Scripts to Remove Space Based Steganography

bash-text-cleaner.sh

#!/bin/bash

# Create the Unicode pattern for sed
INVISIBLE_CHARS=(
    $'\u200B' # Zero-width space
    $'\u200C' # Zero-width non-joiner
    $'\u200D' # Zero-width joiner
    $'\u2060' # Word joiner
    $'\uFEFF' # Zero-width non-breaking space
    $'\u180E' # Mongolian vowel separator
    $'\u200E' # Left-to-right mark
    $'\u200F' # Right-to-left mark
    $'\u202A' # Left-to-right embedding
    $'\u202B' # Right-to-left embedding
    $'\u202C' # Pop directional formatting
    $'\u202D' # Left-to-right override
    $'\u202E' # Right-to-left override
    $'\u2061' # Function application
    $'\u2062' # Invisible times
    $'\u2063' # Invisible separator
    $'\u2064' # Invisible plus
    $'\u206A' # Inhibit symmetric swapping
    $'\u206B' # Activate symmetric swapping
    $'\u206C' # Inhibit arabic form shaping
    $'\u206D' # Activate arabic form shaping
    $'\u206E' # National digit shapes
    $'\u206F' # Nominal digit shapes
    $'\u3164' # Hangul filler
    $'\u1160' # Hangul jamo filler
)

clean_spaces() {
    # Build the sed pattern
    pattern=""
    for char in "${INVISIBLE_CHARS[@]}"; do
        pattern+="$char"
    done
    
    # If a file is provided, read from it; otherwise read from stdin
    if [ "$1" ]; then
        input_text=$(cat "$1")
    else
        input_text=$(cat)
    fi
    
    echo "$input_text" | \
        # Remove all invisible characters
        sed "s/[$pattern]//g" | \
        # Collapse multiple spaces into single spaces
        tr -s ' ' | \
        # Remove leading/trailing whitespace
        sed 's/^[[:space:]]*//;s/[[:space:]]*$//'
}

# Call the function with argument if provided, otherwise use stdin
if [ "$1" ]; then
    clean_spaces "$1"
else
    clean_spaces
fi

bash-usage-text-cleaner

# Make executable
chmod +x clean_spaces.sh

# Use with a file
./clean_spaces.sh input.txt

# Use with pipe
echo "Hidden​‌‍⁠᠎‎‏‪‫‬‭‮⁡⁢⁣⁤‪‫‬‭‮ ㅤᄠmessage   here" | ./clean_spaces.sh

# Use interactively
./clean_spaces.sh
# Type text and press Ctrl+D when done

csharp-text-cleaner.cs

public static class TextCleaner
{
    // Collection of invisible Unicode spaces
    private static readonly string[] InvisibleSpaces = new[]
    {
        "\u200B", // Zero-width space
        "\u200C", // Zero-width non-joiner
        "\u200D", // Zero-width joiner
        "\u2060", // Word joiner
        "\uFEFF", // Zero-width non-breaking space
        "\u180E", // Mongolian vowel separator
        "\u200E", // Left-to-right mark
        "\u200F", // Right-to-left mark
        "\u202A", // Left-to-right embedding
        "\u202B", // Right-to-left embedding
        "\u202C", // Pop directional formatting
        "\u202D", // Left-to-right override
        "\u202E", // Right-to-left override
        "\u2061", // Function application
        "\u2062", // Invisible times
        "\u2063", // Invisible separator
        "\u2064", // Invisible plus
        "\u206A", // Inhibit symmetric swapping
        "\u206B", // Activate symmetric swapping
        "\u206C", // Inhibit arabic form shaping
        "\u206D", // Activate arabic form shaping
        "\u206E", // National digit shapes
        "\u206F", // Nominal digit shapes
        "\u3164", // Hangul filler
        "\u1160"  // Hangul jamo filler
    };

    public static string CleanText(string input)
    {
        if (string.IsNullOrEmpty(input))
            return input;

        // Step 1: Remove all invisible Unicode spaces
        string cleaned = input;
        foreach (string invisibleSpace in InvisibleSpaces)
        {
            cleaned = cleaned.Replace(invisibleSpace, "");
        }

        // Step 2: Replace multiple spaces with single space
        cleaned = string.Join(" ", 
            cleaned.Split(new[] { ' ' }, 
            StringSplitOptions.RemoveEmptyEntries));

        // Step 3: Trim any remaining spaces at start/end
        return cleaned.Trim();
    }
}

perl-text-cleaner

#!/bin/bash

clean_stego() {
    temp_file=$(mktemp)
    
    if [ "$1" ]; then
        cat "$1" > "$temp_file"
    else
        cat > "$temp_file"
    fi
    
    cat "$temp_file" | \
    perl -CSD -pe 's/[\x{200B}\x{200C}\x{200D}\x{2060}\x{FEFF}\x{180E}\x{200E}\x{200F}\x{202A}-\x{202E}\x{2061}-\x{2064}\x{206A}-\x{206F}\x{3164}\x{1160}]//g' | \
    tr -s ' ' | \
    sed 's/^[[:space:]]*//;s/[[:space:]]*$//'
    
    rm "$temp_file"
}

if [ "$1" ]; then
    clean_stego "$1"
else
    clean_stego
fi

powershell-text-cleaner.psm1

function Remove-HiddenSpaces {
    [CmdletBinding()]
    param (
        [Parameter(ValueFromPipeline = $true)]
        [string]$Text,
        
        [Parameter()]
        [string]$Path
    )

    # Array of invisible Unicode characters
    $invisibleChars = @(
        [char]0x200B  # Zero-width space
        [char]0x200C  # Zero-width non-joiner
        [char]0x200D  # Zero-width joiner
        [char]0x2060  # Word joiner
        [char]0xFEFF  # Zero-width non-breaking space
        [char]0x180E  # Mongolian vowel separator
        [char]0x200E  # Left-to-right mark
        [char]0x200F  # Right-to-left mark
        [char]0x202A  # Left-to-right embedding
        [char]0x202B  # Right-to-left embedding
        [char]0x202C  # Pop directional formatting
        [char]0x202D  # Left-to-right override
        [char]0x202E  # Right-to-left override
        [char]0x2061  # Function application
        [char]0x2062  # Invisible times
        [char]0x2063  # Invisible separator
        [char]0x2064  # Invisible plus
        [char]0x206A  # Inhibit symmetric swapping
        [char]0x206B  # Activate symmetric swapping
        [char]0x206C  # Inhibit arabic form shaping
        [char]0x206D  # Activate arabic form shaping
        [char]0x206E  # National digit shapes
        [char]0x206F  # Nominal digit shapes
        [char]0x3164  # Hangul filler
        [char]0x1160  # Hangul jamo filler
    )

    # Get input text either from pipeline/parameter or file
    if ($Path) {
        $inputText = Get-Content -Path $Path -Raw
    }
    else {
        $inputText = $Text
    }

    # Remove invisible characters
    $cleanText = $inputText
    foreach ($char in $invisibleChars) {
        $cleanText = $cleanText.Replace($char, '')
    }

    # Replace multiple spaces with single space and trim
    $cleanText = $cleanText -replace '\s+', ' '
    $cleanText = $cleanText.Trim()

    return $cleanText
}

# Export the function if you want to use it as a module
Export-ModuleMember -Function Remove-HiddenSpaces

poweshell-usage.txt.psm1

# Clean text directly
$text = "Hidden   messages​‌‍⁠  might  be   here"
Remove-HiddenSpaces -Text $text

# Clean text from a file
Remove-HiddenSpaces -Path "input.txt"

# Use with pipeline
"Hidden   messages​‌‍⁠  might  be   here" | Remove-HiddenSpaces

# Save to a file
$text | Remove-HiddenSpaces | Out-File "cleaned.txt"