How to remove the file if multiple conditions are met

Introduction

In Linux, Bash is a popular shell language used for scripting and automation tasks. When working with files, it’s common to have to delete certain information based on specific conditions. In this blog post, we will explore how to remove file content if multiple conditions are met using Bash scripting. We will use an example of deleting information from a file called portscan.txt only if certain conditions are satisfied.

Understanding the Problem

The first step to solving this problem is to understand the conditions that need to be met before deleting information from the file. The conditions are:

• The file with the domains should have 2 or less lines.
• The ports should only be 80 or 443 (i.e., I don’t want to delete the file if 8080, 8443, or any other port exists in the file).

We need to check if these conditions are satisfied before deleting any information from the file. If any of these conditions are not met, we should not delete any information from the file.

Writing the Bash Script

Let’s take a look at the Bash script that we have so far:

#!/bin/bash

lines=$(cat portscan.txt | wc -l)
ports=$(cat portscan.txt | grep -Pv '(^|[^0-9])(80|443)($|[^0-9])')

if [[ $lines < 3 ]] && (( $ports != 80 || $ports != 443 )); then
    echo "I need to delete this"
else
    echo "I will NOT delete this..."
fi

The script starts with the shebang line, which tells the system to use the Bash shell to execute the script. The next two lines of the script store the number of lines in the file and the ports in the file in the variables lines and ports, respectively.

The next line of the script checks if the conditions are met before deleting any information from the file. The if statement checks if the number of lines in the file is less than 3 and if the ports in the file are not equal to 80 or 443. If both conditions are satisfied, the script prints “I need to delete this”. Otherwise, it prints “I will NOT delete this…”.

Understanding the Code

Let’s break down the code and understand how it works.

The first line of the script is the shebang line. It tells the system to use the Bash shell to execute the script.

#!/bin/bash

The next two lines of the script store the number of lines in the file and the ports in the file in the variables lines and ports, respectively.

lines=$(cat portscan.txt | wc -l)
ports=$(cat portscan.txt | grep -Pv '(^|[^0-9])(80|443)($|[^0-9])')

The cat command is used to display the contents of the file. The wc -l command is used to count the number of lines in the file. The output of the cat command is piped to the wc -l command, which counts the number of lines in the file and stores the result in the lines variable.

The grep -Pv '(^|[^0-9])(80|443)($|[^0-9])' command is used to search for lines in the file that do not contain the ports 80 or 443. The grep command with the -P option is used to enable Perl-compatible regular expressions. The -v option is used to invert the search, i.e., to search for lines that do not contain the specified pattern. The regular expression '(^|[^0-9])(80|443)($|[^0-9])' matches the ports 80 or 443 and any non-numeric characters that may precede or follow them. The output of the grep command is stored in the ports variable.

The next line of the script checks if the conditions are met before deleting any information from the file.

if [[ $lines < 3 ]] && (( $ports != 80 || $ports != 443 )); then
    echo "I need to delete this"
else
    echo "I will NOT delete this..."
fi

The if statement checks if the number of lines in the file is less than 3 and if the ports in the file are not equal to 80 or 443. If both conditions are satisfied, the script prints “I need to delete this”. Otherwise, it prints “I will NOT delete this…”.

Improving the Code

The Bash script we have so far works correctly, but there are some improvements we can make to make it more efficient and readable.

Instead of using the cat command to display the contents of the file and then piping it to another command, we can use the < operator to redirect the contents of the file to another command. This is more efficient because it avoids creating unnecessary subshells.

lines=$(wc -l < portscan.txt)
ports=$(grep -Pv '(^|[^0-9])(80|443)($|[^0-9])' < portscan.txt)

We can also simplify the regular expression used in the grep command by using the -w option, which matches whole words only.

ports=$(grep -wv '8080|8443' < portscan.txt)

The grep -wv '8080|8443' command is used to search for lines in the file that do not contain the ports 80 or 443. The -w option is used to match whole words only. The | operator is used to specify multiple patterns to search for. The regular expression '8080|8443' matches the ports 8080 and 8443.

The improved Bash script looks like this:

#!/bin/bash

lines=$(wc -l < portscan.txt)
ports=$(grep -wv '8080|8443' < portscan.txt)

if [[ $lines < 3 ]] && [[ -z $ports ]]; then
    echo "I need to delete this"
else
    echo "I will NOT delete this..."
fi

The [[ -z $ports ]] condition checks if the ports variable is empty. If it is empty, it means that no lines were found in the file that do not contain the ports 80 or 443.

Conclusion

In this blog post, we explored how to remove file content if multiple conditions are met using Bash scripting. We used an example of deleting information from a file called portscan.txt only if certain conditions were satisfied. We learned how to use the cat command to display the contents of a file, how to use the wc command to count the number of lines in a file, and how to use the grep command to search for patterns in a file. We also learned how to use the < operator to redirect the contents of a file to another command, how to simplify regular expressions using the -w option, and how to use the -z option to check if a variable is empty.

To delete the file portscan.txt if certain conditions are met, you can use the following script:

#!/bin/bash

# Count the number of lines in the file
lines=$(wc -l < portscan.txt)

# Check if the number of lines is less than or equal to 2
if [[ $lines -le 2 ]]; then
  # Check if all the ports in the file are either 80 or 443
  if grep -Pv '(^|[^0-9])(80|443)($|[^0-9])' portscan.txt; then
    # If there are any ports that are not 80 or 443, do not delete the file
    echo "I will NOT delete this..."
  else
    # If all the ports are 80 or 443, delete the file
    rm portscan.txt
    echo "I have deleted the file."
  fi
else
  # If the number of lines is greater than 2, do not delete the file
  echo "I will NOT delete this..."
fi

This script first checks if the number of lines in the file is less than or equal to 2. If it is, it then checks if all the ports in the file are either 80 or 443. If all the ports are 80 or 443, it deletes the file. If any of the ports are not 80 or 443, or if the number of lines is greater than 2, it does not delete the file.

I hope this helps! Let me know if you have any questions.

checkfile() {
    awk '
        BEGIN {
            FS = ":"
            status = 1
            ports[80] = 1
            ports[443] = 1
        }
        NR == 3 || !($2 in ports) {status = 0; exit}
        END {exit status}
    ' "$1"
}

file=portscan.txt
checkfile "$file" || echo rm -- "$file"

If I run the awk command on a file, it will exit with a status of 0 if the file has a third line or if it contains a “non-standard” port. On the other hand, if the file has two or fewer lines and only contains “standard” ports, the function will return a non-zero value, and the rm command will be printed. I can remove the echo command if the results look right.

Alternately:

checkfile() {
    # if more than 2 lines, keep the file
    (( $(wc -l < "$1") > 2 )) && return 0

    # if a "non-standard" port exists, keep the file
    grep -qv -e ':80$' -e ':443$' "$1" && return 0

    # delete the file
    return 1
}

or, more tersely

checkfile() {
    (( $(wc -l < "$1") > 2 )) || grep -qv -e ':80$' -e ':443$' "$1"
}