#! /bin/bash
# SPDX-License-Identifier: GPL-2.0
# Copyright (c) 2017, Oracle and/or its affiliates.  All Rights Reserved.
#
# FS QA Test No. 454
#
# Create xattrs with multiple keys that all appear the same
# (in unicode, anyway) but point to different values.  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 attr

# Import common functions.
. ./common/attr

_require_scratch
_require_attrs
_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 $testdir
testfile="${testdir}/attrfile"
touch "${testfile}"

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

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

	$SETFATTR_PROG -n "user.${key}" -v "${value}" "${testfile}" > $tmp.output 2>&1
	if [ $? -ne 0 ]; then
		grep -q 'No space left on device' $tmp.output && \
			_notrun "ran out of space"
		cat $tmp.output
	fi
	echo "Storing ${key} ($(hexbytes "${key}")) -> ${value}" >> $seqres.full
}

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

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

	actual_value="$(_getfattr --absolute-names --only-values -n "user.${key}" "${testfile}")"
	if [ "${actual_value}" != "${value}" ]; then
		echo "Key ${key} has value ${actual_value}, expected ${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\x8ccow.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"

# encoding hidden tag characters in attrnames to create confusing xattrs
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" "secret instructions"
setf "llamapirate" "no secret instructions"

# 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"

_getfattr --absolute-names -d "${testfile}" >> $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\x8ccow.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"

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" "secret instructions"
testf "llamapirate" "no secret instructions"

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 keys?"
crazy_keys="$(_getfattr --absolute-names -d "${testfile}" | grep -E -c '(french_|chinese_|greek_|arabic_|urk)')"
expected_keys=11
test "${crazy_keys}" -ne "${expected_keys}" && echo "Expected ${expected_keys} keys, saw ${crazy_keys}."

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 "llamapirate" $tmp.scrub || echo "No complaints about hidden llm instructions in filenames?"
	echo "Actual xfs_scrub output:" >> $seqres.full
	echo "${output}" >> $seqres.full
fi

# success, all done
status=0
exit
