import collections
import sys

def analyze_binary_file(file_path):
    # Define the length of the byte sequence you are interested in
    sequence_length = 4
    # Use a defaultdict to count occurrences of each byte sequence
    byte_sequence_counts = collections.defaultdict(int)

    try:
        with open(file_path, 'rb') as file:
            # Read the entire file into memory (for very large files consider processing chunks)
            binary_data = file.read()
            # Get the total length of the file
            total_length = len(binary_data)

            # Loop through the binary data and extract each 4-byte sequence
            for i in range(total_length - sequence_length + 1):
                # Extract the sequence of bytes
                sequence = binary_data[i:i + sequence_length]
                # Increment the count for this sequence in the dictionary
                byte_sequence_counts[sequence] += 1

        # Find the most common sequences
        most_common_sequences = sorted(byte_sequence_counts.items(), key=lambda x: x[1], reverse=True)[:20]  # Get top 10

        # Print out the results
        print("Most common 4-byte sequences:")
        for sequence, count in most_common_sequences:
            # Convert each byte sequence to a hexadecimal representation for readability
            sequence_hex = ' '.join(f'{byte:02X}' for byte in sequence)
            print(f"Sequence: {sequence_hex} - Count: {count}")

    except FileNotFoundError:
        print("File not found. Please check the file path.")
    except Exception as e:
        print(f"An error occurred: {e}")

if __name__ == "__main__":
    if len(sys.argv) < 2:
        print("Usage: python script.py <binary_file_path>")
    else:
        file_path = sys.argv[1]
        analyze_binary_file(file_path)