在Bash中，测试数组是否包含某个值的最简单方法是什么?
当前回答
保持简单:
Array1=( "item1" "item2" "item3" "item-4" )
var="item3"
count=$(echo ${Array1[@]} | tr ' ' '\n' | awk '$1 == "'"$var"'"{print $0}' | wc -l)
[ $count -eq 0 ] && echo "Not found" || echo "found"
其他回答
以下是几个可能实现的编译，包括集成验证和简单的基准测试(需要Bash >= 4.0):
#!/usr/bin/env bash
# Check if array contains item [$1: item, $2: array name]
function in_array_1() {
local needle="$1" item
local -n arrref="$2"
for item in "${arrref[@]}"; do
[[ "${item}" == "${needle}" ]] && return 0
done
return 1
}
# Check if array contains item [$1: item, $2: array name]
function in_array_2() {
local needle="$1" arrref="$2[@]" item
for item in "${!arrref}"; do
[[ "${item}" == "${needle}" ]] && return 0
done
return 1
}
# Check if array contains item [$1: item, $2: array name]
function in_array_3() {
local needle="$1" i
local -n arrref="$2"
for ((i=0; i < ${#arrref[@]}; i++)); do
[[ "${arrref[i]}" == "${needle}" ]] && return 0
done
return 1
}
# Check if array contains item [$1: item, $2..$n: array items]
function in_array_4() {
local needle="$1" item
shift
for item; do
[[ "${item}" == "${needle}" ]] && return 0
done
return 1
}
# Check if array contains item [$1: item, $2..$n: array items]
function in_array_5() {
local needle="$1" item
for item in "${@:2}"; do
[[ "${item}" == "${needle}" ]] && return 0
done
return 1
}
# Check if array contains item [$1: item, $2: array name]
function in_array_6() {
local needle="$1" arrref="$2[@]" array i
array=("${!arrref}")
for ((i=0; i < ${#array[@]}; i++)); do
[[ "${array[i]}" == "${needle}" ]] && return 0
done
return 1
}
# Check if array contains item [$1: item, $2..$n: array items]
function in_array_7() {
local needle="$1" array=("${@:2}") item
for item in "${array[@]}"; do
[[ "${item}" == "${needle}" ]] && return 0
done
return 1
}
# Check if array contains item [$1: item, $2..$n: array items]
function in_array_8() {
local needle="$1"
shift
while (( $# > 0 )); do
[[ "$1" == "${needle}" ]] && return 0
shift
done
return 1
}
#------------------------------------------------------------------------------
# Generate map for array [$1: name of source array, $2: name of target array]
# NOTE: target array must be pre-declared by caller using 'declare -A <name>'
function generate_array_map() {
local -n srcarr="$1" dstmap="$2"
local i key
dstmap=()
for i in "${!srcarr[@]}"; do
key="${srcarr[i]}"
[[ -z ${dstmap["${key}"]+set} ]] && dstmap["${key}"]=${i} || dstmap["${key}"]+=,${i}
done
}
# Check if array contains item [$1: item, $2: name of array map]
function in_array_9() {
local needle="$1"
local -n mapref="$2"
[[ -n "${mapref["${needle}"]+set}" ]] && return 0 || return 1
}
#------------------------------------------------------------------------------
# Test in_array function [$1: function name, $2: function description, $3: test array size]
function test() {
local tname="$1" tdesc="$2" tn=$3 ti=0 tj=0 ta=() tct=0 tepapre="" tepapost="" tepadiff=()
local -A tam=()
echo -e "\e[1m${tname} (${tdesc}):\e[0m"
# Generate list of currently defined variables
tepapre="$(compgen -v)"
# Fill array with random items
for ((ti=0; ti < ${tn}; ti++)); do
ta+=("${RANDOM} ${RANDOM} ${RANDOM} ${RANDOM}")
done
# Determine function call type (pass array items, pass array name, pass array map)
case "${tname}" in
"in_array_1"|"in_array_2"|"in_array_3"|"in_array_6") tct=0; ;;
"in_array_4"|"in_array_5"|"in_array_7"|"in_array_8") tct=1; ;;
"in_array_9") generate_array_map ta tam; tct=2; ;;
*) echo "Unknown in_array function '${tname}', aborting"; return 1; ;;
esac
# Verify in_array function is working as expected by picking a few random
# items and checking
echo -e "\e[1mVerification...\e[0m"
for ((ti=0; ti < 10; ti++)); do
tj=$(( ${RANDOM} % ${#ta[@]} ))
echo -n "Item ${tj} '${ta[tj]}': "
if (( ${tct} == 0 )); then
"${tname}" "${ta[tj]}" ta && echo -en "\e[1;32mok\e[0m" || echo -en "\e[1;31mnok\e[0m"
echo -n " "
"${tname}" "${ta[tj]}.x" ta && echo -en "\e[1;31mnok\e[0m" || echo -en "\e[1;32mok\e[0m"
elif (( ${tct} == 1 )); then
"${tname}" "${ta[tj]}" "${ta[@]}" && echo -en "\e[1;32mok\e[0m" || echo -en "\e[1;31mnok\e[0m"
echo -n " "
"${tname}" "${ta[tj]}.x" "${ta[@]}" && echo -en "\e[1;31mnok\e[0m" || echo -en "\e[1;32mok\e[0m"
elif (( ${tct} == 2 )); then
"${tname}" "${ta[tj]}" tam && echo -en "\e[1;32mok\e[0m" || echo -en "\e[1;31mnok\e[0m"
echo -n " "
"${tname}" "${ta[tj]}.x" tam && echo -en "\e[1;31mnok\e[0m" || echo -en "\e[1;32mok\e[0m"
fi
echo
done
# Benchmark in_array function
echo -en "\e[1mBenchmark...\e[0m"
time for ((ti=0; ti < ${#ta[@]}; ti++)); do
if (( ${tct} == 0 )); then
"${tname}" "${ta[ti]}" ta
elif (( ${tct} == 1 )); then
"${tname}" "${ta[ti]}" "${ta[@]}"
elif (( ${tct} == 2 )); then
"${tname}" "${ta[ti]}" tam
fi
done
# Generate list of currently defined variables, compare to previously
# generated list to determine possible environment pollution
echo -e "\e[1mEPA test...\e[0m"
tepapost="$(compgen -v)"
readarray -t tepadiff < <(echo -e "${tepapre}\n${tepapost}" | sort | uniq -u)
if (( ${#tepadiff[@]} == 0 )); then
echo -e "\e[1;32mclean\e[0m"
else
echo -e "\e[1;31mpolluted:\e[0m ${tepadiff[@]}"
fi
echo
}
#------------------------------------------------------------------------------
# Test in_array functions
n=5000
echo
( test in_array_1 "pass array name, nameref reference, for-each-loop over array items" ${n} )
( test in_array_2 "pass array name, indirect reference, for-each-loop over array items" ${n} )
( test in_array_3 "pass array name, nameref reference, c-style for-loop over array items by index" ${n} )
( test in_array_4 "pass array items, for-each-loop over arguments" ${n} )
( test in_array_5 "pass array items, for-each-loop over arguments as array" ${n} )
( test in_array_6 "pass array name, indirect reference + array copy, c-style for-loop over array items by index" ${n} )
( test in_array_7 "pass array items, copy array from arguments as array, for-each-loop over array items" ${n} )
( test in_array_8 "pass array items, while-loop, shift over arguments" ${n} )
( test in_array_9 "pre-generated array map, pass array map name, direct test without loop" ${n} )
结果:
in_array_1 (pass array name, nameref reference, for-each-loop over array items):
Verification...
Item 862 '19528 10140 12669 17820': ok ok
Item 2250 '27262 30442 9295 24867': ok ok
Item 4794 '3857 17404 31925 27993': ok ok
Item 2532 '14553 12282 26511 32657': ok ok
Item 1911 '21715 8066 15277 27126': ok ok
Item 4289 '3081 10265 16686 19121': ok ok
Item 4837 '32220 1758 304 7871': ok ok
Item 901 '20652 23880 20634 14286': ok ok
Item 2488 '14578 8625 30251 9343': ok ok
Item 4165 '4514 25064 29301 7400': ok ok
Benchmark...
real 1m11,796s
user 1m11,262s
sys 0m0,473s
EPA test...
clean
in_array_2 (pass array name, indirect reference, for-each-loop over array items):
Verification...
Item 2933 '17482 25789 27710 2096': ok ok
Item 3584 '876 14586 20885 8567': ok ok
Item 872 '176 19749 27265 18038': ok ok
Item 595 '6597 31710 13266 8813': ok ok
Item 748 '569 9200 28914 11297': ok ok
Item 3791 '26477 13218 30172 31532': ok ok
Item 2900 '3059 8457 4879 16634': ok ok
Item 676 '23511 686 589 7265': ok ok
Item 2248 '31351 7961 17946 24782': ok ok
Item 511 '8484 23162 11050 426': ok ok
Benchmark...
real 1m11,524s
user 1m11,086s
sys 0m0,437s
EPA test...
clean
in_array_3 (pass array name, nameref reference, c-style for-loop over array items by index):
Verification...
Item 1589 '747 10250 20133 29230': ok ok
Item 488 '12827 18892 31996 1977': ok ok
Item 801 '19439 25243 24485 24435': ok ok
Item 2588 '17193 18893 21610 9302': ok ok
Item 4436 '7100 655 8847 3068': ok ok
Item 2620 '19444 6457 28835 24717': ok ok
Item 4398 '4420 16336 612 4255': ok ok
Item 2430 '32397 2402 12631 29774': ok ok
Item 3419 '906 5361 32752 7698': ok ok
Item 356 '9776 16485 20838 13330': ok ok
Benchmark...
real 1m17,037s
user 1m17,019s
sys 0m0,005s
EPA test...
clean
in_array_4 (pass array items, for-each-loop over arguments):
Verification...
Item 1388 '7932 15114 4025 15625': ok ok
Item 3900 '23863 25328 5632 2752': ok ok
Item 2678 '31296 4216 17485 8874': ok ok
Item 1893 '16952 29047 29104 23384': ok ok
Item 1616 '19543 5999 4485 22929': ok ok
Item 93 '14456 2806 12829 19552': ok ok
Item 265 '30961 19733 11863 3101': ok ok
Item 4615 '10431 9566 25767 13518': ok ok
Item 576 '11726 15104 11116 74': ok ok
Item 3829 '19371 25026 6252 29478': ok ok
Benchmark...
real 1m30,912s
user 1m30,740s
sys 0m0,011s
EPA test...
clean
in_array_5 (pass array items, for-each-loop over arguments as array):
Verification...
Item 1012 '29213 31971 21483 30225': ok ok
Item 2802 '4079 5423 29240 29619': ok ok
Item 473 '6968 798 23936 6852': ok ok
Item 2183 '20734 4521 30800 2126': ok ok
Item 3059 '14952 9918 15695 19309': ok ok
Item 1424 '25784 28380 14555 21893': ok ok
Item 1087 '16345 19823 26210 20083': ok ok
Item 257 '28890 5198 7251 3866': ok ok
Item 3986 '29035 19288 12107 3857': ok ok
Item 2509 '9219 32484 12842 27472': ok ok
Benchmark...
real 1m53,485s
user 1m53,404s
sys 0m0,077s
EPA test...
clean
in_array_6 (pass array name, indirect reference + array copy, c-style for-loop over array items by index):
Verification...
Item 4691 '25498 10521 20673 14948': ok ok
Item 263 '25265 29824 3876 14088': ok ok
Item 2550 '2416 14274 12594 29740': ok ok
Item 2269 '2769 11436 3622 28273': ok ok
Item 3246 '23730 25956 3514 17626': ok ok
Item 1059 '10776 12514 27222 15640': ok ok
Item 53 '23813 13365 16022 4092': ok ok
Item 1503 '6593 23540 10256 17818': ok ok
Item 2452 '12600 27404 30960 26759': ok ok
Item 2526 '21190 32512 23651 7865': ok ok
Benchmark...
real 1m54,793s
user 1m54,326s
sys 0m0,457s
EPA test...
clean
in_array_7 (pass array items, copy array from arguments as array, for-each-loop over array items):
Verification...
Item 2212 '12127 12828 27570 7051': ok ok
Item 1393 '19552 26263 1067 23332': ok ok
Item 506 '18818 8253 14924 30710': ok ok
Item 789 '9803 1886 17584 32686': ok ok
Item 1795 '19788 27842 28044 3436': ok ok
Item 376 '4372 16953 17280 4031': ok ok
Item 4846 '19130 6261 21959 6869': ok ok
Item 2064 '2357 32221 22682 5814': ok ok
Item 4866 '10928 10632 19175 14984': ok ok
Item 1294 '8499 11885 5900 6765': ok ok
Benchmark...
real 2m35,012s
user 2m33,578s
sys 0m1,433s
EPA test...
clean
in_array_8 (pass array items, while-loop, shift over arguments):
Verification...
Item 134 '1418 24798 20169 9501': ok ok
Item 3986 '12160 12021 29794 29236': ok ok
Item 1607 '26633 14260 18227 898': ok ok
Item 2688 '18387 6285 2385 18432': ok ok
Item 603 '1421 306 6102 28735': ok ok
Item 625 '4530 19718 30900 1938': ok ok
Item 4033 '9968 24093 25080 8179': ok ok
Item 310 '6867 9884 31231 29173': ok ok
Item 661 '3794 4745 26066 22691': ok ok
Item 4129 '3039 31766 6714 4921': ok ok
Benchmark...
real 5m51,097s
user 5m50,566s
sys 0m0,495s
EPA test...
clean
in_array_9 (pre-generated array map, pass array map name, direct test without loop):
Verification...
Item 3696 '661 6048 13881 26901': ok ok
Item 815 '29729 13733 3935 20697': ok ok
Item 1076 '9220 3405 18448 7240': ok ok
Item 595 '8912 2886 13678 24066': ok ok
Item 2803 '13534 23891 5344 652': ok ok
Item 1810 '12528 32150 7050 1254': ok ok
Item 4055 '21840 7436 1350 15443': ok ok
Item 2416 '19550 28434 17110 31203': ok ok
Item 1630 '21054 2819 7527 953': ok ok
Item 1044 '30152 22211 22226 6950': ok ok
Benchmark...
real 0m0,128s
user 0m0,128s
sys 0m0,000s
EPA test...
clean
别胡闹了!使您的解决方案简单、干净和可重用。
这些函数负责索引数组和关联数组。可以通过将搜索算法从线性搜索升级为二进制搜索(用于大型数据集)来改进它们。
##
# Determines if a value exists in an array.
###
function hasArrayValue ()
{
local -r needle="{$1:?}"
local -nr haystack="{$2:?}" # Where you pass by reference to get the entire array in one argument.
# Linear search. Upgrade to binary search for large datasets.
for value in "${haystack[@]}"; do
if [[ "$value" == "$needle" ]]; then
return 0
fi
done
return 1
}
##
# Determines if a value exists in an associative array / map.
###
function hasMapValue ()
{
local -r needle="{$1:?}"
local -nr haystack="{$2:?}"
# Linear search. Upgrade to binary search for large datasets.
for value in "${haystack[@]}"; do
if [[ $value == $needle ]]; then
return 0
fi
done
return 1
}
是的，同样的逻辑，但在处理bash时，如果函数的名称可以让您知道迭代的对象(或不迭代的对象)，则可能(可能)有用。
这对我来说很管用:
# traditional system call return values-- used in an `if`, this will be true when returning 0. Very Odd.
contains () {
# odd syntax here for passing array parameters: http://stackoverflow.com/questions/8082947/how-to-pass-an-array-to-a-bash-function
local list=$1[@]
local elem=$2
# echo "list" ${!list}
# echo "elem" $elem
for i in "${!list}"
do
# echo "Checking to see if" "$i" "is the same as" "${elem}"
if [ "$i" == "${elem}" ] ; then
# echo "$i" "was the same as" "${elem}"
return 0
fi
done
# echo "Could not find element"
return 1
}
示例调用:
arr=("abc" "xyz" "123")
if contains arr "abcx"; then
echo "Yes"
else
echo "No"
fi
a=(b c d)
if printf '%s\0' "${a[@]}" | grep -Fqxz c
then
echo 'array “a” contains value “c”'
fi
如果你喜欢，你可以使用相同的长选项:
--fixed-strings --quiet --line-regexp --null-data
: NeedleInArgs "$needle" "${haystack[@]}"
: NeedleInArgs "$needle" arg1 arg2 .. argN
NeedleInArgs()
{
local a b;
printf -va '\n%q\n' "$1";
printf -vb '%q\n' "${@:2}";
case $'\n'"$b" in (*"$a"*) return 0;; esac;
return 1;
}
使用:
NeedleInArgs "$needle" "${haystack[@]}" && echo "$needle" found || echo "$needle" not found;
对于bash v3.1及以上版本(printf -v支持) 没有分叉，也没有外部程序 没有循环(除了bash中的内部扩展) 适用于所有可能的值和数组，没有异常，没有什么可担心的
也可以直接使用，比如:
if NeedleInArgs "$input" value1 value2 value3 value4;
then
: input from the list;
else
: input not from list;
fi;
对于从v20.5 b到v3.0的bash, printf缺少-v，因此需要额外的2个fork(但不需要执行，因为printf是bash内置的):
NeedleInArgs()
{
case $'\n'"`printf '%q\n' "${@:2}"`" in
(*"`printf '\n%q\n' "$1"`"*) return 0;;
esac;
return 1;
}
注意，我测试了时间:
check call0: n: t4.43 u4.41 s0.00 f: t3.65 u3.64 s0.00 l: t4.91 u4.90 s0.00 N: t5.28 u5.27 s0.00 F: t2.38 u2.38 s0.00 L: t5.20 u5.20 s0.00
check call1: n: t3.41 u3.40 s0.00 f: t2.86 u2.84 s0.01 l: t3.72 u3.69 s0.02 N: t4.01 u4.00 s0.00 F: t1.15 u1.15 s0.00 L: t4.05 u4.05 s0.00
check call2: n: t3.52 u3.50 s0.01 f: t3.74 u3.73 s0.00 l: t3.82 u3.80 s0.01 N: t2.67 u2.67 s0.00 F: t2.64 u2.64 s0.00 L: t2.68 u2.68 s0.00
Call0和call1是对另一个快速pure-bash变体调用的不同变体 Call2在这里。 N=notfound F=firstmatch L=lastmatch 小写字母为短数组，大写字母为长数组
正如您所看到的，这里的这个变体有一个非常稳定的运行时，所以它不太依赖于匹配位置。运行时主要由数组长度决定。搜索变量的运行时高度依赖于匹配位置。所以在边缘情况下，这个变体可以(快得多)。
但非常重要的是，搜索变量的RAM效率更高，因为这里的这个变量总是将整个数组转换为一个大字符串。
所以如果你的内存很紧，你希望大部分比赛都是早期的，那么就不要在这里使用这个。但是，如果您想要一个可预测的运行时，有很长的数组来匹配(期望延迟或根本不匹配)，并且双RAM使用也不是太大的问题，那么这里有一些优势。
定时测试脚本:
in_array()
{
local needle="$1" arrref="$2[@]" item
for item in "${!arrref}"; do
[[ "${item}" == "${needle}" ]] && return 0
done
return 1
}
NeedleInArgs()
{
local a b;
printf -va '\n%q\n' "$1";
printf -vb '%q\n' "${@:2}";
case $'\n'"$b" in (*"$a"*) return 0;; esac;
return 1;
}
loop1() { for a in {1..100000}; do "$@"; done }
loop2() { for a in {1..1000}; do "$@"; done }
run()
{
needle="$5"
arr=("${@:6}")
out="$( ( time -p "loop$2" "$3" ) 2>&1 )"
ret="$?"
got="${out}"
syst="${got##*sys }"
got="${got%"sys $syst"}"
got="${got%$'\n'}"
user="${got##*user }"
got="${got%"user $user"}"
got="${got%$'\n'}"
real="${got##*real }"
got="${got%"real $real"}"
got="${got%$'\n'}"
printf ' %s: t%q u%q s%q' "$1" "$real" "$user" "$syst"
[ -z "$rest" ] && [ "$ret" = "$4" ] && return
printf 'FAIL! expected %q got %q\n' "$4" "$ret"
printf 'call: %q\n' "$3"
printf 'out: %q\n' "$out"
printf 'rest: %q\n' "$rest"
printf 'needle: %q\n' "$5"
printf 'arr: '; printf ' %q' "${@:6}"; printf '\n'
exit 1
}
check()
{
printf 'check %q: ' "$1"
run n 1 "$1" 1 needle a b c d
run f 1 "$1" 0 needle needle a b c d
run l 1 "$1" 0 needle a b c d needle
run N 2 "$1" 1 needle "${rnd[@]}"
run F 2 "$1" 0 needle needle "${rnd[@]}"
run L 2 "$1" 0 needle "${rnd[@]}" needle
printf '\n'
}
call0() { chk=("${arr[@]}"); in_array "$needle" chk; }
call1() { in_array "$needle" arr; }
call2() { NeedleInArgs "$needle" "${arr[@]}"; }
rnd=()
for a in {1..1000}; do rnd+=("$a"); done
check call0
check call1
check call2
