我需要帮助使这个 bash 脚本运行得更快

Question

我有一个脚本，它获取本地日志文件，读取每一行、卡的 ID 和 IO 类型，提取相关数据字符串，将该字符串与定义文件进行比较，然后为每个位分配 T 或 F 值。然后，它创建一个新的日志文件，其中包含人类可读的位名称和 T/F 值。

以下是我输入的一些示例行：

[09:00:15] STA8   09:58:47 28DEC23  I/O In  07 0000  0000  0000  0000
[09:00:15] STA8   09:58:47 28DEC23  I/O In  08 0000  0010  0000  0000
[09:00:15] STA8   09:58:47 28DEC23  I/O Out 07 --00  ++++  ++++  ++00
[09:00:15] STA8   09:58:47 28DEC23  I/O Out 08 ++++  ++0+  ++++  0000

以下是一些输出示例行：

[09:00:15] STA8   09:58:47 28DEC23  I/O In  07 1:F 2:F 3:F ...
[09:00:15] STA8   09:58:47 28DEC23  I/O In  08 1:F 2:F 3:F ...
[09:00:15] STA8   09:58:47 28DEC23  I/O Out 07 1:F 2:F 3:F 4:F 5:T 6:T 7:T  8:T 9:T 10:T 11:T 12:T ...
[09:00:15] STA8   09:58:47 28DEC23  I/O Out 08 1:T 2:T 3:T 4:T 5:T 6:T 7:F  8:T ...

该脚本运行良好，但对于不是很长的输入文件，可能需要大约 18 秒才能完成。运行 sed 的同一个输入文件，其中包含一长串要查找和制作的更改，几乎是即时的。我不知道为什么这个要花这么长时间。这个确实引用了我制作的包含每一位名称的txt文件，所以我想知道它是否每次都会进行太多不必要的读取，也许我可以只加载它们一次？

这是我的脚本：

#!/bin/bash

#Variables
d=$(date +%Y-%m-%d_%H. -d '1 hour ago')

# Function to read label files and store labels in arrays
read_label_files() {
    local station_id="$1"
    local io_type="$2"
    local card_number="$3"

    local label_file="s${station_id:3}${io_type}${card_number}.txt"
    local label_array=()

    if [ -f "$label_file" ]; then
        IFS=',' read -ra label_array < "$label_file"
    fi

    echo "${label_array[@]}"
}

# Function to add extracted string into an array
data_string_array=()

for ((i=0; i<${#data_string}; i++)); do
    data_string_array[i]="${data_string:i:1}"
done


# Function to convert input values to T or F
convert_input_values() {
    local data_string="$1"

    local output_string=""

    for (( i=0; i<${#data_string}; i++ )); do
        if [ "${data_string:$i:1}" == "1" ]; then
            output_string+="T "
        else
            output_string+="F "
        fi
    done

    echo "$output_string"
}

# Function to convert output values to T or F
convert_output_values() {
    local data_string="$1"

    local output_string=""

    for (( i=0; i<${#data_string}; i++ )); do
        if [ "${data_string:$i:1}" == "+" ]; then
            output_string+="T "
        else
            output_string+="F "
        fi
    done

    echo "$output_string"
}

# Initialize arrays for inputs and outputs
declare -A input_changes
declare -A output_changes

# Process the input file
while read -r line; do
    timestamp=$(echo "$line" | awk '{print $1}')
    station_id=$(echo "$line" | awk '{print $2}')
    io_type=$(echo "$line" | awk '{print $6}')
    card_number=$(echo "$line" | awk '{print $7}')
    logdate=$(echo "$line" | awk '{print $4}')

    # Remove spaces from the data string
    data_string=$(echo "$line" | awk '{$1=$2=$3=$4=$5=$6=$7=""; print $0}' | tr -d ' ')

    if [ "$io_type" = "In" ]; then
        # Read input label file and store labels in an array
        input_labels=($(read_label_files "$station_id" "i" "$card_number"))

        # Convert input values to T or F
        converted_values=($(convert_input_values "$data_string"))

        # Store current values for comparison
        current_values="${input_changes[$station_id,$card_number]}"
        input_changes[$station_id,$card_number]="$data_string"

        # Print the output line with labels and T/F values
        output_line="$timestamp $station_id $logdate I/O In  $card_number -"
        if [ -z "$current_values" ]; then
#       echo "NEW"
            for ((i=0; i<${#input_labels[@]}; i++)); do
                output_line+=" ${input_labels[i]}:${converted_values[i]}"
            done
        else
#       echo "UPDATE"
            for ((i=0; i<${#current_values}; i++)); do
            current_array[i]="${current_values:i:1}"
            done
            #current_array=($current_values)
            for ((i=0; i<${#data_string}; i++)); do
            data_string_array[i]="${data_string:i:1}"
            done
#echo "old ${current_array[@]}"
#echo "new ${data_string_array[@]}"

            for ((i=0; i<${#input_labels[@]}; i++)); do
#echo "Comparing index $i: data_string_array[${i}] = ${data_string_array[i]}, current_array[${i}] = ${current_array[i]}"
            if [ "${data_string_array[i]}" != "${current_array[i]}" ]; then
                output_line+=" ${input_labels[i]}:${converted_values[i]}"
            fi
            done

#echo "Output Line: $output_line"

        fi
        echo "$output_line" >> /home/logs/IO.$d.txt

    elif [ "$io_type" = "Out" ]; then
        # Read output label file and store labels in an array
        output_labels=($(read_label_files "$station_id" "o" "$card_number"))

        # Convert output values to T or F
        converted_values=($(convert_output_values "$data_string"))

        # Store current values for comparison
        current_values="${output_changes[$station_id,$card_number]}"
        output_changes[$station_id,$card_number]="$data_string"

        # Print the output line with labels and T/F values
        output_line="$timestamp $station_id $logdate I/O Out $card_number -"
        if [ -z "$current_values" ]; then
#       echo NEW
            for ((i=0; i<${#output_labels[@]}; i++)); do
                output_line+=" ${output_labels[i]}:${converted_values[i]}"
            done
        else
#       echo UPDATE
            for ((i=0; i<${#current_values}; i++)); do
            current_array[i]="${current_values:i:1}"
            done
            #current_array=($current_values)
            for ((i=0; i<${#data_string}; i++)); do
            data_string_array[i]="${data_string:i:1}"
            done
#echo "old ${current_array[@]}"
#echo "new ${data_string_array[@]}"
            for ((i=0; i<${#output_labels[@]}; i++)); do
#echo "Comparing index $i: data_string_array[${i}] = ${data_string_array[i]}, current_array[${i}] = ${current_array[i]}"
            if [ "${data_string_array[i]}" != "${current_array[i]}" ]; then
                    output_line+=" ${output_labels[i]}:${converted_values[i]}"
                fi
            done
        fi
        echo "$output_line" >> /home/logs/IO.$d.txt
    fi
done < /home/logs/DataLog.$d.txt

Answer 1

答案是不要使用 bash 来做这种事情。我将为此学习Python。