在bash 4.1下使用带有变量名的关联数组

Question

我试图在bash-4.1下解析这样的多个文件

$cat hostname_abc.txt
host_type type_foo
SoftA version123
SoftB version456

获取输出，您可以看到使用Soft [A，B]版本的次数，按主机类型分组：

$./list_versions.sh
[type_foo] 11 times
    SoftA:
        [version123] 1 times
        [version444] 5 times
        [version567] 5 times
    SoftB:
        [version456] 9 times
        [version777] 2 times
[type_bar] 6 times
    SoftA:
        [version444] 6 times
    SoftB:
        [version111] 4 times
        [version777] 2 times

我事先不知道host_type和版本的列表。所以我试图在关联数组中保存每个host_type的计数，并动态创建关联数组的名称，这些数组存储基于模板host_type_Soft [A，B]的每个host_type的每个版本的Soft [A，B]的计数。

我尝试了很多次语法和间接的不同变化，所以我重新编写了一个更符合我目标的可读脚本：

#!/usr/bin/env bash

# ----- generated test conditions -----
echo -e "host_type typeA\nSoftA v2\nSoftB v1" > hostname_1.txt
echo -e "host_type typeB\nSoftA v1\nSoftB v1" > hostname_2.txt
echo -e "host_type typeB\nSoftA v1\nSoftB v0" > hostname_3.txt
echo -e "host_type typeA\nSoftA v0\nSoftB v0" > hostname_4.txt
echo -e "host_type typeA\nSoftA v3\nSoftB v2" > hostname_5.txt
echo -e "host_type typeB\nSoftA v3\nSoftB v1" > hostname_6.txt
echo -e "host_type typeB\nSoftA v2\nSoftB v2" > hostname_7.txt
echo -e "host_type typeA\nSoftA v1\nSoftB v2" > hostname_8.txt
echo -e "host_type typeC\nSoftA v0\nSoftB v4" > hostname_9.txt
list_hostname() {
    for i in {1..9}; do
        echo "hostname_${i}.txt"
    done
}

declare -A list_host_type

while read f; do

    #parse the hostname files
    while read l; do
        [[ $l = *"host_type"* ]] && host_type="$( echo $l | cut -d' ' -f2)"
        [[ $l = *"SoftA"* ]] && versionA="$( echo $l | cut -d' ' -f2)"
        [[ $l = *"SoftB"* ]] && versionB="$( echo $l | cut -d' ' -f2)"
    done < <( cat "$f" )

    #count the number of hosts by host_type
    [[ ${list_host_type[$host_type]} ]] && ((list_host_type[$host_type]++)) || list_host_type[$host_type]='1'

    #create associative arrays with a name only know at runtime
    declare -A "${host_type}_SoftA"
    declare -A "${host_type}_SoftB"

    #count the number of host for the couple host_type and Soft[A,B], stored on the dynamically named assiociative array
    [[ ${${host_type}_SoftA[$versionA]} ]] && ((${host_type}_SoftA[$versionA]++)) || ${host_type}_SoftA[$versionA]='1'
    [[ ${${host_type}_SoftB[$versionB]} ]] && ((${host_type}_SoftB[$versionB]++)) || ${host_type}_SoftB[$versionB]='1'
done < <( list_hostname )

#print a non pretty-formated output
echo '==== result ====='
for m in "${!list_host_type[@]}"; do
    echo "host type: $m  count: ${list_model[$m]}"
    for versionA in "${!${m}_softA[@]}"; do
        echo "    SoftA  version: $versionA  count: ${${m}_SoftA[$versionA]}"
    done
    for versionB in "${!${m}_softB[@]}"; do
        echo "    SoftB  version: $versionB  count: ${${m}_SoftB[$versionB]}"
    done
done

我知道他们是实现我的目标的其他方法，但我想知道我是否可以使用bash-4.1以这种方式关联。

Answer 1

我不认为你可以在Bash中使用带有数组的动态变量名。 （我尝试了一些但却无法弄清楚语法。）即使可能，我认为理解起来也非常困难。

---

可能的解决方法可能是使用单个关联数组，使用“复合键”。也就是说，例如使用主机类型，软件和版本的逗号分隔值：

while read f; do
    line=0
    while read col1 col2; do
        if [[ $line = 0 ]]; then
            host_type=$col2
        else
            soft=$col1
            version=$col2
            index=$host_type,$soft,$version
            ((list_host_type[$index]++))
        fi
        ((line++))
    done < <( cat "$f" )
done < <( list_hostname )

for m in "${!list_host_type[@]}"; do
    echo $m = ${list_host_type[$m]}
done

对于您的样本数据，这将产生：

typeA,SoftA,v2 = 1
typeA,SoftA,v3 = 1
typeA,SoftA,v0 = 1
typeA,SoftA,v1 = 1
typeB,SoftA,v3 = 1
typeB,SoftA,v2 = 1
typeB,SoftA,v1 = 2
typeA,SoftB,v2 = 2
typeA,SoftB,v1 = 1
typeA,SoftB,v0 = 1
typeC,SoftB,v4 = 1
typeB,SoftB,v2 = 1
typeB,SoftB,v0 = 1
typeB,SoftB,v1 = 2
typeC,SoftA,v0 = 1

然后使用此关联数组来计算所需的统计信息。这是一个粗略的示例实现：

get_host_types() {
    local names=(${!list_host_type[@]})
    printf "%s\n" "${names[@]%%,*}" | sort -u
}

get_soft() {
    local host_type=$1
    local names=(${!list_host_type[@]})
    for name in "${names[@]}"; do
        [[ ${name%%,*} = $host_type ]] && echo $name
    done | cut -d, -f2 | sort -u
}

get_versions() {
    local prefix=$1
    local names=(${!list_host_type[@]})
    for name in "${names[@]}"; do
        [[ ${name%,*} = $prefix ]] && echo $name
    done | cut -d, -f3 | sort -u
}

indent="    "
for host_type in $(get_host_types); do
    echo "[$host_type]"
    for soft in $(get_soft $host_type); do
        echo "$indent$soft:"
        for version in $(get_versions $host_type,$soft); do
            index=$host_type,$soft,$version
            echo "$indent$indent[$version] ${list_host_type[$index]} times"
        done
    done
done

作为输出产生：

[typeA]
    SoftA:
        [v0] 1 times
        [v1] 1 times
        [v2] 1 times
        [v3] 1 times
    SoftB:
        [v0] 1 times
        [v1] 1 times
        [v2] 2 times
[typeB]
    SoftA:
        [v1] 2 times
        [v2] 1 times
        [v3] 1 times
    SoftB:
        [v0] 1 times
        [v1] 2 times
        [v2] 1 times
[typeC]
    SoftA:
        [v0] 1 times
    SoftB:
        [v4] 1 times

总而言之，使用适当的编程语言实现它会更好。