep -q "arabic_" $tmp.scrub || echo "No complaints about arabic expanded string?"
 	grep -q "mixed_" $tmp.scrub || echo "No complaints about mixed script confusables?"
 	grep -q "hyphens_" $tmp.scrub || echo "No complaints about hyphenation confusables?"
 	grep -q "dz_digraph_" $tmp.scrub || echo "No complaints about single script confusables?"
 	grep -q "inadequate_" $tmp.scrub || echo "No complaints about inadequate rendering confusables?"
 	grep -q "prohibition_" $tmp.scrub || echo "No complaints about prohibited sequence confusables?"
 	grep -q "zerojoin_" $tmp.scrub || echo "No complaints about zero-width join confusables?"
 	grep -q "toilet_" $tmp.scrub || echo "No complaints about zero-width join confusables with emoji?"

 	# Does xfs_scrub complain at all about the job offer files?  Pre-2023
 	# versions did not know to screen for that.
 	if grep -q "job offer" $tmp.scrub; then
 		grep -q 'job offer.xe2.x80.xa4pdf' $tmp.scrub || echo "No complaints about one dot leader?"
 		grep -q "job offer.xef.xb9.x92pdf" $tmp.scrub || echo "No complaints about small full stop?"
 		grep -q "job offer.xef.xbc.x8epdf" $tmp.scrub || echo "No complaints about fullwidth full stop?"
 		grep -q "job offer.xdc.x81pdf" $tmp.scrub || echo "No complaints about syriac supralinear full stop?"
 		grep -q "job offer.xdc.x82pdf" $tmp.scrub || echo "No complaints about syriac sublinear full stop?"
 		grep -q "job offer.xea.x93.xb8pdf" $tmp.scrub || echo "No complaints about li_su letter tone mya ti?"
 		grep -q "job offer.*could be confused with" $tmp.scrub || echo "No complaints about confusing job offers?"
 		grep -q "job offer.xe2.x80.xa4.xe2.x80.x8dpdf" $tmp.scrub || echo "No complaints about one dot leader with invisible space?"
 		grep -q "llamapirate" $tmp.scrub || echo "No complaints about hidden llm instructions in filenames?"
 	fi

 	echo "Actual xfs_scrub output:" >> $seqres.full
 	cat $tmp.scrub >> $seqres.full
 fi

 # success, all done
 status=0
 exit
	#! /bin/bash
	# SPDX-License-Identifier: GPL-2.0
	# Copyright (c) 2017, Oracle and/or its affiliates. All Rights Reserved.
	#
	# FS QA Test No. 453
	#
	# Create a directory with multiple filenames that all appear the same
	# (in unicode, anyway) but point to different inodes. In theory all
	# Linux filesystems should allow this (filenames are a sequence of
	# arbitrary bytes) even if the user implications are horrifying.
	#
	. ./common/preamble
	_begin_fstest auto quick dir

	# Import common functions.

	_require_scratch
	_require_names_are_bytes

	echo "Format and mount"
	_scratch_mkfs > $seqres.full 2>&1
	_scratch_mount >> $seqres.full 2>&1

	testdir="${SCRATCH_MNT}/test-${seq}"
	mkdir $testdir

	hexbytes() {
	echo -n "$1" \| od -tx1 -w99999 \| head -n1 \| sed -e 's/^0* //g'
	}

	setf() {
	key="$(echo -e "$1")"
	value="$2"

	echo "${value}" > "${testdir}/${key}"
	echo "Storing ${key} ($(hexbytes "${key}")) -> ${value}" >> $seqres.full
	}

	setchild() {
	subdir="$1"
	key="$(echo -e "$2")"

	mkdir -p "${testdir}/${subdir}"
	echo "$subdir" > "${testdir}/${subdir}/${key}"
	echo "Storing ${subdir}/${key} ($(hexbytes "${key}")) -> ${subdir}" >> $seqres.full
	}

	setd() {
	key="$(echo -e "$1")"
	value="$2"

	mkdir -p "${testdir}/${key}"
	echo "${value}" > "${testdir}/${key}/value"
	echo "Storing ${key} ($(hexbytes "${key}")) -> ${value}" >> $seqres.full
	}

	testf() {
	key="$(echo -e "$1")"
	value="$2"
	fname="${testdir}/${key}"

	echo "Testing ${key} ($(hexbytes "${key}")) -> ${value}" >> $seqres.full

	if [ ! -e "${fname}" ]; then
	echo "Key ${key} does not exist for ${value} test??"
	return
	fi

	actual_value="$(cat "${fname}")"
	if [ "${actual_value}" != "${value}" ]; then
	echo "Key ${key} has value ${value}, expected ${actual_value}."
	fi
	}

	testchild() {
	subdir="$1"
	key="$(echo -e "$2")"
	fname="${testdir}/${subdir}/${key}"

	echo "Testing ${subdir}/${key} ($(hexbytes "${key}")) -> ${subdir}" >> $seqres.full

	if [ ! -e "${fname}" ]; then
	echo "Key ${key} does not exist for ${subdir} test??"
	return
	fi

	actual_value="$(cat "${fname}")"
	if [ "${actual_value}" != "${subdir}" ]; then
	echo "Key ${key} has value ${subdir}, expected ${actual_value}."
	fi
	}

	testd() {
	key="$(echo -e "$1")"
	value="$2"
	fname="${testdir}/${key}/value"

	echo "Testing ${key} ($(hexbytes "${key}")) -> ${value}" >> $seqres.full

	if [ ! -e "${fname}" ]; then
	echo "Key ${key} does not exist for ${value} test??"
	return
	fi

	actual_value="$(cat "${fname}")"
	if [ "${actual_value}" != "${value}" ]; then
	echo "Key ${key} has value ${value}, expected ${actual_value}."
	fi
	}

	filter_scrub() {
	grep 'Unicode' \| sed -e 's/^.*Duplicate/Duplicate/g'
	}

	echo "Create files"
	# These two render the same
	setf "french_caf\xc3\xa9.txt" "NFC"
	setf "french_cafe\xcc\x81.txt" "NFD"

	# These two may have different widths
	setf "chinese_\xef\xbd\xb6.txt" "NFKC1"
	setf "chinese_\xe3\x82\xab.txt" "NFKC2"

	# Same point, different byte representations in NFC/NFD/NFKC/NFKD
	setf "greek_\xcf\x93.txt" "GREEK UPSILON WITH ACUTE AND HOOK SYMBOL, NFC"
	setf "greek_\xcf\x92\xcc\x81.txt" "GREEK UPSILON WITH ACUTE AND HOOK SYMBOL, NFD"
	setf "greek_\xce\x8e.txt" "GREEK UPSILON WITH ACUTE AND HOOK SYMBOL, NFKC"
	setf "greek_\xce\xa5\xcc\x81.txt" "GREEK UPSILON WITH ACUTE AND HOOK SYMBOL, NFKD"

	# Arabic code point can expand into a muuuch longer series
	setf "arabic_\xef\xb7\xba.txt" "ARABIC LIGATURE SALLALLAHOU ALAYHE WASALLAM, NFC"
	setf "arabic_\xd8\xb5\xd9\x84\xd9\x89\x20\xd8\xa7\xd9\x84\xd9\x84\xd9\x87\x20\xd8\xb9\xd9\x84\xd9\x8a\xd9\x87\x20\xd9\x88\xd8\xb3\xd9\x84\xd9\x85.txt" "ARABIC LIGATURE SALLALLAHOU ALAYHE WASALLAM, NFKC"

	# Fake slash?
	setf "urk\xc0\xafmoo" "FAKESLASH"

	# Emoji: octopus butterfly owl giraffe
	setf "emoji_\xf0\x9f\xa6\x91\xf0\x9f\xa6\x8b\xf0\x9f\xa6\x89\xf0\x9f\xa6\x92.txt" "octopus butterfly owl giraffe emoji"

	# Line draw characters, because why not?
	setf "\x6c\x69\x6e\x65\x64\x72\x61\x77\x5f\x0a\xe2\x95\x94\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x97\x0a\xe2\x95\x91\x20\x6d\x65\x74\x61\x74\x61\x62\x6c\x65\x20\xe2\x95\x91\x0a\xe2\x95\x9f\xe2\x94\x80\xe2\x94\x80\xe2\x94\x80\xe2\x94\x80\xe2\x94\x80\xe2\x94\x80\xe2\x94\x80\xe2\x94\x80\xe2\x94\x80\xe2\x94\x80\xe2\x94\x80\xe2\x95\xa2\x0a\xe2\x95\x91\x20\x5f\x5f\x69\x6e\x64\x65\x78\x20\x20\x20\xe2\x95\x91\x0a\xe2\x95\x9a\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x9d\x0a.txt" "ugly box because we can"

	# unicode rtl widgets too...
	setf "moo\xe2\x80\xaegnp.txt" "Well say hello,"
	setf "mootxt.png" "Harvey"

	# mixed-script confusables
	setf "mixed_t\xce\xbfp.txt" "greek omicron instead of o"
	setf "mixed_top.txt" "greek omicron instead of o"

	# single-script spoofing
	setf "hyphens_a\xe2\x80\x90b.txt" "hyphens"
	setf "hyphens_a-b.txt" "hyphens"

	setf "dz_digraph_dze.txt" "d-z digraph"
	setf "dz_digraph_\xca\xa3e.txt" "d-z digraph"

	# inadequate rendering
	setf "inadequate_al.txt" "is it l or is it 1"
	setf "inadequate_a1.txt" "is it l or is it 1"

	# symbols
	setf "prohibition_Rs.txt" "rupee symbol"
	setf "prohibition_\xe2\x82\xa8.txt" "rupee symbol"

	# zero width joiners
	setf "zerojoin_moocow.txt" "zero width joiners"
	setf "zerojoin_moo\xe2\x80\x8dcow.txt" "zero width joiners"

	# combining marks
	setf "combmark_\xe1\x80\x9c\xe1\x80\xad\xe1\x80\xaf.txt" "combining marks"
	setf "combmark_\xe1\x80\x9c\xe1\x80\xaf\xe1\x80\xad.txt" "combining marks"

	# fake dotdot entry
	setd ".\xe2\x80\x8d" "zero width joiners in dot entry"
	setd "..\xe2\x80\x8d" "zero width joiners in dotdot entry"

	# utf8 sequence mapping to a u32 unicode codepoint that can be confused
	setf "toilet_bowl.\xf0\x9f\x9a\xbd" "toilet emoji"
	setf "toilet_bow\xe2\x80\x8dl.\xf0\x9f\x9a\xbd" "toilet emoji with zero width joiner"

	# decoy file extensions used in 3cx malware attack, and similar ones
	setchild "one_dot_leader" "job offer\xe2\x80\xa4pdf"
	setchild "small_full_stop" "job offer\xef\xb9\x92pdf"
	setchild "fullwidth_full_stop" "job offer\xef\xbc\x8epdf"
	setchild "syriac_supralinear" "job offer\xdc\x81pdf"
	setchild "syriac_sublinear" "job offer\xdc\x82pdf"
	setchild "lisu_letter_tone" "job offer\xea\x93\xb8pdf"
	setchild "actual_period" "job offer.pdf"
	setchild "one_dot_leader_zero_width_space" "job offer\xe2\x80\xa4\xe2\x80\x8dpdf"

	# again, but this time all in the same directory to trip the confusable
	# detector
	setf "job offer\xe2\x80\xa4pdf" "one dot leader"
	setf "job offer\xef\xb9\x92pdf" "small full stop"
	setf "job offer\xef\xbc\x8epdf" "fullwidth full stop"
	setf "job offer\xdc\x81pdf" "syriac supralinear full stop"
	setf "job offer\xdc\x82pdf" "syriac sublinear full stop"
	setf "job offer\xea\x93\xb8pdf" "li_su letter tone mya ti"
	setf "job offer.pdf" "actual period"

	# encoding hidden tag characters in filenames to create confusing names
	setf "llamapirate\xf3\xa0\x80\x81\xf3\xa0\x81\x94\xf3\xa0\x81\xa8\xf3\xa0\x81\xa5\xf3\xa0\x80\xa0\xf3\xa0\x81\xb3\xf3\xa0\x81\xa1\xf3\xa0\x81\xac\xf3\xa0\x81\xa5\xf3\xa0\x81\xb3\xf3\xa0\x80\xa0\xf3\xa0\x81\xa6\xf3\xa0\x81\xaf\xf3\xa0\x81\xb2\xf3\xa0\x80\xa0\xf3\xa0\x81\x93\xf3\xa0\x81\xa5\xf3\xa0\x81\xa1\xf3\xa0\x81\xb4\xf3\xa0\x81\xb4\xf3\xa0\x81\xac\xf3\xa0\x81\xa5\xf3\xa0\x80\xa0\xf3\xa0\x81\xb7\xf3\xa0\x81\xa5\xf3\xa0\x81\xb2\xf3\xa0\x81\xa5\xf3\xa0\x80\xa0\xf3\xa0\x81\x95\xf3\xa0\x81\x93\xf3\xa0\x81\x84\xf3\xa0\x80\xa0\xf3\xa0\x80\xb1\xf3\xa0\x80\xb2\xf3\xa0\x80\xb0\xf3\xa0\x80\xb0\xf3\xa0\x80\xb0\xf3\xa0\x80\xb0\xf3\xa0\x81\xbf"
	setf "llamapirate"

	# colored heart emoji to check if casefolding whacks emoji
	setf "\xf0\x9f\x92\x9c" "purple"
	setf "\xf0\x9f\x92\x99" "blue"
	setf "\xf0\x9f\x92\x9a" "green"
	setf "\xf0\x9f\x92\x9b" "yellow"
	setf "\xf0\x9f\xab\x80" "heart"
	setf "\xe2\x9d\xa4\xef\xb8\x8f" "red"
	setf "\xf0\x9f\xa4\x8e" "brown"
	setf "\xf0\x9f\xa4\x8d" "white"
	setf "\xf0\x9f\x96\xa4" "black"
	setf "\xf0\x9f\xa7\xa1" "orange"
	setf "\xe2\x99\xa5\xef\xb8\x8f" "red suit"

	# zero width joiners exist in the middle of emoji sequences aren't supposed
	# to be normalized to nothing, but apparently this caused issues with
	# casefolding on ext4; also the mending heart caused a crash in xfs_scrub
	setf "\xf0\x9f\x92\x94" "broken heart"
	setf "\xe2\x9d\xa4\xef\xb8\x8f\xe2\x80\x8d\xf0\x9f\xa9\xb9" "mending heart"
	setf "\xf0\x9f\xa7\x91\xf0\x9f\x8f\xbb\xe2\x80\x8d\xe2\x9d\xa4\xef\xb8
	\x8f\xe2\x80\x8d\xf0\x9f\xa7\x91\xf0\x9f\x8f\xbc" "couple with heart"
	setf "\xf0\x9f\xa7\x91\xf0\x9f\x8f\xbb\xe2\x80\x8d\xe2\x9d\xa4\xef\xb8\x8f\xe2\x80\x8d\xf0\x9f\xa7\x91\xf0\x9f\x8f\xbf" "couple with heart, light and dark skin tone"

	# emoji heart hands with skin tone variations
	setf "\xf0\x9f\xab\xb6\xf0\x9f\x8f\xbf" "dark"
	setf "\xf0\x9f\xab\xb6\xf0\x9f\x8f\xbe" "medium dark"
	setf "\xf0\x9f\xab\xb6\xf0\x9f\x8f\xbd" "medium"
	setf "\xf0\x9f\xab\xb6\xf0\x9f\x8f\xbc" "medium light"
	setf "\xf0\x9f\xab\xb6\xf0\x9f\x8f\xbb" "light"
	setf "\xf0\x9f\xab\xb6" "neutral"

	ls -laR $testdir >> $seqres.full

	echo "Test files"
	testf "french_caf\xc3\xa9.txt" "NFC"
	testf "french_cafe\xcc\x81.txt" "NFD"

	testf "chinese_\xef\xbd\xb6.txt" "NFKC1"
	testf "chinese_\xe3\x82\xab.txt" "NFKC2"

	testf "greek_\xcf\x93.txt" "GREEK UPSILON WITH ACUTE AND HOOK SYMBOL, NFC"
	testf "greek_\xcf\x92\xcc\x81.txt" "GREEK UPSILON WITH ACUTE AND HOOK SYMBOL, NFD"
	testf "greek_\xce\x8e.txt" "GREEK UPSILON WITH ACUTE AND HOOK SYMBOL, NFKC"
	testf "greek_\xce\xa5\xcc\x81.txt" "GREEK UPSILON WITH ACUTE AND HOOK SYMBOL, NFKD"

	testf "arabic_\xef\xb7\xba.txt" "ARABIC LIGATURE SALLALLAHOU ALAYHE WASALLAM, NFC"
	testf "arabic_\xd8\xb5\xd9\x84\xd9\x89\x20\xd8\xa7\xd9\x84\xd9\x84\xd9\x87\x20\xd8\xb9\xd9\x84\xd9\x8a\xd9\x87\x20\xd9\x88\xd8\xb3\xd9\x84\xd9\x85.txt" "ARABIC LIGATURE SALLALLAHOU ALAYHE WASALLAM, NFKC"

	testf "urk\xc0\xafmoo" "FAKESLASH"

	testf "emoji_\xf0\x9f\xa6\x91\xf0\x9f\xa6\x8b\xf0\x9f\xa6\x89\xf0\x9f\xa6\x92.txt" "octopus butterfly owl giraffe emoji"

	testf "\x6c\x69\x6e\x65\x64\x72\x61\x77\x5f\x0a\xe2\x95\x94\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x97\x0a\xe2\x95\x91\x20\x6d\x65\x74\x61\x74\x61\x62\x6c\x65\x20\xe2\x95\x91\x0a\xe2\x95\x9f\xe2\x94\x80\xe2\x94\x80\xe2\x94\x80\xe2\x94\x80\xe2\x94\x80\xe2\x94\x80\xe2\x94\x80\xe2\x94\x80\xe2\x94\x80\xe2\x94\x80\xe2\x94\x80\xe2\x95\xa2\x0a\xe2\x95\x91\x20\x5f\x5f\x69\x6e\x64\x65\x78\x20\x20\x20\xe2\x95\x91\x0a\xe2\x95\x9a\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x90\xe2\x95\x9d\x0a.txt" "ugly box because we can"

	testf "moo\xe2\x80\xaegnp.txt" "Well say hello,"
	testf "mootxt.png" "Harvey"

	testf "mixed_t\xce\xbfp.txt" "greek omicron instead of o"
	testf "mixed_top.txt" "greek omicron instead of o"

	testf "hyphens_a\xe2\x80\x90b.txt" "hyphens"
	testf "hyphens_a-b.txt" "hyphens"

	testf "dz_digraph_dze.txt" "d-z digraph"
	testf "dz_digraph_\xca\xa3e.txt" "d-z digraph"

	testf "inadequate_al.txt" "is it l or is it 1"
	testf "inadequate_a1.txt" "is it l or is it 1"

	testf "prohibition_Rs.txt" "rupee symbol"
	testf "prohibition_\xe2\x82\xa8.txt" "rupee symbol"

	testf "zerojoin_moocow.txt" "zero width joiners"
	testf "zerojoin_moo\xe2\x80\x8dcow.txt" "zero width joiners"

	testf "combmark_\xe1\x80\x9c\xe1\x80\xad\xe1\x80\xaf.txt" "combining marks"
	testf "combmark_\xe1\x80\x9c\xe1\x80\xaf\xe1\x80\xad.txt" "combining marks"

	testd ".\xe2\x80\x8d" "zero width joiners in dot entry"
	testd "..\xe2\x80\x8d" "zero width joiners in dotdot entry"

	testf "toilet_bowl.\xf0\x9f\x9a\xbd" "toilet emoji"
	testf "toilet_bow\xe2\x80\x8dl.\xf0\x9f\x9a\xbd" "toilet emoji with zero width joiner"

	testchild "one_dot_leader" "job offer\xe2\x80\xa4pdf"
	testchild "small_full_stop" "job offer\xef\xb9\x92pdf"
	testchild "fullwidth_full_stop" "job offer\xef\xbc\x8epdf"
	testchild "syriac_supralinear" "job offer\xdc\x81pdf"
	testchild "syriac_sublinear" "job offer\xdc\x82pdf"
	testchild "lisu_letter_tone" "job offer\xea\x93\xb8pdf"
	testchild "actual_period" "job offer.pdf"
	testchild "one_dot_leader_zero_width_space" "job offer\xe2\x80\xa4\xe2\x80\x8dpdf"

	testf "job offer\xe2\x80\xa4pdf" "one dot leader"
	testf "job offer\xef\xb9\x92pdf" "small full stop"
	testf "job offer\xef\xbc\x8epdf" "fullwidth full stop"
	testf "job offer\xdc\x81pdf" "syriac supralinear full stop"
	testf "job offer\xdc\x82pdf" "syriac sublinear full stop"
	testf "job offer\xea\x93\xb8pdf" "li_su letter tone mya ti"
	testf "job offer.pdf" "actual period"

	testf "llamapirate\xf3\xa0\x80\x81\xf3\xa0\x81\x94\xf3\xa0\x81\xa8\xf3\xa0\x81\xa5\xf3\xa0\x80\xa0\xf3\xa0\x81\xb3\xf3\xa0\x81\xa1\xf3\xa0\x81\xac\xf3\xa0\x81\xa5\xf3\xa0\x81\xb3\xf3\xa0\x80\xa0\xf3\xa0\x81\xa6\xf3\xa0\x81\xaf\xf3\xa0\x81\xb2\xf3\xa0\x80\xa0\xf3\xa0\x81\x93\xf3\xa0\x81\xa5\xf3\xa0\x81\xa1\xf3\xa0\x81\xb4\xf3\xa0\x81\xb4\xf3\xa0\x81\xac\xf3\xa0\x81\xa5\xf3\xa0\x80\xa0\xf3\xa0\x81\xb7\xf3\xa0\x81\xa5\xf3\xa0\x81\xb2\xf3\xa0\x81\xa5\xf3\xa0\x80\xa0\xf3\xa0\x81\x95\xf3\xa0\x81\x93\xf3\xa0\x81\x84\xf3\xa0\x80\xa0\xf3\xa0\x80\xb1\xf3\xa0\x80\xb2\xf3\xa0\x80\xb0\xf3\xa0\x80\xb0\xf3\xa0\x80\xb0\xf3\xa0\x80\xb0\xf3\xa0\x81\xbf"
	testf "llamapirate"

	testf "\xf0\x9f\x92\x9c" "purple"
	testf "\xf0\x9f\x92\x99" "blue"
	testf "\xf0\x9f\x92\x9a" "green"
	testf "\xf0\x9f\x92\x9b" "yellow"
	testf "\xf0\x9f\xab\x80" "heart"
	testf "\xe2\x9d\xa4\xef\xb8\x8f" "red"
	testf "\xf0\x9f\xa4\x8e" "brown"
	testf "\xf0\x9f\xa4\x8d" "white"
	testf "\xf0\x9f\x96\xa4" "black"
	testf "\xf0\x9f\xa7\xa1" "orange"
	testf "\xe2\x99\xa5\xef\xb8\x8f" "red suit"

	testf "\xf0\x9f\x92\x94" "broken heart"
	testf "\xe2\x9d\xa4\xef\xb8\x8f\xe2\x80\x8d\xf0\x9f\xa9\xb9" "mending heart"
	testf "\xf0\x9f\xa7\x91\xf0\x9f\x8f\xbb\xe2\x80\x8d\xe2\x9d\xa4\xef\xb8
	\x8f\xe2\x80\x8d\xf0\x9f\xa7\x91\xf0\x9f\x8f\xbc" "couple with heart"
	testf "\xf0\x9f\xa7\x91\xf0\x9f\x8f\xbb\xe2\x80\x8d\xe2\x9d\xa4\xef\xb8\x8f\xe2\x80\x8d\xf0\x9f\xa7\x91\xf0\x9f\x8f\xbf" "couple with heart, light and dark skin tone"

	testf "\xf0\x9f\xab\xb6\xf0\x9f\x8f\xbf" "dark"
	testf "\xf0\x9f\xab\xb6\xf0\x9f\x8f\xbe" "medium dark"
	testf "\xf0\x9f\xab\xb6\xf0\x9f\x8f\xbd" "medium"
	testf "\xf0\x9f\xab\xb6\xf0\x9f\x8f\xbc" "medium light"
	testf "\xf0\x9f\xab\xb6\xf0\x9f\x8f\xbb" "light"
	testf "\xf0\x9f\xab\xb6" "neutral"

	echo "Uniqueness of inodes?"
	stat -c '%i' "${testdir}/"* \| sort \| uniq -c \| while read nr inum; do
	if [ "${nr}" -gt 1 ]; then
	echo "${nr} ${inum}"
	fi
	done

	echo "Test XFS online scrub, if applicable"

	if _check_xfs_scrub_does_unicode "$SCRATCH_MNT" "$SCRATCH_DEV"; then
	LC_ALL="C.UTF-8" ${XFS_SCRUB_PROG} -v -n "${SCRATCH_MNT}" 2>&1 \| filter_scrub > $tmp.scrub

	grep -q "french_" $tmp.scrub \|\| echo "No complaints about french e accent?"
	grep -q "greek_" $tmp.scrub \|\| echo "No complaints about greek letter mess?"
	grep -q "arabic_" $tmp.scrub \|\| echo "No complaints about arabic expanded string?"
	grep -q "mixed_" $tmp.scrub \|\| echo "No complaints about mixed script confusables?"
	grep -q "hyphens_" $tmp.scrub \|\| echo "No complaints about hyphenation confusables?"
	grep -q "dz_digraph_" $tmp.scrub \|\| echo "No complaints about single script confusables?"
	grep -q "inadequate_" $tmp.scrub \|\| echo "No complaints about inadequate rendering confusables?"
	grep -q "prohibition_" $tmp.scrub \|\| echo "No complaints about prohibited sequence confusables?"
	grep -q "zerojoin_" $tmp.scrub \|\| echo "No complaints about zero-width join confusables?"
	grep -q "toilet_" $tmp.scrub \|\| echo "No complaints about zero-width join confusables with emoji?"

	# Does xfs_scrub complain at all about the job offer files? Pre-2023
	# versions did not know to screen for that.
	if grep -q "job offer" $tmp.scrub; then
	grep -q 'job offer.xe2.x80.xa4pdf' $tmp.scrub \|\| echo "No complaints about one dot leader?"
	grep -q "job offer.xef.xb9.x92pdf" $tmp.scrub \|\| echo "No complaints about small full stop?"
	grep -q "job offer.xef.xbc.x8epdf" $tmp.scrub \|\| echo "No complaints about fullwidth full stop?"
	grep -q "job offer.xdc.x81pdf" $tmp.scrub \|\| echo "No complaints about syriac supralinear full stop?"
	grep -q "job offer.xdc.x82pdf" $tmp.scrub \|\| echo "No complaints about syriac sublinear full stop?"
	grep -q "job offer.xea.x93.xb8pdf" $tmp.scrub \|\| echo "No complaints about li_su letter tone mya ti?"
	grep -q "job offer.*could be confused with" $tmp.scrub \|\| echo "No complaints about confusing job offers?"
	grep -q "job offer.xe2.x80.xa4.xe2.x80.x8dpdf" $tmp.scrub \|\| echo "No complaints about one dot leader with invisible space?"
	grep -q "llamapirate" $tmp.scrub \|\| echo "No complaints about hidden llm instructions in filenames?"
	fi

	echo "Actual xfs_scrub output:" >> $seqres.full
	cat $tmp.scrub >> $seqres.full
	fi

	# success, all done
	status=0
	exit